Video target data association method and device and storage medium

Abstract

The invention discloses a video target data association method and device and a storage medium. The data association method of the video target comprises the steps of obtaining a first image feature of a target object and a second image feature of an observation object; performing feature similarity calculation of N feature categories on the first image feature and the second image feature; screening the N groups of feature similarity results based on the feature similarity of the rough set, and fusing the screened results to obtain a feature fusion result; based on maximum entropy intuitionistic fuzzy clustering, performing correlation cost matrix calculation according to the feature fusion result to obtain a correlation cost matrix calculation result; judging whether the target object isassociated with the observation object or not according to an association cost matrix calculation result; if not, performing target track management on the target object, and counting a new startingtrack and a new ending track of the target object in the video to obtain the ending track set and the new track set; and performing fuzzy trajectory association according to the final trajectory set and the new trajectory set.

Description

technical field [0001] The present application relates to the field of electronic technology, and in particular to a data association method, device and storage medium of video objects. Background technique [0002] Video multi-target tracking is one of the important research contents of machine vision, which mainly obtains basic motion information such as position, attitude and trajectory of moving targets in video. With the development of digital computing technology, video multi-target tracking has opened up multiple research fields and application fields, involving intelligent video surveillance, virtual reality, human-computer interaction, automatic driving, traffic control, oceanography, intelligent robots, remote sensing , biomedicine and other fields have attracted more and more scholars and researchers to actively participate and achieved a large number of research results. However, in the environment of complex background and densely occluded targets, there are ma...

AI Technical Summary

Problems solved by technology

But based on generative association methods, they sometimes cannot distinguish the object from the background well, because the background pixels and other object pixels within the bounding box of the object are inevitably considered as part of the object, thus making the object appearance model Presence of inaccurate information that prevents it from correctly distinguishing between objects and backgrounds, resulting in possible tracking failures

Images