Extracting residential information by remote sensing technology is significant for the loss estimation of natural disaster and the study of urban extension and environmental change.In this paper,taking Jiangning county of Nanjing as a case study area,the extraction of re sidential information from SPOT images is discussed.Firstly, the characteristics of residential areas in this area on this image are studied,secondly,spectral characteristics of residential areas and other land-use types on SPOT-4(XI) image are analyzed to find the possibility of extracting residential areas from the background according to spectral characteristics.Thirdly,a simple model of decision tree is proposed on the basis of spectral magnitude relations and some proper thresholds of residents and other land-use types.But some roads still cannot be separated from residential areas because their spectral characteristics are similar.Therefore,their shape characteristics are analyzed.The result is generalized and converted to vector coverage.Then the shape indexes of every spots are calculated and categorized choosing a threshold to remove the roads.Finally,the vector coverage of residential areas is overlaid on the original image to check the effectness of this model,and an accuracy assessment is given to the result by random samples.The results suggest that this model is simple and effective,especially for the residential areas over 10000 m2,and the analyzedfor is much higher than the supervised classification's,however,some pixels near the water-bodies and the roads are judged by mistakes.This problem can be solved by the rule judgment based on the knowledge of spatial relations.Therefore,the cities,towns and villages in the south of Yangze River where there are various types of land cover can be extracted from the images by this model,and the model is not limited by the time,only the thresholds will be changed.

以南京市江宁县为研究区域，首先分析了该区域居民地的影像特征，然后研究了居民地及其背景地物在SPOT―4(Ⅺ)卫星影像4个波段上的光谱特征，并由此探讨了它们在光谱特征上的可分性。研究发现，除道路在光谱特征上与居民地差异不大而难以完全分开外，其它背影地物均可以依据各波段亮度值的大小关系或适当的阈值与居民地分开。但道路和居民地在形状上存在明显差异，因此可以利用形状指数的差异加以去除。最后分析建立了基于光谱特征和形状特征的简单决策树模型，对研究区域居民地信息进行了提取并对结果进行了精度评价。结果表明，该方法的总体提取效果较好，特别是对于面积大于10000m^2的城镇和集村。其提取精度与通常的监督分类方法相比有了很大的提高，只是在水际交界处和道路两侧有误判现象。因此，利用该模型可以将背景地物类型复杂的江南地区的城镇和集村居民地自动提取出来，并且模型受时相影响较小，只是在域值大小上会存在一些差异。

In consideration of the features of remote sensing image, this paper presents a new method for classification of remote sensing images based on multiple classifiers combination. In this method, three supervised classifications, Mahalanobis Distance, Maximum Likelihood and SVM, which are of more precision and better diversity in classification, are selected to serve as the sub-classifications,  and the simple vote classification, maximum probability category method and fussy integral method are combined together according to certain rules. The authors adopted Huairen county in Shanxi as the study area for land use classification using color infrared aerial images. Experimental result showed that the overall classification accuracy was improved by 12% and Kappa coefficient was increased by 0.12 in comparison with SVM classification which has the highest accuracy in single sub-classifications. This result indicates that the classification of multiple classifiers combination is an effective classification method.

 针对遥感影像分类特点，提出了一种基于多分类器组合的遥感影像分类方法。该方法选取分类性能以及多样性最好的马氏距离、支持向量机（SVM）和最大似然等3种分类器作为子分类器，自定义规则对简单投票法、最大概率类别法以及模糊积分法进行组合，并以山西怀仁县为研究区，对基于航摄数字正射影像进行分类。结果表明，与单个子分类器中精度最高的SVM分类相比，基于多分类器组合的遥感影像分类总体分类精度提高了12%，Kappa系数提高了0.12，该方法是一种有效的分类方法。

Abstract: Spatial distribution status of construction land is closely related to the regional economic and social development. Therefore, timely monitoring and delivery of data on the dynamics of construction land are far-reaching for policy and decision making processes. Classifying land-use/land-cover and analyzing changes are among the most common applications of remote sensing. One of the most basic and difficult classification tasks is to distinguish the construction land from other land surfaces. Landsat imagery is one of the most widely used sources of data in remote sensing of construction land. Several techniques of construction land extraction using Landsat data are described in some literatures, but their applications are constrained by low accuracy in various situations, and usually using the technique of single index or multi-index. The purpose of this study was to devise a method to improve the accuracy of construction land extraction in the presence of various kinds of environmental noise. Thus we introduce a multi-features decision tree (DT) classification model for improving classification accuracy in the areas that including bare land, shadow and some streams, in which the other classification methods often fail to classify correctly. The model integrates four spectral indexes, the pattern recognition technique and spatial algorithms. The four spectral indexes are the normalized difference three bands index (NDTBI), the normalized difference building index (NDBI), the modified normalized difference water index (MNDWI) and the normalized difference vegetation index (NDVI) respectively. The pattern recognition technique is referred to support vector machine (SVM). And the spatial algorithm is to create buffer zone.The test site was deliberately selected so that it consists of complex surface features, such as bare land, hill shade, and some small streams that are liable to be mixed up with construction land on the Landsat imagery. For that reason, Landsat-8 OLI images (path/row 128/41) were selected in sight of its perfect performance in quality. All the Landsat images used are of product type L1T and were geometrically corrected and converted to top-of-atmosphere reflectance consequently. The subset image of one transition zone between urban and rural region in Bijie city of Guizhou province was selected as the test site, the area of which is 144 km2. Besides, the urban center of Qixingguan district of Bijie city was selected to produce thematic map of construction land for application inspection of classification robustness.Building decision tree (DT) nodes is the key of the methodology. Firstly, a new index called NDTBI was developed to be combined with NDBI to identify all the construction land from background. NDTBI and NDBI were separately arranged into the first and second node of DT. However, after executing the DT of the two nodes NDTBI and NDBI, noise such as bare land, shade, water existed together with all construction land at the same time. Secondly, MNDWI and NDVI were added into DT nodes in order to separate water and shadow from construction land. After executing the DT of the above four nodes, the bare land and streams, which share the same spectral feature with construction land, were the only objects mixed up with construction land. Therefore, the SVM classification, in the light of the optimal performance in land-cover classification, provides the opportunity to suppress the bare land noise. Meanwhile, the spatial algorithm was used to separate the small streams from construction land. To execute SVM classification, the training samples were selected by using principal components (PC) transformation of the multi-spectral images. The spatial algorithm is to create buffer zone for the small stream using vectors from visual interpretation. As a result, a segmentation binary image was obtained and added into DT. Two principles were proposed for the buffer zone creating: on the premise that construction land could not be included in the buffer zone, when some channel segment of stream is closely adjacent to the construction land, the width and shape of buffer zone should be same as that of river.To assess the accuracy, the high resolution fusion image (15 m) was taken as the reference dataset, a total of 564 sampling pixels were randomly drawn from the strata (i.e., construction land and non-construction land), 277 pixels from construction land and 287 from non-construction land. The accuracy assessment for test site reached 97.52%. Besides, for application inspection of the classification robustness, the Landsat-8 multispectral images of the urban center of Qixingguan district was used to produce the thematic map of construction land, which proved to be perfect with the overall accuracy 98.03%.The method developed in the paper is easy for understanding and operating, widely applicable, and capable of separating the disturbing noise from construction land. Furthermore, the model dramatically improved the accuracy of extracting construction land from the moderate resolution images. And the validation results suggest the widely applicable in western region of China, especially for the area with land-use/land-cover diversity.

城乡交接带的土地利用/覆盖类型兼具城镇和农村的典型特征。为了解决土地覆盖类型复杂、存在"同谱异物"现象的西部山区环境中建设用地信息难以精确提取的问题，该文提出一种包含多个特征节点的决策树分类法，该方法以Landsat-8影像为主要数据源，以决策树分类法为框架，结合地物光谱特征及空间特征，建立以4种归一化指数（归一化三波段指数normalized difference three bands index，NDTBI；归一化建筑指数normalized difference building index，NDBI；改进的归一化水体指数modified normalized difference water index，MNDWI；归一化植被指数normalized difference vegetation index，NDVI）、支持向量机（support vector machine，SVM）分类结果和河流缓冲区作为特征节点的决策树分类器，对贵州省毕节市城乡交接带建设用地专题信息进行提取。NDTBI是该文新构建的指数，取名为归一化三波段指数，目的是为了弥补归一化建筑指数NDBI的不足；支持向量机分类结果的使用在多指数法的基础上提高了地物的可分离性；以构建河流缓冲区的方式加入的地物空间信息, 进一步提高了信息提取的精确性。由于决策树特征节点的构建过程是利用先验知识来优化特征值和提高精度的过程，克服了利用单一指数法、多指数法及单独使用模式识别法中出现的问题，精度评价结果显示总体精度达到了97.52%。为了验证方法的推广性，采用毕节市七星关区中心城区遥感影像数据该方法进行验证，精度评价结果显示总体精度达到98.03%。

The fast expansion of urban built-up land and accompanied sharp decrease in farm land have made timely monitoring of landuse changes become more important than ever before.The ability to monitor the built-up land dynamics in a cost-effective manner is highly desirable for local communities and decision makers alike.Fortunately,satellite remote sensing technique offers considerable promise to meet this requirement.Although the use of remote sensing technique in the monitoring of land use changes has become more and more popular and satellite imagery has been frequently used to discriminate built-up lands from non-built-up lands for the last few decades,the extraction of built-up land information from remote sensing imagery is still not an easy task due largely to the heterogeneous characteristics of the built-up land.Among many techniques developed for the extraction of built-up land information,the index-based built-up index(IBI) was created based on three existing thematic indices rather than original multispectral bands.The use of the three thematic indices-soil-adjusted vegetation index(SAVI),modified normalized difference water index(MNDWI) and normalized difference built-up index(NDBI)-greatly help the delineation of built-up land features in remote sensing imagery,because these three indices represent three major landuse components,which are vegetation,water and built-up land,respectively.Therefore,the IBI can significantly enhance built-up land information while suppressing background noise.Consequently,the built-up land can be effectively extracted from the IBI image with high accuracy.In order to quicken image processing,this built-up extraction technique has been programmed to form an easy-use module using the ER Mapper scripting language.The module was further integrated in the ER Mapper package by adding a button to the manual bar.This allows users to automatically perform the extraction procedure with high accuracy just in a few minutes.

建筑用地的急剧增加和耕地资源的迅速减少,使得土地利用动态变化监测显得尤为重要。遥感作为监测土地利用动态变化的一种有效手段,已经得到日益广泛的应用。但是建筑用地由于其光谱的异质性,而难以用简单的方法将它们从遥感影像中准确提取出来,遥感建筑用地指数(Index-based Built-up Index,IBI)是针对这一问题提出的。它的构建采用的是三个专题指数波段(SAVI植被指数、MNDWI水体指数、NDBI建筑指数),而不是影像的原始波段。由于这三个指数互为负相关,因此,可以有效地增强和提取遥感影像中的建筑用地信息。通过将IBI指数提取建筑用地的影像处理过程编成可自动执行的模块,并集成于大型的遥感商业软件中,使得影像数据处理和建筑用地信息提取时间大大缩短,提高了建筑用地信息增强和提取的效率。

Based on a data dimension compression technique, this paper studies the principles and method of remote sensing information extraction for urban built up land. With the detailed analysis of urban land use types, the study selects three indices,i.e. Normalized Difference Built up Index(NDBI), Modified Normalized Difference Water Index (MNDWI) and Soil Adjusted Vegetation Index(SAVI), to represent three major urban land use/cover classes, including built up land, water body, and vegetation. This reduced 7 multispectral bands of a Landsat 7 ETM+ subscene of Fuzhou city to three index bands generated from the original multispectral bands and thus dramatically decreased band correlation, data redundancy and spectral confusion between different land use/cover classes. The three index bands are then used to compose a new image. A maximum likelihood based supervised classification was carried out on the new three band image and the built up land is finally extracted by masking out non built up land classes. The extraction result achieves a 91.2% overall accuracy. Therefore, the method is an effective one for the remote sensing information extraction of urban land use.

通过压缩数据维的方式，研究城市建筑用地信息准确提取的原理和方法。通过对城市土地利用类型的分析，选取了归一化差异建筑指数、修正归一化差异水体指数和土壤调节植被指数来代表城市建成区的3种最主要地类――建筑用地、水体和植被。通过将ETM 影像原有的7个波段压缩为由它们衍生的这3个采用比值运算构成的指数波段，大大压缩了数据维数、减少了数据的相关度并降低了不同地类的光谱混淆性。因此采用简单的最大似然分类和掩膜处理技术，就可以将城市建筑用地信息提取出来，其精度可达91．2％。

A new method for extraction of built-up land information both in suburban area and in urban district by using Landsat TM/ETM + imagery is proposed in this paper. Firstly, to suppress the information of bare soil with the middle-infrared(TM7), near-infrared(TM4) and green band (TM2), it is necessary to build a secondary index, which is called normalized difference bareness and built-up index(NDBBI). At the same time, to enhance the information of bare soil from existing indices of bare soil index(BSI)and modified normalized difference water index(MNDWI), another secondary index is built, which is called enhanced bare soil index(EBSI). Finally, the indices of NDBBI, EBSI, SAVI and MNDWI are applied to constructing a new index for delineating built-up land features in satellite imagery, which is called enhanced index-based built-up index(EIBI). The new index(EIBI)can be employed to extract the built-up land information both in suburban area and in urban district. This approach has been successful in Fuzhou and Zhangzhou experimental regions. Built-up features can be extracted objectively and sufficiently with the accuracy above 90%.

以Landsat TM/ETM + 图像为数据源,研究城镇和农村建筑用地信息的提取方法。首先利用TM 7,4,2波段创建归一化差值裸地与建筑用地指数(normalized difference bareness and built-up index, NDBBI ); 然后根据裸地在裸土指数(bare doil index, BSI)图像上的亮度值最高、在改进型归一化差值水体指数(modified normalized difference water index, MNDWI)图像的亮度值最低的特征,提出了增强型裸土指数(enhanced bare soil index, EBSI); 最后选用NDBBI,EBSI,MNDWI和SAVI(soil adjustment vegetation index, SAVI)4个指数,构建一种新型的建筑用地指数,称为"增强的指数型建筑用地指数"(enhanced index-based built-up index,EIBI),可快速地提取建筑用地信息。实验结果表明,用EIBI提取的建筑用地信息客观,人为干预少,可信度高,提取精度可达90%以上,适合于同时提取城市和农村建筑用地信息。

With the popularization of high resolution remote sensing data of domestic satellite in such fields as land resources, geology, and environment, domestic high-resolution remote sensing data are likely to become the preferred data source for monitoring the development status of mining areas in the near future. Using the ZY-1 02C and GF-1 images, the authors designed an integrated solution for geodatabase building of remote sensing images, image processing, geometric correction, information extraction, spatial calculation, statistical analysis, and final mapping production, and successfully applied such means to the related work in Tibet. The results achieved by the authors can increase the depth and scope of the application of the domestic satellite remote sensing data, and provide technical support and paradigms for large-scale and multi-period dynamic remote sensing monitoring of mines.

随着高分辨率国产遥感卫星数据的推广应用，矿山遥感监测必将成为该数据的重要应用领域之一。结合西藏自治区矿山遥感监测工作的特点，以资源一号02C（ZY-1 02C）及高分一号（GF-1）卫星影像为数据源，在ArcGIS环境下，提出并实现了从国产卫星遥感数据管理、增强与校正、信息提取、统计分析以及成果图制作等一体化解决方案。该研究成果有助于推进国产卫星遥感数据在矿山遥感监测领域的应用广度和深度，为大规模开展多期次动态矿山遥感监测工作提供技术支持和应用范例。

The IKONOS data of Beijing Yuanmingyuan is fused with Tasseled Cap（KT） and PCA methods.The fusion results are analyzed and compared with full image and vegetation subset.The result shows that，in study area，the KT fusion method is better than PCA in full image and vegetation subset.The fusion results are differential with different KT transformation matrix，and the method of fusion should be chosen according to study area，data，and classification methods.

应用缨帽变换（KT）和主成分分析（PCA）方法，对北京圆明园周围的IKONOS全色波段和多光谱波段进行融合，并分别对整景影像和植被区的融合结果进行对比研究，结果表明：在该实验区，整景影像和植被区缨帽变换融合结果都优于主成分析结果，不同的缨帽变换系数矩阵在整景影像和植被区融合质量会有差别，应根据具体地点、时相，分类方法做适当的选择。

文中提出了IKONOS多光谱图像缨帽变换方法.缨帽变换是多光谱波段的一种线性变换,且该变换能消除多光谱图像的相对光谱响应相关性,并对全色图像可视化和自动特征提取都非常有用.IKONOS缨帽变换系数是Tames H.Horne对近二百多幅IKONOS图像的分析得到的.文中用江苏盐城的一幅IKONOS图像进行了实验,实验结果表明:缨帽变换对区分不同类型植被类型如树、灌木、草地、农作物等非常有效,同时也能很好将植被从人造物如道路和建筑区分开来.