Number time-varying multi-target tracking method based on Gaussian mixture probability hypothesis density

Abstract

The invention discloses a number time-varying multi-target tracking method based on Gaussian mixture probability hypothesis density. The number time-varying multi-target tracking method comprises thefollowing steps: adding an identity identifier, historical state extraction mark information and a historical weight vector as auxiliary parameters to construct a new Gaussian component expression forexpressing a target; initializing a target posterior component set according to the new Gaussian component expression; calculating a prediction component set of the target according to the componentset of a new target and the prediction component set of a survival target; calculating the target posterior component set based on the measurement set and the prediction component set of the target; transforming the obtained target posterior component set, and reducing the transformed target posterior component set; extracting state estimation of the target; if the target is tracked for one moment, ending target tracking; and if a plurality of moments are tracked, repeatedly iterating all the moments. The method has high tracking performance and robustness, and can meet actual engineering requirements.

Description

technical field [0001] The invention belongs to the technical field of intelligent information processing, and in particular relates to a time-varying multi-target tracking method based on Gaussian mixture probability assumption density, which can be used in aviation and ground traffic control, road planning and obstacle avoidance of mobile robots, unmanned aerial vehicles and other systems target detection and tracking. Background technique [0002] In recent years, the Probability hypothesis density (PHD) filter based on finite set statistics theory has greatly reduced the computational complexity because it does not require complex data association process, which has attracted extensive attention from scholars in the field of multi-target tracking. [0003] The PHD filter is an approximation method of the multi-objective Bayesian filter. What it transmits at each moment is not the complete posterior density of the target, but the probability hypothesis density of the targ...

AI Technical Summary

Problems solved by technology

[0018] Aiming at the problem that the GM-PHD filter has low filtering precision and high calculation cost, the present invention proposes a time-varying multi-target tracking method based on Gaussian mixture probability hypothesis density, which solves the problem of tracking targets in a low detection probability environment. Multi-target Tracking Problem with Varying Numbers

Images