航空学报 > 2022, Vol. 43 Issue (5): 325250-325250   doi: 10.7527/S1000-6893.2021.25250

在线学习的循环自适应机动目标跟踪算法

熊伟, 朱洪峰, 崔亚奇   

  1. 海军航空大学 信息融合研究所, 烟台 264001
  • 收稿日期:2021-01-11 修回日期:2021-02-22 发布日期:2021-03-26
  • 通讯作者: 朱洪峰 E-mail:1181630959@qq.com
  • 基金资助:
    国家自然科学基金(61790554);国家自然科学基金青年科学基金(62001499)

Recurrent adaptive maneuvering target tracking algorithm based on online learning

XIONG Wei, ZHU Hongfeng, CUI Yaqi   

  1. Institute of Information Fusion, Naval Aviation University, Yantai 264001, China
  • Received:2021-01-11 Revised:2021-02-22 Published:2021-03-26
  • Supported by:
    National Natural Science Foundation of China (61790554); Youth Program of National Natural Science Foundation of China (62001499)

摘要: 针对机动目标难以精确跟踪的问题,提出了一种可在线学习的循环Kalman神经网络跟踪算法。考虑到状态转移矩阵、量测噪声和过程噪声矩阵在机动目标跟踪中难以实时、离线估计,且在实际应用中对应数据集获取成本高,因此使用在线学习的神经网络对其进行实时估计。由于Kalman滤波算法本身是一种循环结构,将简单的全连接层网络与其嵌合,全连接层网络实时输出状态转移矩阵、量测和过程噪声矩阵估计,构成一种广义的循环Kalman神经网络,根据网络最终输出的位置估计进行端到端的在线学习,并且通过理论推导证明了其在线学习的可行性。将提出的循环Kalman神经网络同3种经典机动目标算法进行了仿真对比,结果表明:循环Kalman神经网络跟踪需要很少的先验信息,在最优区域内较之其他3种算法具有最高的跟踪精度和鲁棒性,并且具有效率高、训练成本低以及可扩展性强的特点。

关键词: 机动目标跟踪, 循环神经网络, Kalman滤波, 在线学习, 端到端

Abstract: To overcome the problem of difficulty in accurate tracking of maneuvering targets, a recurrent Kalman neural network tracking algorithm that can be learned online is proposed. Considering that the state transition matrix, measurement noise and process noise matrix are difficult to estimate in real time and offline in maneuvering target tracking, and the cost for acquisition of corresponding data set is high in practical applications, the neural network of online learning is used to estimate them in real time. Since the Kalman filter algorithm itself is a cyclic structure, a simple fully connected layer network is integrated with it. The fully connected layer network outputs the state transition matrix, and measurement and process noise matrix estimation in real time, forming a generalized cyclic Kalman neural network. The end-to-end online learning is carried out according to the position estimation finally output by the network, and the feasibility of the online learning is proved through theoretical deduction. The simulation results show that the proposed recurrent Kalman neural network needs very little prior information, and has the highest tracking accuracy and robustness in the optimal region in comparison with three classical algorithms, demonstrating the characteristics of high efficiency, low training cost and strong scalability.

Key words: maneuvering target tracking, recurrent neural network, Kalman filter, online learning, end-to-end

中图分类号: