Unsupervised urban detection from High-Resolution Remote-Sensing Imagery based on Improved Harris corner detector

Abstract

Abstract:

Traditional urban detection methods are mainly based on global image feature, such as texture, spectrum and shape etc. However, these features are not invariant to scale and illumination changes, which consequently reduce the robust of the existing algorithms. To solve this problem, we propose the use of local feature for urban detection from high-resolution remote-sensing imagery. The proposed method consists of three steps: First, we extract a large set of local feature point by Harris corner detector. In order to achieve a reliable extraction of corners from urban areas, we further propose two criterions to validate and filter them. Afterwards, we incorporate the extracted corners into a likelihood function, and use it to measure the possibility of each pixel belonging to the urban area. Finally, we extract urban area by an adaptive binary segmentation method. Experimental results show that the proposed approach outperforms the existing algorithms in terms of detection accuracy.

Key words: high-resolution remote-sensing imagery, urban extraction, corner detection, probability likelihood function voting

CLC Number:

TP391

References

[1] Guo, L. Ma, S.C. Ye. Remote Sensing Image Extraction of Residential Areas Based on Radon and Tree-structured Wavelet Transformation[J]. Geomatics & Spatial Information Technology, 2012: 35(1), 150-153 (过林，马莉，叶诗淳. 基于Radon和树型小波变换的遥感影像居民地提取[J].测绘与空间地理信息, 2012: 35(1), 150-153)
[2] W. Sun, G. Xu, P. Gong. Textual and Local Spatial Statistics for the Object-oriented Classification of Urban Areas Using High Resolution Imagery [J]. International Journal of Remote Sensing, 2006:27(22), 4963-4990
[3] M. Pesaresi, A. Gerhardinger, F. Kayitakire. A robust built-up area presence index by anisotropic rotation-invariant textural measure[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2008:1(3), 180-192
[4] J. A. Benediktsson, J. A. Palmason, J. R. Sveinsson, Classification of hyperspectral data from urban areas based on extended morphological profiles [J]. IEEE Transaction on Geoscience and Remote Sensing, 2005:43(3), 480-491
[5] M. Pesaresi, J. A. Benediktsson. A new approach for the morphological segmentation of high-resolution satellite imagery [J]. IEEE Transaction on Geoscience and Remote Sensing, 2001:39(2), 309-320
[6] P. Zhong, R. Wang. A multiple conditional random fields ensemble model for urban area detection in remote sensing optical images [J]. IEEE Transaction on Geoscience and Remote Sensing, 2007:45(12), 3978-3988
[7] C. ünsalan, K. L. Boyer. Classifying land development in high-resolution panchromatic satellite images using straight-line statistics [J]. IEEE Transaction on Geoscience and Remote Sensing, 2004: 42(4), 907-919
[8] X. Huang, L. P. Zhang, P. Li. Classification of very high spatial resolution imagery based on the fusion of edge and multispectral information [J]. Photogrammetri Engineering and Remote Sensing, 2008: 74(12), 1585-1596
[9] T.M Wang, J.C Wang, Y. Yang. A Fully Automatic Endoscopic Image Correction Method Using Harris Corner Detection [J]. Acta Automatica Sinica, 2011:37(11), 1360-1367.（王田苗, 王君臣, 杨艳等. 基于 Harris 角点的内窥镜影像变形全自动校正算法. 自动化学报, 2011:37(11), 1360-1367）
[10] M.F. Wang, S.H. Yang, Q.Z. Wu. A Geometric Quality Assessment Algorithm of Remote Sensing Image Based on Corner Detection [J]. Acta Geodaetica et Cartographica Sinica, 2011:40(2), 175-179(王明富; 杨世洪; 吴钦章等. 基于角点检测的遥感影像几何质量评价方法[J]. 测绘学报，2011: 40(2), 175-179)
[11] C. G. Harris, M. Stephens. A Combined Corner and Edge Detector. In Proceedings of Fourth Alley Vision Conference, 1988: 182-192
[12] J.S. Ma, J. Shen, S.C. Xu. A Parallel Implementation of Douglas-Peucker Algorithm for Real-Time Map Generalization of Polyline Features on Multi-core Processor Computers[J], Geomatics and Information Science of Wuhan University, 2011:36(12), 1423-1426 (马劲松; 沈婕; 徐寿成. 利用Douglas-Peucker并行算法在多核处理器上实时综合地图线要素, 武汉大学学报(信息科学版) ,2011:36(12), 1423-1426)