遥感图像土地覆盖分类中多源特征数据选择研究

多源特征数据可以提高遥感图像的分类精度,选择合适的特征数据十分重要。利用基尼指数对多尺度纹理信息、主成分变换前三分量、地形数据等特征进行选择,选出最佳特征子集。利用支持向量机、神经网络分类法、最大似然法分别对全部特征数据和最佳特征子集结合多光谱数据进行分类。实验结果表明:基尼指数可以有效地对多源特征数据进行选择,特征选择可以提高分类器效率,提高分类精度。     

Land cover classification of VHR airborne images for citrus grove identification

Managing land resources using remote sensing techniques is becoming a common practice. However, data analysis procedures should satisfy the high accuracy levels demanded by users (public or private companies and governments) in order to be extensively used. This paper presents a multi-stage classification scheme to update the citrus Geographical Information System (GIS) of the Comunidad Valenciana region (Spain). Spain is the first citrus fruit producer in Europe and the fourth in the world. In particular, citrus fruits represent 67% of the agricultural production in this region, with a total production of 4.24 million tons (campaign 2006-2007). The citrus GIS inventory, created in 2001, needs to be regularly updated in order to monitor changes quickly enough, and allow appropriate policy making and citrus production forecasting. Automatic methods are proposed in this work to facilitate this update, whose processing scheme is summarized as follows. First, an object-oriented feature extraction process is carried out for each cadastral parcel from very high spatial resolution aerial images (0.5 m). Next, several automatic classifiers (decision trees, artificial neural networks, and support vector machines) are trained and combined to improve the final classification accuracy. Finally, the citrus GIS is automatically updated if a high enough level of confidence, based on the agreement between classifiers, is achieved. This is the case for 85% of the parcels and accuracy results exceed 94%. The remaining parcels are classified by expert photo-interpreters in order to guarantee the high accuracy demanded by policy makers.     

Land cover classification of finer resolution remote sensing data integrating temporal features from time series coarser resolution data

Land cover classification of finer resolution remote sensing data is always difficult to acquire high-frequency time series data which contains temporal features for improving classification accuracy. This paper proposed a method of land cover classification with finer resolution remote sensing data integrating temporal features extracted from time series coarser resolution data. The coarser resolution vegetation index data is first fused with finer resolution data to obtain time series finer resolution data. Temporal features are extracted from the fused data and added to improve classification accuracy. The result indicates that temporal features extracted from coarser resolution data have significant effect on improving classification accuracy of finer resolution data, especially for vegetation types. The overall classification accuracy is significantly improved approximately 4% from 90.4% to 94.6% and 89.0% to 93.7% for using Landsat 8 and Landsat 5 data, respectively. The user and producer accuracies for all land cover types have been improved.     

顾及物候特征的喀斯特断陷盆地土地覆盖遥感分类

在喀斯特分布区,基岩、植被、裸地等多种地表覆盖交错分布,地物覆盖高度异质,并且呈现出短周期规律性变化和长期动态趋势变化,单一时相的影像进行土地覆盖分类精度非常有限。针对这一问题,本文提出一种顾及物候特征的多时相遥感影像分类策略,利用具有高时间分辨率的MODIS NDVI时间序列产品作为数据源,选择BFAST(Breaks For Additive Seasonal and Trend)方法进行NDVI时间序列的物候分解,采用动态阈值法对时序分解的物候轨迹进行标记,最后将物候标记特征与原始光谱时序综合特征进行组合,选择支持向量机(SVM)分类器进行土地利用覆盖分类,并且对比了不同特征空间下的分类结果。以云南省壮族苗族自治州丘北县和砚山县为研究区进行分类实验,结果表明,BFAST模型可以有效地分解出NDVI时序中的关键物候特征,相比基于单纯光谱特征的分类,物候驱动的喀斯特断陷盆地区土地覆盖分类精度有明显的提升,在NDVI、光谱和物候组合特征空间下,土地覆盖分类精度最高,总体精度和Kappa系数分别为88.94%和0.8693,尤其在灌木林、有林地、石旮旯地与稀疏植被的区分中,SOS、POS和GSG等物候特征具有较强的可分性,表明物候特征在地物识别中的有效性。     

利用OpenStreetMap数据进行高空间分辨率遥感影像分类

针对高分辨率遥感影像分类样本标注困难的问题,提出了一种利用OpenStreetMap （OSM）数据自动获取标注样本的方法。与现有的利用OSM数据进行分类的方法不同,该方法加入了空间特征以弥补单独使用光谱特征分类的不足。首先,基于OSM数据提供的地物类别和位置信息进行样本标注,为了降低OSM数据中少量错误信息对分类结果的影响,采用聚类分析的方法对样本进行提纯;其次,使用形态学轮廓来提取影像的结构特征,挖掘高分辨率遥感影像丰富的空间信息,与光谱特征相叠加并输入分类器进行分类。试验证明,本文提出的方法能够有效避免人工样本标注所需要的人力物力;同时,联合影像的光谱空间特征能够更好地描述地物特性,得到较高的分类精度。     

基于光谱和纹理特征的山区高分辨率遥感影像分类

本文在只做阴影补偿而不做地形校正的情况下,使用光谱和纹理特征相结合的方法进行山区高分辨率遥感影像分类。实验取得了78%的分类精度,表明该方法合理可行,具有一定的实用性。     

Land use/land cover changes near HAzira Region, Gujarat using remote sensing satellite data

Human activities have great influence on fragile coastal ecosystem. For sustainable use of coastal resources it is very important to understand land use/land cover changes and its implications on coastal systems. Remote sensing data because of its synoptic, multispectral and multi temporal nature can be a very good source for mapping, monitoring and understanding these changes. IRS LISS III sensor data were used to find out the rate of land use/land cover changes in Hazira area near Surat, Gujarat. Because of major industrial activities it has become a hot spot area which requires regular monitoring. In the present study, land cover information of the period 1970–1972 from the Survey of India topographical maps, and satellite data of the year 1989 and 1999–2002 have been used and visual analysis has been carried out to measure the land use/land cover changes. Erosion and deposition has been observed around the newly constructed jetty. Forest area and agriculture area is found to decreased, whereas built-up area has increased.     

多光谱遥感影像植被覆盖分类研究进展

利用多光谱遥感影像进行植被覆盖分类是目前遥感技术应用的热点研究领域之一。在广泛调研文献的基础上,综述了近年来多光谱遥感影像植被分类研究现状和进展,较全面深入地分析了各种植被分类特征、分类算法的优缺点、适应性和应用情况,指出了当前面临的难点和挑战,并对未来发展趋势进行了展望。未来多光谱遥感影像的植被分类不仅要从分类算法上进行创新,提高分类器的自动化程度、分类效率和学习速度,扩大适用范围,增强鲁棒性,而且同样不能忽视对植被分类新特征的挖掘,提高特征的可分性,融合多源数据、利用多时相影像、挖掘更多新特征参与植被分类是未来的发展趋势。     

A Boosted Genetic Fuzzy Classifier for land cover classification of remote sensing imagery

A Boosted Genetic Fuzzy Classifier (BGFC) is proposed in this paper, for land cover classification from multispectral images. The model comprises a set of fuzzy classification rules, which resemble the reasoning employed by humans. Fuzzy rules are generated in an iterative fashion, incrementally covering subspaces of the feature space, as directed by a boosting algorithm. Each rule is able to select the required features, further improving the interpretability of the obtained model. After the rule generation stage, a genetic tuning stage is employed, aiming at improving the cooperation among the fuzzy rules, thus increasing the classification performance attained after the first stage. The BGFC is tested using an IKONOS multispectral VHR image, in a lake-wetland ecosystem of international importance. For effective classification, we consider advanced feature sets, containing spectral and textural feature types. Comparative results with well-known classifiers, commonly employed in remote sensing tasks, indicate that the proposed system is able to handle multi-dimensional feature spaces more efficiently, effectively exploiting information from different feature sources.     

像元尺度上分类不确定性评价及可视化表达

传统的地物类别尺度上的遥感影像分类不确定性评价仅能实现分类精度的数学度量,无法反映分类不确定性的空间分布,难以完整、准确地描述和理解遥感影像分类信息的不确定性.文章首先在像元尺度上对遥感影像分类的不确定性进行评价,并在此基础上利用计算机技术从彩色可视化、用户交互式可视化和用户选择性可视化模式3个方面在空间域上对分类不确定性进行描述,从视觉感知角度表达遥感影像分类的不确定性信息,从而使用户更加形象直观地理解不确定性信息数据的大小及其空间分布.     

A multi-level context-guided classification method with object-based convolutional neural network for land cover classification using very high resolution remote sensing images

Classification of very high resolution imagery (VHRI) is challenging due to the difficulty in mining complex spatial and spectral patterns from rich image details. Various object-based Convolutional Neural Networks (OCNN) for VHRI classification have been proposed to overcome the drawbacks of the redundant pixel-wise CNNs, owing to their low computational cost and fine contour-preserving. However, classification performance of OCNN is still limited by geometric distortions, insufficient feature representation, and lack of contextual guidance. In this paper, an innovative multi-level context-guided classification method with the OCNN (MLCG-OCNN) is proposed. A feature-fusing OCNN, including the object contour-preserving mask strategy with the supplement of object deformation coefficient, is developed for accurate object discrimination by learning simultaneously high-level features from independent spectral patterns, geometric characteristics, and object-level contextual information. Then pixel-level contextual guidance is used to further improve the per-object classification results. The MLCG-OCNN method is intentionally tested on two validated small image datasets with limited training samples, to assess the performance in applications of land cover classification where a trade-off between time-consumption of sample training and overall accuracy needs to be found, as it is very common in the practice. Compared with traditional benchmark methods including the patch-based per-pixel CNN (PBPP), the patch-based per-object CNN (PBPO), the pixel-wise CNN with object segmentation refinement (PO), semantic segmentation U-Net (U-NET), and DeepLabV3+(DLV3+), MLCG-OCNN method achieves remarkable classification performance (> 80 %). Compared with the state-of-the-art architecture DeepLabV3+, the MLCG-OCNN method demonstrates high computational efficiency for VHRI classification (4–5 times faster).     

Land cover changed object detection in remote sensing data with medium spatial resolution

Land cover change information is crucial to analyse the process and the change patterns of environments and ecological systems. Recent studies have incorporated object-based image analysis for its ability to generate meaningful geographical objects into studies of change detection. In this research, we developed a systematic methodology to realise multi-type land cover changed object detection with medium spatial resolution remote sensing images in Beijing, China. Optimum index factor (OIF) was applied to determine the best change indicators and the chi-square transformation was carried out to determine the change threshold of the 4 classes of changed object. The clustering change vectors in the feature space were proposed to discriminate the change types. According to the accuracy assessment, the overall accuracy of changed/unchanged object detection was approximately 93.9% with an overall kappa of 0.824, and the change type discrimination also achieved an overall accuracy of 81.67%, indicating the effectiveness of the proposed method.     

An assessment of biodiversity hotspots using remote sensing and GIS

This study focuses on the assessment of the status of world’s remaining closed forests (WRCF), population distribution, and protected areas in global biodiversity hotspots using remote sensing and Geographic Information System (GIS). Conservation International (CI) has identified 25 eco-regions, called biodiversity hotspots that are especially rich in endemic species and are particularly threatened by human activities. This study uses globally consistent and comprehensive geo-spatial data sets generated using rerriote sensing and other sources, and the application of GIS layering methods. The consistent data set has made it possible to identify and quantify relationships between the WRCF, human population, and protected areas in biodiversity hotspots. It is expected that such information will provide a scientific basis for biodiversity hotspots management and assist in policy formulations at the national and international levels.     

条件随机场框架下基于随机森林的城市土地利用/覆盖遥感分类

针对"基于像素的条件随机场(conditional random fields,CRFs)模型能否在m级分辨率的多光谱遥感图像分类中表现良好"的问题,提出了集成图像的光谱、方向梯度直方图和多尺度多方向Texton纹理等多种线索的CRFs模型定义方法。利用上述特征,选择随机森林(random forests,RF)定义CRFs关联势函数;利用特征对比度加权的Potts函数定义CRFs交互势函数,并且建立了多标签的RF-CRFs模型;对该模型进行分项参数训练以及基于图割的α-膨胀算法推理;利用典型城区的Quick Bird多光谱图像进行模型的验证与精度评价。结果表明RF-CRFs模型的分类精度可达82.52%以上,比RF分类器的分类精度提高了3.35%。     

基于分形纹理的遥感影像土地覆盖的分类方法研究

提出一种基于分形理论和改进模糊C均值聚类的遥感图像非监督分类方法,该方法尝试将图像的光谱信息和纹理特征相结合。将图像进行主分量变换,根据第一主分量计算图像的布朗运动的各方向的分形维数,差分盒维数和"空隙"等纹理特征作为分类依据。采用改进的模糊C均值聚类,并用混淆矩阵方法评定分类结果精度。通过对试验区的分类试验,说明该方法对改善土地覆盖分类精度行之有效。     

Soil resource assessment and mapping using remote sensing and GIS

In this study digital image processing for physiographic analysis and soil resource mapping of Solani watershed was carried out using satellite remote sensing data and GIS. Digital image processing of satellite data facilitated in accurately delineating and identifying various soil mapping units. The physiography of the study area is mainly influenced by denudational and colluvial processes in the upper part and by sedimentation processes in the lower part. Topography of the land and nature of parent material along with the time factor seemed to have played a vital role in the genesis of soils. Majority of the mapping units are Typic Haplustepts with Entisols and Inceptisols being the major soil orders. The soils of the Siwalik hills experiences severe erosion, which prevents the maturation of soil profile. The present study demonstrated that satellite remote sensing and GIS is a valuable tool for physiographic analysis and soil resource mapping.     

行星遥感影像目标识别与分类进展

从行星遥感海量数据中对地形地貌特征进行识别和分类,是行星科学研究中的一项重要基础工作.本文综述了自实施月球和深空探测任务以来,国际、国内采用行星影像数据进行地形地貌识别与分类技术的研究进展.首先,从月球、火星以及其他行星探测任务3个方面,对相关的探测任务和获取的影像数据进行简介.然后,在介绍通用目标识别与分类方法研究进...     

面向对象的高光谱遥感影像稀疏表示分类

稀疏表示用于高光谱遥感影像分类多是基于像素层次来处理的。文中提出一种面向对象的高光谱遥感影像稀疏表示分类方法。首先从高光谱影像中提取4个波段组成标准的多波段影像,进行面向对象的影像分割;然后计算各对象在各波段上的光谱均值,并选取少量样本进行训练;最后利用基于Fisher字典学习的稀疏表示进行高光谱遥感影像的分类。实验结果表明,该方法可以利用较少的样本得到较好的分类效果,与基于像素层的稀疏分类相比较,分类精度与效率均有所提高,分类结果更接近真实地物,避免了零碎图斑。     

RADARSAT-2全极化SAR数据地表覆盖分类

全极化合成孔径雷达(SAR)能够测量每一观测目标的全散射矩阵,但地物分布的复杂性往往造成不同地物具有相似的后向散射信号特征,因而增加了地物信息提取的难度。文中基于北京地区的RADARSAT-2全极化雷达数据,在图像处理的特征分解的基础上,利用PolSARPro软件提取包含地物散射机理信息的各种极化参数,按H-α、A-α、H-A对全极化SAR影像进行基于散射机理的分类,继而将分类结果作为Wishart H/A/α、Wishart H/α的初始类别划分。最后,采用决策树分类算法对基于Wishart分布的监督分类及以上两种分类算法进行融合处理,从而实现地物的分类,并将分类结果与经典的分类算法进行对比分析,验证了文中方法的有效性。