利用角点进行高分辨率遥感影像居民地检测方法

测绘学报

利用角点进行高分辨率遥感影像居民地检测方法

陶超¹,邹峥嵘丁晓利³

收稿日期:2012-09-21 修回日期:2013-12-02 出版日期:2014-02-20 发布日期:2013-12-19
通讯作者: 陶超
基金资助:
科技部科技支撑计划

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

Received:2012-09-21 Revised:2013-12-02 Online:2014-02-20 Published:2013-12-19

摘要/Abstract

摘要：

传统的城区检测方法大多是基于影像的全局特征，如纹理、光谱、形状等。当影像出现尺度、光照等条件变化时，将导致这些特征出现变化，造成算法的稳健性下降。而局部不变特征（例如，角点）却不易受到这些因素的影响。为此，本文提出一种无监督的基于角点特征的高分辨率遥感影像城区检测方法。该方法首先在传统的Harris算子的基础上，加入局部和全局约束准则检测影像中的角点，然后根据影像中角点的分布情况，自适应地构建似然函数来度量影像中每一个像素点属于城区的概率，最后采用二值分割的方法提取影像中的城市区域。实验结果表明：该方法可以快速、可靠地检测到影像中的城市区域，具有较高的实际应用价值。

关键词: 高分辨率遥感影像, 城区检测, 角点提取, 概率似然函数

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

中图分类号:

TP391

陶超邹峥嵘丁晓利. 利用角点进行高分辨率遥感影像居民地检测方法[J]. 测绘学报.

参考文献

[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)

[1]	何直蒙, 丁海勇, 安炳琪. 高分辨率遥感影像建筑物提取的空洞卷积E-Unet算法[J]. 测绘学报, 2022, 51(3): 457-467.
[2]	张玉鑫, 颜青松, 邓非. 高分辨率遥感影像建筑物提取多路径RSU网络法[J]. 测绘学报, 2022, 51(1): 135-144.
[3]	张涛, 丁乐乐, 史芙蓉. 高分辨率遥感影像城中村提取的景观语义指数方法[J]. 测绘学报, 2021, 50(1): 97-104.
[4]	左宗成, 张文, 张东映. 融合可变形卷积与条件随机场的遥感影像语义分割方法[J]. 测绘学报, 2019, 48(6): 718-726.
[5]	董志鹏, 王密, 李德仁, 王艳丽, 张致齐. 遥感影像目标的尺度特征卷积神经网络识别法[J]. 测绘学报, 2019, 48(10): 1285-1295.
[6]	范荣双, 陈洋, 徐启恒, 王竞雪. 基于深度学习的高分辨率遥感影像建筑物提取方法[J]. 测绘学报, 2019, 48(1): 34-41.
[7]	董志鹏, 王密, 李德仁, 王艳丽, 张致齐. 利用对象光谱与纹理实现高分辨率遥感影像云检测方法[J]. 测绘学报, 2018, 47(7): 996-1006.
[8]	郑卓, 方芳, 刘袁缘, 龚希, 郭明强, 罗忠文. 高分辨率遥感影像场景的多尺度神经网络分类法[J]. 测绘学报, 2018, 47(5): 620-630.
[9]	杨幸彬, 吕京国, 江珊, 张丹璐. 高分辨率遥感影像DSM的改进半全局匹配生成方法[J]. 测绘学报, 2018, 47(10): 1372-1384.
[10]	刘莹, 陶超, 闫培, 邹峥嵘. 图割能量驱动的高分辨率遥感影像震害损毁建筑物检测[J]. 测绘学报, 2017, 46(7): 910-917.
[11]	林祥国, 张继贤. 面向对象的形态学建筑物指数及其高分辨率遥感影像建筑物提取应用[J]. 测绘学报, 2017, 46(6): 724-733.
[12]	董志鹏, 王密, 李德仁. 一种融合超像素与最小生成树的高分辨率遥感影像分割方法[J]. 测绘学报, 2017, 46(6): 734-742.
[13]	陈一祥, 秦昆, 张晔, 袁媛. 视觉显著性与知觉组织相结合的高分影像居民地提取方法[J]. 测绘学报, 2017, 46(12): 1959-1968.
[14]	龚健雅, 王密, 杨博. 高分辨率光学卫星遥感影像高精度无地面控制精确处理的理论与方法[J]. 测绘学报, 2017, 46(10): 1255-1261.
[15]	林祥国, 宁晓刚. 融合直角点和直角边特征的高分辨率遥感影像居民点提取方法[J]. 测绘学报, 2017, 46(1): 83-89.