Detection for Flood Change with SAR Images Based on Fusion and T-Distribution

Based on fusion and T-distribution model, a new approach for detecting flood changes with multi-temporal SAR images is presented. Firstly, by incorporating the advantages of image differencing and log-ratio operator, a novel fusion strategy based on experience is introduced. Then, the final difference image with better effect in vision can be obtained by fusing with difference image and log-ratio image. According to the histogram of the final difference image obtained by fusion strategy, the two ranges of absolute changed and absolute unchanged classes in the histogram can be got, respectively. Then the fuzzy range between the two ranges is obtained, which are unable to identify changed or unchanged classes. Under the T-distribution assumption of the fuzzy range in the histogram, a thresholding approach based on the Kittler-Illingworth (KI) threshold selection criterion (TM_KI) is proposed. Finally, the change-detection map is produced by using the proposed thresholding procedure to the fusing difference image. Through experimental comparisons, analysis of results confirm the proposed method not only can reduce the affection by speckle noise and enhance the subtle changed areas brought by flooding, but also effectively detect small changed areas, so that this method can improve the performance of change detection.