Unsupervised change detection in urban area using multitemporal ERS-1/2 InSAR data
Refereed conference paper presented and published in conference proceedings


Times Cited
Altmetrics Information
.

Other information
AbstractIn this paper, the potential of multitemporal ERS-1/2 InSAR data for detecting urban land-cover changes is investigated on a test area within Shanghai city, China. A new unsupervised change-detection approach is proposed, which is characterized by the combined use of two temporal variations of backscattering intensity and long-term coherence from multitemporal ERS-1/2 SAR images. The proposed approach is made up of two steps: feature extraction and unsupervised 2-D (two dimensional) thresholding. In the first step, two features are based on the concepts of backscattering intensity variation and long-term coherence variation respectively, and have been defined according to the analysis of different signal behavior of interferometric SAR in the presence of land-cover classes in urban area. In the second step, an unsupervised 2-D thresholding technique based on maximum 2-D Renyi's entropy criterion is proposed, which is performed on the two difference images derived from the two change features to produce an accurate change-detection map with two classes "change" and "no-change". Experimental results obtained from a set of six multitemporal ERS-1/2 SAR images confirm the effective of the proposed approach, and that ERS-1/2 InSAR data could be exploited for detecting urban land-cover changes. © 2005 IEEE.
All Author(s) ListJiang L., Liao M., Lu L., Lin H.
Name of Conference2005 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2005
Start Date of Conference25/07/2005
End Date of Conference29/07/2005
Place of ConferenceSeoul
Country/Region of ConferenceSouth Korea
Year2005
Month12
Day1
Volume Number6
Pages4002 - 4005
ISBN0780390504
LanguagesEnglish-United Kingdom
KeywordsBackscattering intensity variation, Change detection, Interferometric SAR, Long-term coherence variation, Urban

Last updated on 2020-11-08 at 01:35