Search

The classification of tree species can significantly benefit from high spatial and spectral information acquired by unmanned aerial vehicles (UAVs) associated with advanced feature extraction and classification methods. Different from the traditional feature extraction methods, that highly depend on user’s knowledge, the convolutional neural network (CNN)-based method can automatically learn and extract the spatial-related features layer by layer. However, in order to capture significant features of the data, the CNN classifier requires a large number of training samples, which are hardly available when dealing with tree species in tropical forests. This study investigated the following topics concerning the classification of 14 tree species in a subtropical forest area of Southern Brazil: i) the performance of the CNN method associated with a previous step to increase and balance the sample set (data augmentation) for tree species classification as compared to the conventional machine learning methods support vector machine (SVM) and random forest (RF) using the original training data; ii) the performance of the SVM and RF classifiers when associated with a data augmentation step and spatial features extracted from a CNN. Results showed that the CNN classifier outperformed the conventional SVM and RF classifiers, reaching an overall accuracy (OA) of 84.37% and Kappa of 0.82. The SVM and RF had a poor accuracy with the original spectral bands (OA 62.67% and 59.24%) but presented an increase between 14% and 21% in OA when associated with a data augmentation and spatial features extracted from a CNN.

Made available in DSpace on 2020-12-12T01:54:59Z (GMT). No. of bitstreams: 0 Previous issue date: 2020-04-02 Fundação de Amparo à Pesquisa e Inovação do Estado de Santa Catarina Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq) Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES) The classification of tree species can significantly benefit from high spatial and spectral information acquired by unmanned aerial vehicles (UAVs) associated with advanced classification methods. This study investigated the following topics concerning the classification of 16 tree species in two subtropical forest fragments of Southern Brazil: i) the potential integration of UAV-borne hyperspectral images with 3D information derived from their photogrammetric point cloud (PPC); ii) the performance of two machine learning methods (support vector machine–SVM and random forest–RF) when employing different datasets at a pixel and individual tree crown (ITC) levels; iii) the potential of two methods for dealing with the imbalanced sample set problem: a new weighted SVM (wSVM) approach, which attributes different weights to each sample and class, and a deep learning classifier (convolutional neural network–CNN), associated with a previous step to balance the sample set; and finally, iv) the potential of this last classifier for tree species classification as compared to the above mentioned machine learning methods. Results showed that the inclusion of the PPC features to the hyperspectral data provided a great accuracy increase in tree species classification results when conventional machine learning methods were applied, between 13 and 17% depending on the classifier and the study area characteristics. When using the PPC features and the canopy height model (CHM), associated with the majority vote (MV) rule, the SVM, wSVM and RF classifiers reached accuracies similar to the CNN, which outperformed these classifiers for both areas when considering the pixel-based classifications (overall accuracy of 84.4% in Area 1, and 74.95% in Area 2). The CNN was between 22% and 26% more accurate than the SVM and RF when only the hyperspectral bands were employed. The wSVM provided a slight increase in accuracy not only for some lesser represented classes, but also some major classes in Area 2. While conventional machine learning methods are faster, they demonstrated to be less stable to changes in datasets, depending on prior segmentation and hand-engineered features to reach similar accuracies to those attained by the CNN. To date, CNNs have been barely explored for the classification of tree species, and CNN-based classifications in the literature have not dealt with hyperspectral data specifically focusing on tropical environments. This paper thus presents innovative strategies for classifying tree species in subtropical forest areas at a refined legend level, integrating UAV-borne 2D hyperspectral and 3D photogrammetric data and relying on both deep and conventional machine learning approaches. Division of Remote Sensing National Institute for Space Research (INPE) Department of Forest Engineering Santa Catarina State University (UDESC) Department of Electrical Engineering Pontifical Catholic University of Rio de Janeiro (PUC) Department of Sustainable Agro-Ecosystems and Bioresources Research and Innovation Centre Department of Geography Santa Catarina State University (UDESC) Department of Cartography São Paulo State University (UNESP) Department of Cartography São Paulo State University (UNESP) Fundação de Amparo à Pesquisa e Inovação do Estado de Santa Catarina: 2017TR1762 CNPq: 313887/2018-7 CAPES: 88882.330700/2018-01

This work explores the integration of airborne Light Detection and Ranging (LiDAR) data and WorldView-2 (WV2) images to classify the land cover of a subtropical forest area in Southern Brazil. Diff...

Recently, recurrent neural networks have been proposed for crop mapping from multitemporal remote sensing data. Most of these proposals have been designed and tested in temperate regions, where a single harvest per season is the rule. In tropical regions, the favorable climate and local agricultural practices, such as crop rotation, result in more complex spatio-temporal dynamics, where the single harvest per season assumption does not hold. In this context, a demand arises for methods capable of recognizing agricultural crops at multiple dates along the multitemporal sequence. In the present work, we propose to adapt two recurrent neural networks, originally conceived for single harvest per season, for multidate crop recognition. In addition, we propose a novel multidate approach based on bidirectional fully convolutional recurrent neural networks. These three architectures were evaluated on public Sentinel-1 data sets from two tropical regions in Brazil. In our experiments, all methods achieved state-of-the-art accuracies with a clear superiority of the proposed architecture. It outperformed its counterparts in up to 3.8% and 7.4%, in terms of per-month overall accuracy, and it was the best performing method in terms of F1-score for most crops and dates on both regions.

This work aims at investigating unsupervised and semi-supervised representation learning methods based on generative adversarial networks for remote sensing scene classification. The work introduces a novel approach, which consists in a semi-supervised extension of a prior unsupervised method, known as MARTA-GAN. The proposed approach was compared experimentally with two baselines upon two public datasets, UC-MERCED and NWPU-RESISC45. The experiments assessed the performance of each approach under different amounts of labeled data. The impact of fine-tuning was also investigated. The proposed method delivered in our analysis the best overall accuracy under scarce labeled samples, both in terms of absolute value and in terms of variability across multiple runs.

Knowing the spatial distribution of endangered tree species in a forest ecosystem or forest remnants is a valuable information to support environmental conservation practices. The use of Unmanned Aerial Vehicles (UAVs) offers a suitable alternative for this task, providing very high-resolution images at low costs. In parallel, recent advances in the computer vision field have led to the development of effective deep learning techniques for end-to-end semantic image segmentation. In this scenario, the DeepLabv3+ is well established as the state-of-the-art deep learning method for semantic segmentation tasks. The present paper proposes and assesses the use of DeepLabv3+ for mapping the threatened Dipteryx alata Vogel tree, popularly also known as cumbaru. We also compare two backbone networks for feature extraction in the DeepLabv3+ architecture: the Xception and MobileNetv2. Experiments carried out on a dataset consisting of 225 UAV/RGB images of an urban area in Midwest Brazil demonstrated that DeepLabv3+ was able to achieve in mean overall accuracy and Fl-score above 90%, and IoU above 80%. The experimental analysis also pointed out that the MobileNetv2 backbone overcame its counterpart by a wide margin due to its comparatively simpler architecture in view of the available training data.

Citrus producers need to monitor orchards frequently, and would benefit greatly from having automated tools to analyze aerial images acquired by drones over the plantations. However, analysing large aerial data sets to enable producers to take management decisions that would optimize productivity and sustainability over time and space remains challenging. Motivated by the success of deep learning in computer vision, this work proposes a novel approach based on Fully Convolutional Regression Networks and Multi-Task Learning to detect individual full-grown trees, tree seedlings, and tree gaps in citrus orchards for inventory tracking. We show that the proposal can identify eight-year-old orange trees with accuracy between 95–99% in high-density commercial plantations where adjacent crowns overlap. This quality of detection was achieved on RGB orthomosaics with a pixel size of about 9.5 cm and requires the nominal spacing between adjacent trees as a priori information. Our results also highlight that detecting tree seedlings and tree gaps remains a challenge. For these two categories, classification sensitivity (recall) was between 59–100% and 63–94%, respectively.

Deforestation is one of the major threats to natural ecosystems. This process has a substantial contribution to climate change and biodiversity reduction. Therefore, the monitoring and early detection of deforestation is an essential process for preservation. Techniques based on satellite images are among the most attractive options for this application. However, many approaches involve some human intervention or are dependent on a manually selected threshold to identify regions that suffer deforestation. Motivated by this scenario, the present work evaluates Deep Learning-based strategies for automatic deforestation detection, namely, Early Fusion (EF), Siamese Network (SN), and Convolutional Support Vector Machine (CSVM) as well as Support Vector Machine (SVM), used as the baseline. The target areas are two regions with different deforestation patterns: the Amazon and Cerrado biomes in Brazil. The experiments used two co-registered Landsat 8 images acquired at different dates. The strategies based on Deep Learning achieved the best performance in our analysis in comparison with the baseline, with SN and EF superior to CSVM and SVM. In the same way, a reduction of the salt-and-pepper effect in the generated probabilistic change maps was noticed as the number of training samples increased. Finally, the work assesses how the methods can reduce the time invested in the visual inspection of deforested areas.

The monitoring of agricultural activities at a regular basis is crucial to assure that the food production meets the world population demands, which is increasing yearly. Such information can be derived from remote sensing data. In spite of topic’s relevance, not enough efforts have been invested to exploit modern pattern recognition and machine learning methods for agricultural land-cover mapping from multi-temporal, multi-sensor earth observation data. Furthermore, only a small proportion of the works published on this topic relates to tropical/subtropical regions, where crop dynamics is more complicated and difficult to model than in temperate regions. A major hindrance has been the lack of accurate public databases for the comparison of different classification methods. In this context, the aim of the present paper is to share a multi-temporal and multi-sensor benchmark database that can be used by the remote sensing community for agricultural land-cover mapping. Information about crops in situ was collected in Luís Eduardo Magalhães (LEM) municipality, which is an important Brazilian agricultural area, to create field reference data including information about first and second crop harvests. Moreover, a series of remote sensing images was acquired and pre-processed, from both active and passive orbital sensors (Sentinel-1, Sentinel-2/MSI, Landsat-8/OLI), correspondent to the LEM area, along the development of the main annual crops. In this paper, we describe the LEM database (crop field boundaries, land use reference data and pre-processed images) and present the results of an experiment conducted using the Sentinel-1 and Sentinel-2 data.

Optical imagery is often affected by the presence of clouds. Aiming to reduce their effects, different reconstruction techniques have been proposed in the last years. A common alternative is to extract data from active sensors, like Synthetic Aperture Radar (SAR), because they are almost independent on the atmospheric conditions and solar illumination. On the other hand, SAR images are more complex to interpret than optical images requiring particular handling. Recently, Conditional Generative Adversarial Networks (cGANs) have been widely used in different image generation tasks presenting state-of-the-art results. One application of cGANs is learning a nonlinear mapping function from two images of different domains. In this work, we combine the fact that SAR images are hardly affected by clouds with the ability of cGANS for image translation in order to map optical images from SAR ones so as to recover regions that are covered by clouds. Experimental results indicate that the proposed solution achieves better classification accuracy than SAR based classification.

In tropical/subtropical regions, the favorable climate associated with the use of agricultural technologies, such as no tillage, minimum cultivation, irrigation, early varieties, desiccants, flowering inducing, and crop rotation, makes agriculture highly dynamic. In this letter, we present the Campo Verde agricultural database. The purpose of creating and sharing these data is to foster advancement of remote sensing technology in areas of tropical agriculture, primarily the development and testing of methods for crop recognition and agricultural mapping. Campo Verde is a municipality of Mato Grosso state, localized in the Cerrado (Brazilian Savanna) biome, in central west Brazil. Soybean, maize, and cotton are the primary crops cultivated in this region. Double cropping systems are widely adopted in this area. There is also livestock and forestry production. Our database provides the land-use classes for 513 fields by month for one Brazilian crop year (between October 2015 and July 2016). This information was gathered during two field campaigns in Campo Verde (December 2015 and May 2016) and by visual interpretation of a time series of Landsat-8/Operational Land Imager (OLI) images using an experienced interpreter. A set of 14 preprocessed synthetic aperture radar Sentinel-1 and 15 Landsat-8/OLI mosaic images is also made available. It is important to promote the use of radar data for tropical agricultural applications, especially because the use of optical remote sensing in these regions is hindered by the high frequency of cloud cover. To demonstrate the utility of our database, results of an experiment conducted using the Sentinel-1 data set are presented.

This paper proposes a new distributed architecture for supervised classification of large volumes of earth observation data on a cloud computing environment. The architecture supports distributed execution, network communication, and fault tolerance in a transparent way to the user. The architecture is composed of three abstraction layers, which support the definition and implementation of applications by researchers from different scientific investigation fields. The implementation of architecture is also discussed. A software prototype (available online), which runs machine learning routines implemented on the cloud using the Waikato Environment for Knowledge Analysis (WEKA), a popular free software licensed under the GNU General Public License, is used for validation. Performance issues are addressed through an experimental analysis in which two supervised classifiers available in WEKA were used: random forest and support vector machines. This paper further describes how to include other classification methods in the available software prototype.

The rapid increase in the number of aerial and orbital Earth observation systems is generating a huge amount of remote sensing data that need to be readily transformed into useful information for policy and decision makers. This exposes an urgent demand for image interpretation tools that can deal efficiently with very large volumes of data. In this work, we introduce a set of methods that support distributed processing of georeferenced raster and vector data in a computer cluster, which may be a virtual cluster provided by cloud computing infrastructure services. The set of methods comprise a particular technique for indexing distributed georeferenced datasets, as well as strategies for distributing efficiently the processing of spatial context-aware operations. They provide the means for the development of scalable applications, capable of processing large volumes of geospatial data. We evaluated the proposed methods in a remote sensing image interpretation application, built on the MapReduce framework, and executed in a cloud computing infrastructure. The experimental results corroborate the capacity of the methods to support efficient handling of very large earth observation datasets.

Deforestation is one of the main causes of biodiversity reduction, climate change among other destructive phenomena. Thus, early detection of deforestation processes is of paramount importance. Motivated by this scenario, this work presents an evaluation of methods for automatic deforestation detection, specifically Early Fusion (EF) Convolutional Network, Siamese Convolutional Network (S-CNN) and the well-known Support Vector Machine (SVM), taken as the baseline. These methods were evaluated in a region of the Brazilian Legal Amazon (BLA). Two Landsat 8 images acquired in 2016 and 2017 were used in our experiments. The impact of training set size was also investigated. The Deep Learning-based approaches clearly outperformed the SVM baseline in our approaches, both in terms of F1-score and Overall Accuracy, with a superiority of S-CNN over EF.

Accurate crop type identification and crop area estimation from remote sensing data in tropical regions are still considered challenging tasks. The more favorable weather conditions, in comparison to the characteristic conditions of temperate regions, permit higher flexibility in land use, planning, and management, which implies complex crop dynamics. Moreover, the frequent cloud cover prevents the use of optical data during large periods of the year, making SAR data an attractive alternative for crop mapping in tropical regions. This paper evaluates the effectiveness of Deep Learning (DL) techniques for crop recognition from multi-date SAR images from tropical regions. Three DL strategies are investigated: autoencoders, convolutional neural networks, and fully-convolutional networks. The paper further proposes a post-classification technique to enforce prior knowledge about crop dynamics in the target area. Experiments conducted on a Sentinel-1 multitemporal sequence of a tropical region in Brazil reveal the pros and cons of the tested methods. In our experiments, the proposed crop dynamics model was able to correct up to 16.5% of classification errors and managed to improve the performance up to 3.2% and 8.7% in terms of overall accuracy and average F1-score, respectively.

This paper proposes a distributed strategy for region-growing segmentation of arbitrarily large images. The strategy is suited for most distributed architectures, including cloud-computing environments. It focuses on handling very large data and tackles the main problem of tiled-based segmentation: artifacts that occur in the segments adjacent to tile borders. Our proposal is to use a specific indexing mechanism and a hierarchical stitching method to suppress segmentation artifacts. The strategy was validated by a series of experiments carried out on a virtual cluster in a commercial cloud-computing infrastructure, over WorldView-2 images of different sizes. The experiments demonstrated that the proposed strategy is able to eliminate tile-based segmentation artifacts. The experimental analysis further showed that the strategy brings significant gains in terms of processing time, particularly for very large images, as more processing units are added to the distributed processing infrastructure.

This letter evaluates metaheuristics for the supervised parameter tuning of multiresolution-region-growing segmentation. Three groups of metaheuristics are tested in terms of convergence speed and solution quality. Generalized pattern search, mesh adaptive direct search, and Nelder–Mead represent the single-solution group. Differential evolution (DE) represents the population group. DE followed by each of the aforementioned single-solution metaheuristics represents the hybrid metaheuristic group. This letter reveals that the optimization objective functions typically have countless local minima, many of them leading to very poor solutions. Experiments on three data sets demonstrated that single-solution-based methods often lead to a solution with unacceptable quality. DE was less susceptible to be stuck in local minima when compared to single-solution methods, but it was slower in reaching the minima. Moreover, hybrid methods presented the best tradeoff between accuracy and convergence speed.

This paper presents a method to estimate the temporal interaction in a Conditional Random Field (CRF) based approach for crop recognition from multitemporal remote sensing image sequences. This approach models the phenology of different crop types as a CRF. Interaction potentials are assumed to depend only on the class labels of an image site at two consecutive epochs. In the proposed method, the estimation of temporal interaction parameters is considered as an optimization problem, whose goal is to find the transition matrix that maximizes the CRF performance, upon a set of labelled data. The objective functions underlying the optimization procedure can be formulated in terms of different accuracy metrics, such as overall and average class accuracy per crop or phenological stages. To validate the proposed approach, experiments were carried out upon a dataset consisting of 12 co-registered LANDSAT images of a region in southeast of Brazil. Pattern Search was used as the optimization algorithm. The experimental results demonstrated that the proposed method was able to substantially outperform estimates related to joint or conditional class transition probabilities, which rely on training samples.

Made available in DSpace on 2020-12-12T01:18:55Z (GMT). No. of bitstreams: 0 Previous issue date: 2020-03-01 Per-point classification is a traditional method for remote sensing data classification, and for radar data in particular. Compared with optical data, the discriminative power of radar data is quite limited, for most applications. A way of trying to overcome these diculties is to use Region-Based Classification (RBC), also referred to as Geographical Object-Based Image Analysis (GEOBIA). RBC methods first aggregate pixels into homogeneous objects, or regions, using a segmentation procedure. Moreover, segmentation is known to be an ill-conditioned problem because it admits multiple solutions, and a small change in the input image, or segmentation parameters, may lead to significant changes in the image partitioning. In this context, this paper proposes and evaluates novel approaches for SAR data classification, which rely on specialized segmentations, and on the combination of partial maps produced by classification ensembles. Such approaches comprise a meta-methodology, in the sense that they are independent from segmentation and classification algorithms, and optimization procedures. Results are shown that improve the classification accuracy from Kappa = 0.4 (baseline method) to a Kappa = 0.77 with the presented method. Another test site presented an improvement from Kappa = 0.36 to a maximum of 0.66 also with radar data. Image Processing Division National Institute for Space Research (INPE) Department of Informatics and Computer Sciences Rio de Janeiro State University (UERJ) Department of Electrical Engineering Pontifical Catholic University of Rio de Janeiro (PUC-Rio) Institute of Science and Technology São Paulo State University (Unesp) Institute of Science and Technology São Paulo State University (Unesp)

Agriculture monitoring is a key task for producers, governments and decision makers. The analysis of multitemporal remote sensing data provides a cost-effective way to perform this task. Recurrent Neural Networks (RNNs) have been successfully used in temporal modeling problems, while Convolutional Neural Networks (CNNS) are the state-of-the-art in image classification, mainly due to their ability to capture spatial context. In this work, we propose the use of a hybrid network architecture for crop mapping that combines RNNs and CNNs. We evaluate this architecture experimentally upon a Sentinel-1A database from a tropical region in Brazil. The ability of recurrent networks to model temporal context is compared with the conventional image stacking approach. The impact of using CNN learned features rather than context aware handcrafted features is also investigated. In our analysis the hybrid architecture achieved better average class accuracy than alternative approaches based on image stacking and GLCM features.

This work presents a dense fully convolutional architecture for crop type recognition from multitemporal RS images. Basically, we adapted a dense fully convolutional net to deal with stacks of multitemporal data. The proposed approach was tested upon a public dataset comprising two Sentinel-1A sequences from a tropical region in South America. We took as baseline a dense convolutional network designed for patch classification. Thematic and spatial accuracy, as well as the computational load were evaluated experimentally. The proposed architecture matched the baseline in terms of recognition rates and proved to be very efficient computationally in the inference phase.

Visual tracking is a challenging task due to a number of factors, such as occlusions, deformations, illumination variations and abrupt motion changes present in a video sequence. Generally, trackers are robust to some of these factors, but do not achieve satisfactory results when dealing with multiple factors at the same time. More robust results when multiple factors are present can be obtained by combining the results of different trackers. In this paper we propose a multiple tracker fusion method, named Symbiotic Tracker Ensemble with Feedback Learning (SymTE-FL), which combines the results of a set of trackers to produce a unified tracking estimate. The novelty of the method consists in providing feedback to the individual trackers, so that they can correct their own estimates, thus improving overall tracking accuracy. The proposal is validated by experiments conducted upon a publicly available database. The results show that the proposed method delivered in average more accurate tracking estimates than those obtained with individual trackers running independently and with the original approach.

This work presents a spatio-temporal Conditional Random Field (CRF) based model for crop recognition from multi-temporal remote sensing image sequences. The association potential at each image site is based on the class posterior probabilities computed by a Random Forest (RF) classifier given the features at the corresponding site. A contrast-sensitive Potts model is used as a label smoothing method in the spatial domain, whereas the interactions in the temporal domain are modeled based on expert knowledge about the possible transitions between adjacent epochs. The CRF based model was tested for crop mapping in two subtropical areas based on a sequences of 9 Landsat and 14 Sentinel-1 images from Ipua, Sao Paulo and Campo Verde, Mato Grosso, respectively, two municipalities in Brazil. The experiments showed significant improvements of the accumulated F1 score per class against a mono-temporal CRF approach of up to 50% and 75% for a total of 8 and 11 classes using Optical and SAR images respectively.

Detection and classification of tree species from remote sensing data were performed using mainly multispectral and hyperspectral images and Light Detection And Ranging (LiDAR) data. Despite the comparatively lower cost and higher spatial resolution, few studies focused on images captured by Red-Green-Blue (RGB) sensors. Besides, the recent years have witnessed an impressive progress of deep learning methods for object detection. Motivated by this scenario, we proposed and evaluated the usage of Convolutional Neural Network (CNN)-based methods combined with Unmanned Aerial Vehicle (UAV) high spatial resolution RGB imagery for the detection of law protected tree species. Three state-of-the-art object detection methods were evaluated: Faster Region-based Convolutional Neural Network (Faster R-CNN), YOLOv3 and RetinaNet. A dataset was built to assess the selected methods, comprising 392 RBG images captured from August 2018 to February 2019, over a forested urban area in midwest Brazil. The target object is an important tree species threatened by extinction known as Dipteryx alata Vogel (Fabaceae). The experimental analysis delivered average precision around 92% with an associated processing times below 30 miliseconds.

This work proposes and evaluates strategies based on Stacked Supervised Auto-Encoders (SSAE) for face representation in video surveillance applications. The study focuses on the identification task with a single sample per person (SSPP) in the gallery. Variations in terms of pose, facial expression, illumination and occlusion are approached in two ways. First, the SSAE extracts features from face images, which are robust to such variations. Second, we propose methods to exploit the multiple samples per persons probes (MSPPP) that can be extracted from video sequences. Three variants of the proposed method are compared upon HONDA/UCSD and VIDTIMIT video datasets. The experimental results demonstrate that strategies combining SSAE and MSPPP are able to outperform other SSPP methods, such a local binary patterns, in face recognition from video.