Search

Your search keyword '"David Sheeren"' showing total 23 results
Start Over Author "David Sheeren" Topic 02 engineering and technology
23 results on '"David Sheeren"'

1. Spatial dependence between training and test sets: another pitfall of classification accuracy assessment in remote sensing

Author

N. Karasiak, Claude Monteil, Jean-François Dejoux, David Sheeren, Dynamiques et écologie des paysages agriforestiers (DYNAFOR), École nationale supérieure agronomique de Toulouse [ENSAT]-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE), Centre d'études spatiales de la biosphère (CESBIO), Centre National de la Recherche Scientifique (CNRS)-Institut de Recherche pour le Développement (IRD)-Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Institut national des sciences de l'Univers (INSU - CNRS)-Observatoire Midi-Pyrénées (OMP), Météo France-Centre National d'Études Spatiales [Toulouse] (CNES)-Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut de Recherche pour le Développement (IRD)-Météo France-Centre National d'Études Spatiales [Toulouse] (CNES)-Centre National de la Recherche Scientifique (CNRS), and French Ministry of Higher Education and Research (University of Toulouse)

Subjects
Contextual image classification, Pixel, Property (programming), Computer science, Overfitting, Cross-validation, 02 engineering and technology, Remote sensing, Python (programming language), Accuracy assessment, Artificial Intelligence, Sample size determination, 020204 information systems, 0202 electrical engineering, electronic engineering, information engineering, [INFO]Computer Science [cs], 020201 artificial intelligence & image processing, Spatial dependence, computer, Spatial analysis, Spatial autocorrelation, Software, Independence (probability theory), computer.programming_language
Abstract

International audience; Spatial autocorrelation is inherent to remotely sensed data. Nearby pixels are more similar than distant ones. This property can help to improve the classification performance, by adding spatial or contextual features into the model. However, it can also lead to overestimation of generalisation capabilities, if the spatial dependence between training and test sets is ignored. In this paper, we review existing approaches that deal with spatial autocorrelation for image classification in remote sensing and demonstrate the importance of bias in accuracy metrics when spatial independence between the training and test sets is not respected. We compare three spatial and non-spatial cross-validation strategies at pixel and object levels and study how performances vary at different sample sizes. Experiments based on Sentinel-2 data for mapping two simple forest classes show that spatial leave-one-out cross-validation is the better strategy to provide unbiased estimates of predictive error. Its performance metrics are consistent with the real quality of the resulting map contrary to traditional non-spatial cross-validation that overestimates accuracy. This highlight the need to change practices in classification accuracy assessment. To encourage it we developped Museo ToolBox, an open-source python library that makes spatial cross-validation possible.

Published
2021
Full Text
View/download PDF

2. Deep Learning for Automatic Colorization of Legacy Grayscale Aerial Photographs

Author

Grzegorz Skupinski, Quentin Poterek, Pierre-Alexis Herrault, David Sheeren, Laboratoire Image, Ville, Environnement (LIVE), Université de Strasbourg (UNISTRA)-Centre National de la Recherche Scientifique (CNRS), Dynamiques et écologie des paysages agriforestiers (DYNAFOR), École nationale supérieure agronomique de Toulouse [ENSAT]-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE), and Zone Atelier Environnementale Urbaine part of the French Long Term Ecosystem Research Network

Subjects
Atmospheric Science, Computer science, Geophysics. Cosmic physics, 02 engineering and technology, Land cover, 010501 environmental sciences, 01 natural sciences, Grayscale, remote sensing, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, 0202 electrical engineering, electronic engineering, information engineering, Colorization, Computer vision, Computers in Earth Sciences, Spectral data, TC1501-1800, 0105 earth and related environmental sciences, grayscale imagery, QC801-809, business.industry, Deep learning, Photography, deep learning, historical aerial photograph, 15. Life on land, Random forest, Ocean engineering, 020201 artificial intelligence & image processing, Artificial intelligence, business, generative adversarial network (GAN), Generative adversarial network
Abstract

Legacy grayscale aerial photographs represent one of the main available sources for studying the past state of the environment and its relationship to the present. However, these photographs lack spectral information thereby hindering their use in current remote sensing approaches that rely on spectral data for characterizing surfaces. This article proposes a conditional generative adversarial network, a deep learning model, to enrich legacy photographs by predicting color channels for an input grayscale image. The technique was used to colorize two orthophotographs (taken in 1956 and 1978) covering the entire Eurométropole de Strasbourg. To assess the model's performances, two strategies were proposed: first, colorized photographs were evaluated with metrics such as peak signal-to-noise ratio (PSNR), and structural similarity index (SSIM); second, random forest classifications were performed to extract land cover classes from grayscale and colorized photographs, respectively. The results revealed strong performances, with PSNR = 25.56 ± 2.20 and SSIM = 0.93 ± 0.06 indicating that the model successfully learned the mapping between grayscale and color photographs over a large territory. Moreover, land cover classifications performed on colorized data showed significant improvements over grayscale photographs, respectively, +6% and +17% for 1956 and 1978. Finally, the plausibility of outputs images was evaluated visually. We conclude that deep learning models are powerful tools for improving radiometric properties of old aerial grayscale photographs and land cover mapping. We also argue that the proposed approach could serve as a basis for further developments aiming to promote the use of aerial photographs archives for landscapes reconstruction.

Published
2020
Full Text
View/download PDF

3. Graph-Based Approach to Improve Individual Tree Crown Delineation in Temperate Forest using Structural And Spectral Information

Author

Thomas Houet, Thierry Erudel, David Sheeren, Xavier Briottet, Sophie Fabre, M. Deluzet, ONERA / DOTA, Université de Toulouse [Toulouse], ONERA-PRES Université de Toulouse, Dynamiques et écologie des paysages agriforestiers (DYNAFOR), École nationale supérieure agronomique de Toulouse [ENSAT]-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE), Littoral, Environnement, Télédétection, Géomatique UMR 6554 (LETG), Université de Nantes (UN)-Université de Brest (UBO)-Université de Rennes 2 (UR2), and Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Centre National de la Recherche Scientifique (CNRS)

Subjects
Watershed, LiDAR, 010504 meteorology & atmospheric sciences, 0211 other engineering and technologies, 02 engineering and technology, 01 natural sciences, Individual tree crown, [SPI]Engineering Sciences [physics], Délinéation, Segmentation, Forest, 021101 geological & geomatics engineering, 0105 earth and related environmental sciences, Mathematics, [PHYS]Physics [physics], Graph rewriting, business.industry, Hyperspectral imaging, Temperate forest, Pattern recognition, Image segmentation, Delineation, 15. Life on land, Tree (graph theory), Hyperspectral, Forêt, Artificial intelligence, Scale (map), business
Abstract

International audience; Forest characterization at tree scale is possible with remotely sensed images of high spatial resolution. A first step is the Individual Tree Crown (ITC) delineation which corresponds to the segmentation of canopy cover into different tree crowns. In this study, a new method based on an initial watershed segmentation of Canopy Height Model (CHM) is proposed. This method is based on a graph transformation of the initial segmentation map in order to apply structural criteria (calculated owning to CHM) and spectral criterion (computed on red, green and blue bands). Adaptive thresholds are defined according to the studied forest characteristics in order to improve low quality segmentation cases. This method has been applied on a complex forest site (Broadleaf dominant, steep relief…). The results show a 17% increase of global performance in comparison to the reference watershed segmentation.; La caractérisation de la forêt à l'échelle de l'arbre est possible avec des images de télédétection de haute résolution spatiale. Une première étape est la délimitation de la couronne individuelle des arbres (ITC) qui correspond à la segmentation du couvert forestier en différentes couronnes d'arbres. Dans cette étude, une nouvelle méthode basée sur une segmentation initiale des bassins versants du modèle de hauteur de la canopée (CHM) est proposée. Cette méthode est basée sur une transformation graphique de la carte de segmentation initiale afin d'appliquer des critères structurels (calculés en propriété au CHM) et spectraux (calculés sur des bandes rouges, vertes et bleues). Des seuils adaptatifs sont définis en fonction des caractéristiques forestières étudiées afin d'améliorer les cas de segmentation de faible qualité. Cette méthode a été appliquée sur un site forestier complexe (dominante feuillue, relief escarpé…). Les résultats montrent une augmentation de 17% de la performance globale par rapport à la segmentation des bassins versants de référence.

Published
2021
Full Text
View/download PDF

4. Submerged macrophyte assessment in rivers: An automatic mapping method using Pléiades imagery

Author

Arnaud Elger, Stephanie Courty, Yves Auda, David Sheeren, Diane Espel, Laboratoire Ecologie Fonctionnelle et Environnement (ECOLAB), Institut Ecologie et Environnement (INEE), Centre National de la Recherche Scientifique (CNRS)-Centre National de la Recherche Scientifique (CNRS)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Observatoire Midi-Pyrénées (OMP), Météo France-Centre National d'Études Spatiales [Toulouse] (CNES)-Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut de Recherche pour le Développement (IRD)-Météo France-Centre National d'Études Spatiales [Toulouse] (CNES)-Centre National de la Recherche Scientifique (CNRS)-Institut de Recherche pour le Développement (IRD)-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées, Adict Solutions, Géosciences Environnement Toulouse (GET), Institut national des sciences de l'Univers (INSU - CNRS)-Centre National de la Recherche Scientifique (CNRS)-Institut de Recherche pour le Développement (IRD)-Université Toulouse III - Paul Sabatier (UT3), Météo France-Centre National d'Études Spatiales [Toulouse] (CNES)-Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut de Recherche pour le Développement (IRD)-Météo France-Centre National d'Études Spatiales [Toulouse] (CNES)-Centre National de la Recherche Scientifique (CNRS)-Institut de Recherche pour le Développement (IRD), Dynamiques et écologie des paysages agriforestiers (DYNAFOR), École nationale supérieure agronomique de Toulouse [ENSAT]-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE), École nationale supérieure agronomique de Toulouse [ENSAT], Agence de l'Eau Adour-Garonne, Association Nationale de la Recherche et de la Technologie, French National Research Agency (ANR), Laboratoire Ecologie Fonctionnelle et Environnement (LEFE), Université de Toulouse (UT)-Université de Toulouse (UT)-Observatoire Midi-Pyrénées (OMP), Institut de Recherche pour le Développement (IRD)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Université de Toulouse (UT)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National d'Études Spatiales [Toulouse] (CNES)-Centre National de la Recherche Scientifique (CNRS)-Météo-France -Institut de Recherche pour le Développement (IRD)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National d'Études Spatiales [Toulouse] (CNES)-Centre National de la Recherche Scientifique (CNRS)-Météo-France -Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université de Toulouse (UT), Université de Toulouse (UT)-Université de Toulouse (UT)-Institut national des sciences de l'Univers (INSU - CNRS)-Observatoire Midi-Pyrénées (OMP), Université de Toulouse (UT)-Université de Toulouse (UT)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National d'Études Spatiales [Toulouse] (CNES)-Centre National de la Recherche Scientifique (CNRS)-Météo-France -Institut de Recherche pour le Développement (IRD)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National d'Études Spatiales [Toulouse] (CNES)-Centre National de la Recherche Scientifique (CNRS)-Météo-France -Centre National de la Recherche Scientifique (CNRS), École nationale supérieure agronomique de Toulouse (ENSAT), Institut National Polytechnique (Toulouse) (Toulouse INP), Université de Toulouse (UT)-Université de Toulouse (UT)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université de Toulouse (UT)-Université de Toulouse (UT)-Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE), and Université de Toulouse (UT)-Université de Toulouse (UT)

Subjects
Satellite Imagery, Environmental Engineering, [SDV]Life Sciences [q-bio], 0208 environmental biotechnology, Multispectral image, Support Vector Regression, 02 engineering and technology, 010501 environmental sciences, 01 natural sciences, Fluvial ecosystem, Normalized Difference Vegetation Index, Rivers, Machine learning, Satellite imagery, 14. Life underwater, Waste Management and Disposal, Ecosystem, Aquatic vegetation, 0105 earth and related environmental sciences, Water Science and Technology, Civil and Structural Engineering, Remote sensing, Random Forest, Ecological Modeling, Sampling (statistics), Spectral bands, Vegetation, 15. Life on land, Pollution, 6. Clean water, 020801 environmental engineering, Macrophyte, Random forest, 13. Climate action, Remote Sensing Technology, Environmental science, Environmental Monitoring
Abstract

International audience; Submerged macrophyte monitoring is a major concern for hydrosystem management, particularly for understanding and preventing the potential impacts of global change on ecological functions and services. Macrophyte distribution assessments in rivers are still primarily realized using field monitoring or manual photo-interpretation of aerial images. Considering the lack of applications in fluvial environments, developing operational, low-cost and less time-consuming tools able to automatically map and monitor submerged macrophyte distribution is therefore crucial to support effective management programs. In this study, the suitability of very fine-scale resolution (50 cm) multispectral Pléiades satellite imagery to estimate submerged macrophyte cover, at the scale of a 1 km river section, was investigated. The performance of nonparametric regression methods (based on two reliable and well-known machine learning algorithms for remote sensing applications, Random Forest and Support Vector Regression) were compared for several spectral datasets, testing the relevance of 4 spectral bands (red, green, blue and near-infrared) and two vegetation indices (the Normalized Difference Vegetation Index, NDVI, and the Green-Red Vegetation Index, GRVI), and for several field sampling configurations. Both machine learning algorithms applied to a Pléiades image were able to reasonably well predict macrophyte cover in river ecosystems with promising performance metrics (R² above 0.7 and RMSE around 20%). The Random Forest algorithm combined to the 4 spectral bands from Pléiades image was the most efficient, particularly for extreme cover values (0% and 100%). Our study also demonstrated that a larger number of fine-scale field sampling entities clearly involved better cover predictions than a smaller number of larger sampling entities.

Published
2020
Full Text
View/download PDF

5. Optimal dates for deciduous tree species mapping using full years sentinel-2 time series in south west France

Author

Jean-François Dejoux, David Sheeren, Claude Monteil, Mathieu Fauvel, N. Karasiak, Dynamiques et écologie des paysages agriforestiers (DYNAFOR), École nationale supérieure agronomique de Toulouse [ENSAT]-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE), Centre d'études spatiales de la biosphère (CESBIO), Centre National de la Recherche Scientifique (CNRS)-Institut de Recherche pour le Développement (IRD)-Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Institut national des sciences de l'Univers (INSU - CNRS)-Observatoire Midi-Pyrénées (OMP), and Météo France-Centre National d'Études Spatiales [Toulouse] (CNES)-Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut de Recherche pour le Développement (IRD)-Météo France-Centre National d'Études Spatiales [Toulouse] (CNES)-Centre National de la Recherche Scientifique (CNRS)

Subjects
lcsh:Applied optics. Photonics, 010504 meteorology & atmospheric sciences, [SDV]Life Sciences [q-bio], 0211 other engineering and technologies, Satellite image time series, 02 engineering and technology, lcsh:Technology, 01 natural sciences, Forest, Spatial analysis, 021101 geological & geomatics engineering, 0105 earth and related environmental sciences, Remote sensing, Mathematics, lcsh:T, Phenology, lcsh:TA1501-1820, Vegetation, Spectral bands, Biodiversity, 15. Life on land, Annual cycle, Deciduous, lcsh:TA1-2040, Map, Satellite Image Time Series, France, Sentinel-2, lcsh:Engineering (General). Civil engineering (General), Scale (map), Spatial autocorrelation, Tree species
Abstract

International audience; The free to use Sentinel-2 (S2) sensors with 5-day revisit time at high spatial resolution in 10 spectral bands is a revolution in the remote sensing domain. Including 6 spectral bands in the near infrared, with 3 dedicated for the red-edge (where the vegetation significatively increases), these european satellites are very promising for mapping tree species distribution at a national scale. Here, we study the contribution of three one-year S2 Satellite Image Time Series (SITS) for mapping deciduous species distribution in the southwest of France. The annual cycle of vegetation (called phenology) can contribute to the identification of tree species. For some specific dates, species can have different phenological behaviours (senesence, flowering…). To train and validate the maps, we used the Support Vector Machine algorithm with a spatial cross-validation method. To train the algorithm with the same number of samples per species, we decided to undersample each class to the smallest class using a K-means clustering method. Moreover, a Sequential Feature Selection (SFS) has been implemented to detect the optimal dates per species. Our results are promising with high accuracy for Red oak andWillow (average score of the three one-year respectively F1-Combining double low line-0.99, F1-Combining double low line-0.94) based on the optimal dates. However, it appears that the performances when using the each full SITS are far below the optimal dates models (average ΔF1-Combining double low line-0.32). We did not find, except for Willow and Red oak, that the optimal dates were the same for each year. Perspectives is to find an algorithm robust to temporal or spectral noise and to smooth the time series.

Published
2020
Full Text
View/download PDF

6. From Local to Global: A Transfer Learning-Based Approach for Mapping Poplar Plantations at Large Scale

Author

Véronique Chéret, Yousra Hamrouni, David Sheeren, Eric Paillassa, Claude Monteil, Dynamiques et écologie des paysages agriforestiers (DYNAFOR), École nationale supérieure agronomique de Toulouse [ENSAT]-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE), Conseil National du Peuplier, Centre national de la propriété forestière, and Institut pour le développement forestier (IDF)

Subjects
environmental_sciences, Computer science, Active learning (machine learning), [SDV]Life Sciences [q-bio], 0211 other engineering and technologies, Context (language use), 02 engineering and technology, Machine learning, computer.software_genre, Field (computer science), Task (project management), active learning, Classifier (linguistics), 0202 electrical engineering, electronic engineering, information engineering, mapping, 021101 geological & geomatics engineering, [SDV.EE]Life Sciences [q-bio]/Ecology, environment, Contextual image classification, business.industry, 020206 networking & telecommunications, Poplar plantations, 15. Life on land, Random forest, large-scale, Key (cryptography), Artificial intelligence, Scale (map), Transfer of learning, business, computer, Sentine1-2
Abstract

Reliable estimates of poplar plantations area are not available at the French national scale due to the unsuitability and low update rate of existing forest databases for this short-rotation species. While supervised classification methods have been shown to be highly accurate in mapping forest cover from remotely sensed images, their performance depends to a great extent on the labelled samples used to build the models. In addition to their high acquisition cost, such samples are often scarce and not fully representative of the variability in class distributions. Consequently, when classification models are applied to large areas with high intra-class variance, they generally yield poor accuracies. In this paper, we propose the use of active learning (AL) to efficiently adapt a classifier trained on a source image to spatially distinct target images with minimal labelling effort and without sacrificing classification performance. The adaptation consists in actively adding to the initial local model, new relevant training samples from other areas, in a cascade that iteratively improves the generalisation capabilities of the classifier, leading to a global model tailored to different areas. This active selection relies on uncertainty sampling to directly focus on the most informative pixels for which the algorithm is the least certain of their class labels. Experiments conducted on Sentinel-2 time series showed that when the same number of training samples was used, active learning outperformed passive learning (random sampling) by up to 5% of overall accuracy and up to 12% of class F-score. In addition, and depending on the class considered, the random sampling required up to 50% more samples to achieve the same performance of an active learning-based model. Moreover, the results demonstrate the suitability of the derived global model to accurately map poplar plantations among other tree species with overall accuracy values up to 14% higher than those obtained with local models. The proposed approach paves the way for national-scale mapping in an operational context.

Published
2020
Full Text
View/download PDF

7. Statistical Stability and Spatial Instability in Mapping Forest Tree Species by Comparing 9 Years of Satellite Image Time Series

Author

David Sheeren, Mathieu Fauvel, Nicolas Karasiak, Jérôme Willm, Claude Monteil, Jean-François Dejoux, Dynamiques Forestières dans l'Espace Rural (DYNAFOR), Institut National de la Recherche Agronomique (INRA)-École nationale supérieure agronomique de Toulouse [ENSAT]-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées, Centre d'études spatiales de la biosphère (CESBIO), Centre National de la Recherche Scientifique (CNRS)-Institut de Recherche pour le Développement (IRD)-Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Institut national des sciences de l'Univers (INSU - CNRS)-Observatoire Midi-Pyrénées (OMP), Météo France-Centre National d'Études Spatiales [Toulouse] (CNES)-Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut de Recherche pour le Développement (IRD)-Météo France-Centre National d'Études Spatiales [Toulouse] (CNES)-Centre National de la Recherche Scientifique (CNRS), French Ministry of Higher Education and Research (University of Toulouse), Centre National D'etudes Spatiales, Institut National de la Recherche Agronomique (INRA)-École nationale supérieure agronomique de Toulouse (ENSAT), Institut National Polytechnique (Toulouse) (Toulouse INP), Université de Toulouse (UT)-Université de Toulouse (UT)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université de Toulouse (UT)-Université de Toulouse (UT), Institut de Recherche pour le Développement (IRD)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Université de Toulouse (UT)-Institut national des sciences de l'Univers (INSU - CNRS)-Observatoire Midi-Pyrénées (OMP), and Université de Toulouse (UT)-Université de Toulouse (UT)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National d'Études Spatiales [Toulouse] (CNES)-Centre National de la Recherche Scientifique (CNRS)-Météo-France -Institut national des sciences de l'Univers (INSU - CNRS)-Centre National d'Études Spatiales [Toulouse] (CNES)-Centre National de la Recherche Scientifique (CNRS)-Météo-France -Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE)

Subjects
cartographie spatiale, [SDV.SA]Life Sciences [q-bio]/Agricultural sciences, environmental_sciences, 010504 meteorology & atmospheric sciences, 0211 other engineering and technologies, 02 engineering and technology, image satellite, 01 natural sciences, spatial autocorrelation, cross-validation, Cross-validation, forest, tree species, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, forêt, Statistics, 0202 electrical engineering, electronic engineering, information engineering, Spatial dependence, lcsh:Science, Spatial analysis, 0105 earth and related environmental sciences, 021101 geological & geomatics engineering, Mathematics, biodiversity, [STAT.AP]Statistics [stat]/Applications [stat.AP], Series (stratigraphy), analyse statistique, accuracy, 020206 networking & telecommunications, Vegetation, 15. Life on land, time series, Agricultural sciences, Support vector machine, Tree (data structure), 13. Climate action, Applications, General Earth and Planetary Sciences, lcsh:Q, Signal and Image Processing, Satellite Image Time Series, Sciences agricoles, Traitement du signal et de l'image (Informatique)
Abstract

International audience; Mapping forest composition using multiseasonal optical time series remains a challenge. Highly contrasted results are reported from one study to another suggesting that drivers of classification errors are still under-explored. We evaluated the performances of single-year Formosat-2 time series to discriminate tree species in temperate forests in France and investigated how predictions vary statistically and spatially across multiple years. Our objective was to better estimate the impact of spatial autocorrelation in the validation data on measurement accuracy and to understand which drivers in the time series are responsible for classification errors. The experiments were based on 10 Formosat-2 image time series irregularly acquired during the seasonal vegetation cycle from 2006 to 2014. Due to lot of clouds in the year 2006, an alternative 2006 time series using only cloud-free images has been added. Thirteen tree species were classified in each single-year dataset based on the Support Vector Machine (SVM) algorithm. The performances were assessed using a spatial leave-one-out cross validation (SLOO-CV) strategy, thereby guaranteeing full independence of the validation samples, and compared with standard non-spatial leave-one-out cross-validation (LOO-CV). The results show relatively close statistical performances from one year to the next despite the differences between the annual time series. Good agreements between years were observed in monospecific tree plantations of broadleaf species versus high disparity in other forests composed of different species. A strong positive bias in the accuracy assessment (up to 0.4 of Overall Accuracy (OA)) was also found when spatial dependence in the validation data was not removed. Using the SLOO-CV approach, the average OA values per year ranged from 0.48 for 2006 to 0.60 for 2013, which satisfactorily represents the spatial instability of species prediction between years.

Published
2019
Full Text
View/download PDF

8. Identification of the London plane in urban alignment based on hyperspectral data and contextual information

Author

David Sheeren, Josselin Aval, Sophie Fabre, Emmanuel Zenou, Jean Demuynck, Xavier Briottet, Mathieu Fauvel, ONERA / DOTA, Université de Toulouse [Toulouse], ONERA-PRES Université de Toulouse, Institut Supérieur de l'Aéronautique et de l'Espace (ISAE-SUPAERO), École nationale supérieure agronomique de Toulouse [ENSAT], Centre d'études spatiales de la biosphère (CESBIO), Centre National de la Recherche Scientifique (CNRS)-Institut de Recherche pour le Développement (IRD)-Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Institut national des sciences de l'Univers (INSU - CNRS)-Observatoire Midi-Pyrénées (OMP), Météo France-Centre National d'Études Spatiales [Toulouse] (CNES)-Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut de Recherche pour le Développement (IRD)-Météo France-Centre National d'Études Spatiales [Toulouse] (CNES)-Centre National de la Recherche Scientifique (CNRS), and CNRS

Subjects
Geographic information system, Support Vector Machine, 010504 meteorology & atmospheric sciences, Computer science, 0211 other engineering and technologies, Urban remote sensing, 02 engineering and technology, 01 natural sciences, Regularization (mathematics), [SPI]Engineering Sciences [physics], Airborne hyperspectral data, Contextual information, Marked Point Process, Marked point process, 021101 geological & geomatics engineering, 0105 earth and related environmental sciences, [PHYS]Physics [physics], business.industry, Plane (geometry), Geographic Information System, Street tree, Hyperspectral imaging, Pattern recognition, Normalized Digital Surface Model, Support vector machine, Identification (information), London plane, Artificial intelligence, business
Abstract

International audience; This paper presents an approach for identifying the London plane in urban alignment based on hyperspectral data and contextual information. The proposed approach allows the London plane street trees of a study case to be perfectly identified thanks to both a supervised classification and a post regularization of the species prediction, based on the alignment membership derived from a Marked Point Process approach.

Published
2019
Full Text
View/download PDF

9. A Generic Framework for Combining Multiple Segmentations in Geographic Object-Based Image Analysis

Author

Onur Tasar, David Sheeren, Sébastien Lefèvre, Environment observation with complex imagery (OBELIX), Université de Bretagne Sud (UBS)-SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE (IRISA-D5), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-Télécom Bretagne-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-Télécom Bretagne-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-Télécom Bretagne-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS), Dynamiques Forestières dans l'Espace Rural (DYNAFOR), Institut National de la Recherche Agronomique (INRA)-École nationale supérieure agronomique de Toulouse (ENSAT), Institut National Polytechnique (Toulouse) (Toulouse INP), Université de Toulouse (UT)-Université de Toulouse (UT)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université de Toulouse (UT)-Université de Toulouse (UT), Geometric Modeling of 3D Environments (TITANE), Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), ANR-13-JS02-0005,ASTERIX,Analyse Spatio-temporelle pour la Télédétection de l'Environnement par Reconnaissance dans les Images compleXes(2013), Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Université de Bretagne Sud (UBS)-Centre National de la Recherche Scientifique (CNRS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-Télécom Bretagne-Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-CentraleSupélec-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Université de Rennes (UNIV-RENNES)-CentraleSupélec-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Centre National de la Recherche Scientifique (CNRS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-Télécom Bretagne-Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-CentraleSupélec, Institut National de la Recherche Agronomique (INRA)-Ecole Nationale Supérieure Agronomique de Toulouse-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées, CentraleSupélec-Télécom Bretagne-Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Rennes (ENS Rennes)-Université de Bretagne Sud (UBS)-Centre National de la Recherche Scientifique (CNRS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-CentraleSupélec-Télécom Bretagne-Université de Rennes 1 (UR1), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Rennes (ENS Rennes)-Centre National de la Recherche Scientifique (CNRS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA), and Institut National de la Recherche Agronomique (INRA)-École nationale supérieure agronomique de Toulouse [ENSAT]-Institut National Polytechnique (Toulouse) (Toulouse INP)

Subjects
segmentation evaluation, Computer science, [SDV]Life Sciences [q-bio], Geography, Planning and Development, 0211 other engineering and technologies, lcsh:G1-922, 02 engineering and technology, segmentation fusion, consensus, remote sensing, geobia, Set (abstract data type), 0202 electrical engineering, electronic engineering, information engineering, Earth and Planetary Sciences (miscellaneous), Segmentation, Relevance (information retrieval), Sensitivity (control systems), Computers in Earth Sciences, 021101 geological & geomatics engineering, GEOBIA, Pixel, business.industry, Process (computing), Pattern recognition, Quality Score, 020201 artificial intelligence & image processing, Artificial intelligence, Scale (map), business, lcsh:Geography (General)
Abstract

International audience; The Geographic Object-Based Image Analysis (GEOBIA) paradigm relies strongly on the segmentation concept, i.e., partitioning of an image into regions or objects that are then further analyzed. Segmentation is a critical step, for which a wide range of methods, parameters and input data are available. To reduce the sensitivity of the GEOBIA process to the segmentation step, here we consider that a set of segmentation maps can be derived from remote sensing data. Inspired by the ensemble paradigm that combines multiple weak classifiers to build a strong one, we propose a novel framework for combining multiple segmentation maps. The combination leads to a fine-grained partition of segments (super-pixels) that is built by intersecting individual input partitions, and each segment is assigned a segmentation confidence score that relates directly to the local consensus between the different segmentation maps. Furthermore, each input segmentation can be assigned some local or global quality score based on expert assessment or automatic analysis. These scores are then taken into account when computing the confidence map that results from the combination of the segmentation processes. This means the process is less affected by incorrect segmentation inputs either at the local scale of a region, or at the global scale of a map. In contrast to related works, the proposed framework is fully generic and does not rely on specific input data to drive the combination process. We assess its relevance through experiments conducted on ISPRS 2D Semantic Labeling. Results show that the confidence map provides valuable information that can be produced when combining segmentations, and fusion at the object level is competitive w.r.t. fusion at the pixel or decision level.

Published
2019
Full Text
View/download PDF

10. Detection of individual trees in urban alignment from airborne data and T contextual information: A marked point process approach

Author

Mathieu Fauvel, Josselin Aval, David Sheeren, Emmanuel Zenou, Xavier Briottet, Karine Adeline, Jean Demuynck, Sophie Fabre, Institut National Polytechnique de Toulouse - INPT (FRANCE), Institut National de la Recherche Agronomique - INRA (FRANCE), Institut Supérieur de l'Aéronautique et de l'Espace - ISAE-SUPAERO (FRANCE), Office National d'Etudes et Recherches Aérospatiales - ONERA (FRANCE), Département d'Ingénierie des Systèmes Complexes - DISC (Toulouse, France), ONERA / DOTA, Université de Toulouse [Toulouse], ONERA-PRES Université de Toulouse, Département d'Ingénierie des Systèmes Complexes (DISC), Institut Supérieur de l'Aéronautique et de l'Espace (ISAE-SUPAERO), Dynamiques Forestières dans l'Espace Rural (DYNAFOR), Institut National de la Recherche Agronomique (INRA)-Ecole Nationale Supérieure Agronomique de Toulouse-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées, Institut National de la Recherche Agronomique (INRA)-École nationale supérieure agronomique de Toulouse [ENSAT]-Institut National Polytechnique (Toulouse) (Toulouse INP), and Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE)

Subjects
Geographic information system, 010504 meteorology & atmospheric sciences, 0211 other engineering and technologies, Urban remote sensing, 02 engineering and technology, Ingénierie de l'environnement, 01 natural sciences, 11. Sustainability, Computers in Earth Sciences, Urban heat island, Baseline (configuration management), Engineering (miscellaneous), Air quality index, 021101 geological & geomatics engineering, 0105 earth and related environmental sciences, Marked point process, business.industry, [SDE.IE]Environmental Sciences/Environmental Engineering, Street tree, Vegetation, 15. Life on land, Tree (graph theory), Atomic and Molecular Physics, and Optics, Computer Science Applications, Airborne data, Identification (information), Geography, 13. Climate action, Region growing, Individual tree crown delineation, business, Cartography
Abstract

International audience; With the current expansion of cities, urban trees have an important role for preserving the health of its in- habitants. With their evapotranspiration, they reduce the urban heat island phenomenon, by trapping CO2 emission, improve air quality. In particular, street trees or alignment trees, create shade on the road network, are structuring elements of the cities and decorate the roads. Street trees are also subject to specific conditions as they have little space for growth, are pruned and can be affected by the spread of diseases in single-species plantations. Thus, their detection, identification and monitoring are necessary. In this study, an approach is proposed for mapping these trees that are characteristic of the urban environment. Three areas of the city of Toulouse in the south of France are studied. Airborne hyperspectral data and a Digital Surface Model (DSM) for high vegetation detection are used. Then, contextual information is used to identify the street trees. Indeed, Geographic Information System (GIS) data are considered to detect the vegetation canopies close to the streets. Afterwards, individual street tree crown delineation is carried out by modeling the discriminative contextual features of individual street trees (hypotheses of small angle between the trees and similar heights) based on Marked Point Process (MPP). Compared to a baseline individual tree crown delineation method based on region growing, our method logically provides the best results with F-score values of 91%, 75% and 85% against 70%, 41% and 20% for the three studied areas respectively. Our approach mainly succeeds in identifying the street trees. In addition, the contribution of the angle, the height and the GIS data in the street tree mapping has been studied. The results encourage the use of the angle, the height and the GIS data together. However, with only the angle and the height, the results are similar to those obtained with the inclusion of the GIS data for the first and the second study cases with F-score values of 88%, 79% and 62% against 91%, 75% and 85% for the three study cases respectively. Finally, it is shown that the GIS data only is not sufficient.

Published
2018
Full Text
View/download PDF

11. Object-based classification of grasslands from high resolution satellite image time series using Gaussian mean map kernels

Author

David Sheeren, Stéphane Girard, Mailys Lopes, Mathieu Fauvel, Dynamiques Forestières dans l'Espace Rural (DYNAFOR), Institut National de la Recherche Agronomique (INRA)-Ecole Nationale Supérieure Agronomique de Toulouse-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées, Modelling and Inference of Complex and Structured Stochastic Systems (MISTIS), Inria Grenoble - Rhône-Alpes, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Jean Kuntzmann (LJK), Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut Polytechnique de Grenoble - Grenoble Institute of Technology-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes (UGA)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut Polytechnique de Grenoble - Grenoble Institute of Technology-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes (UGA)-Institut National Polytechnique de Grenoble (INPG), This work was granted by INRA and by Défi Mastodons-CNRS., Institut National de la Recherche Agronomique (INRA)-École nationale supérieure agronomique de Toulouse [ENSAT]-Institut National Polytechnique (Toulouse) (Toulouse INP), Modelling and Inference of Complex and Structured Stochastic Systems (MISTIS ), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Laboratoire Jean Kuntzmann (LJK ), Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes [2016-2019] (UGA [2016-2019])-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes [2016-2019] (UGA [2016-2019]), Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE), Institut polytechnique de Grenoble (FRANCE), Institut National de la Recherche Agronomique - INRA (FRANCE), Institut National de la Recherche en Informatique et en Automatique - INRIA (FRANCE), Université Pierre Mendès France, Grenoble 2 - UPMF (FRANCE), Université Joseph Fourier Grenoble 1 - UJF (FRANCE), Institut National Polytechnique de Toulouse - INPT (FRANCE), Institut National de la Recherche Agronomique (INRA)-École nationale supérieure agronomique de Toulouse (ENSAT), Institut National Polytechnique (Toulouse) (Toulouse INP), Université de Toulouse (UT)-Université de Toulouse (UT)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université de Toulouse (UT)-Université de Toulouse (UT), and Lopes, Mailys

Subjects
[SDV.SA]Life Sciences [q-bio]/Agricultural sciences, 010504 meteorology & atmospheric sciences, Computer science, Science, Gaussian, Biodiversité et Ecologie, SVM, Multispectral image, 0211 other engineering and technologies, 02 engineering and technology, Ingénierie de l'environnement, [SDV.SA.SDS]Life Sciences [q-bio]/Agricultural sciences/Soil study, 01 natural sciences, Normalized Difference Vegetation Index, Object analysis, Kernel (linear algebra), symbols.namesake, kernel methods, [MATH.MATH-ST]Mathematics [math]/Statistics [math.ST], 021101 geological & geomatics engineering, 0105 earth and related environmental sciences, object scale, Pixel, Covariance matrix, business.industry, [SDE.IE]Environmental Sciences/Environmental Engineering, Science des sols, grasslands, Kernel methods, Pattern recognition, 15. Life on land, Gaussian mean map kernels, Support vector machine, Kernel method, object analysis, Kernel (image processing), Grasslands, supervised classification, svm, gaussian mean map kernels, symbols, Supervised classification, General Earth and Planetary Sciences, Satellite Image Time Series, Artificial intelligence, [SDE.BE]Environmental Sciences/Biodiversity and Ecology, business
Abstract

International audience; This paper deals with the classification of grasslands using high resolution satellite image time series. Grasslands considered in this work are semi-natural elements in fragmented landscapes, i.e., they are heterogeneous and small elements. The first contribution of this study is to account for grassland heterogeneity while working at the object scale by modeling its pixels distributions by a Gaussian distribution. To measure the similarity between two grasslands, a new kernel is proposed as a second contribution: the a-Gaussian mean kernel. It allows to weight the influence of the covariance matrix when comparing two Gaussian distributions. This kernel is introduced in Support Vector Machine for the supervised classification of grasslands from south-west France. A dense intra-annual multispectral time series of Formosat-2 satellite is used for the classification of grasslands management practices, while an inter-annual NDVI time series of Formosat-2 is used for permanent and temporary grasslands discrimination. Results are compared to other existing pixel- and object-based approaches in terms of classification accuracy and processing time. The proposed method shows to be a good compromise between processing speed and classification accuracy. It can adapt to the classification constraints and it encompasses several similarity measures known in the literature. It is appropriate for the classification of small and heterogeneous objects such as grasslands.

Published
2017
Full Text
View/download PDF

12. Tree species classification in temperate forests using formosat-2 satellite image time series

Author

Jean-François Dejoux, Veliborka Josipović, David Sheeren, Mailys Lopes, Carole Planque, Mathieu Fauvel, Jérôme Willm, Dynamiques Forestières dans l'Espace Rural (DYNAFOR), Institut National de la Recherche Agronomique (INRA)-École nationale supérieure agronomique de Toulouse [ENSAT]-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées, Dynamiques et écologie des paysages agriforestiers (DYNAFOR), École nationale supérieure agronomique de Toulouse [ENSAT]-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE), Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées, Sheeren, David, Centre National d'Études Spatiales - CNES (FRANCE), Centre National de la Recherche Scientifique - CNRS (FRANCE), Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE), Institut National de la Recherche Agronomique - INRA (FRANCE), Institut de Recherche pour le Développement - IRD (FRANCE), Université Toulouse III - Paul Sabatier - UT3 (FRANCE), and Institut National Polytechnique de Toulouse - INPT (FRANCE)

Subjects
Time series, 010504 meteorology & atmospheric sciences, Biodiversité et Ecologie, Science, Multispectral image, Forest management, 0211 other engineering and technologies, whittaker, 02 engineering and technology, Overfitting, 01 natural sciences, phenology, Biodiversity and Ecology, forest, Temperate forest, espèce arborée, tree species, Forest ecology, time series, classification, smoothing, biodiversity, Forest, Milieux et Changements globaux, 021101 geological & geomatics engineering, 0105 earth and related environmental sciences, Remote sensing, Whittaker, Hyperspectral imaging, Biodiversity, 15. Life on land, Classification, Geography, Phenology, 13. Climate action, General Earth and Planetary Sciences, Satellite Image Time Series, [SDE.BE]Environmental Sciences/Biodiversity and Ecology, Temperate rainforest, Smoothing, Tree species, forêt tempérée
Abstract

International audience; Mapping forest composition is a major concern for forest management, biodiversity assessment and for understanding the potential impacts of climate change on tree species distribution. In this study, the suitability of a dense high spatial resolution multispectral Formosat-2 satellite image time-series (SITS) to discriminate tree species in temperate forests is investigated. Based on a 17-date SITS acquired across one year, thirteen major tree species (8 broadleaves and 5 conifers) are classified in a study area of southwest France. The performance of parametric (GMM) and nonparametric (k-NN, RF, SVM) methods are compared at three class hierarchy levels for different versions of the SITS: (i) a smoothed noise-free version based on the Whittaker smoother; (ii) a non-smoothed cloudy version including all the dates; (iii) a non-smoothed noise-free version including only 14 dates. Noise refers to pixels contaminated by clouds and cloud shadows. The results of the 108 distinct classifications show a very high suitability of the SITS to identify the forest tree species based on phenological differences (average κ=0.93 estimated by cross-validation based on 1235 field-collected plots). SVM is found to be the best classifier with very close results from the other classifiers. No clear benefit of removing noise by smoothing can be observed. Classification accuracy is even improved using the non-smoothed cloudy version of the SITS compared to the 14 cloud-free image time series. However conclusions of the results need to be considered with caution because of possible overfitting. Disagreements also appear between the maps produced by the classifiers for complex mixed forests, suggesting a higher classification uncertainty in these contexts. Our findings suggest that time-series data can be a good alternative to hyperspectral data for mapping forest types. It also demonstrates the potential contribution of the recently launched Sentinel-2 satellite for studying forest ecosystems.

Published
2016
Full Text
View/download PDF

13. Détermination du régime des feux en milieu de savane à Madagascar à partir de séries temporelles d'images MODIS

Author

Anne Jacquin, David Sheeren, Gérard Balent, and Véronique Chéret

Subjects
Brightness, Watershed, Spectral signature, 010504 meteorology & atmospheric sciences, Fire season, 0211 other engineering and technologies, 02 engineering and technology, 15. Life on land, Albedo, 01 natural sciences, Normalized Difference Vegetation Index, 13. Climate action, General Earth and Planetary Sciences, Environmental science, Spectral analysis, Scale (map), Cartography, 021101 geological & geomatics engineering, 0105 earth and related environmental sciences, Remote sensing
Abstract

In savannah areas where fire is a predominant practice, the localization and the monitoring of burned areas are essential information to develop an accurate management system of this ecosystem. This problem is addressed through the analysis of time series of medium spatial-resolution remotely sensed images. The authors studied the savannah localized on the Marovoay watershed, on the north-west coast of Madagascar. These present the particularity of a low vegetation cover. The methodological developments proposed in this article concern more specifically two domains: the spectral signature of burned areas and the method for mapping these areas. First, a spectral analysis is undertaken to assess the capacity of six spectral indexes NDVI, SAVI, BAI, GEMI, Albedo and Brightness Index to discriminate burned areas. Results show that the Brightness Index is the best. Then, a method for mapping annual burned areas at the scale of the watershed is developed. It is based on the processing of a MODIS eight-day composite times series over the period 2000–2007. Analysis of the intra-annual variations of the Brightness Index leads to the definition of two spatial indicators – annual and seasonal – elaborated to localize the burned areas and to determine the period at which the fire occurs within the fire season. The ROC curves are used as a threshold tool to define the optimal value of the burned area indicator that minimizes both omission and commission errors. The validation of the MODIS burned areas maps consists of the comparison with burned areas maps produced with high spatial-resolution remotely sensed images. The quality of the results is good, with a Kappa index between 0.74 and 0.76 and a cartographic index between 76% and 79%.

Published
2011
Full Text
View/download PDF

14. Tree species discrimination in temperate woodland using high spatial resolution Formosat-2 time series

Author

C. Planque, Jérôme Willm, David Sheeren, Jean-François Dejoux, Mathieu Fauvel, Dynamiques Forestières dans l'Espace Rural (DYNAFOR), Institut National de la Recherche Agronomique (INRA)-École nationale supérieure agronomique de Toulouse [ENSAT]-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées, Dynamiques et écologie des paysages agriforestiers (DYNAFOR), École nationale supérieure agronomique de Toulouse [ENSAT]-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE), Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées, and ProdInra, Migration

Subjects
[INFO.INFO-TS] Computer Science [cs]/Signal and Image Processing, Multispectral image, 0211 other engineering and technologies, 02 engineering and technology, Woodland, forest, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Forest ecology, Time series, satellite data, 021101 geological & geomatics engineering, Remote sensing, Hyperspectral imaging, 04 agricultural and veterinary sciences, Vegetation, 15. Life on land, [SDE.BE] Environmental Sciences/Biodiversity and Ecology, Support vector machine, Geography, classification, Habitat, 040103 agronomy & agriculture, identification, 0401 agriculture, forestry, and fisheries, [SDE.BE]Environmental Sciences/Biodiversity and Ecology, imagery
Abstract

National audience; Mapping tree species is an important issue for forest ecosystem services and habitat assessment. In this study, the ability of Formosat-2 multispectral image time series to discriminate thirteen tree species of temperate woodland is investigated. The discrimination is performed using several learning classifiers and testing three levels of classification. The classification accuracies in terms of kappa vary from 0.80 to 0.96 highlighting the benefits of using seasonal variations in spectral reflectance for tree species identification. The results suggest that time-series data can be a good alternative to hyperspectral data for mapping forest types. It also demonstrate the potential contribution of the forthcoming Sentinel-2 images for studying forest ecosystems.

Published
2015
Full Text
View/download PDF

15. Robust path opening versus path opening for the detection of hedgerows in rural landscapes

Author

Mathieu Fauvel, Hugues Talbot, François Cokelaer, David Sheeren, J. Chanussov, Mauro Dalla Mura, Carole Planque, ProdInra, Migration, Dynamiques Forestières dans l'Espace Rural (DYNAFOR), Institut National de la Recherche Agronomique (INRA)-École nationale supérieure agronomique de Toulouse [ENSAT]-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées, Dynamiques et écologie des paysages agriforestiers (DYNAFOR), École nationale supérieure agronomique de Toulouse [ENSAT]-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE), Université Joseph Fourier - Grenoble 1 (UJF), IFP Energies nouvelles (IFPEN), University of Iceland, LAB'URBA (LAB'URBA), Université Paris-Est Marne-la-Vallée (UPEM)-Université Paris-Est Créteil Val-de-Marne - Paris 12 (UPEC UP12), and Université Paris Est

Subjects
Flexibility (engineering), Rural landscapes, hedgerows detection, Geodesic, business.industry, Computer science, [SDV]Life Sciences [q-bio], 020206 networking & telecommunications, 02 engineering and technology, 15. Life on land, [SHS]Humanities and Social Sciences, [SDV] Life Sciences [q-bio], robust path opening, Path (graph theory), 0202 electrical engineering, electronic engineering, information engineering, very high spatial resolution images, 020201 artificial intelligence & image processing, Computer vision, Noise (video), Artificial intelligence, [SHS] Humanities and Social Sciences, support vector data description, business
Abstract

International audience; The automatic detection of hedgerows in very high resolution remote sensing images is addressed in this paper. In particular, the use of advanced morphological filters, such as path operators, is proposed. Conventional path openings have been already proposed in the literature to discriminate between forest objects and hedge objects in very high resolution optical images. They have shown greater flexibility with respect to geodesic openings. However, path operators are sensitive to noise and in practical situations they are likely to produce missed detections. In particular, path operators are unable to extract long hedgerows as a single object. In order to tackle this limitation, robust path openings are investigated in this work. In the experimental results, robust path opening shows superior performances for the detection of hedgerows.

Published
2014

16. Automatic Extraction of Forests from Historical Maps Based on Unsupervised Classification in the CIELab Color Space

Author

David Sheeren, Pierre-Alexis Herrault, Martin Paegelow, Mathieu Fauvel, Géographie de l'environnement (GEODE), Centre National de la Recherche Scientifique (CNRS)-Université Toulouse - Jean Jaurès (UT2J), Dynamiques Forestières dans l'Espace Rural (DYNAFOR), Institut National de la Recherche Agronomique (INRA)-Ecole Nationale Supérieure Agronomique de Toulouse-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées, Institut National de la Recherche Agronomique (INRA)-École nationale supérieure agronomique de Toulouse [ENSAT]-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Toulouse Le Mirail (Toulouse 2) (UTM), Université de Toulouse, PRES Toulouse University, Midi-Pyrenees, Danny Vandenbroucke, Bénédicte Bucher, Joep Crompvoets, ANR-10-JCJC-1804,MODE RESPYR,MODElisation Rétrospective et prospectivE des changements d'occupation des Sols dans les PYRénées(2010), French National Research Agency [ANR MODE-RESPYR 2010 1804 01-01], and Université Toulouse - Jean Jaurès (UT2J)-Centre National de la Recherche Scientifique (CNRS)

Subjects
Scheme (programming language), 010504 meteorology & atmospheric sciences, Computer science, Image quality, [SDV]Life Sciences [q-bio], Automatic procedure, 02 engineering and technology, Color space, 01 natural sciences, Image (mathematics), Early world maps, 0202 electrical engineering, electronic engineering, information engineering, Computer vision, automatic extraction, 0105 earth and related environmental sciences, computer.programming_language, historical maps, business.industry, Elevation, cielab color space, [SHS.GEO]Humanities and Social Sciences/Geography, 15. Life on land, GIS, Contour line, RGB color model, 020201 artificial intelligence & image processing, Artificial intelligence, historical maps based, business, computer
Abstract

Part II; International audience; In this chapter, we describe an automatic procedure to capture features on old maps. Early maps contain specific informations which allow us to reconstruct trajectories over time and space for land use/cover studies or urban area development. The most commonly used approach to extract these elements requires a user intervention for digitizing which widely limits its utilization. Therefore, it is essential to propose automatic methods in order to establish reproducible procedures. Capturing features automatically on scanned paper maps is a major challenge in GIS for many reasons: (1) many planimetric elements can be overlapped, (2) scanning procedure may conduct to a poor image quality, (3) lack of colors complicates the distinction of the elements. Based on a state of art, we propose a method based on color image segmentation and unsupervised classification (K-means algorithm) to extract forest features on the historical 'Map of France'. The first part of the procedure conducts to clean maps and eliminate elevation contour lines with filtering techniques. Then, we perform a color space conversion from RGB to L*a*b color space to improve uniformity of the image. To finish, a post processing step based on morphological operators and contextual rules is applied to clean-up features. Results show a high global accuracy of the proposed scheme for different excerpt of this historical map.

Published
2013
Full Text
View/download PDF

17. Detection of hedges in a rural landscape using a local orientation feature: from linear opening to path opening

Author

Jon Atli Benediktsson, Benoit Arbelot, David Sheeren, Jocelyn Chanussot, Mathieu Fauvel, Dynamiques Forestières dans l'Espace Rural (DYNAFOR), Institut National de la Recherche Agronomique (INRA)-Ecole Nationale Supérieure Agronomique de Toulouse-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées, SIGMAPHY (GIPSA-SIGMAPHY), Département Images et Signal (GIPSA-DIS), Grenoble Images Parole Signal Automatique (GIPSA-lab), Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Stendhal - Grenoble 3-Université Joseph Fourier - Grenoble 1 (UJF)-Institut Polytechnique de Grenoble - Grenoble Institute of Technology-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes (UGA)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Stendhal - Grenoble 3-Université Joseph Fourier - Grenoble 1 (UJF)-Institut Polytechnique de Grenoble - Grenoble Institute of Technology-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes (UGA)-Grenoble Images Parole Signal Automatique (GIPSA-lab), Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Stendhal - Grenoble 3-Université Joseph Fourier - Grenoble 1 (UJF)-Institut Polytechnique de Grenoble - Grenoble Institute of Technology-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes (UGA)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Stendhal - Grenoble 3-Université Joseph Fourier - Grenoble 1 (UJF)-Institut Polytechnique de Grenoble - Grenoble Institute of Technology-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes (UGA)-GIPSA Pôle Sciences des Données (GIPSA-PSD), Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Stendhal - Grenoble 3-Université Joseph Fourier - Grenoble 1 (UJF)-Institut Polytechnique de Grenoble - Grenoble Institute of Technology-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes (UGA)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Stendhal - Grenoble 3-Université Joseph Fourier - Grenoble 1 (UJF)-Institut Polytechnique de Grenoble - Grenoble Institute of Technology-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes (UGA), University of Iceland [Reykjavik], Cartographie et Géomatique (COGIT), Laboratoire des Sciences et Technologies de l'Information Géographique (LaSTIG), École nationale des sciences géographiques (ENSG), Institut National de l'Information Géographique et Forestière [IGN] (IGN)-Institut National de l'Information Géographique et Forestière [IGN] (IGN)-École nationale des sciences géographiques (ENSG), Institut National de l'Information Géographique et Forestière [IGN] (IGN)-Institut National de l'Information Géographique et Forestière [IGN] (IGN), Institut National de la Recherche Agronomique (INRA)-École nationale supérieure agronomique de Toulouse [ENSAT]-Institut National Polytechnique (Toulouse) (Toulouse INP), GIPSA - Signal Images Physique (GIPSA-SIGMAPHY), Université Stendhal - Grenoble 3-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Stendhal - Grenoble 3-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Grenoble Images Parole Signal Automatique (GIPSA-lab), Université Stendhal - Grenoble 3-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Stendhal - Grenoble 3-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS), Scientific Council of Toulouse INP, and University of Iceland

Subjects
Atmospheric Science, 010504 meteorology & atmospheric sciences, Computer science, 0211 other engineering and technologies, path opening, 02 engineering and technology, 01 natural sciences, directional morphological filters, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, local orientation, Computers in Earth Sciences, Spatial analysis, 021101 geological & geomatics engineering, 0105 earth and related environmental sciences, Feature detection (computer vision), Contextual image classification, Pixel, Orientation (computer vision), business.industry, Pattern recognition, Object detection, Detection, Feature (computer vision), very high spatial resolution image, Path (graph theory), Artificial intelligence, hedges, support vector data description, business, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing
Abstract

The detection of hedges is addressed in this paper. A hierarchical detection scheme in two steps is proposed. It is based on the use of both spatial information and spectral information in the detection process. First, woody elements are detected using the spectral information. From the membership map, the local orientation of each pixel is computed using directional filters. The morphological directional profile is defined as the composition of the outputs of directional filters with a varying orientation parameter. The local orientation feature is defined as the difference between the maximum and the minimum values of the morphological directional profile. A second detection step is done using the local orientation feature and the membership value to the woody elements class to extract the hedges. Experiments conducted on several real satellite images show that the method provides very good results in terms of detection accuracies. For one experiment, the overall accuracy is increased 80% to 91% with the proposed method. Furthermore, the methods is robust even if the size of the training samples is limited.

Published
2013
Full Text
View/download PDF

18. Hedges detection using local directional features and support vector data description

Author

Jocelyn Chanussot, Mathieu Fauvel, David Sheeren, Jon Atli Benediktsson, Dynamiques Forestières dans l'Espace Rural (DYNAFOR), Institut National de la Recherche Agronomique (INRA)-Ecole Nationale Supérieure Agronomique de Toulouse-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées, Cartographie et Géomatique (COGIT), Laboratoire des Sciences et Technologies de l'Information Géographique (LaSTIG), École nationale des sciences géographiques (ENSG), Institut National de l'Information Géographique et Forestière [IGN] (IGN)-Institut National de l'Information Géographique et Forestière [IGN] (IGN)-École nationale des sciences géographiques (ENSG), Institut National de l'Information Géographique et Forestière [IGN] (IGN)-Institut National de l'Information Géographique et Forestière [IGN] (IGN), SIGMAPHY (GIPSA-SIGMAPHY), Département Images et Signal (GIPSA-DIS), Grenoble Images Parole Signal Automatique (GIPSA-lab), Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Stendhal - Grenoble 3-Université Joseph Fourier - Grenoble 1 (UJF)-Institut Polytechnique de Grenoble - Grenoble Institute of Technology-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes (UGA)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Stendhal - Grenoble 3-Université Joseph Fourier - Grenoble 1 (UJF)-Institut Polytechnique de Grenoble - Grenoble Institute of Technology-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes (UGA)-Grenoble Images Parole Signal Automatique (GIPSA-lab), Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Stendhal - Grenoble 3-Université Joseph Fourier - Grenoble 1 (UJF)-Institut Polytechnique de Grenoble - Grenoble Institute of Technology-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes (UGA)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Stendhal - Grenoble 3-Université Joseph Fourier - Grenoble 1 (UJF)-Institut Polytechnique de Grenoble - Grenoble Institute of Technology-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes (UGA)-GIPSA Pôle Sciences des Données (GIPSA-PSD), Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Stendhal - Grenoble 3-Université Joseph Fourier - Grenoble 1 (UJF)-Institut Polytechnique de Grenoble - Grenoble Institute of Technology-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes (UGA)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Stendhal - Grenoble 3-Université Joseph Fourier - Grenoble 1 (UJF)-Institut Polytechnique de Grenoble - Grenoble Institute of Technology-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes (UGA), University of Iceland [Reykjavik], Institut National de la Recherche Agronomique (INRA)-École nationale supérieure agronomique de Toulouse [ENSAT]-Institut National Polytechnique (Toulouse) (Toulouse INP), GIPSA - Signal Images Physique (GIPSA-SIGMAPHY), Université Stendhal - Grenoble 3-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Stendhal - Grenoble 3-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Grenoble Images Parole Signal Automatique (GIPSA-lab), and Université Stendhal - Grenoble 3-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Stendhal - Grenoble 3-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)

Subjects
Structure (mathematical logic), 010504 meteorology & atmospheric sciences, Pixel, Computer science, Orientation (computer vision), business.industry, Detector, 0211 other engineering and technologies, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Pattern recognition, 02 engineering and technology, 01 natural sciences, Object detection, Image (mathematics), Support vector machine, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Computer vision, Artificial intelligence, business, Spatial analysis, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, 021101 geological & geomatics engineering, 0105 earth and related environmental sciences
Abstract

International audience; The detection of hedges in very high spatial resolution remote sensing image is discussed in the paper. A spatialspectral detector is proposed. The spatial information is modeled per pixel as the local orientation of the structure to which the pixel belongs. The local orientation is computed from the morphological directional profile built with a serie of linear openings in several directions. These features are used as inputs to a support vector data description, a detection algorithm. Experimental results on a real satellite image show that the local orientation helps in discriminating hedges from other woody elements, which is not possible using the spectral information only.

Published
2012
Full Text
View/download PDF

19. Mapping ash tree colonization in an agricultural mountain landscape: Investigating the potential of hyperspectral imagery

Author

G. Bertoni, A. Jacquin, Annick Gibon, Mathieu Fauvel, Sylvie Ladet, David Sheeren, Dynamiques Forestières dans l'Espace Rural (DYNAFOR), Institut National de la Recherche Agronomique (INRA)-École nationale supérieure agronomique de Toulouse [ENSAT]-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées, École nationale supérieure agronomique de Toulouse [ENSAT], Institut National Polytechnique (Toulouse) (Toulouse INP), and Université Fédérale Toulouse Midi-Pyrénées

Subjects
[SDV]Life Sciences [q-bio], SVM CLASSIFIER, 0211 other engineering and technologies, Hyperspectral imaging, Confusion matrix, 020206 networking & telecommunications, 02 engineering and technology, 15. Life on land, TREE SPECIES DETECTION, [SHS]Humanities and Social Sciences, Kernel alignment, Support vector machine, Svm classifier, Kernel (image processing), FRAXINUS EXCELSIOR L, HYPERSPECTRAL IMAGERY, 0202 electrical engineering, electronic engineering, information engineering, ENCROACHED GRASSLANDS, IMAGERIE SPECTRALE, Tree species, ECOLOGIE, 021101 geological & geomatics engineering, Remote sensing, Mathematics
Abstract

International audience; In this contribution, we evaluate the potential of hyperspectral imagery for identifying ash tree and other dominant species in encroached mountain grasslands. The method is based on a supervised approach using Support Vector Machines in which kernel parameters are fixed by kernel alignment. We present the application of the method and the first results obtained. The statistical measures derived from the confusion matrix show that tree species are well discriminated with accuracies > 90%. These results confirm the possibility of detecting tree species with this data and the performance of the SVM classifier.

Published
2011
Full Text
View/download PDF

20. Discriminating small wooded elements in rural landscape from aerial photography: a hybrid pixel/object-based analysis approach

Author

Gérard Balent, David Sheeren, Jean-Paul Lacombe, Sylvie Ladet, N. Bastin, Annie Ouin, Dynamiques Forestières dans l'Espace Rural (DYNAFOR), Institut National de la Recherche Agronomique (INRA)-Ecole Nationale Supérieure Agronomique de Toulouse-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées, Institut National de la Recherche Agronomique (INRA)-École nationale supérieure agronomique de Toulouse [ENSAT]-Institut National Polytechnique (Toulouse) (Toulouse INP), Institut National Polytechnique de Toulouse - INPT (FRANCE), Institut National de la Recherche Agronomique - INRA (FRANCE), and Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE)

Subjects
010504 meteorology & atmospheric sciences, Computer science, [SDU.STU.GP]Sciences of the Universe [physics]/Earth Sciences/Geophysics [physics.geo-ph], [SDE.MCG]Environmental Sciences/Global Changes, 0211 other engineering and technologies, [PHYS.PHYS.PHYS-GEO-PH]Physics [physics]/Physics [physics]/Geophysics [physics.geo-ph], 02 engineering and technology, 01 natural sciences, Aerial photography, Segmentation, Milieux et Changements globaux, 021101 geological & geomatics engineering, 0105 earth and related environmental sciences, Etudes de l'environnement, Pixel, Hedges, Object based, 15. Life on land, Remote sensing, Hybrid approach, Ancillary data, [SHS.ENVIR]Humanities and Social Sciences/Environmental studies, General Earth and Planetary Sciences, Géophysique, Landscape ecology, Cartography
Abstract

International audience; While small, fragmented wooded elements do not represent a large surface area in agricultural landscape, their role in the sustainability of ecological processes is recognized widely. Unfortunately, landscape ecology studies suffer from the lack of methods for automatic detection of these elements. We propose a hybrid approach using both aerial photographs and ancillary data of coarser resolution to automatically discriminate small wooded elements. First, a spectral and textural analysis is performed to identify all the planted-tree areas in the digital photograph. Secondly, an object-orientated spatial analysis using the two data sources and including a multi-resolution segmentation is applied to distinguish between large and small woods, copses, hedgerows and scattered trees. The results show the usefulness of the hybrid approach and the prospects for future ecological applications.

Published
2009
Full Text
View/download PDF

21. La morphologie mathématique binaire pour l'extraction automatique des bâtiments dans les images THRS

Author

David Sheeren, Sébastien Lefèvre, Jonathan Weber, Dynamiques Forestières dans l'Espace Rural (DYNAFOR), Institut National de la Recherche Agronomique (INRA)-École nationale supérieure agronomique de Toulouse [ENSAT]-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées, Laboratoire des Sciences de l'Image, de l'Informatique et de la Télédétection (LSIIT), Centre National de la Recherche Scientifique (CNRS), Université de Strasbourg (UNISTRA), and Institut National de la Recherche Agronomique (INRA)-Ecole Nationale Supérieure Agronomique de Toulouse-Institut National Polytechnique (Toulouse) (Toulouse INP)

Subjects
010504 meteorology & atmospheric sciences, Morphological filtering, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 0211 other engineering and technologies, SEGMENTATION, Binary number, 02 engineering and technology, Mathematical morphology, 01 natural sciences, MORPHOLOGIE MATHEMATIQUE, Computer vision, Segmentation, ComputingMilieux_MISCELLANEOUS, 021101 geological & geomatics engineering, 0105 earth and related environmental sciences, [INFO.INFO-DB]Computer Science [cs]/Databases [cs.DB], IMAGE SATELLITAIRE, business.industry, Binary image, General Medicine, Thresholding, Panchromatic film, Geography, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], RECONSTRUCTION GEODESIQUE, Artificial intelligence, IMAGERIE SCIENTIFIQUE, business, Smoothing, LISSAGE MORPHOLOGIQUE
Abstract

National audience; Cet article présente une nouvelle méthode de détection et d'extraction des bâtiments en milieu urbain à partir d'images satellitaires à très haute résolution spatiale. L'approche proposée est fondée sur l'application et l'enchaînement automatique d'opérateurs issus de la morphologie mathématique binaire. Plusieurs étapes constituent la méthode : (1) binarisation de l'image, (2) filtrage du bruit et des éléments de taille inférieure aux bâtiments par lissage morphologique, (3) détection des bâtiments par application d'une transformée en tout ou rien adaptative, avec un élément structurant de taille et de forme variable, (4) restauration de la forme des bâtiments par reconstruction géodésique. Deux stratégies différentes de binarisation sont proposées lors de l'étape initiale. La première consiste à binariser l'image par seuillage, le seuil étant défini soit de manière automatique, soit de manière empirique en fonction de l'image traitée. La seconde est fondée sur l'application d'une classification non supervisée pour laquelle le nombre de classes n'est pas fixé a priori. La méthode a été mise en oeuvre sur une image Quickbird panchromatique de la région de Strasbourg. Les résultats obtenus confirment l'intérêt et l'efficacité de l'approche.

Published
2007
Full Text
View/download PDF

22. Automatic building extraction in VHR images using advanced morphological operators

Author

Sebastien Lefevre, Jonathan Weber, David Sheeren, Laboratoire des Sciences de l'Image, de l'Informatique et de la Télédétection (LSIIT), Centre National de la Recherche Scientifique (CNRS), Dynamiques Forestières dans l'Espace Rural (DYNAFOR), Institut National de la Recherche Agronomique (INRA)-École nationale supérieure agronomique de Toulouse [ENSAT]-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées, and Institut National de la Recherche Agronomique (INRA)-Ecole Nationale Supérieure Agronomique de Toulouse-Institut National Polytechnique (Toulouse) (Toulouse INP)

Subjects
Structuring element, Computer science, business.industry, Feature extraction, 0211 other engineering and technologies, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Pattern recognition, 02 engineering and technology, Image segmentation, Mathematical morphology, Thresholding, Panchromatic film, Hit-or-miss transform, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Computer vision, Artificial intelligence, business, Image resolution, 021101 geological & geomatics engineering
Abstract

International audience; This paper presents a new method for buildings extraction in Very High Resolution (VHR) remotely sensed images based on binary mathematical morphology (MM) operators. The proposed approach involves several advanced morphological operators among which an adaptive hit-or-miss transform with varying sizes and shapes of the structuring element and a bidimensional granulometry intended to determine the optimal filtering parameters automatically. A clustering-based approach for image binarization is also introduced. This one avoids an empirical thresholding of input panchromatic images. Experiments made on a Quickbird VHR-image show the effectiveness of the method.

Published
2007
Full Text
View/download PDF

23. Discovering Rules with Genetic Algorithms to Classify Urban Remotely Sensed Data

Author

David Sheeren, Anne Puissant, Christiane Weber, Arnaud Quirin, Pierre Gançarski, Laboratoire des Sciences de l'Image, de l'Informatique et de la Télédétection (LSIIT), Université Louis Pasteur - Strasbourg I-Centre National de la Recherche Scientifique (CNRS), Identités et Différenciation de l'Environnement des Espaces et des Sociétés (IDEES), Université de Caen Normandie (UNICAEN), Normandie Université (NU)-Normandie Université (NU)-Université Le Havre Normandie (ULH), Normandie Université (NU)-Université de Rouen Normandie (UNIROUEN), Normandie Université (NU)-Centre National de la Recherche Scientifique (CNRS)-Institut de Recherche Interdisciplinaire Homme et Société (IRIHS), Université de Rouen Normandie (UNIROUEN), Normandie Université (NU)-Normandie Université (NU)-Université de Rouen Normandie (UNIROUEN), Normandie Université (NU), Image et ville (IV), Normandie Université (NU)-Normandie Université (NU)-Université de Caen Normandie (UNICAEN), Normandie Université (NU)-Université Le Havre Normandie (ULH), Normandie Université (NU)-Institut de Recherche Interdisciplinaire Homme et Société (IRIHS), Normandie Université (NU)-Centre National de la Recherche Scientifique (CNRS), Identité et Différenciation de l’Espace, de l’Environnement et des Sociétés (IDEES), Centre National de la Recherche Scientifique (CNRS)-Institut de Recherche Interdisciplinaire Homme et Société (IRIHS), and Normandie Université (NU)-Université de Caen Normandie (UNICAEN)

Subjects
010504 meteorology & atmospheric sciences, Computer science, Feature extraction, 0211 other engineering and technologies, Genetic programming, 02 engineering and technology, computer.software_genre, 01 natural sciences, Genetic algorithm, 021101 geological & geomatics engineering, 0105 earth and related environmental sciences, Remote Sensing Data, Genetic Algorithm, Contextual image classification, business.industry, Pattern recognition, [SHS.GEO]Humanities and Social Sciences/Geography, Image segmentation, Classification, Knowledge acquisition, Domain knowledge, Artificial intelligence, Data mining, business, computer, Classifier (UML)
Abstract

The classification methods applied in the object- oriented image analysis approach are often based on the use of domain knowledge. A key issue in this approach is the acquisition of this knowledge which is generally implicit and not formalized. In this paper, we examine the possibilities of using genetic programming for the automatic extraction of classification rules from urban remotely sensed data. The method proposed is composed of several steps: segmentation, feature extraction, selection of training sets, acquisition of rules, classification. Features related to the spectral, spatial and contextual properties of the objects are used in the classification procedure. Experiments are made on a Quickbird MS image. The quality of the results shows the effectiveness of the proposed genetic classifier in the object-oriented, knowledge-based approach.

Published
2006
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results