使用交互多模型算法的高速高机动目标跟踪

Tracking of High Speed and High Maneuvering Target Based on IMM Algorithm

对机动目标进行跟踪一直是甚具挑战性的问题,特别是跟踪高速高机动目标在理论上和实践上都有较高的技术难度。现有各种算法在这个问题上均有各自的缺点和不足。该文在现有的运动机动模型和IMM算法的基础上,提出了使用多种机动模型交互的IMM算法进行高速高机动目标跟踪。不同机动模型之间的互补使这种算法克服了使用单一模型的一些问题。使用“当前”统计模型、二级滤波模型和CV模型进行交互是一种可行的高速高机动目标跟踪方案。为验证算法的有效性,进行了Monte Carlo仿真。仿真结果表明,该算法在性能和计算复杂度之间取得了较好的平衡,有很好的可实现性。

It is a challengeable problem to track maneuvering targets, especially tracking the high speed and high maneuvering targets, which has both theoretically and practically technical difficulties. The existing algorithms have shortcomings when applied in this problem. Based on the existing maneuvering models and the IMM algorithm, this paper proposes a kind of IMM algorithm which uses many kinds of maneuvering models for the high speed and high maneuvering target tracking. Because of mutual supplement among different models, this algorithm overcomes some problems in using the single model. This algorithm is thought to be a feasible method for tracking high speed and high maneuvering targets which uses the ＂current＂ statistical model, the two-stage filter model and the CV model to interact. In order to verify the validity of this algorithm, Monte Carlo simulation is performed. The results indicate that this algorithm achieves better balance between the performance and computation complexity, and is very practicable.