Remote sensing image change detection method and device and electronic equipment

Abstract

The invention discloses a remote sensing image change detection method and device and electronic equipment, and the method comprises the steps: obtaining a first remote sensing image and a second remote sensing image, determining an entropy difference image and a mean value difference image of the first remote sensing image and the second remote sensing image, determining a gray difference image of the first remote sensing image and the second remote sensing image, weighting the entropy difference image and the mean difference image according to the gray difference image to obtain a feature fusion difference image; segmenting the feature fusion difference image according to a preset threshold to obtain change detection results of the first remote sensing image and the second remote sensing image, thereby effectively combining gray features and texture features of the first remote sensing image and the second remote sensing image, overcoming adverse effects of speckle noise in the remote sensing images on the detection results, solving the problem that a change region with an unobvious feature cannot be distinguished from a background region during detection based on a single texture feature, so that the change detection precision of the dual-temporal remote sensing image is improved.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a method, device and electronic equipment for detecting changes in remote sensing images. Background technique [0002] In recent years, with the rapid development of aerospace technology, sensor technology, new remote sensing platforms and other related disciplines, synthetic aperture radar (Synthetic Aperture Radar, SAR for short) has achieved all-day, all-weather and large-scale coverage of most areas of the world. Continuous dynamic observation and repeated observation of remote sensing data record the change information of the coverage area, making it possible to detect changes based on SAR images. [0003] Due to the inherent speckle noise problem in SAR images, change detection based on SAR images is more difficult to process than optical remote sensing images. At present, in the related art, a difference image is obtained by combining the neighborhoo...

AI Technical Summary

Problems solved by technology

The above method only has good detection results for two SAR images with a large difference in the degree of phase information confusion. When the chaos of the front and rear phase information of the two temporal SAR images is relatively similar, it is easy to miss the detection of the changed area; Moreover, this method cannot overcome the adverse effects of coherent speckle noise

Images