MRPT: Millimeter-Wave Radar-Based Pedestrian Trajectory Tracking for Autonomous Urban Driving
MRPT: Millimeter-Wave Radar-Based Pedestrian Trajectory Tracking for Autonomous Urban Driving
复制标题
DOI：
10.1109/tim.2021.3139658
复制
发表时间：
2022
影响因子：
5.6
通讯作者：
Zhenyuan Zhang;Xiao-jian Wang;Darong Huang;X. Fang;Mu Zhou;Ying Zhang
中科院分区：
文献类型：
--
作者：
Zhenyuan Zhang;Xiao-jian Wang;Darong Huang;X. Fang;Mu Zhou;Ying Zhang
行人代表着灵活且不易察觉的目标，特别是在恶劣天气条件下，其轨迹跟踪在城市自主驾驶中决定行人的行为起着至关重要的作用。因此，本文提出了一种基于毫米波雷达的行人轨迹跟踪(MRPT)系统，可以实现全天候高精度的轨迹感知。更具体地说，为了提高在强背景杂波下的跟踪性能，提出了一种基于检测前跟踪的算法，将行人检测和跟踪结合起来，而不是传统方法将两者视为两个独立的阶段。在此基础上，提出了一种基于目标存在概率和马尔可夫转移矩阵相结合的连续检测方法，直接利用非阈值雷达数据实现了较好的行人检测性能。此外，基于二进制相位复用(BPM)策略，利用低成本的汽车调频连续波(FMCW)多输入多输出(MIMO)雷达传感器对所提出的系统进行了验证。大量的仿真和实验结果表明，在低信噪比条件下，MRPT比传统方法具有更好的行人检测和跟踪性能。
Pedestrians represent agile and low-observable targets, especially under adverse weather conditions, whose trajectory tracking plays a crucial role in determining pedestrian behavior in autonomous urban driving. Thus, this article presents a millimeter-wave radar-based pedestrian trajectory-tracking (MRPT) system that enables all-weather trajectory perception with high precision. More specifically, to improve the tracking performance in the presence of strong background clutters, a track-before-detection-based algorithm is proposed to address pedestrian detection and tracking jointly, instead of regarding them as two separate phases in conventional methods. After that, a continuous detection method based on the integration of target existence probability and the Markov transition matrix is proposed to achieve superior pedestrian detection performance by directly using unthresholded radar data. In addition, based on the binary-phase-multiplex (BPM) strategy, the proposed system is validated using a low-cost automotive frequency-modulated-continuous-waveform (FMCW) multiple-input–multiple-output (MIMO) radar sensor. Consequently, extensive simulation and experimental results demonstrate that MRPT exhibits better pedestrian detection and tracking performance under low signal-noise-ratio (SNR) conditions compared with traditional methods.