居民区相对于其他区域具有更明显更丰富的边缘特征. 根据这一特点，提出一种利用边缘密度特征差异
进行高分辨率遥感影像居民区自动提取的方法. 该方法首先利用Mean Shift 算法平滑原始影像，然后检测平滑影
像上的边缘并拟合成直线段，最后利用影像中的边缘密度分布构建空间投票矩阵，并结合Ostu 阈值分割方法提取
居民区. 实验表明：该方法可用于提取场景比较复杂的影像中的居民区，且具有较高的准确率和鲁棒性.
Built-up area contains obvious edge features. We propose a method to extract edge-based built-up
area from high resolution remote sensing images. The algorithm includes three steps: smoothing the original
image with a mean shift algorithm, extracting edges with the Canny operator and fitting them as several
straight lines, and forming a spatial voting matrix based on the edge distribution and extracting the built-up
area using the Ostu’s method. Experimental results show that the proposed approach can detect built-up areas
in images with complicated background. It is highly robust and accurate.
[1] Benediktsson J A, Pesaresi M, Arnason K. Cla¬s¬¬sification and feature extraction for remote sensing images from built-up areas based on morphological transformations [J]. IEEE Transactions on Geoscience and Remote S¬e¬nsing, 2003,41( 9): 1940–1949.
[2] Weigl K， Giraudon G, Berthod M. Applic¬ation of projection learning to the detection of built-up areas in spot satellite images [R]. Rapports de recherche-INRIA, 1993.
[3] Fang W, Chao W, Hong Z. Residential area inf¬ormation extraction by combining china a¬i¬r¬¬¬borne sar and optical images[C]//IEEE International Geoscience and Remote Sensing Symposium, 2004.
[4] Zhong P, Wang R. A multiple conditional random fields ensemble model for built-up area detection in remote sensing optical images [J]. IEEE Transactions on Geoscience and Remote Sensing, 2007, 45(12): 3978¬–3988.
[5] Unsalan C，Boyer K. L. A theoretical and experimental investigation of graph theoretical measures for land development in satellite imagery [J]. IEEE Tran¬sactions on Pattern Analysis and Machine Inte¬lligence, 2005, 27(4): 575–589.
[6] Karathanassi V, Iossifidis C, Rokos D. A texture-based classifica-tion method for clas¬sifying built areas according to their density [J]. International Journal of Remote Sensing, 2000, 21( 9): 1807–1823.
[7] Bruzzone L， Carlin L. A multilevel context-based system for classification of very high spatial resolution images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2006,44(9):2587–2600.
[8] Fauvel M, Chanussot J, Benedikt¬sson J A. Decision fusion for the classification of urban remote sensing images[J]. IEEE Tran¬sactions on Geoscience and Remote Sensing, 2006, 44(10) :2828–2838.
[9] Hu Xiangyun, Shen Jiajie, Shan Jie, Pan Li. L¬o¬c¬al edge distributions for detection of sali¬ent structure textures and objects [J]. IEEE Geoscience and Remote Sensing Letters.
[10] Comaniciu D. Mean Shift: A robust approach toward feature space analysis [J].IEEE Tran¬sactions on Pattern Analysis and Machine Inte¬lligence, 2002, 24(5): 1-18.
[11] Comaniciu D, Ramesh V, Meer P. Real-time tra¬¬c¬¬¬king of non-rigid objects using mean shift [C]//IEEE Conference on Computer Vision and Pattern Recognition, 2000.
[12] Otsu N. A threshold selection method from gra¬y¬-level histograms [J]. IEEE Transactions on Systems, Man and Cybernetics , 1979, SMC-9(1): 62–66.
[13] Rosin P L. A simple method for detecting sa¬lient regions [J]. Pattern recognition, 2009, 42(11): 263-2371.
[14] Sirmacek B, Unsalan C. Built-up area detec¬tion using local feature points and spatial vot¬ing [J].IEEE Geoscience and Remote Sen¬sing Letters, 2010,7 (1):146-150.
