Zeng Zhiyuan, Wen Jie, Luo Jianan, Ding Gege, Geng Xiongfei
China Waterborne Transport Research Institute, Beijing 100088, China.
School of Electronic Information, Wuhan University, Wuhan 430072, China.
Sensors (Basel). 2024 Oct 12;24(20):6569. doi: 10.3390/s24206569.
To address the challenges of sparse point clouds in current MIMO millimeter-wave radar environmental mapping, this paper proposes a dense 3D millimeter-wave radar point cloud environmental mapping algorithm. In the preprocessing phase, a radar SLAM-based approach is introduced to construct local submaps, which replaces the direct use of radar point cloud frames. This not only reduces data dimensionality but also enables the proposed method to handle scenarios involving vehicle motion with varying speeds. Building on this, a 3D-RadarHR cross-modal learning network is proposed, which uses LiDAR as the target output to train the radar submaps, thereby generating a dense millimeter-wave radar point cloud map. Experimental results across multiple scenarios, including outdoor environments and underground tunnels, demonstrate that the proposed method can increase the point cloud density of millimeter-wave radar environmental maps by over 50 times, with a point cloud accuracy better than 0.1 m. Compared to existing algorithms, the proposed method achieves superior environmental map reconstruction performance while maintaining a real-time processing rate of 15 Hz.
为应对当前多输入多输出（MIMO）毫米波雷达环境地图绘制中稀疏点云的挑战，本文提出了一种密集三维毫米波雷达点云环境地图绘制算法。在预处理阶段，引入了一种基于雷达同步定位与地图构建（SLAM）的方法来构建局部子地图，该方法取代了直接使用雷达点云帧的方式。这不仅降低了数据维度，还使所提方法能够处理涉及不同速度车辆运动的场景。在此基础上，提出了一种三维雷达高分辨率（3D-RadarHR）跨模态学习网络，该网络以激光雷达作为目标输出，对雷达子地图进行训练，从而生成密集的毫米波雷达点云地图。在包括室外环境和地下隧道在内的多个场景中的实验结果表明，所提方法能够将毫米波雷达环境地图的点云密度提高50倍以上，点云精度优于0.1米。与现有算法相比，所提方法在保持15赫兹实时处理速率的同时，实现了卓越的环境地图重建性能。
