Multi-target tracking system in dynamic video sequence

Abstract

The invention relates to a multi-target tracking system in a dynamic video sequence, belonging to the technical field of image processing. The multi-target tracking system comprises an input module, a moving target detection module, a PHD (Probability Hypothesis Density) filter module and an output module, wherein the moving target detection module comprises a background area initialization submodule, a background area updating submodule, a foreground image extraction submodule, a morphology processing submodule and a connected domain analysis submodule; and the PHD filter module comprises a Gauss element parameter prediction submodule, a Gauss element updating submodule, a Gauss element trimming submodule and a state extraction submodule. The invention provides more reliable measurement information for the video tracking system through the improved moving target detection module, solves the problems of possible complex computation of particle filters and probability hypothesis density filters and unreliable state extraction under the condition that targets are crossed, ensures the effectiveness and the reliability of the video tracking system, avoids the data association computation and is widely used in various fields of multi-target video monitoring.

Description

technical field [0001] The invention relates to a system in the technical field of image processing, in particular to a multi-target tracking system in a dynamic video sequence based on Gaussian Mixture Probability Hypothesis Density (GM-PHD) filtering. Background technique [0002] Video target tracking is the core technology of video surveillance technology, widely used in all-weather, automatic, real-time monitoring of scenes, visual traffic control, sports video analysis, medical auxiliary diagnosis and other fields. The so-called video target tracking refers to the detection, extraction, identification and tracking of the moving target in the video image sequence, and obtains the motion parameters of the moving target, such as the position of the target center of mass, velocity, acceleration, etc., as well as the trajectory for further processing and tracking. Analysis, enabling behavioral understanding of motor targets for higher level tasks. [0003] The difficulty o...

AI Technical Summary

Problems solved by technology

The present invention uses GM-PHD to realize PHD filter recursion in the video multi-target system, uses the improved moving target detection result as the input of the GM-PHD filter, realizes video multi-target tracking under the framework of probability hypothesis density filtering, and solves the problem of The multi-target video tracking problem with changing target numbers in dynamic and complex scenes has the advantages of simplified calculation, good real-time performance and strong robustness

Images