Target joining algorithm based on multi-feature fusion match

Abstract

A target joining method based on multi-feature fusion match belongs to the technical field of multi-camera video monitoring, which is implemented as the following steps: firstly fusing a form feature of a target and a statistical feature of a color, calculating preliminary match similarity between a target to be joined in the exisitng camera view and a target to be matched in the adjacent camera view, thereby carrying out the preliminary match; counting the amount of the targets to be matched after the preliminary match, if the amount is less than one, determining the target to be joined as a new target, and if not, carrying out secondary match on the target to be joined and the target to be matched, namely, extracting a space distribution feature of the color according to an edge feature of the target, dividing the target into color blocks, fusing the average color feature and location feature of the color blocks, and calculating secondary match similarity between the targets through a secondary match matrix, thus judging whether the two targets is matched. In the invention, the difficulty that the target feature changes along with the changes of time and place can be resolved efficiently through the multi-feature fusion match, and meanwhile the accuracy of the target joining can be improved.

Description

technical field [0001] The invention belongs to the technical field of multi-camera video monitoring. Background technique [0002] Video surveillance technology uses computer vision and image processing methods to detect moving objects, classify objects, track objects, and analyze object behavior in surveillance scenes. Because of its good application prospects, it has attracted attention in many countries. highly valued. However, in most practical scenes, when detecting and tracking moving objects in a single-camera environment, how to overcome the interference of light changes and shadows in the surrounding scene, how to correctly track occluded moving objects, how to multi-angle, long-term, Large-scale target tracking has always been a difficult research point. Therefore, object tracking in a multi-camera environment has received much attention in wide-area surveillance scenarios. [0003] In the multi-camera target tracking system, the main difficulty is how to estab...

AI Technical Summary

Problems solved by technology

However, since the human body is a non-rigid body, the features are easy to change with time and place, which brings a fatal blow to the target handover algorithm based on feature matching; moreover, different cameras may have different internal parameters and photometric performance, It will also affect the accuracy of feature matching; the traditional target handover algorithm based on feature matching only uses the statistical characteristics of the target color, ignoring the spatial distribution characteristics of the target color, and the spatial distribution characteristics of the target color are very important to the target. a kind of information

Images