Multiple extended targets tracking in complex scenes has high application value in fields such as autonomous driving and target recognition.A cardinalized probability hypothesis density(CPHD)filter built on elliptic random hypersurface model(ER-HM)is presented in this paper.Firstly,based on the theory of finite set statistics,the Bayesian filtering framework of multiple ex-tended targets is established by using CPHD filter.Then,ERHM is used to describe the measurement source distribution of the ex-tended target,and unscented transform is used to embed the CPHD filtering process.Lastly,the simulation results show that the tracking performance of the proposed ERHM-CPHD filter is better than that of the traditional gamma Gaussian inverse Wishart CPHD(GGIW-CPHD)filter,and the parameter estimation of the extended targets is more accurate,when the clutter density is high and the position of newly generated targets is determined or the number of multiple extended targets is relatively large.The proposed method has good application prospects in using high-resolution radar for multi-target tracking.
关键词
多扩展目标跟踪/椭圆随机超曲面/势概率假设密度滤波器/无迹变换
Key words
multiple extended target tracking/elliptic random hypersurface model/cardinalized probability hypothesis density(CPHD)filter/unscented transform
维普
万方数据