期刊名称：ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
印刷版ISSN：2194-9042
电子版ISSN：2194-9050
出版年度：2009
卷号：XXXVIII-4/W10
出版社：Copernicus Publications
摘要：The objective of this research is to perform automatic change detection within urban areas using multitemporal spaceborne SAR data in Shanghai. Two scenes of ENVISAT ASAR C-VV images were acquired in September, 2008 and one scene of ERS-2 SAR C-VV image was acquired in September, 1999. A generalized version of Kittler Illingworth minimum-error thresholding algorithm, that takes into account the non-Gaussianity of SAR images, was tested to automatically classify the SAR ratio image into two classes, change and no change. Two types of comparison operators were performed. First, the conventional ratio image was calculated in a way that only increases in backscatter coefficient are detected. Second, a modified ratio operator that takes into accounts both positive and negative changes was also examined. Various probability density functions such as, Log normal, Generalized Gaussian, Nakagami ratio, and Weibull ratio were tested to model the distribution of the change and no change classes. An iterative refinement of the Log normal model is also applied to improve the resolution of the change map. The preliminary results showed that this unsupervised change detection algorithm is very effective in detecting temporal changes in urban areas using SAR images. The best change detection result was obtained using Log normal model with modified ratio operator at 81.5%, which is over 10% high than that of the other three models tested. The initial findings indicated that change detection accuracy varies depending on how the assumed conditional class density function fits the histograms of change and no change classes
关键词：Change detection; SAR; Minimum-error thresholding; Ratio image; Modified ratio; Urban area
