空军工程大学信息与导航学院,陕西,西安,710077
网络出版:2018-07-25,
纸质出版:2018
移动端阅览
樊鹏飞, 李鸿艳. 基于GIW-PHD的扩展目标联合跟踪与分类算法[J]. 电子学报, 2018,46(7):1562-1570.
FAN Peng-fei, LI Hong-yan. Joint Tracking and Classification of Extended Object Based on the GIW-PHD Filter[J]. Acta Electronica Sinica, 2018, 46(7): 1562-1570.
樊鹏飞, 李鸿艳. 基于GIW-PHD的扩展目标联合跟踪与分类算法[J]. 电子学报, 2018,46(7):1562-1570. DOI: 10.3969/j.issn.0372-2112.2018.07.004.
FAN Peng-fei, LI Hong-yan. Joint Tracking and Classification of Extended Object Based on the GIW-PHD Filter[J]. Acta Electronica Sinica, 2018, 46(7): 1562-1570. DOI: 10.3969/j.issn.0372-2112.2018.07.004.
在使用估计器对扩展目标进行跟踪时,算法的精度会受到系统演化模型选择的影响.针对该问题,本文提出将扩展目标的形态信息直接作为目标的类别信息,每一类别确定了目标相关的运动模型,在多模型(Multiple Model,MM)高斯逆威沙特概率假设密度(Gaussian Inverse Wishart PHD,GIW-PHD)滤波器的基础上,实现对扩展目标的联合跟踪与分类.仿真实验通过比较所提算法与GIW-PHD、MM-GIW-PHD两种滤波方法的性能,验证了本文所提算法的有效性.
When using the estimator for the extended object tracking
the algorithm accuracy is affected by the choice of the system evolution model.In this paper
we propose to take the extension information directly as the class-based information of the extended object
where each class determines the relevant motion models.Then we propose a joint tracking and classification algorithm based on the Multiple Model (MM) Gaussian Inverse Wishart Probability Hypothesis Density (GIW-PHD) filter.Simulation results demonstrated the efficiency of the proposed algorithm
compared with the performance of the GIW-PHD and MM-GIW-PHD filtering methods.
0
浏览量
217
下载量
4
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621