A hierarchical approach to Compact Airborne Spectrographic Imager (CASI) high-resolution image classification of Little Miami River Watershed for environmental modelling

Compact Airborne Spectrographic Imager (CASI) hyperspectral imagery was acquired over the Little Miami River Watershed in Ohio, USA, which was one of the largest hyperspectral image acquisitions. A hierarchical approach was employed using two different classification algorithms: ‘image object segmentation’ for level 1 and ‘spectral angle mapper’ (SAM) for level 2. This classification scheme was developed to overcome the spectral inseparability of urban and rural features and to deal with radiometric distortions due to cross-track illumination. The land‐use/land‐cover (LULC) classes were urban/built, corn, soya bean, wheat, forest, dry herbaceous, grass, lentic, lotic, urban barren, rural barren and unclassified. The final phase of processing was completed after an extensive quality assurance and quality control (QA/QC) phase with 902 points. The overall accuracy was 83.9%. The data set was made available for public research and application; certainly, this product represents an improvement over more commonly utilized, coarser spatial resolution data sets such as National Land Cover Data (NLCD).     

An assessment of two classification methods for mapping Thames Estuary intertidal habitats using CASI data

The aim of this study was to find the most appropriate method of classification for the Thames intertidal habitat types at Crayford Marsh and Dartford Creek by using Compact Airborne Spectrographic Imager (CASI ) data. Preliminary evaluation of commonly available classification algorithms produced two candidate techniques: the Maximum Likelihood Classifier (MLC) and the Spectral Angle Mapper (SAM). Pre-classification enhancements and the two different classifiers were compared. Ten different dataset combinations were created for two pilot sites: one at Crayford Marsh and one at Dartford Creek. These consisted of the original CASI bandset (15 bands in spatial mode from blue to near-infrared) and nine other combinations resulting from band subsets, Principal Component Analysis (PCA) and Normalized Difference Vegetation Index (NDVI ). Twelve classes were established for each site although only some of these were common to both. Each classified image was accuracy assessed using a combination of field mapping, field photographs and air photograph interpretation as reference data. The most accurate classification (68% for Crayford Marsh and 53% for Dartford Creek) for both sites comprised the use of MLC with a dataset created from PCs 2, 3 and 4 from a PCA carried out on the original 15 band data, combined with an additional NDVI band. CASI data proved useful for the mapping of salt-marsh vegetation and sediments especially in the Crayford Marsh site. In the Dartford Creek site, however, there was significant confusion between some classes. Further work is recommended to test the classification     

Coastal wetland vegetation classification with a Landsat Thematic Mapper image

Coastal wetland vegetation classification with remotely sensed data has attracted increased attention but remains a challenge. This paper explored a hybrid approach on a Landsat Thematic Mapper (TM) image for classifying coastal wetland vegetation classes. Linear spectral mixture analysis was used to unmix the TM image into four fraction images, which were used for classifying major land covers with a thresholding technique. The spectral signatures of each land cover were extracted separately and then classified into clusters with the unsupervised classification method. Expert rules were finally used to modify the classified image. This research indicates that the hybrid approach employing sub-pixel information, an analyst's knowledge and characteristics of coastal wetland vegetation distribution shows promise in successfully distinguishing coastal vegetation classes, which are difficult to separate with a maximum likelihood classifier (MLC). The hybrid method provides significantly better classification results than MLC.     

Classification of floodplain vegetation by data fusion of spectral (CASI) and LiDAR data

To safeguard the goals of flood protection and nature development, a river manager requires detailed and up‐to‐date information on vegetation structures in floodplains. In this study, remote‐sensing data on the vegetation of a semi‐natural floodplain along the river Waal in the Netherlands were gathered by means of a Compact Airborne Spectrographic Imager (CASI; spectral information) and LiDAR (structural information). These data were used to classify the floodplain vegetation into eight and five different vegetation classes, respectively. The main objective was to fuse the CASI and LiDAR‐derived datasets on a pixel level and to compare the classification results of the fused dataset with those of the non‐fused datasets. The performance of the classification results was evaluated against vegetation data recorded in the field. The LiDAR data alone provided insufficient information for accurate classification. The overall accuracy amounted to 41% in the five‐class set. Using CASI data only, the overall accuracy was 74% (five‐class set). The combination produced the best results, raising the overall accuracy to 81% (five‐class set). It is concluded that fusion of CASI and LiDAR data can improve the classification of floodplain vegetation, especially for those vegetation classes which are important to predict hydraulic roughness, i.e. bush and forest. A novel measure, the balance index, is introduced to assess the accuracy of error matrices describing an ordered sequence of classes such as vegetation structure classes that range from bare soil to forest.     

Mapping functional vegetation abundance in a coastal dune environment using a combination of LSMA and MLC: a case study at Kenfig NNR,Wales

The interactions between wind-blown sand transport, pioneer vegetation and succession vegetation in coastal dune fields play an important role in landform development and determine the balance between stabilization and re-activation of these aeolian landscapes. High-resolution mapping of vegetation communities across a dune field – in particular, the mixture of different functional plant types such as pioneer versus succession species – is critical for the calculation of landscape metrics that enable a rigorous and quantitative testing of numerical simulation models, as well as for informing targeted land management actions that maintain biodiversity and ecological functions. This article presents a method of using maximum likelihood classification (MLC) to inform linear spectral mixture analysis (LSMA) for quantifying sub-pixel abundance of sand, pioneer and succession vegetation in a coastal dune area in Wales, from archived imagery obtained from the Compact Airborne Spectral Imager (CASI) in 1997. LSMA is first applied to derive sub-pixel fractional abundances of soil, green vegetation (GV) and non-GV elements. An MLC is developed separately for automatically identifying pixels believed to contain a mixture of the two functional vegetation types, and this then serves as a basis for applying a transform that interprets the LSMA results in terms of sand and pioneer and succession vegetation communities. Very high resolution (0.1 m pixels) colour aerial photography, taken simultaneously with the CASI data, and field survey data from both 1997 and 2009 were used to aid the MLC and the transform algorithm and were also used for a limited validation exercise. The LSMA abundance maps achieved an overall accuracy of 82.7% (kappa coefficient κ?=?0.78). The reduced MLC vegetation maps (four classes) achieved an overall accuracy of 98.2% (kappa coefficient κ?=?0.96). Although it was not possible to validate the final pioneer and succession vegetation abundance maps quantitatively, a qualitative review of the results for selected locations within the dune field indicates the viability of applying MLC to help direct a transformation of LSMA abundance maps into functional vegetation abundance data.     

Identification of invasive vegetation using hyperspectral remote sensing in the California Delta ecosystem

Estuaries are among the most invaded ecosystems on the planet. Such invasions have led in part, to the formation of a massive $1 billion restoration effort in California's Sacramento–San Joaquin River Delta. However, invasions of weeds into riparian, floodplain, and aquatic habitats threaten the success of restoration efforts within the watershed and jeopardize economic activities. The doctrine of early detection and rapid response to invasions has been adopted by land and water resource managers, and remote sensing is the logical tool of choice for identification and detection. However meteorological, physical, and biological heterogeneity in this large system present unique challenges to successfully detecting invasive weeds. We present three hyperspectral case studies which illustrate the challenges, and potential solutions, to mapping invasive weeds in wetland systems: 1) Perennial pepperweed was mapped over one portion of the Delta using a logistic regression model to predict weed occurrence. 2) Water hyacinth and 3) submerged aquatic vegetation (SAV), primarily composed of Brazilian waterweed, were mapped over the entire Delta using a binary decision tree that incorporated spectral mixture analysis (SMA), spectral angle mapping (SAM), band indexes, and continuum removal products. Perennial pepperweed detection was moderately successful; phenological stage influenced detection rates. Water hyacinth was mapped with modest accuracies, and SAV was mapped with high accuracies. Perennial pepperweed and water hyacinth both exhibited significant spectral variation related to plant phenology. Such variation must be accounted for in order to optimally map these species, and this was done for the water hyacinth case study. Submerged aquatic vegetation was not mapped to the species level due to complex non-linear mixing problems between the water column and its constituents, which was beyond the scope of the current study. We discuss our study in the context of providing guidelines for future remote sensing studies of aquatic systems.     

基于CASI影像的黑河中游种植结构精细分类研究

基于CASI高光谱影像资料,计算出NDVI和纹理数据并综合进行SVM(Support Vector Machine)分类,3种信息的组合形成4种分类方案,是为了探讨CASI数据在种植结构精细分类中的应用潜力,为定量研究和监测提供数据基础。数据在分类前利用同步ASD数据和CE\|318数据进行了辐射定标和大气校正。分类结果与地面实际调查数据对比验证结果表明:① 4种分类结果均与地面实际调查情况基本一致,并分别取得了96.78%、97.21%、88.00%、88.38% 的分类精度和0.9676、0.9691、0.8674、0.8716的Kappa系数;② CASI数据信息丰富,在植被的精细分类方面具有很大的应用潜力;③ 结合空间特征信息和NDVI数据可以有效地提高分类精度。     

基于高光谱影像的三江源区不同退化程度高寒草甸分类研究

三江源地区是我国最重要的生态功能区之一。近年来,受全球气候变暖及日趋频繁的人类活动的影响,三江源地区高寒草甸生态系统退化现象明显。以三江源称多县清水河镇东北部地区为实验区,基于环境小卫星HJ\|1A HSI高光谱数据,结合不同退化程度高寒草甸地面光谱采集和样方调查,采用MLC和SAM方法对不同退化程度的高寒草甸开展了分类研究。结果表明:基于高光谱数据的不同退化程度高寒草甸采用SAM方法分类总体精度达到75%以上,证实了分类方法的可行性,基于高光谱数据分类能有效区分盖度相近、退化程度不同的草地类型,其中SAM分类结果更加精细准确,优于MLC方法,SAM方法对中度退化草甸区分能力最高,对其他退化程度草甸区分能力稍弱。     

Mapping woodland species composition and structure using airborne spectral and LiDAR data

Tree and shrub species composition and vegetation structure are key components influencing the quality of woodland or forest habitat for a wide range of organisms. This paper investigates the unique thematic classes that can be derived using integrated airborne LiDAR and spectral data. The study area consists of a heterogeneous, semi‐natural broadleaf woodland on an ancient site and homogeneous broadleaf and conifer woodland on an adjoining plantation. A parcel‐based unsupervised classification approach was employed, using the first two Principal Components from 12 selected wavebands of HyMap data and a Digital Canopy Height Model extracted from LiDAR data. The resultant 52 data clusters were amalgamated into 10 distinct thematic classes that contain information on species composition and vegetation structure. The thematic classes are relevant to the National Vegetation Classification (NVC) scheme for woodlands and scrub of Great Britain. Furthermore, in distinguishing structural subdivisions within the species‐based NVC classes, the thematic classification provides greater information for quantifying woodland habitat. The classes show degeneration from and regeneration to mature woodland communities and thus reflect the underlying processes of vegetation succession and woodland management. This thematic classification is ecologically relevant and is a forward development in woodland maps created from remote sensing data.     

A multitemporal multiple density slice method for wetland mapping across the state of Queensland,Australia

The Australian and Queensland Governments are developing comprehensive wetland maps at a scale of 1:100 000 for the state of Queensland, Australia. Spectral classifications for water features were developed using Landsat Thematic Mapper (TM) and Enhanced Thematic Mapper (ETM+) imagery acquired over a 16‐year period. A multiple density slice/supervised classification method, the Standing Water Body (SWB) method, was developed to separate the main spectral and land cover elements of wetlands (vegetation, water and shadow cast by vegetation and topographic relief) and used rules to combine spectral classes to provide multitemporal (MT) information on wetland extent and water inundation regimes for features of at least 0.25 ha. Accuracy assessment in four trial areas compared the SWB method to the Normalized Difference Water Index (NDWI). The assessments of classified features were scale adjusted to maximum class‐area proportions to enable statistical comparison and to account for the large area of non‐wetland in the four trial areas. The average overall accuracy for wetland classification was 95.9% for the SWB method and 95.3% for the NDWI. The average unadjusted KHAT statistic for the wetland classification was 0.84 and 0.90 for the SWB and NDWI, respectively. The scale‐adjusted KHAT statistic was much lower for both methods, averaging 0.45 for the SWB and 0.39 for the NDWI, mainly due to large omission errors. A method for the implementation of the SWB method for systematic and repeatable mapping of wetland areas is presented. The study recommends enhancement of the SWB classification through the inclusion of the NDWI classification and ancillary data such as vegetation mapping and drainage networks.     

Combining magnitude and shape features for hyperspectral classification

The spectral angle mapper (SAM) and maximum likelihood classification (MLC) are two traditional classifiers for hyperspectral classification. This paper presents two methods to combine magnitude and shape features, one for each classifier. As the magnitude and shape features are complementary, combining both features can improve the classification accuracy. First, magnitude features are represented by the spectral radiance vector, whereas shape features are represented by the spectral gradient vector. Then, in SAM, each feature vector generates a spectral angle for each class. The two generated angles are added together to obtain a single similarity, which is used for the final classification. Similarly, in MLC, after the dimensionality reduction using Fisher's linear discriminant (FLD), each feature vector in the new feature space generates a likelihood. The two generated likelihoods are multiplied to obtain a single value, which is adopted for the final classification. Experimental results on an Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) data set demonstrate that the proposed methods outperform the methods with a single feature set.     

Hyperspectral aerial images. A valuable tool for submerged vegetation recognition in the Orbetello Lagoons,Italy

Results obtained in mapping algal belts in the Orbetello Lagoons are described using Daedalus/MIVIS hyperspectral scanner aerial images. MIVIS has a spectral coverage in the Visible, Near-IR, Mid-IR and Thermal-IR regions, with 102 channels. The objective of the work is a procedure for the algal species recognition, using methods of spectral data analysis. The 1-2m deep brackish, shallow water basin areas of the Orbetello Lagoons have poor water circulation and considerable eutrophication phenomena. During MIVIS overflight, spectra of submerged vegetation (Cymodocea sp., Cladophora sp., Chaetomorpha sp., Gracilaria sp., Enteromorpha sp., Ruppia sp. and Ulva sp.) were collected from a boat equipped with a field portable multi-spectral radiometer operating between 380 and 780nm. In situ collected spectra and MIVIS spectra, in the visible and the near infrared region for prototype area, were compared to select the representative spectra of submerged vegetation. The Spectral Angle Mapper (SAM) has been the method adopted for the spectral classification.     

Mapping salt-marsh vegetation by multispectral and hyperspectral remote sensing

Tidal marshes are characterized by complex patterns both in their geomorphic and ecological features. Such patterns arise through the elaboration of a network structure driven by the tidal forcing and through the interaction between hydrodynamical, geophysical and ecological components (chiefly vegetation). Intertidal morphological and ecological structures possess characteristic extent (order of kilometers) and small-scale features (down to tens of centimeters) which are not simultaneously accessible through field observations, thus making remote sensing a necessary observation tool. This paper describes a set of remote sensing observations from several satellite and airborne platforms, the collection of concurrent ground reference data and the vegetation distributions that may be inferred from them, with specific application to the Lagoon of Venice (Italy). The data set comprises ROSIS, CASI, MIVIS, IKONOS and QuickBird acquisitions, which cover a wide range of spatial and spectral resolutions. We show that spatially-detailed and quantitatively reliable vegetation maps may be derived from remote sensing in tidal environments through unsupervised (K-means) and supervised algorithms (Maximum Likelihood and Spectral Angle Mapper). We find that, for the objective of intertidal vegetation classification, hyperspectral data contain largely redundant information. This in particular implies that a reduction of the spectral features is required for the application of the Maximum Likelihood classifier. A large number of experiments with different feature extraction/selection algorithms show that the use of four bands derived from Maximum Noise Fraction transforms and four RGBI broad bands obtained by spectral averaging yield very similar classification performances. The classifications from hyperspectral data are somewhat superior to those from multispectral data, but the close performance and the results of the features reduction experiments show that spatial resolution affects classification accuracy much more importantly than spectral resolution. Monitoring schemes of tidal environment vegetation may thus be based on high-resolution satellite acquisitions accompanied by systematic ancillary field observations at a relatively limited number of reference sites, with practical consequences of some relevance.     

The role of digital bathymetry in mapping shallow marine vegetation from hyperspectral image data

Hyperspectral remote sensing is a proven technology for measurement of coastal ocean colour, including sea‐bed mapping in optically shallow waters. Using hyperspectral imagery of shallow (<15 m deep) sea bed acquired with the Compact Airborne Spectrographic Imager (CASI‐550), we examined how changes in the spatial resolution of bathymetric grids, created from sonar data (echosounding) and input to conventional image classifiers, affected the accuracy of distributional maps of invasive (Codium fragile ssp. tomentosoides) and native (kelp) seaweeds off the coast of Nova Scotia, Canada. The addition of a low‐resolution bathymetric grid, interpolated from soundings by the Canadian Hydrographic Service, improved the overall classification accuracies by up to ～10%. However, increasing the bathymetric resolution did not increase the accuracy of classification maps produced with the supervised (Maximum Likelihood) classifier as shown by a slightly lower accuracy (2%) when using an intermediate‐resolution bathymetric grid interpolated from soundings with a recreational fish finder. Supervised classifications using the first three eigenvectors from a principal‐components analysis were consistently more accurate (by at least 27%) than unsupervised (K‐means classifier) schemes with similar data compression. With an overall accuracy of 76%, the most reliable scheme was a supervised classification with low‐resolution bathymetry. However, the supervised approach was particularly sensitive, and variations in accuracy of 2% resulted in overestimations of up to 53% in the extent of C. fragile and kelp. The use of a passive optical bathymetric algorithm to derive a high‐resolution bathymetric grid from the CASI data showed promise, although fundamental differences between this grid and those created with the sonar data limited the conclusions. The bathymetry (at any spatial resolution) appeared to improve the accuracy of the classifications both by reducing the confusion among the spectral classes and by removing noise in the image data. Variations in the accuracy of depth estimates and inescapable positional inaccuracies in the imagery and ground data largely accounted for the observed differences in the classification accuracies. This study provides the first detailed demonstration of the advantages and limitations of integrating digital bathymetry with hyperspectral data for the mapping of benthic assemblages in optically shallow waters.     

An integrated approach to a biophysiologically based classification of floating aquatic macrophytes

Globally, invasive species are identified as one of the most serious threats to ecological stability and biodiversity. Water hyacinth (Eichhornia crassipes), an aggressive invasive aquatic species, has caused severe economic and ecological impacts in the Sacramento-San Joaquin River Delta in California. In the Delta, water hyacinth co-occurs with native pennywort (Hydrocotyle umbellata L.) and non-native water primrose (Ludwigia spp.). All of the species express a wide range of phenotypic variability, making it difficult to map them with remote sensing techniques because their spectral response is highly variable. We present an integrated approach to mapping these floating species using a sequence of hyperspectral methods, such as spectral angle mapper (SAM), linear spectral unmixing (LSU), continuum removal and several indices in a decision tree format. The ensuing tree, based on biophysiological differences between the species, was robust and consistent across three separate years and over multiple flightlines each year, spread across an area of approximately 2500 km². The most important inputs used to create the tree were reflectance in the short-wave infrared (SWIR), Red Edge Index, near-infrared (NIR) reflectance, LSU fractions and SAM rule values. The floating species were mapped with average accuracy of 88% for water hyacinth, 87% for pennywort and 71% for water primrose.     

Pixel- and feature-level fusion of hyperspectral and lidar data for urban land-use classification

The complexity of urban areas makes it difficult for single-source remotely sensed data to meet all urban application requirements. Airborne light detection and ranging (lidar) can provide precise horizontal and vertical point cloud data, while hyperspectral images can provide hundreds of narrow spectral bands which are sensitive to subtle differences in surface materials. The main objectives of this study are to explore: (1) the performance of fused lidar and hyperspectral data for urban land-use classification, especially the contribution of lidar intensity and height information for land-use classification in shadow areas; and (2) the efficiency of combined pixel- and object-based classifiers for urban land-use classification. Support vector machine (SVM), maximum likelihood classification (MLC), and object-based classifiers were used to classify lidar, hyperspectral data and their derived features, such as the normalized digital surface model (nDSM), normalized difference vegetation index (NDVI), and texture measures, into 15 urban land-use classes. Spatial attributes and rules were used to minimize misclassification of the objects showing similar spectral properties, and accuracy assessments were carried out for the classification results. Compared with hyperspectral data alone, hyperspectral–lidar data fusion improved overall accuracy by 6.8% (from 81.7 to 88.5%) when the SVM classifier was used. Meanwhile, compared with SVM alone, the combined SVM and object-based method improved OA by 7.1% (from 87.6 to 94.7%). The results suggest that hyperspectral–lidar data fusion is effective for urban land-use classification, and the proposed combined pixel- and object-based classifiers are very efficient and flexible for the fusion of hyperspectral and lidar data.     

Land-cover classification in a moist tropical region of Brazil with Landsat Thematic Mapper imagery

This research aims to improve land-cover classification accuracy in a moist tropical region in Brazil by examining the use of different remote-sensing-derived variables and classification algorithms. Different scenarios based on Landsat Thematic Mapper (TM) spectral data and derived vegetation indices and textural images and different classification algorithms, maximum likelihood classification (MLC), artificial neural network (ANN), classification tree analysis (CTA) and object-based classification (OBC), were explored. The results indicate that a combination of vegetation indices as extra bands into Landsat TM multi-spectral bands did not improve the overall classification performance, but the combination of textural images was valuable for improving vegetation classification accuracy. In particular, the combination of both vegetation indices and textural images into TM multi-spectral bands improved the overall classification accuracy (OCA) by 5.6% and the overall kappa coefficient (OKC) by 6.25%. Comparison of the different classification algorithms indicated that CTA and ANN have poor classification performance in this research, but OBC improved primary forest and pasture classification accuracies. This research indicates that use of textural images or use of OBC are especially valuable for improving the vegetation classes such as upland and liana forest classes that have complex stand structures and large patch sizes.     

Mapping the land-cover distribution in arid and semiarid urban landscapes with Landsat Thematic Mapper imagery

Mapping the land-cover distribution in arid and semiarid urban landscapes using medium spatial resolution imagery is especially difficult due to the mixed-pixel problem in remotely sensed data and the confusion of spectral signatures among bare soils, sparse density shrub lands, and impervious surface areas (ISAs hereafter). This article explores a hybrid method consisting of linear spectral mixture analysis (LSMA), decision tree classifier, and cluster analysis for mapping land-cover distribution in two arid and semiarid urban landscapes: Urumqi, China, and Phoenix, USA. The Landsat Thematic Mapper (TM) imagery was unmixed into four endmember fraction images (i.e. high-albedo object, low-albedo object, green vegetation (GV), and soil) using the LSMA approach. New variables from these fraction images and TM spectral bands were used to map seven land-cover classes (i.e. forest, shrub, grass, crop, bare soil, ISA, and water) using the decision tree classifier. The cluster analysis was further used to modify the classification results. QuickBird imagery in Urumqi and aerial photographs in Phoenix were used to assess classification accuracy. Overall classification accuracies of 86.0% for Urumqi and 88.7% for Phoenix were obtained, much higher accuracies than those utilizing the traditional maximum likelihood classifier (MLC). This research demonstrates the necessity of using new variables from fraction images to distinguish between ISA and bare soils and between shrub and other vegetation types. It also indicates the different effects of spatial patterns of land-cover composition in arid and semiarid landscapes on urban land-cover classification.     

CHRIS 高光谱图像森林类型分类方法比较研究

以长白山为试验区,选择CHRIS/PROBA高光谱零度角遥感数据,在对其进行预处理的基础上,通过应用最大似然法(MLC)、最小距离法、支持向量机法(SVM)和光谱角填图法(SAM)等几种常用的高光谱遥感分类方法对影像进行森林类型分类。利用混淆矩阵对分类结果进行验证,结果显示:在高光谱遥感森林类型分类中,SVM总体分类精度最高,为84.60％;其次是MLC,为 83.53％,最小距离法73.81％,SAM 56.49％。Kappa系数从高到底为:SVM 0.78,MLC 0.77,最小距离法0.68,SAM 0.52。经过比较分析,得出SVM分类方法精度最高,这表明该方法用于高光谱遥感森林分类中的实用性和优越性。     

Land-cover classification in a moist tropical region of Brazil with Landsat TM imagery

This research aims to improve land-cover classification accuracy in a moist tropical region in Brazil by examining the use of different remote sensing-derived variables and classification algorithms. Different scenarios based on Landsat Thematic Mapper (TM) spectral data and derived vegetation indices and textural images, and different classification algorithms - maximum likelihood classification (MLC), artificial neural network (ANN), classification tree analysis (CTA), and object-based classification (OBC), were explored. The results indicated that a combination of vegetation indices as extra bands into Landsat TM multispectral bands did not improve the overall classification performance, but the combination of textural images was valuable for improving vegetation classification accuracy. In particular, the combination of both vegetation indices and textural images into TM multispectral bands improved overall classification accuracy by 5.6% and kappa coefficient by 6.25%. Comparison of the different classification algorithms indicated that CTA and ANN have poor classification performance in this research, but OBC improved primary forest and pasture classification accuracies. This research indicates that use of textural images or use of OBC are especially valuable for improving the vegetation classes such as upland and liana forest classes having complex stand structures and having relatively large patch sizes.