Image deduplication method and system

Abstract

The invention discloses an image duplication removal method and system, and relates to the technical field of video monitoring. The method comprises the following steps: extracting a target area of each frame of original image in a video image through a target detection algorithm to obtain a target image; calculating a hash value of each frame of target image; taking the ith frame of target imageas a first comparison image; taking the (i+W)th frame of target image as a second comparison image; respectively calculating gradient values of the first comparison image and the second comparison image; judging whether the first comparison image and the second comparison image are repeated or not through the hash value, and if yes, storing the target image with the large gradient value and the original image corresponding to the target image with the large gradient value. According to the method, target detection and image deduplication are combined, the key target area in the original imageis determined through target detection, deduplication and image definition judgment are only carried out on the key target area, the calculation amount of deduplication judgment and image definition calculation is reduced, and meanwhile the definition calculation error in the target movement process is eliminated.

Description

technical field [0001] The invention relates to the technical field of video monitoring, in particular to an image deduplication method and system. Background technique [0002] In security or daily video intelligent monitoring, it is often necessary to extract the monitored key targets and upload them to the background server. However, since the video is continuous, there will be a large number of repeated image uploads within a period of time, resulting in storage space and waste of network bandwidth. At present, the conventional image deduplication method generally calculates the Hash value of the entire image, and compares the Hamming distance between the Hash values ​​of each image. When the Hamming distance is less than the set threshold, it is judged that the two images are the same or Similar to delete redundant images. When performing similarity comparison, in some scenes, the key object does not change, but the background changes, the existing image deduplication...

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to provide a method and system for image deduplication, which solves the problem of repeated uploads in existing image deduplication methods

Images