SAR (synthetic aperture radar) image change detection method combining multi-threshold segmentation with fuzzy clustering

Abstract

The invention discloses an SAR (synthetic aperture radar) image change detection method combining multi-threshold segmentation with fuzzy clustering. The method mainly aims at overcoming the defect of existing fuzzy clustering algorithms and is used for SAR image change detection by combining multi-threshold segmentation with fuzzy clustering. The implementation steps of the method include: (1), subjecting two SAR images to median filtering; (2), calculating to obtain a logarithmic ratio differential image after normalization; (3), adopting the Otsu method based on standard particle swarm optimization to perform multi-threshold segmentation to the logarithmic ratio differential image after normalization; (4), initializing membership matrixes U0 and U1; (5), adopting the FLICM (fuzzy local information C-means) algorithm to perform fuzzy clustering to pixels which cannot be determined whether changes occur or not after multi-threshold segmentation; (6), deblurring; and (7), outputting change detection results. The multi-threshold segmentation and fuzzy clustering are combined for SAR image change detection, so that change detection time is reduced, and change detection accuracy is improved.

Description

technical field [0001] The invention belongs to the technical field of computers, and further relates to a SAR image change detection method combined with multi-threshold segmentation and fuzzy clustering in the technical field of image processing. The invention obtains difference images from two SAR images of different time phases, and then performs multi-threshold segmentation and fuzzy clustering on the difference images to realize SAR image change detection, which can be used for ground object coverage and utilization, natural disaster monitoring and evaluation, and urban planning , map update and other fields. Background technique [0002] Synthetic Aperture Radar (SAR) technology has been applied more and more widely in recent years. Compared with ordinary optical remote sensing images, SAR images can be acquired all-weather, and with the continuous improvement of SAR image resolution, more and more image processing technologies based on it. Image change detection te...

AI Technical Summary

Problems solved by technology

However, since FCM does not consider the spatial information of samples, it is sensitive to noise, which affects the effect of clustering.

Fuzzy Local Information C-Means (FLICM) algorithm is a relatively new clustering algorithm, which improves the shortcoming of FCM which is sensitive to noise, and introduces the number of samples in the clustering objective function. Local spatial information achieves a better clustering effect than FCM, but because the calculation of neighborhood information is added to all samples, compared with F...

Images