摘要
毫米波雷达在进行静态目标识别时存在目标丢失和信息缺失、识别效果较差的问题。采用一种基于机器学习算法的方法来实现静态物体识别与跟踪。选取雷达检测目标的相对速度和相对距离作为观测量,使用高斯隐马尔科夫模型学习毫米波雷达检测结果的标签数据,获取目标相对距离、相对速度和目标状态之间的非线性关系。结合高斯聚类方法与毫米波雷达数据实现对目标标签结果的预测,通过前向后向算法实现目标跟踪。结果表明,使用的模型能够在受试车车速达到30 m/s时,对140 m远处的静态目标实现良好的识别、预测和跟踪效果。
Millimeter-wave radar has the problems of target loss and missing information when performing static target recognition. This paper uses machine learning algorithm to recognize and track targets. Taking the relative distance and relative velocity of the radar target as observation quantity, the Gaussian Hidden Markov Model(GHMM) is used to learn the labeled data from radar, and the nonlinear relationship among the relative distance, relative velocity and target states are obtained. Moreover, through the clustering of Gaussian Model(GM), the target’s label can be predicted according to the radar signal, and the forward-backward algorithm can be used to track the target. The results show that the model can effectively improve the accuracies of the target prediction and the tracking effect when the distance is around 140 meters and the speed is around 30 m/s.
作者
林雨田
张钰
高利
赵亚男
LIN Yutian;ZHANG Yu;GAO Li;ZHAO Yanan(School of Mechanical Engineering,Beijing Institute of Technology,Bejing 100081,China)
出处
《激光杂志》
CAS
北大核心
2022年第6期46-52,共7页
Laser Journal
基金
国家重点研发计划(No.2018YFB0105205-02)
国家重点研发计划(No.2017YFC0804808)
国家重点研发计划(No.2017YFC0804803)。
关键词
毫米波雷达
静态物体检测
高斯隐马尔科夫模型
机器学习
millimeter wave radar
static object detection
gaussian hidden markov model
machine learning