A Moving Target Tracking Method Based on Particle Filter and Mean-shift

2019 2nd International Conference on Advanced Materials, Intelligent Manufacturing and Automation

Hong, Yu^1

School of Mathematics and Computer, Yuzhang Normal University, Nanchang, JiangXi Province

330103, China^1

关键词: Hybrid tracking;    K-means;    Mean shift;    Moving target tracking;    Multiple hypothesis;    Particle filter;    Tracking method;    Tracking speed;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/569/3/032015/pdf
DOI  :  10.1088/1757-899X/569/3/032015

来源: IOP

【 摘 要 】

Due to the limitation of using a single algorithm Mean-shift or particle filter, the deterministic tracker Mean-shift is introduced into the framework of particle filter, and a new hybrid tracking method based on particle filter and Mean-shift is proposed. The tracking method first uses Dynamic K-Means Soft Clustering algorithm to cluster multiple hypotheses, and then carries out Mean-shift deterministic search for the centers of clusters. The tracking experiments show that the proposed method can perform well when the target changes, rotates and scales, and achieves a satisfactory tracking speed.