基于联合概率数据互联的多假设跟踪算法  

Multiple hypothesis tracking algorithm based on joint probabilistic data association

作　　者：闫龙 王曙曜 黄磊 姚远 YAN Long;WANG Shu-yao;HUANG Lei;YAO Yuan(No.8 Research Academy of CSSC, Nanjing 211153)

机构地区：[1]中国船舶集团有限公司第八研究院,南京211153

出　　处：《雷达与对抗》2021年第1期23-28,共6页Radar & ECM

摘　　要：针对杂波环境下密集目标的跟踪,在多假设跟踪(MHT)算法框架的基础上将联合概率数据互联(JPDA)算法以联合概率分配的方式引入不相容航迹树间的假设分支生成处理,利用联合概率数据互联在点航迹互斥分配处理中的优势保证簇内不相容航迹树的互斥性。仿真测试和实装测试结果验证了算法的实时性、有效性和鲁棒性,提高了点航迹关联正确率及杂波环境中对密集目标的跟踪性能。Aiming at the tracking of dense targets in clutter environment,based on the framework of the multiple hypothesis tracking(MHT)algorithm,the joint probability allocation of the joint probabilistic data association(JPDA)algorithm is introduced into the hypothesis branch generation processing between incompatible track trees.The advantage of the JPDA in plot-track mutual exclusion allocation processing is utilized to ensure the mutual exclusion of incompatible track trees in the clutter.Simulation test and actual test results show that the algorithm is real-time,effective and robust,improving the accuracy of plot-track association and the tracking performance of dense targets in clutter environment.

关 键 词：杂波环境 密集目标 MHT JPDA 

分 类 号：TN957.52[电子电信—信号与信息处理]