Multi-target tracking method based on dynamic group division

Abstract

The invention relates to a multi-target tracking method based on dynamic group division, which comprises the steps as follows: S1, for a certain time in a video scene, whether a target enters or leaves a scene area or not is judged firstly and a target set is updated according to a detection result; S2, a grouping threshold of the target set is set and hierarchical clustering is used to cluster the target set at last time by distances, and then a target position at last time is divided into different groups according to a clustering result at last time; S3, each group in the target set is provided with a tracker; the trackers use a Bayesian framework to deduce the optimal value of each target at a current time position according to the position state of each target at last time and the observation value of each target on an image at the current time in the groups; and the optimal value of each target at the current time position is used for updating the position state of each target in the target set so as to prepare deducing the position of each target at next time.

Description

technical field [0001] The invention relates to the field of computer vision, in particular to a multi-target detection and tracking in the field of intelligent video analysis. Background technique [0002] With the development of basic science such as visual computing theory and the increasing demand for machine vision in various applications, computer vision has been more widely used. Computer intelligent video surveillance is an emerging application direction and a frontier subject that has attracted much attention in the field of computer vision. It mainly uses computer vision technology to process, analyze and understand video signals, and to control the video surveillance system, so that the video surveillance system has human-like intelligence. The main goal of the intelligent video surveillance system is to reduce the dependence on manual labor, and automatically complete the real-time detection of interested targets such as people and vehicles in complex environmen...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to solve the problem of using multiple independent single target trackers to track multiple apparently similar targets in the prior art. When the targets are relatively close, target merging errors occur; and use a single target tracker in the joint state space For multi-target trackers, due to the high dimensionality of the joint state space, the technical defect of greatly increasing the complexity of calculations

Images