High-Resolution Remote Sensing Image Change Detection Based on Fusion of Spectral and Geometrical Features

摘要：

This paper proposes a change in detection method based on fusion of spectral and geometrical features for multi temporal high-resolution remote sensing image. The theory basis of the fusion algorithm is the fuzzy set theory. First, the spectral and geometrical difference images are created for multi-temporal images. Then taking different images as input, the changed and unchanged classes of image would be acquired based on fuzzy classification method. Third, a fusion model of membership images based on the fuzzy set theory is used to distinguish the changed and unchanged classes of image. Finally, change detection results are obtained using the threshold segmentation algorithm. Experimental results approved that compared to other methods based on spectral or geometrical difference image, the method in which fusion change detection combines spectral and geometrical features has a higher overall change detection ratio and a lower residual detection ratio.

关键词： high-resolution image change detection fuzzy set fusion

作者: Yaohua Yi Shufeng Liu Shaohong Shen Changhui Yu

作者单位: School of Printing and Packaging, Wuhan University, 129 Luoyu Road, Wuhan, China School of Printing and Packaging, Wuhan University, 129 Luoyu Road, Wuhan, China School of Arts & Me Changjiang River Scientific Research Institute, 23 Huangpu Road, Wuhan, China School of Remote Sensing Information Engineering, Wuhan University, 129 Luoyu Road, Wuhan, China

会议类型: 国际会议

会议名称: 2010 International Conference on Image Analysis and Signal Processing(2010 图像分析与信号处理国际会议 IASP 10)

会议地点: 厦门

会议语种:英文

页码: 117-122

在线出版日期: 2010-04-12（万方平台首次上网日期，不代表论文的发表时间）