Optimising the use of hyperspectral and LiDAR data for mapping reedbed habitats

Reedbeds are important habitats for supporting biodiversity and delivering a range of ecosystem services, yet reedbeds in the UK are under threat from intensified agriculture, changing land use and pollution. To develop appropriate conservation strategies, information on the distribution of reedbeds is required. Field surveys of these wetland environments are difficult, time consuming and expensive to execute for large areas. Remote sensing has the potential to replace or complement such field surveys, yet the specific application to reedbed habitats has not been fully investigated. In the present study, airborne hyperspectral and LiDAR imagery were acquired for two sites in Cumbria, UK. The research aimed to determine the most effective means of analysing hyperspectral data covering the visible, near infrared (NIR) and shortwave infrared (SWIR) regions for mapping reedbeds and to investigate the effects of incorporating image textural information and LiDAR-derived measures of canopy structure on the accuracy of reedbed delineation. Due to the high dimensionality of the hyperspectral data, three image compression algorithms were evaluated: principal component analysis (PCA), spectrally segmented PCA (SSPCA) and minimum noise fraction (MNF). The LiDAR-derived measures tested were the canopy height model (CHM), digital surface model (DSM) and the DSM-derived slope map. The SSPCA-compressed data produced the highest reedbed accuracy and processing efficiency. The optimal SSPCA dataset incorporated 12 PCs comprised of the first 3 PCs derived from each of the spectral segments: visible (392-700 nm), NIR (701-972 nm), SWIR-1 (973-1366 nm) and SWIR-2 (1530-2240 nm). Incorporating image textural measures produced a significant improvement in the classification accuracy when using MNF-compressed data, but had no impact when using the SSPCA-compressed imagery. A significant improvement (+ 11%) in the accuracy of reedbed delineation was achieved when a mask generated by applying a 3 m threshold to the LiDAR-derived CHM was used to filter the reedbed map derived from the optimal SSPCA dataset. This paper demonstrates the value in combining appropriately compressed hyperspectral imagery with LiDAR data for the effective mapping of reedbed habitats.     

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.     

A comparison of local variance,fractal dimension,and Moran's I as aids to multispectral image classification

The accuracy of traditional multispectral maximum‐likelihood image classification is limited by the multi‐modal statistical distributions of digital numbers from the complex, heterogenous mixture of land cover types in urban areas. This work examines the utility of local variance, fractal dimension and Moran's I index of spatial autocorrelation in segmenting multispectral satellite imagery with the goal of improving urban land cover classification accuracy. Tools available in the ERDAS Imagine^TM software package and the Image Characterization and Modeling System (ICAMS) were used to analyse Landsat ETM?+ imagery of Atlanta, Georgia. Images were created from the ETM?+ panchromatic band using the three texture indices. These texture images were added to the stack of multispectral bands and classified using a supervised, maximum likelihood technique. Although each texture band improved the classification accuracy over a multispectral only effort, the addition of fractal dimension measures is particularly effective at resolving land cover classes within urbanized areas, as compared to per‐pixel spectral classification techniques.     

Extracting structural attributes from IKONOS imagery for Eucalyptus plantation forests in KwaZulu-Natal,South Africa,using image texture analysis and artificial neural networks

The suitability of optical IKONOS satellite data (multispectral and panchromatic) for the estimation of forest structural attributes – for example, stems per hectare (SPHA), diameter at breast height (DBH), mean tree height (MTH), basal area (BA) and volume in plantation forest environments – was assessed in this study. The relationships of these forest structural attributes to statistical image texture from IKONOS imagery were analysed. The coefficients of determination (R ²) of multilinear regression models developed for the estimation of SPHA, DBH, MTH, BA and volume using statistical texture features from multispectral data were 0.63, 0.68, 0.81, 0.86 and 0.86, respectively. When the statistical texture features from panchromatic data were applied, the R ² for the respective forest structural attributes increased by 25%, 31%, 6%, 0.2% and 0.2%, respectively. Artificial neural network (ANN) models produced strong and significant relationships between estimated and actual measures of SPHA, DBH, MTH, BA and volume with an R ² of 0.83, 0.83, 0.90, 0.90 and 0.92, respectively, based on multispectral IKONOS data. Based on panchromatic IKONOS imagery, the R ² for the respective forest structural attributes increased by 18%, 12%, 5%, 3% and 6%, respectively. Results such as these bode well for the application of high spatial resolution imagery to forest structural assessment.     

Land‐use classification of multispectral aerial images using artificial neural networks

During the past decade, there have been significant improvements in remote sensing technologies, which have provided high‐resolution data at shorter time intervals. Considerable effort has been directed towards developing new classification strategies for analysing this imagery, but the use of artificial intelligence‐based analysis techniques has been somewhat limited. The aim of this study was to develop an artificial neural network (ANN)‐based technique for the classification of multispectral aerial images for land use in agricultural and environmental applications. The specific land‐use classes included water, forest, and several types of agricultural fields. Multispectral images at a 1‐m resolution were obtained for the state of Georgia, USA from a Geographic Information Systems (GIS) data clearinghouse. These false‐colour images contained green, red and infrared true‐colour information. Three approaches were used for the preparation of the inputs to the ANN. These included histograms of the pixel intensities, textural parameters extracted from the image, and matrices of the pixels for spatial information. A probabilistic neural network was used. Seven hundred images were used for model development and 175 for independent model evaluation. The overall accuracy for the evaluation data set was 74% for the histogram approach, 71% for the spatial approach and 89% for the textural approach. The evaluation of ANNs based on various combinations of all three approaches did not show an improvement in accuracy. We also found that some approaches could be used selectively for certain classes. For example, the textural approach worked best for forest classes. For future studies, edge detection prior to classification, with more careful selection of each class, should be included for land‐use classification of multispectral images.     

Textural and local spatial statistics for the object‐oriented classification of urban areas using high resolution imagery

Textural and local spatial statistical information is important in the classification of urban areas using very high resolution imagery. This paper describes the utility of textural and local spatial statistics for the improvement of object‐oriented classification for QuickBird imagery. All textural/spatial bands were used as additional bands in the supervised object‐oriented classification. The texture analysis is based on two levels: segmented image objects and moving windows across the whole image. In the texture analysis over image objects, the angular second moment textural feature at a 45° angle showed an improved classification performance with regard to buildings, depicting the patterns of buildings better than any other directions. The texture analysis based on moving windows across the whole image was conducted with various window sizes (from 3×3 to 13×13), and four grey‐level co‐occurrence matrix (GLCM) textural features (homogeneity, contrast, angular second moment, and entropy) were calculated. The contrast feature with the 7×7 window size improved classification up to 6%. One type of local spatial statistics, Moran's I feature with the vertical neighbourhood rule, improved the classification accuracy even further, up to 7%. Comparison of results between spectral and spectral+textural/spatial information indicated that textural and spatial information can be used to improve the object‐oriented classification of urban areas using very high resolution imagery.     

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.     

Analysis of wavelet packet and statistical textures for object-oriented classification of forest-agriculture ecotones using SPOT 5 imagery

Textural features of high-resolution remote sensing imagery are a powerful data source for improving classification accuracy because using only spectral information is not sufficient for the classification of objects with within-field spectral variability. This study presents the methods of using an object-oriented texture analysis algorithm for improving high-resolution remote sensing imagery classification, including wavelet packet transform texture analysis, the grey-level co-occurrence matrix (GLCM) and local spatial statistics. Wavelet packet transform texture analysis, with the method of optimization and selection of wavelet texture for feature extraction, is a good candidate for object-oriented classification. Feature optimization is used to reduce the data dimensions in combinations of textural sub-bands and spectral bands. The result of the classification accuracy assessment indicates the improvement of texture analysis for object-oriented classification in this study. Compared with the traditional method that uses only spectral bands, the combination of GLCM homogeneity and spectral bands increases the overall accuracy from 0.7431 to 0.9192. Furthermore, wavelet packet transform texture analysis is the optimal method, increasing the overall accuracy to 0.9216 using a smaller data dimension. Local spatial statistical measures also increase the classification total accuracy, but only from 0.7431 to 0.8088. This study demonstrates that wavelet packet and statistical textures can be used to improve object-oriented classification; specifically, the texture analysis based on the multiscale wavelet packet transform is optimal for increasing the classification accuracy using a smaller data dimension.     

Object-based urban detailed land cover classification with high spatial resolution IKONOS imagery

Improvement in remote sensing techniques in spatial/spectral resolution strengthens their applicability for urban environmental study. Unfortunately, high spatial resolution imagery also increases internal variability in land cover units and can cause a ‘salt-and-pepper’ effect, resulting in decreased accuracy using pixel-based classification results. Region-based classification techniques, using an image object (IO) rather than a pixel as a classification unit, appear to hold promise as a method for overcoming this problem. Using IKONOS high spatial resolution imagery, we examined whether the IO technique could significantly improve classification accuracy compared to the pixel-based method when applied to urban land cover mapping in Tampa Bay, FL, USA. We further compared the performance of an artificial neural network (ANN) and a minimum distance classifier (MDC) in urban detailed land cover classification and evaluated whether the classification accuracy was affected by the number of extracted IO features. Our analysis methods included IKONOS image data calibration, data fusion with the pansharpening (PS) process, Hue–Intensity–Saturation (HIS) transferred indices and textural feature extraction, and feature selection using a stepwise discriminant analysis (SDA). The classification results were evaluated with visually interpreted data from high-resolution (0.3 m) digital aerial photographs. Our results indicate a statistically significant difference in classification accuracy between pixel- and object-based techniques; ANN outperforms MDC as an object-based classifier; and the use of more features (27 vs. 9 features) increases the IO classification accuracy, although the increase is statistically significant for the MDC but not for the ANN.     

联合快舟一号影像纹理信息的城市土地覆盖分类

仅依靠光谱信息无法满足高分辨率遥感分类的应用需求,辅之以纹理特征信息进行分类,可提高影像分类精度。利用KZ\|1卫星影像和Landsat\|8卫星影像数据,基于面向对象的影像分割法和灰度共生矩阵纹理分析法对新疆石河子市局部城区进行了地表覆盖分类实验,将不同空间分辨率的全色影像纹理信息、光谱信息构成多种影像特征组合进行分类比较研究,以选择最佳的分类特征集。结果表明:KZ-1影像能为城市区域的土地覆盖分类提供丰富的纹理信息,面向对象的影像分割可较好地利用高分辨率数据的几何结构信息实现优化的影像分割,从而提高多光谱影像的分类精度,总体分类精度为90.06%,Kappa系数为87.93%,比单纯利用光谱信息分类的总体精度提高了8.02%,Kappa系数提高了9.65%,表明KZ\|1数据可为光谱分类提供丰富的纹理信息,从而提高城市区域的土地覆盖分类精度。     

Multispectral image segmentation by a multichannel watershed‐based approach

Watershed transformation in mathematical morphology is a powerful morphological tool for image segmentation that is usually defined for greyscale images and applied to the gradient magnitude of an image. This paper presents an extension of the watershed algorithm for multispectral image segmentation. A vector‐based morphological approach is proposed to compute gradient magnitude from multispectral imagery, which is then input into watershed transformation for image segmentation. The gradient magnitude is obtained at multiple scales. After an automatic elimination of local irrelevant minima, a watershed transformation is applied to segment the image. The segmentation results were evaluated and compared with other multispectral image segmentation methods, in terms of visual inspection, and object‐based image classification using high resolution multispectral images. The experimental results indicate that the proposed method can produce accurate segmentation results and higher classification accuracy, if the scales and contrast parameter are appropriately selected in the gradient computation and subsequent local minima elimination. The proposed method shows encouraging results and can be used for segmentation of high resolution multispectral imagery and object based classification.     

A comparison of texture measures for the per-field classification of Mediterranean land cover

Land cover of a Mediterranean region was classified within an artificial neural network (ANN) on a per-field basis using Landsat Thematic Mapper (TM) imagery. In addition to spectral information, the classifier used geostatistical structure functions and texture measures extracted from the co-occurrence matrix. Geostatistical measures of texture resulted in a more accurate classification of Mediterranean land cover than statistics derived from the co-occurrence matrix. The primary advantage of geostatistical measures was their robustness over a wide range of land cover types, field sizes and forms of class mixing. Spectral information and the variogram (geostatistical texture measure) resulted in the highest overall classification accuracies.     

基于遥感光谱和空间变量随机森林的黄河三角洲刺槐林健康等级分类

对刺槐林健康状况进行准确分类制图,是进行刺槐林健康状况评估与生态修复的前提。以高分辨率IKONOS影像、基于影像提取的不同窗口、不同灰度共生矩阵纹理信息以及反映局部空间自相关的Local Getis-Ord Gi(Getis统计量)为数据源,结合实测生态样方数据,利用多决策树的组合分类模型随机森林(RF)对刺槐林健康进行分级,对6种方法的分类精度进行了比较且对分类变量的重要性进行了排序。结果显示:19m×19m是最佳纹理计算窗口;灰度共生矩阵均值是最优纹理变量;基于波段4计算的Getis统计量对RF分类具有最重要的作用;较之利用全部光谱、纹理和Getis统计量的80个波段/变量,利用前向选择得到的前16个重要性变量进行RF分类,获得了最高的分类精度(总精度为93.14%,Kappa系数为0.894)。研究证实了从高分影像提取的空间特征信息有助于提高对具有规则分布格局的人工刺槐林健康等级的分类精度;前向选择方法可以利用较少的预测变量获得较高的分类精度。     

Combining high spatial resolution multi-temporal satellite data with leaf-on LiDAR to enhance tree species discrimination at the crown level

ABSTRACT

The long-standing goal of discriminating tree species at the crown-level from high spatial resolution imagery remains challenging. The aim of this study is to evaluate whether combining (a) high spatial resolution multi-temporal images from different phenological periods (spring, summer and autumn), and (b) leaf-on LiDAR height and intensity data can enhance the ability to discriminate the species of individual tree crowns of red oak (Quercus rubra), sugar maple (Acer saccharum), tulip poplar (Liriodendron tulipifera), and black cherry (Prunus serotina) in the Fernow Experimental Forest, West Virginia, USA. We used RandomForest models to measure a loss of classification accuracy caused by iteratively removing from the classification one or more groups from six groups of variables: spectral reflectance from all multispectral bands in the (1) spring, (2) summer, and (3) autumn images, (4) vegetation indices derived from the three multispectral datasets, (5) canopy height and intensity from the LiDAR imagery, and (6) texture related variables from the panchromatic and LiDAR datasets. We also used ANOVA and decision tree analyses to elucidate how the multispectral and LiDAR datasets combine to help discriminate tree species based on their unique phenological, spectral, textural, and crown architectural traits. From these results, we conclude that combing high spatial resolution multi-temporal satellite data with LiDAR datasets can enhance the ability to discriminate tree species at the crown level.     

影响ETM影像土地利用/覆盖分类精度因素的研究

训练样本量、辅助数据和分类法是影响土地利用/覆盖分类精度的3个主要因素,通过找到这3个因素的最佳组合方式以提高分类精度,分别在25%、50%、75%、100%样本量下,加入NDVI、DEM和纹理均值特征作为辅助数据,比较了分类回归树、支持向量机、最大似然法3种分类法的效果,探讨了训练样本、辅助数据以及分类技术对土地利用/覆盖分类精度的影响。结果表明：支持向量机总体分类精度较高,在相同样本量和没有有效辅助数据的情况下,SVM可以获得最佳的分类结果,总体分类精度在85%以上;在进行分类时,加入NDVI和纹理均值特征使分类回归树分类精度提高了2.82%,说明该方法对有效辅助数据的加入较为敏感;在获取的训练样本集有限而可获取有效的辅助数据时,应优先考虑利用分类回归树进行土地利用/覆盖分类。     

Textural classification for ecological research using ATM images

Investigation of spectral and textural classification of high resolution ATM image of a semi-natural scene is presented. Pure spectral classification using bands 5, 7, 9 and the maximum likelihood classifier yielded 56, 63 and 64 per cent overall classification accuracies with 1-25m, 2-5m, and 50m spatial resolution data respectively. Application of combined spectral and textural classification using bands 5, 7, 9 and various texture features from seven texture algorithms ( spatial grey level dependence matrices-SGLDM, grey level run length matrices-GLRLM, busyness, neighbouring grey level dependence matrices-NGLDM, sum and difference histograms-SADH, and fractal analysis), yielded overall classification accuracies from 58-65 per cent at 1-25 m resolution. It is concluded that texturally-based classifications improve overall classification although improvements are not dramatic. The first-order texture measures from algorithms like GLDH and SADH have shown more promise than second-order algorithms, like SGLDM and NGLDM. The energy feature from most of the texture algorithms shows considerable classification potential. A selection of distance metric corresponding to the size of the spatial unit for a given cover type improves the classification of that class. With degradation of spatial resolution the overall accuracy of textural classification improves up to 69 per cent for 5-0 m resolution data.     

Combining multi-scale textural features from the panchromatic bands of high spatial resolution images with ANN and MLC classification algorithms to extract urban land uses

ABSTRACT

High spatial resolution images have been increasingly used for urban land-use classification, but high spectral variations within same land use, the spectral confusion among different land uses, and the shadow problem often lead to poor classification performance of the traditional per-pixel classification methods. Main objectives of this paper were to extract phenomena with different altitudes with the absence of elevation features and shadowed areas without defining a shadow class, identifying the most effective textural features in classification by Regression analysis and also class differentiation with similar spectral properties. To achieve these aims, the panchromatic image of WorldView2, GeoEye1, and QuickBird satellites were applied in order to extract the statistical features of the first and the second order of multi-scale texture analysis, due to high potential for providing more detailed and high spatial resolution in five different window sizes, four different cell shifts, and three different angles or directions. Overall, 137 features were used as input in two classification algorithms including Maximum Likelihood Classifier (MLC) and Artificial Neural Network (ANN). The results showed that the multi-scale textural features and ANN made possible to differentiate three major classes of asphalt, vegetation and building surfaces even with the presence of shadowed area and the absence of elevation features. The experiments also presented that the more the elevation of vertical objects, the more the effect of textural parameters on extraction of these classes. Furthermore, the investigations denoted the validity of the Regression analysis in the detection of most effective textural features in classification.     

Use of textural measurements to map invasive wetland plants in the Hudson River National Estuarine Research Reserve with IKONOS satellite imagery

At this point, models, and accompanying field data, that could be used to predict the likely response of estuaries and tidal marshes to future environmental change are lacking. To improve this situation, monitoring efforts in these complex ecosystems need to be intensified, and new, efficient monitoring techniques should be developed. In this context, our research assessed the use of IKONOS satellite imagery to map plant communities at Tivoli Bays, in the Hudson River National Estuarine Research Reserve (HRNERR). Tivoli Bays, a freshwater tidal wetland, contains a unique assemblage of plant communities, including three invasive plants (Trapa natans, Phragmites australis, and Lythrum salicaria). To study the effects of textural information on the accuracy of land cover maps produced for the HRNERR, seven different 11-class land cover maps were produced using a maximum-likelihood classification on seven combinations of spectral and textural data derived from an IKONOS image. Conventional contingency tables served as a basis for an accuracy assessment of these maps. The overall classification accuracies, as assessed by the contingency tables, ranged from 45% to 77.7%. The maximum-likelihood classification relying on four spectral and four 5-by-5 filter textural bands (created by superposing a textural filter separately on each band of the IKONOS image) had the lowest overall accuracy, whereas the one based on four spectral and four 3-by-3 filter textural bands associated with all segments, identified by an object-based classification of the IKONOS image, had the highest accuracy. Results suggest that a combination of per-pixel classification and incorporation of texture for segments generated through an object-based classification slightly increases classification accuracy from 76.2% for the maximum-likelihood classification of the four spectral bands of the IKONOS image to 77.7% for the combination of spectral and textural information produced for selected segments. Further analysis indicates that better results may be obtained by using other types of data within the segments and that the traditional approach to the selection of training and accuracy sites may negatively bias the results for a combination per-pixel and object-based classification.     

Per-field classification: an example using SPOT HRV imagery

Abstract

The classification of land cover on remotely sensed imagery is usually undertaken in a per-pixel format within an image file or in a per-field format within a non-image file. The latter is more accurate but does not produce an image output and is not readily input to a vector-based geographical information system. We propose setting the pixels in each field to a representative statistic for that field and then using a per-pixel classifier to perform a per-field classification in an image file. This procedure was evaluated using SPOT high resolution visible (HRV) imagery. The highest classification accuracy of 62.1 per cent (12 class) was achieved using measures of prior probabilities and image texture within the proposed per-field format.     

Analysis of co‐occurrence and discrete wavelet transform textures for differentiation of forest and non‐forest vegetation in very‐high‐resolution optical‐sensor imagery

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.