Search

This paper investigates the invasion of a reach of the Touws River by the deciduous alien tree Tamarix ramosissima Ledeb. (Pink Tamarisk, Saltcedar). The objectives of the paper were to investigate the utility of a delta-normalised difference vegetation index (dNDVI) in evaluating the status, pattern and process of invasion, and to evaluate the implications of the invasion for riverscape morphodynamics and physical habitat structure and function. The spectral classification developed had an overall accuracy of 59.89%, omission error of 28.25%, and commission error of 11.86%. The classification of vegetation was used to quantify the aerial extent and pattern of invasion (currently at least 65.50% of the valley floor vegetation cover). Field observations and existing knowledge of seed dispersal mechanisms and germination constraints of the invasive tree were compared with those of the indigenous sweet thorn Vachellia karroo, to provide insight into invasion patterns and processes within the reach. The linear channel-flanking distribution of the invasion has the potential to alter reach hydrology and morphodynamics, which are key building blocks of physical habitat structure and function. The spectral classification approach demonstrated is relatively simple, has a strong biophysical basis in that it exploits a known, predictable and observable seasonal vegetation response that produces a clear spectral signature, and can be applied to long reaches of rivers impacted by alien vegetation invasions. [ABSTRACT FROM AUTHOR]

The study anticipated to understand sand encroachment evolution through analysis of sand contribution across space and time using remote sensing in Laâyoune-Tarfaya basin, Morocco, over the period from 1987 to 2011. The assessment based on supervised classifications of Landsat imagery orthorectified data, using Maximum Likelihood (ML), Minimum Distance (MD) and Support Vector Machine (SVM) classifiers. In order to ameliorate the information, principal components analysis (PCA) and co-occurrence measurement algorithm were used for choosing bands and data transformation. Images differencing was applied on image pairs derived from classification to analyze sand encroachment evolution. All classifiers present enhanced performances, and revealed that area covered by sand was increased by 7%, 4.66% and 4.59% for ML, MD and SVM, respectively. Consequently, images differencing results confirmed that sand material increasing arise not only from coastal area contribution but also mostly from erosion of complicated sand dunes exist in the middle part of the studied area. Evaluating of the presented phenomenon dimensions and its consequences are extremely important to increase the local authorities awareness and mainly for avoiding or minimizing the consequences of the future sand dunes threats. [ABSTRACT FROM AUTHOR]

Vegetation classification is a fundamental task in several applications such as forest management, remote sensing-based crop monitoring, and mitigation of plant diseases, digital prototyping of plants, and plant phenotyping, among others. We propose a novel supervoxel-based methodology to accurately detect vegetation from small-footprint full-waveform airborne laser scanning data in urban and mountainous scenes. Mathematically, the full-waveform decomposition and fitting model based on multiple kernels is presented to generate high-density 3D point clouds and their relevant attributes. The homogeneous supervoxels are then generated by using an enhanced probability density clustering (PDC) algorithm. For each supervoxel, we employ latent Dirichlet allocation to obtain supervoxels features through generalisation of geometric and full-waveform features of point clouds. The Support Vector Machine (SVM) and ensemble classifier random forest (RF) are used to classify these supervoxels into vegetation and non-vegetation. Our experiments on urban and mountainous scenes demonstrate that our approach achieves an overall accuracy of 98.27% and 96.47% respectively by RF classifier and achieves an overall accuracy of 98.16% and 97.67% on the same data sets by SVM classifier. By integrating full-waveform information and more meaningful generalised features, our method outperforms state-of-the-art methods at preserving a trade-off between missing alarm rate and false alarm rate. [ABSTRACT FROM PUBLISHER]

During recent years, many studies have been undertaken to investigate how spectral characteristics of forests can provide information on spatial patterns of tree species diversity (TSD). Important advances have been made, and significant relationships between TSD and remotely sensed indicators of net primary productivity and environmental heterogeneity have been reported. However, the season-dependence of these relationships has not yet been fully investigated, and the influence of phenology remains poorly understood. In this study, we aim to assess how the relationships between remote sensing indicators and TSD depend on the season of the year. TSD measures, including species richness, Shannon’s diversity and Simpson’s diversity, were determined for 82 field plots in the Afromontane cloud forests of Taita Hills, Kenya. A time series of 15 Landsat images were used to calculate a set of spectral and heterogeneity metrics. The relationship between remote-sensing metrics and TSD measures was analysed by simple and multivariate regression analysis. We conclude that the relationships between remote-sensing metrics and TSD are season-dependent. Hence, it is demonstrated the date of image acquisition is an important aspect to be considered in biodiversity studies. Given that the dependence of the relationships is closely linked to climate seasonality defining vegetation phenology, the relationships may also vary according to geographical conditions. [ABSTRACT FROM AUTHOR]

In this article, a vegetation classification hypothesis based on plant biochemical composition is presented. The basic idea of this hypothesis is that the vegetation species/crops have their own biochemical composition characteristics, which are separable from each other for those co-existing species at a specific region. Therefore, vegetation species can be classified based on the biochemical composition characteristics, which can be retrieved from hyperspectral remote-sensing data. In order to test this hypothesis, an experiment was conducted in north-western China. Field data on the biochemical compositions and spectral responses of different plants and an Earth-observing 1 (EO-1) Hyperion image were simultaneously collected. After analysing the relationship between biochemical composition and spectral data collected from Hyperion, the vegetation biochemical compositions were estimated using sample biochemical data and bands of Hyperion data. The vegetation classification was completed using the biochemical content classifier (BCC) and maximum-likelihood classifier (MLC) with all Hyperion bands (MLC_A) and selected bands (MLC_S), which were used for estimating considered biochemical contents (cellulose and carotenoid). The overall classification accuracy of the BCC (95.2%) was as good as MLC_S (95.2%) and better than MLC_A (91.1%), as was the kappa value (BCC 92.849%, MLC_S 92.845%, MLC_A 86.637%), suggesting that the BCC was a feasible classification method. The biochemical-based classification method has higher vegetation classification accuracy and execution speed, reduces data dimension and redundancy and needs only a few spectral bands to retrieve biochemical contents instead of using all of the spectral bands. It is an effective method to classify vegetation based on plant biochemical composition characteristics. [ABSTRACT FROM AUTHOR]

Multispectral data from the Landsat 5 (L5) Thematic Mapper (TM) sensor provide the backbone of the extensive archive of moderate-resolution Earth imagery. Even after more than 24 years of service, the L5 TM is still operational. Given the longevity of the satellite, the detectors have aged and the sensor's radiometric characteristics have changed since launch. The calibration procedures and parameters in the National Land Archive Production System (NLAPS) have also changed with time. Revised radiometric calibrations in 2003 and 2007 have improved the radiometric accuracy of recently processed data. This letter uses the Normalized Difference Vegetation Index (NDVI) as a metric to evaluate the radiometric calibration. The calibration change has improved absolute calibration accuracy, consistency over time, and consistency with Landsat 7 (L7) Enhanced Thematic radiometry and will provide the basis for continued long-term studies of the Earth's land surfaces. [ABSTRACT FROM AUTHOR]

The extraction of texture features from high-resolution remote sensing imagery provides a complementary source of data for those applications in which the spectral information is not sufficient for identification or classification of spectrally similar landscape features. This study presents the results of grey-level co-occurrence matrix (GLCM) and wavelet transform (WT) texture analysis for forest and non-forest vegetation types differentiation in QuickBird imagery. Using semivariogram fitting, the optimal GLCM windows for the land cover classes within the scene were determined. These optimal window sizes were then applied to eight GLCM texture measures (mean, variance, homogeneity, dissimilarity, contrast, entropy, angular second moment, and correlation) for the scene classification. Using wavelet transformation, up to five levels of macro-texture were computed and tested in the classification process. Comparing the classification results, (1) the spectral-only bands classification gave an overall accuracy of 58.69%; (2) the statistically derived 21×21 optimal mean texture combined with spectral information gave the best results among the GLCM optimal windows with an accuracy of 73.70%; and (3) the combined optimal WT-texture levels 4 and 5 gave an accuracy of 63.56%. The combined classification of these three optimal results gave an overall accuracy of 77.93%. The results indicate that even though vegetation texture was generally measured better by the GLCM-mean texture (micro-textures) than by WT-derived texture (macro-textures), the results show that the micro-macro texture combination would improve the differentiation and classification of the overall vegetation types. Overall, the results suggests that computer-assisted classification of high-spatial-resolution remotely sensed imagery has a good potential to augment the present ground-based forest inventory methods. [ABSTRACT FROM AUTHOR]

The relevance vector machine (RVM), a Bayesian extension of the support vector machine (SVM), has considerable potential for the analysis of remotely sensed data. Here, the RVM is introduced and used to derive a multi-class classification of land cover with an accuracy of 91.25%, a level comparable to that achieved by a suite of popular image classifiers including the SVM. Critically, however, the output of the RVM includes an estimate of the posterior probability of class membership. This output may be used to illustrate the uncertainty of the class allocations on a per-case basis and help to identify possible routes to further enhance classification accuracy. [ABSTRACT FROM AUTHOR]

Though the multi-classifier system (MCS) has been used widely in the area of machine learning, it has rarely been used in processing remotely sensed data. To test whether MCS could improve land cover classification results from remote sensing imagery, conservative voting, majority voting, and plurality voting were processed to combine individual classification results in this study. Considering the characteristics of high spatial resolution imagery, object-oriented classification methods were employed. Firstly, the objects were acquired by segmenting the original images at two scales; then taking the "objects" as the classification units, five kinds of classifiers iterative self-organising data analysis (ISODATA), Mahalanobis distance, maximum likelihood, neural network, and expert system were selected to classify urban vegetation categories using different samples and feature spaces to maintain independence among individual classifiers. The three voting rules were then used to combine the individual classification results. For unclassified objects, the ISODATA method was used again to identify their categories. The accuracy assessment showed that the three combined classification results gained higher accuracy than the individual classifier, and the plurality voting rules obtained the best identification results. [ABSTRACT FROM AUTHOR]

The difficulty of collecting information at conventional field studies and relatively coarse spatial and spectral resolution of Landsat images forced the use of environmental variables as ancillary data in vegetation mapping. The aim of this study is to increase the accuracy of species level vegetation classification incorporating environmental variables in the Amanos Mountains region of southern central Turkey. In the first part of the study, ordinary vegetation classification is attained by using a maximum likelihood method to Landsat images with the help of forest management maps. Discriminant analysis is used in the second part of the study in two different stages. First, Fisher's linear equations for each of the pre‐defined nine vegetation groups are calculated and values of the pixels are assigned by the greatest probability value. Second, distance raster value of maximum likelihood classification is used as a threshold. The distance raster pixels having values less than one is accepted as misclassified and replaced with the results of discriminant analysis results. As a result of this study 19.6 % increase in overall accuracy is obtained by using the relationships between environmental variables and vegetation existence. [ABSTRACT FROM AUTHOR]

Leaf area index (LAI) is a key parameter of atmosphere–vegetation exchanges, affecting the net ecosystem exchange and the productivity. At regional or continental scales, LAI can be estimated by remotely‐sensed spectral vegetation indices (SVI). Nevertheless, relationships between LAI and SVI show saturation for LAI values greater than 3–5. This is one of the principal limitations of remote sensing of LAI in forest canopies. In this article, a new approach is developed to determine LAI from the spatial variability of radiometric data. To test this method, in situ measurements for LAI of 40 stands, with three dominant species (European beech, oak and Scots pine) were available over 5 years in the Fontainebleau forest near Paris. If all years and all species are pooled, a good linear relationship without saturation is founded between average stand LAI measurements and a model combining the logarithm of the standard deviation and the skewness of the normalized difference vegetation index (NDVI) ( R 2 = 0.73 rmse = 1.08). We demonstrate that this relation can be slightly improved by using different linear models for each year and each species ( R 2 = 0.82 rmse = 0.86), but the standard deviation is less sensitive to the species and the year effects than the mean NDVI and is therefore a performing index. [ABSTRACT FROM AUTHOR]

Image classification of historical aerial photographs is very useful for the study of medium-to-long term (10–50 years) vegetation changes. To determine the quality of information derived from the classification process, accuracy assessment of the classification is implemented. Error matrix, which is primarily used in remote sensing for accuracy assessment, is typically based on an evaluation of the derived classification against some ‘ground truth’ or reference dataset. Regrettably ‘ground truths’ for some old historical photographs are rarely available. To solve this problem we formulate, in this Part I, methods of classification of aerial photographs and computation of accuracy assessment parameters of classification products in the absence of ground data, using the fuzzy classification technique. In addition, since point estimates of these accuracy parameters require associated standard errors, in order to be useful for statistical analysis, the method of computation of standard errors of accuracy measures using the bootstrap resampling techniques is presented. These methods are tested with historical aerial photographs, of part of Adulam Nature Reserve, Israel, spanning a period of 51 years. Results illustrate the applicability and efficiency of the proposed methods. [ABSTRACT FROM AUTHOR]

The objective of this study is to find a better method for sub-pixel classification of vegetation. The proposed new technique of a linear mixing model (LMM) is the sequential combination of spectral LMM and temporal LMM. Sub-pixel components of 'relative green vegetation' are derived by spectral LMM; sub-pixel components of vegetation types are estimated by subsequent temporal LMM. The proposed method was applied to five temporal Landsat Enhanced Thematic Mapper (ETM) images for the year 2000 for areas south of Lake Baikal, Russia. Dominant vegetation types there are pine, birch/aspen, shrubs and wheat with weedy plants. Ground truth data of vegetation types were prepared by field survey and visual interpretation of Landsat ETM images by experts. Both the comparisons of classification results among the proposed method and conventional LMM methods and the simulation results among them indicate that the proposed spectral and temporal LMM has better accuracy than conventional methods. [ABSTRACT FROM AUTHOR]

A classification procedure for National Oceanic and Atmospheric Administration Advanced Very High Resolution Radiometer (NOAA AVHRR) data based on image segmentation following supervised classification by regions is presented. The procedure was appliedto channel 1 (0.58-0.68 mu m) and channel 2 (0.72-1.10 mu m) AVHRR mosaics composed of images acquired between 13 and 26 June 1993 for the state of Mato Grosso, Brazil. Eight vegetation classes were identified using this procedure. The result was compared with an existing vegetation map of Mato Grosso state for reference. The quantitative evaluation yielded a kappa coefficient of 0.4. The result indicate that image segmentation and supervised classification by regions is a procedure that is useful for mapping vegetation classes on a regional scale. [ABSTRACT FROM AUTHOR]