Urban Water Area Change Detection of Multitemporal SAR Images Using Density-Ratio Estimation and Density Peaks Clustering

Conference: EUSAR 2018 - 12th European Conference on Synthetic Aperture Radar
06/04/2018 - 06/07/2018 at Aachen, Germany

Proceedings: EUSAR 2018

Pages: 4Language: englishTyp: PDF

Personal VDE Members are entitled to a 10% discount on this title

Yan, Tianheng; Yang, Xiangli (School of Electronic Information, Wuhan University, Wuhan 430072, China)
Yang, Wen (School of Electronic Information, Wuhan University, Wuhan 430072, China & The CETC Key Laboratory of Aerospace Information Applications, Shijiazhuang 050081, China)
Liao, Ming-Sheng (The State Key Laboratory LIESMARS, Wuhan University, Wuhan 430072, China)

The availability of high spatial-resolution synthetic aperture radar (SAR) data provides great potential to urban environmental monitoring. In this paper, a water change detection framework for high resolution SAR time-series images is proposed. Rather than estimating the statistical distribution, we directly generate the difference map by estimating density ratio of two images. The density peaks clustering is then adopted to difference map series to excavate the change patterns of urban water areas. Experimental results demonstrate the effectiveness of the proposed framework.