Method and system for tracking multiple targets in a monitoring scene

Abstract

The invention discloses a multi-target tracking method and system in a monitoring scene, based on multi-hypothesis tracking after pruning optimization, the method includes the following steps: receiving a target detection frame of a current frame; based on the target detection frame of the current frame, Generate hypotheses for the possible positions of each target; based on all the hypotheses of the most recent frames, solve the maximum independent subset sum problem, obtain non-conflicting hypothetical paths that each target can choose, and output each frame before the multiple frames. position of each target; combine the solution of the maximum independent subset sum problem and the Hungarian algorithm to perform pruning and optimization to obtain multi-target tracking results. The present invention proposes a new method for optimizing pruning, which greatly reduces the complexity of the multi-hypothesis tracking algorithm. For multi-target tracking in monitoring scenarios, it can make full use of CPU resources without occupying GPU resources to track multi-targets in real time; and by changing the length of time to integrate information, the balance of algorithm complexity and accuracy can be adjusted.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a real-time tracking method and system for multiple targets in a monitoring scene. Background technique [0002] In the process of intelligent analysis of surveillance video, the usual process is to extract the detection frame of the target, and give each target its own unique identification code through the multi-target tracking method to distinguish different targets. Multi-target tracking method is a very classic problem in the field of computer research. Usually the algorithm converts the tracking problem into a graphical model for solution. However, it is usually difficult to flexibly adjust the balance between the accuracy and speed of the algorithm. Most of the improvements in multi-object tracking methods in recent years are based on deep learning-based feature extraction methods. By introducing a deep feature extraction network into the multi-target tracking method,...

AI Technical Summary

Problems solved by technology

However, in the original multi-hypothesis tracking algorithm, although the maximum independent subset sum algorithm (MWIS) will prune the hypothesis tree, the number of hypotheses for each target will still multiply geometrically over time before reaching the pruning time point. growth, it is difficult to make judgments based on long-term hypothetical information

Images