A Building Detection Algorithm Based on Visual Attention and Feature Fusion in High Resolution SAR Images

doi:10.13485/j.cnki.11-2089.2014.0162

Abstract

Abstract:

A building detection algorithm based on visual attention and feature fusion is proposed for high spatial resolution SAR images. Firstly, visual attention model is constructed on the basis of great difference between buildings and backgrounds, and used to segment the ROIs of buildings. Secondly, bright lines and shadow regions are extracted in the segmented ROIs. Finally, D-S evidence theory is used to fusion the focus of attention, bright line and shadow region, and then the buildings are detected. Experimental results demonstrate that, the proposed algorithm has high detection accuracy for rectangular buildings in SAR images.

Key words: SAR image processing, Building detection, Visual attention model, D-S evidence theory, Feature fusion

CLC Number:

TP751

SU Juan ZHANG Qiang CHEN Wei WANG Jiping. A Building Detection Algorithm Based on Visual Attention and Feature Fusion in High Resolution SAR Images[J]. Acta Geodaetica et Cartographica Sinica, 2014, 43(9): 939-944.

References

[1] 赵凌君. 高分辨率SAR图像建筑物提取方法研究[D]. 国防科技大学，2009
Zhao Lingjun. Building Extraction from High Resolution SAR Imagery[D]. National University of Defense Technology, 2009
[2] Ferro A, Brunner D, Bruzzone L. Building detection and RADAR Footprint Reconstruction from Single VHR SAR Images. IGARSS 2010: 291-295
[3] 苏娟，鲜勇，宋建社. SAR图像与可见光图像融合的建筑物提取算法[J]. 兵工学报，2010，31(11)：1448-1454
Su Juan, Xian Yong, Song Jianshe. A Building Extraction Algorithm Based on the Fusion of SAR and Optical Images[J]. ACTA ARMAMENTARII, 2010, 31(11): 1448-1454
[4] 陶超，谭毅华，蔡华杰，杜博，田金文. 面向对象的高分辨率遥感影像城区建筑物分级提取方法[J]. 测绘学报，2010，39(1): 39-45
TAO Chao, Tan Yihua, Cai Huajie, Du Bo, Tian Jinwen. Object-oriented Method of Hierarchical Urban Building Extraction from High-resolution Remote-Sensing Imagery[J]. Acta Geodaetica et Cartographica Sinica, 2010, 39(1): 39-45
[5] 程亮，龚健雅. LiDAR辅助下利用超高分辨率影像提取建筑物轮廓方法[J]. 测绘学报，2008，37(3)：391-399
Cheng Liang, Gong Jian-ya. Building Boundary Extraction Using Very High Resolution Images and LiDAR[J]. Acta Geodaetica et Cartographica Sinica, 2008, 37(3): 391-399
[6] Mayer H. Automatic object extraction from aerial imagery – A survey focusing on buildings[J]. Computer vision and image understanding, 1999, 74(2): 138-149
[7] Tupin F. Extraction of 3D information using overlay detection on SAR images[C]. 2nd GRSS/ISPRS Joint Workshop on Remote Sensing and Data Fusion over Urban Areas. 2003: 72-76
[8] Zhang F l, Shao Y, Zhang X, Balz T. Building L-shape footprint extraction from high resolution SAR image[C]. Joint Urban Remote Sensing Event, Munich, Germany, April 11-13, 2011: 273-276
[9] Michaelsen E, Stilla U, Soergel U, Doktorski L Extraction of building polygons from SAR images: Grouping and decision-level in the GESTALT system[J]. Pattern recognition letters, 2010, 31:1071-1076
[10] Itti L, Koch C, Niebur E. A model of saliency-based visual attention for rapid scene analysis[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, 20(11): 1254-1259
[11] Navalpakkam V, Itti L. An integrated model of top-down and bottom-up attention for optimizing detection speed[C]. CVPR 2006: 2049-2056
[12] Rosin P.L. A simple method for detecting salient regions[J]. Pattern Recognition, 2009, 42(11): 2363-2371
[13] Borji A, Itti L. State-of-the-art in visual attention modeling[J]. IEEE transactions on pattern analysis and machine intelligence, 2013, 35(1): 185-207
[14] Jung C, Kim C. A unified spectral-domain approach for saliency detection and its application to automatic object segmentation[J]. IEEE transactions on image processing, 2012, 21(3): 1272-1283
[15] Dempster A P. Upper and Lower Probabilities Induced by Multivalued Mapping[J]. Annals of Mathematical Statistics, 1967, 38(2): 325-339
[16] Shafer G, Logan R. Implementing Dempster’s Rule for Hierarchical Evidence[J]. Artificial Intelligence, 1987, 33(3):271-298
[17] 张浩. 多信息融合图像边缘特征提取及图像配准研究与应用[D], 浙江大学, 2008
Zhang Hao. Research and application of Image edge Feature Extraction Based on Multiple Information Fusion and Image Registration Technique [D]. Zhejiang University, 2008
[18] 孙子文，李慧，纪志成. 基于D-S证据理论的融合图像隐写分析[J]. 控制与决策，2011，26(8): 1-5
Sun Zi-wen, Li Hui, Ji Zhi-cheng. Fusion image steganalysis based on Dempster-Shafer evidence theory[J]. Control and decision, 2011, 26(8): 1-5
[19] 吴艳，焦惊眉，杨晓丽，肖平，李明. 基于Contourlet域HMT和D-S证据融合的SAR图像分割[J]. 测绘学报，2011，40(2): 148-155
Wu Yan, JIAO Jingmei, Yang Xiaoli, Xiao Ping, Li Ming. Segmentation algorithm for SAR Images based on Fusion of HMT in the Contourlet domain and D-S Theory of evidence[J]. Acta Geodaetica et Cartographica Sinica, 2011, 40(2): 148-155
[20] Matas J, Chum O, Urban M. Robust wide baseline stereo from maximally stable extremal regions[C]. BMVC, 2002
[21] Brunner D, Lemoine G, Bruzzone L. Earthquake damage assessment of buildings using VHR optical and SAR imagery[J]. IEEE transactions on geoscience and remote sensing, 2010, 48(5): 2403-2420
[22] Ban S.W, Lee I, Lee M. Dynamic visual selective attention model[J]. Neurocomputing, 2008, 71: 853-856