Method and system for reconstructing high-resolution image from fuzzy monitoring video

Abstract

The embodiment of the invention relates to the technical field of video processing, and particularly discloses a method and system for reconstructing a high-resolution image from a fuzzy monitoring video. According to the embodiment of the invention, a fuzzy monitoring video is obtained, and a plurality of fuzzy background pictures and a plurality of fuzzy target pictures are generated according to the fuzzy monitoring video; performing image enhancement, image restoration and super-resolution reconstruction on the plurality of fuzzy background pictures to generate a high-resolution background picture; performing image enhancement, image restoration and super-resolution reconstruction on the plurality of blurred target pictures to generate a high-resolution target picture; and performing fusion processing on the high-resolution background picture and the high-resolution target picture to generate a high-resolution monitoring image. According to the method, the background picture and the target picture in the fuzzy monitoring video can be extracted and subjected to high-resolution reconstruction, the high-resolution background picture and the high-resolution target picture are obtained and fused to generate the high-resolution monitoring image, and the details of the background and the target can be effectively prevented from being omitted.

Description

technical field [0001] The invention belongs to the technical field of video processing, in particular to a method and system for reconstructing high-resolution images from fuzzy surveillance videos. Background technique [0002] At present, in the fields of remote sensing imaging, medical diagnosis and public security, it is necessary to obtain more detailed information through high-resolution images, but due to the resolution limitation of image acquisition equipment, the clarity of digital images will be affected. A solution to the problem is to reconstruct a high-resolution image through fuzzy surveillance video to improve the clarity of the image. The existing methods for reconstructing high-resolution images from fuzzy surveillance videos are mainly to select the optimal image from the blurred surveillance video, and to process the optimal image through professional image processing software to generate high-resolution images. This method of reconstructing high-resolu...

AI Technical Summary

Problems solved by technology

The existing methods for reconstructing high-resolution images from fuzzy surveillance videos are mainly to select the optimal image from the blurred surveillance video, and to process the optimal image through professional image processing software to generate high-resolution images. This method of reconstructing high-resolution images usually tends to cause the details in the surveillance video to be missed, and it is impossible to obtain more details of the surveillance target in the surveillance video

Images