Estimation of Wheat/Rice Residue Burning Areas in Major Districts of Haryana,India, Using Remote Sensing Data

Haryana has emerged as an important state for Rice & Wheat production in India contributing significantly in the central pool. Mechanized combine harvesting technologies, which have become common in Rice Wheat System (RWS) in India, leave behind large quantities of straw in the field for open burning of residue. Besides causing pollution, the burning kills the useful micro flora of the soil causing soil degradation. There is no field survey (Girdawari) data available with the Government for the areas where stubble burning is taking place. The present paper describes the methodology and results of wheat and rice residue burning areas for three districts of Haryana namely Kaithal, Kurukshetra and Karnal for the year 2010 using complete enumeration approach of multi-date IRS-P6 AWiFS and LISS-III data. In season ground truth was collected using hand held GPS and used to identify area of burnt wheat/rice residues, associated crops and land features. After geo-referencing the satellite images, district images were masked-out and multi-date image data stacks were created. Normalized Difference Vegetation Index (NDVI) of each date was generated and used at the time of classification along with other spectral bands. The non-agricultural classes in the image included: forest, wasteland, water bodies, urban/settlement and permanent vegetation etc. The vector of these non-agriculture classes were extracted from the land use, imported and mask was generated. During the classification non-agriculture area was excluded by using mask of these classes. From this the agricultural area could be separated out. The area was estimated by computing pixels under the classified image mask. In season multi-date AWiFS data along with available single-date LISS-III data between third week of April to last week of May are found to be useful for estimation of wheat residue burning areas estimation. The data between second week of October to last week of November is useful for estimation of rice residue burning areas estimation at district level.     

Exploitation of TerraSAR-X Data for Land use/Land Cover Analysis Using Object-Oriented Classification Approach in the African Sahel Area, Sudan

Recently, object-oriented classification techniques based on image segmentation approaches are being studied using high-resolution satellite images to extract various thematic information. In this study different types of land use/land cover (LULC) types were analysed by employing object-oriented classification approach to dual TerraSAR-X images (HH and HV polarisation) at African Sahel. For that purpose, multi-resolution segmentation (MRS) of the Definiens software was used for creating the image objects. Using the feature space optimisation (FSO) tool the attributes of the TerraSAR-X image were optimised in order to obtain the best separability among classes for the LULC mapping. The backscattering coefficients (BSC) for some classes were observed to be different for HH and HV polarisations. The best separation distance of the tested spectral, shape and textural features showed different variations among the discriminated LULC classes. An overall accuracy of 84 % with a kappa value 0.82 was resulted from the classification scheme, while accuracy differences among the classes were kept minimal. Finally, the results highlighted the importance of a combine use of TerraSAR-X data and object-oriented classification approaches as a useful source of information and technique for LULC analysis in the African Sahel drylands.     

结合空间信息的EDCC测度光谱匹配分类方法

光谱匹配分类方法以光谱相似性测度为分类准则,一种相似性测度只对应于光谱曲线的一种特征,用于光谱匹配分类效果并不好;组合不同类型的相似性测度能够有效改善分类效果,但光谱匹配分类往往忽略了相邻像元间的相关性。为了更好地利用空间信息,提高光谱匹配分类精度,首先组合欧氏距离测度和相关系数测度,得到欧氏距离-相关系数测度;其次通过加入空间乘子,得到结合空间信息的欧氏距离-相关系数测度,从而在光谱匹配分类中增加了空间信息约束。采用两组高光谱影像进行实验验证,结果表明,相比于单一相似性测度及组合相似性测度,结合空间信息的欧氏距离-相关系数测度用于光谱匹配分类能够有效改善分类精度。     

植被指数时序数据距离测度方法评价

利用MODIS增强型植被指数(EVI)时序数据,基于中国陆地生态系统55种植被类型上的468个测试点和一个测试区进行了实验,综合比较欧氏距离、光谱信息离散度、光谱角余弦、核光谱角余弦、相关系数、光谱角余弦-欧氏距离6种距离测度方法对遥感植被指数时序数据聚类精度的影响,结果表明:相关系数方法的聚类精度最差;光谱角余弦-欧氏距离方法充分利用了植被指数时序数据的曲线幅度和形状特征,在这6种距离测度方法中表现出了最优的聚类效果;只对光谱亮度敏感的欧氏距离方法或只对曲线形状敏感的光谱角余弦方法,无论是在区分地物类型方面,还是在区域应用上,表现效果均较差;核光谱角余弦虽然在点数据测试上表现较差,但在区域应用上却有较好的表现;光谱信息离散度无论是在点数据测试上还是在区域应用上均表现出了较为适中的效果。     

Remote sensing mapping of macroalgal farms by modifying thresholds in the classification tree

Remote sensing is the main approach to map aquatic vegetation, and classification tree (CT) is superior to various classification methods. Based on previous studies, modified CT can be developed from traditional CT by adjusting the thresholds based on the statistical relationship between spectral features to classify different images without ground-truth data. However, no studies have yet employed this method to resolve marine vegetation. In this study, three Gao-Fen 1 satellite images obtained on 30 January 2014, 5 November 2014 and 21 January 2015 were selected, and two features were then employed to extract macroalgae farms. Results show that the overall accuracies of traditional CTs for three images are 92.0, 94.2 and 93.9%, respectively, whereas those of the two corresponding modified CTs for images obtained on 21 January 2015 and 5 November 2014 are 93.1 and 89.5%, respectively. This indicates modified CTs can map macroalgae with multi-date imagery and monitor their spatiotemporal distribution in coastal environments.     

Does environmental data increase the accuracy of land use and land cover classification?

Optical image classification converts spectral data into thematic information from the spectral signature of each object in the image. However, spectral separability is influenced by intrinsic characteristics of the targets, as well as the characteristics of the images used. The classification process will present more reliable results when aspects associated with natural environments (climate, soil, relief, water, etc.) and anthropic environments (roads, constructions, urban area) begin to be considered, as they determine and guide land use and land cover (LULC). The objectives of this study are to evaluate the integration of environmental variables with spectral variables and the performance of the Random Forest algorithm in the classification of Landsat-8 OLI images, of a watershed in the Eastern Amazon, Brazil. The classification process used 96 predictive variables, involving spectral, geological, pedological, climatic and topographic data and Euclidean distances. The selection of variables to construct the predictive models was divided into two approaches: (i) data set containing only spectral variables, and (ii) set of environmental variables added to the spectral data. The variables were selected through nonlinear correlation analysis, with the Randomized Dependence Coefficient and the Recursive Feature Elimination (RFE) method, using the Random Forest classifier algorithm. The spectral variables NDVI, bands 2, 4, 5, 6 and 7 of the dry season and band 4 of the rainy season were selected in both approaches (i and ii). The Euclidean distance from the urban area, Arenosol soil class, annual precipitation, precipitation in February and precipitation of the wettest quarter were the variables selected from the auxiliary data set. This study showed that the addition of environmental data to the spectral data reduces the limitation of the latter, regarding the discrimination of the different classes of LULC, in addition to improving the accuracy of the classification. The addition of soil classes to spectral variables provided a reduction in errors for vegetation classification (Evergreen Forest and Cerrado Sensu Stricto), as it was able to inform about nutrient availability and water storage capacity. The study demonstrates that the addition of environmental variables to the spectral variables can be an alternative to improve monitoring in areas of ecotone in Neotropical regions.     

Radiometric Correction of Multispectral Images Using Radon Transform

Satellite imagery analysis has played a key role in environmental monitoring and modeling over the past few decades. Remotely sensed multitemporal, multisensor data are often required in Earth observation applications. A common problem associated with the use of multisource image data is the gray value differences caused by non-surface factors such as different illumination, atmospheric or sensor conditions. Radiometric corrections serve to remove the effects that alter the spectral characteristics of land features, except for actual changes in ground target, becoming mandatory in multi-sensor, multi-date studies. This paper presents methodology for correction of Landsat TM images in Radon domain. We propose radiometric correction using Radon Transform based regression method. The transform domain method statistically determines correction values based on contrast between spectral properties of various homogeneous areas. TM band 1 is the band most affected by atmospheric scattering whereas TM band 5 is less affected by atmospheric scattering effect. Hence TM Band 5 is taken as the reference image. Results are assessed statistically and compared with results of popular spatial domain Regression Line Method. The application of the methods for vegetation analyses is also shown in this paper. Test results show that the method gives improved results in removal of atmospheric influence.     

Mobile user identification based on road networks and multiple distance measures

Mobile user identification aims at matching different mobile devices of the same user using trajectory data, which has attracted extensive research in recent years. Most of the previous work extracted trajectory features based on regular grids, which will lead to incorrect feature representation due to lack of geographic information. Besides, most trajectory similarity models only considered one single distance measure to calculate the similarity between users, which ignore the connection between different distance measures and may lead to some false matches. In light of this, we present a novel user identification method based on road networks and multiple distance measures in this article. The proposed method segments a city map into several grids and road segments based on road networks. Then it extracts location and road information of trajectories to jointly construct user features. Multiple distance measures are fused by a discriminant model to improve the effect of user identification. Experiments on real GPS trajectory datasets show that our proposed method outperforms related similarity measure methods and is stable for mobile user identification. Meanwhile, our method can also achieve good identification results even on sparse trajectory datasets.     

一种改进的火星车多光谱影像深度新颖目标探测方法

火星车（即巡视探测器）是对火星表面探测和科学研究的重要手段。针对火星车采集到的日益增长的遥感数据,亟需一种能够智能化地从海量影像中探测出有科学价值的新颖目标的方法。传统的新颖探测多采用基于距离测度和基于影像重建的方法,其中基于距离测度的方法逐像素计算新颖分数,未考虑空间上下文信息;基于影像重建的方法侧重对典型地貌背景进行重建,新颖性表现为影像重建误差,对小型新颖目标如钻孔、除尘点等提取效果不佳。提出一种改进的火星车多光谱影像深度新颖目标探测方法(convolution auto-encoder combined Mahalanobis distance method, CAE-M),利用全卷积自编码神经网络提取深层特征进行典型地貌重建,并联合马氏距离将新颖目标与典型地貌背景分离,充分挖掘空间维与光谱维特征,提高火星车新颖目标探测结果的准确性。实验采用好奇号火星车多光谱影像数据集,在盖尔撞击坑地表采用Reed-Xiaoli探测器、主成分分析、卷积自编码神经网络、生成对抗网络与CAE-M进行对比实验,结果表明,CAE-M在探测精度和可视化解释上均优于对比方法,在不同类别的新颖目标探测上都有着均衡稳定的表现。     

Classification of Satellite Images in Assessing Urban Land Use Change Using Scale Optimization in Object-Oriented Processes (A Case Study: Ardabil City,Iran)

By using satellite imagery, the recognition and evaluation of various phenomena and extraction of information necessary for the planning of land resources or other purposes are easily accomplished. The purpose of this study is to compare the efficiency of seven commonly used methods of monitored classification of satellite data to evaluate land use changes using TM and OLI Landsat, IRS, Spot5 and Quick Bird bands as well as different color combinations of these images to detect agricultural land, residential areas and aquatic areas using object-oriented processing. Digital processing of satellite images was carried out in 1998 and 2016 using advanced methods. Training samples were extracted in five user classes by eCognition software using segmentation scale optimization, different color combinations and coefficients of shape and compression. The appropriate segmentation scale for arable land, human complications and the blue areas were, respectively, 50, 8 and 10. Then each image was classified separately using seven methods and extracted samples, and efficiency of each classification method was obtained by calculating two general health and Kappa coefficients. The results show that the accuracy of each classification method and the neural network with a total accuracy of 94.475 and Kappa coefficient of 92.095 were selected as the most accurate classification method. These results show that the sampling of educational samples with proper precision of the classes in the images and dependency probability of each satellite images pixel can be useful in classifying group available in helpful area.     

结合UPSCALING技术与对象多特征的土地利用覆盖信息提取研究

应用SPOT融合数据,以北京密云地区为例,提出了整合Upscaling技术与对象多特征方法的新思路,通过基于半变异函数的 空间变异特征分析,建立了面向对象多特征与多分辨率数据集的多尺度分类决策树,并对自动分类效率进行了初步探讨。     

Evaluation of data fusion and image segmentation in earth observation based rapid mapping workflows

This paper is an exploratory study, which aimed to discover the synergies of data fusion and image segmentation in the context of EO-based rapid mapping workflows. Our approach pillared on the geographic object-based image analysis (GEOBIA) focusing on multiscale, internally-displaced persons’ (IDP) camp information extraction from very high spatial resolution (VHSR) images. We applied twelve pansharpening algorithms to two subsets of a GeoEye-1 image scene that was taken over a former war-induced ephemeral settlement in Sri Lanka. A multidimensional assessment was employed to benchmark pansharpening algorithms with respect to their spectral and spatial fidelity. The multiresolution segmentation (MRS) algorithm of the eCognition Developer software served as the key algorithm in the segmentation process. The first study site was used for comparing segmentation results produced from the twelve fused products at a series of scale, shape, and compactness settings of the MRS algorithm. The segmentation quality and optimum parameter settings of the MRS algorithm were estimated by using empirical discrepancy measures. Non-parametric statistical tests were used to compare the quality of image object candidates, which were derived from the twelve pansharpened products. A wall-to-wall classification was performed based on a support vector machine (SVM) classifier to classify image objects candidates of the fused images. The second site simulated a more realistic crisis information extraction scenario where the domain expertise is crucial in segmentation and classification. We compared segmentation and classification results of the original images (non-fused) and twelve fused images to understand the efficacy of data fusion. We have shown that the GEOBIA has the ability to create meaningful image objects during the segmentation process by compensating the fused image’s spectral distortions with the high-frequency information content that has been injected during fusion. Our findings further questioned the necessity of the data fusion step in rapid mapping context. Bypassing time-intensive data fusion helps to actuate EO-based rapid mapping workflows. We, however, emphasize the fact that data fusion is not limited to VHSR image data but expands over many different combinations of multi-date, multi-sensor EO-data. Thus, further research is needed to understand the synergies of data fusion and image segmentation with respect to multi-date, multi-sensor fusion scenarios and extrapolate our findings to other remote sensing application domains beyond EO-based crisis information retrieval.     

面向对象分类特征优化选取方法及其应用

与传统基于像元的分类方法比较,面向对象的分类方法可利用的地物信息更加丰富,然而如何从众多信息中筛选出能够有效提取不同地物的分类特征,从而提高分类效率与精度,是使用面向对象方法分类时急需解决的问题。SEaTH算法（分离阈值法）是一种有效的自动选取分类特征并计算阈值的方法,但其只考虑了类间距离,容易存在信息的冗余,从而对分类精度造成一定影响。本文在SEaTH算法的基础上,综合考虑了特征间的相关性、类间距离以及类内距离,对SEaTH算法进行了优化,并将改进前后的两种方法运用到广东省肇庆市TM影像及环境一号卫星影像土地覆盖分类中进行对比分析。实验结果表明,改进后的方法筛选出的特征在提取地物上更为有效,尤其使耕地的分类精度提高了12.26%,使分类总体精度由80%提高到了85.26%。改进后的方法对不易获取多时相影像的地区的土地覆盖分类具有重要意义。     

深度学习的半监督遥感图像检索

遥感图像数据的海量性、多样性和复杂性等特点对遥感图像检索的速度和精度提出了更高的要求,其中特征提取是影响遥感图像检索效果的关键。本文方法首先对遥感图像进行预处理,然后基于稀疏自动编码的方法在大量未标注的遥感图像上进行特征学习得到特征字典,基于卷积神经网络的思想,使用训练出来的特征字典对遥感图像进行卷积和池化得到每幅图像的特征图;接下来使用特征图训练Softmax分类器;最后对待检索图像分类,在同一类别中计算特征间的距离,进而实现遥感图像的检索。实验结果表明,该方法能够有效提高遥感图像检索的速度和准确度。     

一种基于极化距离测度的SAR变化检测方法

本文在经典的极化分类Wishart距离基础上提出了一种对变化敏感的极化距离测度,发展了相应的多时相极化SAR变化检测方法。以北京地区的多时相全极化RADARSAT-2影像进行了实验,对比分析了提出的极化距离测度与各个极化通道后向散射系数对数比值对不同类型地物变化的区分能力,结果表明,提出的极化距离测度不仅对所有的变化类型均有良好的检测作用,而且对变化区域有更高的区分力。这说明本文提出的极化SAR变化检测方法具有广泛的应用价值。     

联合显著性和多层卷积神经网络的高分影像场景分类

高分辨率遥感影像中的场景信息,对于影像解译和现实世界的理解具有重要意义。传统的场景分类方法多利用中、低层人工特征,但是高分辨率遥感影像的信息丰富,场景构成复杂,需要高层次的特征来表达。本文提出了一种联合显著性和多层卷积神经网络的方法,首先利用显著性采样获取包含影像主要信息的有意义的块,将这些块作为样本集输入卷积神经网络中进行训练,获得不同层次的特征表达,最后联合多层特征利用支持向量机进行分类。两组高分影像场景数据UC Merced 21类和Wuhan 7类试验表明,显著性采样能够有效地获取主要目标,减弱其他无关目标的影响,降低数据冗余;卷积神经网络能够自动学习高层次的特征,相比已有方法,本文方法能够有效提高分类精度。     

基于高分一号卫星的城市扩张变化监测研究

廊坊是京津冀城市群的地理中心,位于京津两个国际都市之间。本文选取廊坊市中心为研究对象,利用高分一号卫星数据和航空影像,分析廊坊市2010~2016年的城市扩张变化情况,为京津冀协同发展制定政策并为城市制订规划提供依据。首先对遥感影像进行预处理,对高分一号卫星影像,按用地类型分别采用监督分类、面向对象和植被指数法提取城市2016年地表现状信息,并进行精度评价;对2010年的航空影像进行数字化,两类数据结合进行基于分类的变化检测和精度评价,分析城市空间变化特征。结果表明,厂房、建筑和未建成区分别采用监督分类、建筑阈值分类和面向对象法分类效果较好;廊坊市城市扩张的驱动力主要为经济发展、政策因素、历史条件、地形等。     

一种基于Fréchet距离的复杂线状要素匹配方法

在不同空间数据集中,同名实体往往有不同的空间表现形式,识别多源异构数据集中的同名实体是空间数据集成和应用的关键。集成不同来源的空间数据是提高GIS数据质量的重要方法,识别同名实体是数据集成和分析的先决条件。根据线要素的形状将其分为简单线要素和复杂线要素,针对现有复杂线要素匹配方法中的不足,提出了Fréchet距离的复杂线状要素匹配方法。该方法首先通过曲线要素的几何和拓扑特性获取候选匹配集,然后结合基于Fréchet距离和要素简化方法实现要素的简化。最后提出基于Fréchet距离的要素匹配改进方法,通过引入简化要素的三元组信息来存储简化后的复杂线要素的属性信息,再根据三元组信息选取要素间的匹配对,完成对不同类型匹配对的检测,实现复杂线状要素匹配。试验结果表明,该匹配方法能有效解决复杂线要素的匹配问题,并能够识别1:0、1:N和M:N匹配。     

Comparative performance of convolutional neural network,weighted and conventional support vector machine and random forest for classifying tree species using hyperspectral and photogrammetric data

ABSTRACT

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.     

一种切空间协同表示的高光谱遥感影像分类方法

协同表示分类（collaborative representation classification,CRC）算法近年来成为高光谱遥感分类的研究热点。地物类别间区分性不高会严重影响现有CRC算法的性能。流形结构可有效地解决非线性问题,并解决高光谱遥感影像因数据冗余导致的类别间区分性低的问题。提出了一种基于切空间的高光谱遥感影像协同表示分类算法（tangent space collaborative representation classification,TCRC）和一种基于欧氏距离的自适应加权的切空间协同表示分类算法（weighted tangent space collaborative representation classification,WTCRC）。TCRC算法利用测试样本的切平面来估计区域流形,在测试样本的切空间中使用协同表示算法,寻找测试样本在各类训练样本中的最优线性表示估计,并用其最小误差来对测试样本进行分类。在此基础上,利用测试样本邻域像元、训练样本与测试样本的欧氏距离作为权矩阵来自适应调整各样本对测试样本的影响。实验采用ROSIS（reflective optics system image spectro-meter）和AVIRIS（airbone visible infrared imaging spectrometer）高光谱遥感影像对所提出算法的性能进行了评价,结果表明TCRC和WTCRC在分类效果上比CRC有明显的提升,WTCRC相较于TCRC具有更好的分类效果,具有更强鲁棒性。