Adaptive polarimetric SAR image superpixel segmentation method and system

Abstract

The invention discloses an adaptive polarimetric SAR image superpixel segmentation method and system, and the method comprises the steps of taking a polarimetric SAR image segmentation problem as a multi-objective optimization problem, and taking a fuzzy clustering energy function and a fuzzy clustering performance function as two objective functions which need to be minimized in the optimization problem; using a multi-objective evolutionary algorithm for solving, and in order to adaptively determine the number of superpixels, a special individual coding mode is designed, wherein the center of each superpixel is controlled by a corresponding activation index. On the optimization strategy, a special mutation operator is designed for the activation index, and the optimization speed of the algorithm is increased. The verification of the super-pixel classification effect is carried out on the two data sets, the segmentation indexes on the image super-pixel segmentation are superior to those of the two existing methods, and the classification indexes on the image classification are superior to those of the two existing methods. The invention has universality for different data sets, and the effect of the method is better than that of an existing method.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a superpixel segmentation method and system for an adaptive polarimetric SAR image. Background technique [0002] Polarimetric Synthetic Aperture Radar (Polarimetric Synthetic Aperture Radar) has now become one of the most cutting-edge technologies for earth observation imaging in the international remote sensing community, and polarimetric SAR (PolSAR) image segmentation processing has become an important part of remote sensing technology applications. Polarization SAR measures the target with full polarization, which can obtain more information about the target than single-polarization SAR. It is precisely because of the advantages of polarimetric SAR that it has attracted more and more attention from different countries and institutions in earth observation and remote sensing, which has promoted the research and development of polarimetric SAR image techno...

AI Technical Summary

Problems solved by technology

The disadvantage of these two algorithms is that the time cost is very high, and the number of superpixels cannot be controlled

This algorithm has high computational efficiency, but the algorithm has a strict limit on the number of superpixels, and the shape of the generated superpixels is also very irregular.

These methods all have the problem of poor boundary fitting, resulting in that the boundary of the segmented superpixel and the boundary of the real object in the image cannot be well coincided.

Images