基于灰关联的分类信息辅助多目标跟踪

Classification-Aided Tracking Multiple Targets Based On Gray Correlation Analysis

密集多回波环境下对弹道多目标跟踪时,通过灰关联方法融合了目标运动状态空间似然值和HRRP特征分类信息,提出了分类信息辅助多目标跟踪的CAT算法;结合目标电磁仿真数据,建立了多目标跟踪和识别交互仿真场景,并与JPDA和NN跟踪算法进行比较,仿真结果表明,CAT克服了轨迹合并和误跟的现象,较好的实现了多目标跟踪。

Tracking ballistic muhi-targets in densely multi-return environment,HRRP classification and state-sapce feature of targets is fused through their gray correlation coefficients. A novel CAT （ Classification-Aided Tracking） algorithm is investigated. With electromagnetic simulation data of targets, a simulative scene of combining tracking and classification is constituted. By comparing with conditional JPDA and NN algorithm, the result shows that the CAT algorithm overcomes the phenomena of track-coalition and errortrack, and has nice performance of tracking multiple targets.