New Multiple-Target Tracking Strategy Using Domain Knowledge and Optimization
New Multiple-Target Tracking Strategy Using Domain Knowledge and Optimization
复制标题
DOI：
10.1109/tsmc.2016.2615188
复制
发表时间：
2017-04-01
影响因子：
8.7
通讯作者：
Chen, Wen-Hua
中科院分区：
文献类型：
--
作者：
Ding, Runxiao;Yu, Miao;Chen, Wen-Hua
为了充分利用领域知识，提出了一种考虑动态模型的噪声控制输入与环境之间相互作用的环境相关车辆动态建模方法。在此基础上，提出了一种用于地面运动目标跟踪的领域知识辅助运动视界估计方法。该方法在评估过程中考虑了环境物理约束和目标与环境的交互行为，并将不同类型的领域知识纳入评估过程。此外，为了解决混乱环境下多目标跟踪的数据关联模糊问题，将DMHE与多假设跟踪结构相结合。数值仿真结果表明，该方法及其扩展比传统的不利用领域知识或仅利用简单物理约束信息的跟踪方法具有更好的跟踪性能。
This paper proposes an environment-dependent vehicle dynamic modeling approach considering interactions between the noisy control input of a dynamic model and the environment in order to make best use of domain knowledge. Based on this modeling, a new domain knowledge-aided moving horizon estimation (DMHE) method is proposed for ground moving target tracking. The proposed method incorporates different types of domain knowledge in the estimation process considering both environmental physical constraints and interaction behaviors between targets and the environment. Furthermore, in order to deal with a data association ambiguity problem of multiple-target tracking in a cluttered environment, the DMHE is combined with a multiple-hypothesis tracking structure. Numerical simulation results show that the proposed DMHE-based method and its extension could achieve better performance than traditional tracking methods which utilize no domain knowledge or simple physical constraint information only.