摘要
针对杂波环境中多目标跟踪问题,引入了航迹似然度的概念,航迹似然度从概率的意义上给出了该航迹为实际目标航迹的可能性。在目标跟踪过程中,采用了将传统的航迹状态更新与提出的航迹似然度更新同时进行的方式,有效的解决了航迹分叉方法中由于系统维持的航迹数过多导致的系统资源不足的问题。航迹似然度的引入还避免了额外的航迹初始与航迹终止过程。通过合理选择及动态调整门限可以较好的满足跟踪实时性,仿真实例进一步验证了算法的有效性。
Aiming at the problem of multitarget tracking in clutter, the concept of degree of hkehhood for each track was introduced. The degree of likelihood denoted the possibility of a trajectory being the track of actual target in the sense of probability. In the process of target tracking, the degree of likelihood and the target state were updated in the same circle of filtering, which effectively solved the problem of the absence of system resources resulted from overmany tracks in method of track splitting. The proposed method also obviated the need for track initiation and track termination. Proper assignment and dynamic adjusting of threshold made the real-time tracking more effective. Finally a simulation example further verified the effectiveness of our method.
出处
《科学技术与工程》
北大核心
2014年第16期264-267,272,共5页
Science Technology and Engineering
基金
国家自然科学基金资助(61174024)
西京学院科研基金项目资助(XJ130108)资助
关键词
目标跟踪
航迹分叉
似然度
卡尔曼滤波
target tracking track splitting degree of likelihood Kalman filtering