Mean-shift-clustering-based maneuvering object tracking algorithm of particle filtering

Abstract

The invention relates to a mean-shift-clustering-based maneuvering object tracking algorithm of particle filtering. With a feature space method of Mean shift, clustering of a particle set is calculated adaptively and thus the cluster of the particle set can be determined accurately and adaptively without initializing a clustering center and the clustering number; and a target is expressed precisely by the cluster. When target probability density estimation and similarity measurement is carried out, position information of a pixel point is described by using a kernel function; target probability estimation is carried out by combining the position information of the pixel point and spatial information; and a target template is described precisely, so that the target tracking precision is enhanced. When a particle filtering tracking result is determined, a certain weight value is assigned for a current tracking result probability model and the target template is updated so that the dynamic performance of the algorithm can be enhanced and the anti-interference capability of the tracking process can be improved.

Description

Technical field [0001] The invention relates to a tracking method of a space mobile target, in particular to a particle filter mobile target tracking algorithm based on Mean shift clustering. Background technique [0002] The document "Improved particle filter algorithm based on genetic algorithm, Journal of Shanghai Jiaotong University, 2011, Vol45(10), p1526-1530" proposes an improved particle filter target tracking algorithm based on genetic algorithm. This method aims at the particle degradation problem in the particle filter caused by the quantity and quality of particles, and uses genetic algorithm to optimize the initial particles to improve the quality of the initial particles. A large number of particles are obtained through sequential importance sampling (SIS), and then a small number of particles are optimized by genetic algorithm as the initial particles of particle filtering. The tracking algorithm can not only improve the quality of the initial particles, but also ...

AI Technical Summary

Problems solved by technology

The tracking algorithm described in the literature introduces the genetic algorithm into particle resampling to increase particle diversity; however, the optimization method is single, the particle diversity is small, and the accuracy of new particles is low, which will cause a sharp increase in the amount of calculation and low tracking speed, which does not meet the industrial requirements. real-time requirements

When the algorithm describes the target template, it does not comprehensively consider the influence of color information and spatial information on the template similarity, which affects the accuracy of the algorithm tracking results, and the target template only depends on the selection of the initial frame target. When the target deforms, etc. , the target template does not change accordingly, so the method is not dynamic and has weak anti-interference ability

Images