SAR image change detection method based on quantum-inspired immune clone

Abstract

The invention discloses an SAR image change detection method based on quantum-inspired immune clone, which mainly solves the problems of long time consumption, easy falling into local optimal solution, and inaccurate positioning of complex image borders in the prior optimizing method. The method comprises the following steps: (1) filtering the two time-phase to-be-changed detection images, and calculating the logarithmic ratio difference striograph; (2) setting the population size, class number k and halt conditions, and randomly generating a quantum antibody Q(t) as the initial clustering center; (3) observing Q(t) into a binary antibody p(t), calculating the affinity fk of each antibody, and reserving the optimal antibody qbest of Q(t); (4) carrying out mutation operation on Q(t) to obtain Qm(t); (5) recombining Qm(t) to obtain Qc(t); (6) observing Qc(t) into a binary antibody pc(t), and calculating the affinity fc of each antibody; (7) selectively operating pc(t) to obtain the filial generation antibodies; and (8) if the filial generation antibodies satisfy the halt conditions, dividing the image class corresponding to the antibody with the highest affinity in the filial generation antibodies as the output result. The invention has the advantages of high change detection precision and accurate border positioning, and can be used for detecting changes of complex images.

Description

technical field [0001] The invention belongs to the field of image processing, in particular to a division and clustering technology, which can be used for the detection of multi-temporal SAR image change regions. Background technique [0002] With the development of satellite remote sensing technology, remote sensing data has increased rapidly. The SAR data has become an important remote sensing data because it is not affected by the atmospheric environment and cloud cover. It is of great significance how to accurately and quickly find out the region of significant change from SAR images of different time phases automatically. [0003] The research on finding the two categories of "non-change" and "change" in SAR images is still in the preliminary stage. There are roughly two routes. One route is the post-classification comparison method, also known as the post-classification comparison method. The time-phase images are independently classified, and then the two classifie...

AI Technical Summary

Problems solved by technology

However, the existing optimization methods often take a long time to deal with optimization problems, and are easy to fall into local optimum during the search process. At the same time, for the change detection problem of complex images, there are often shortcomings of inaccurate edge positioning. Affects the performance of area consistency and edge preservation of image change detection

Images