Multi-view SAR image segmentation method and device

Abstract

The invention provides a multi-view SAR image segmentation method and device. The method comprises: reading a to-be-segmented multi-view SAR image; initializing a double-weight w; repeating the steps of calculating a Gamma distribution scale parameter beta, calculating a probability p(z|w) of the image, calculating a distribution function p(w) of the double-weight w, calculating a quality function L, updating the double-weight w according to a gradient method, substituting the updated double-weight w into the quality function L, and stopping executing the above steps until |L(t + 1) - L(t)| is less than a preset threshold epsilon, and then determining the category of each pixel in the above image according to the current double-weight w; and outputting a segmentation result according to the category of each pixel. The method has good anti-noise performance in image segmentation, the segmentation result has less mis-classification, and fitting of the segmentation boundaries is accurate.

Description

technical field [0001] The present invention relates to the technical field of image segmentation, in particular to a multi-view SAR image segmentation method and device. Background technique [0002] Synthetic Aperture Radar (SAR) is a high-resolution imaging radar that records the shape of ground objects by receiving the electromagnetic waves scattered by the target and converting them into images. The inherent speckle noise caused by its unique imaging mechanism gives the image segmentation a Great difficulty came. Although multi-look technology can reduce part of the noise, there are still a lot of speckle noise in multi-look SAR images in practical applications. Therefore, the anti-noise and accuracy of multi-look SAR image segmentation methods have always been a hot research issue. [0003] At present, the methods of multi-view SAR image segmentation mainly include: threshold method, boundary method, clustering method and statistical model method. Among them, the mos...

AI Technical Summary

Problems solved by technology

The most commonly used mixture model is the Gaussian Mixture Model (Gaussian Mixture Model, GMM), which assumes that the gray value of the pixel in the image obeys the Gaussian distribution. However, the weight coefficient in the traditional GMM is represented by a vector and only related to clustering. Single weight, and the SAR image obeys the Gamma distribution, the above problems will cause the traditional GMM to model the SAR image inaccurately

[0004] Aiming at the problems of poor anti-noise performance and unsatisfactory segmentation results of the multi-view SAR image segmentation method mentioned above, no effective solution has been proposed so far.

Images