基于图神经网络的4D毫米波雷达目标检测方法

doi:10.3778/j.issn.1002-8331.2401-0160

摘要/Abstract

摘要： 4D毫米波雷达具有体积小、成本低、全天候运行、测速能力强、距离分辨率高等优势，非常适用于自动驾驶系统。然而，目前基于毫米波雷达的目标检测方法通常直接移植于激光雷达，无法有效适应于毫米波雷达点云特征，因此检测性能较差。针对此问题，提出一种基于图神经网络的4D毫米波雷达目标检测方法。设计基于拓扑图以及初始特征图传播信息并更新点云特征的图神经网络，该网络作为点云特征编码器可输出高可分的节点嵌入；将带有节点嵌入的点云投影至二维鸟瞰图；利用具有通道注意力机制的主干网络抽取多尺度特征，并于通道维上进行融合以输出融合特征图；将融合特征图输入检测头以获得目标的有效检测。基于公开数据集View-of-Delft的实验结果表明，与现有主流算法相比，所提方法具有较好的目标检测性能。

关键词: 自动驾驶, 4D毫米波雷达, 目标检测, 图神经网络

Abstract: The 4D millimeter-wave radar has the advantages of small size, low cost, all-weather operation, strong speed measurement ability, and high distance resolution, making it very suitable for autonomous driving systems. However, the existing target detection methods based on 4D millimeter-wave radar are usually directly transplanted from lidar, which cannot effectively adapt to the millimeter-wave radar point cloud features, resulting in poor detection performance. Concerning this, a 4D millimeter-wave radar target detection method based on graph neural network is developed. In the proposed method, a graph neural network based on topological graph and feature propagation is designed to update the point cloud features, which serves as a point cloud feature encoder to output high-dimensional node embeddings. The point cloud with node embeddings is projected onto a two-dimensional bird’s eye view. A backbone network with a channel attention mechanism is used to extract its multi-scale features and fuse them in the channel dimension to output fused feature maps. The fused feature maps are input to the detection head to achieve effective target detection. Experimental results on the public dataset View-of-Delft demonstrate that the proposed method has better target detection performance compared to existing mainstream algorithms.

Key words: autonomous driving, 4D millimeter-wave radar, target detection, graph neural network

黄梓峰, 王洪雁, 马嘉康. 基于图神经网络的4D毫米波雷达目标检测方法[J]. 计算机工程与应用, 2025, 61(10): 145-154.

HUANG Zifeng, WANG Hongyan, MA Jiakang. 4D Millimeter-Wave Radar Target Detection Method Based on Graph Neural Network[J]. Computer Engineering and Applications, 2025, 61(10): 145-154.

参考文献

[1] LEVINSON J, ASKELAND J, BECKER J, et al. Towards fully autonomous driving: systems and algorithms[C]//Proceedings of the 2011 IEEE Intelligent Vehicles Symposium. Piscataway: IEEE, 2011: 163-168.
[2] YURTSEVER E, LAMBERT J, CARBALLO A, et al. A survey of autonomous driving: common practices and emerging technologies[J]. IEEE Access, 2020, 8: 58443-58469.
[3] BADUE C, GUIDOLINI R, CARNEIRO R V, et al. Self-driving cars: a survey[J]. Expert Systems with Applications, 2021, 165: 113816.
[4] LIU L, OUYANG W L, WANG X G, et al. Deep learning for generic object detection: a survey[J]. International Journal of Computer Vision, 2020, 128(2): 261-318.
[5] MAO J G, SHI S S, WANG X G, et al. 3D object detection for autonomous driving: a comprehensive survey[J]. International Journal of Computer Vision, 2023, 131(8): 1909-1963.
[6] ZHAO Z Q, ZHENG P, XU S T, et al. Object detection with deep learning: a review[J]. IEEE Transactions on Neural Networks and Learning Systems, 2019, 30(11): 3212-3232.
[7] HASCH J, TOPAK E, SCHNABEL R, et al. Millimeter-wave technology for automotive radar sensors in the 77 GHz frequency band[J]. IEEE Transactions on Microwave Theory and Techniques, 2012, 60(3): 845-860.
[8] ENGELS F, HEIDENREICH P, WINTERMANTEL M, et al. Automotive radar signal processing: research directions and practical challenges[J]. IEEE Journal of Selected Topics in Signal Processing, 2021, 15(4): 865-878.
[9] CHEN Q P, XIE Y F, GUO S F, et al. Sensing system of environmental perception technologies for driverless vehicle: a review of state of the art and challenges[J]. Sensors and Actuators A: Physical, 2021, 319: 112566.
[10] ZHOU T H, YANG M M, JIANG K, et al. MMW radar-based technologies in autonomous driving: a review[J]. Sensors, 2020, 20(24): 7283.
[11] JIANG M J, XU G, PEI H, et al. 4D high-resolution imagery of point clouds for automotive mmWave radar[J]. IEEE Transactions on Intelligent Transportation Systems, 2024, 25(1): 998-1012.
[12] BRISKEN S, RUF F, H?HNE F. Recent evolution of automotive imaging radar and its information content[J]. IET Radar, Sonar & Navigation, 2018, 12(10): 1078-1081.
[13] PALFFY A, POOL E, BARATAM S, et al. Multi-class road user detection with 3+ 1D radar in the view-of-delft dataset[J]. IEEE Robotics and Automation Letters, 2022, 7(2): 4961-4968.
[14] LANG A H, VORA S, CAESAR H, et al. PointPillars: fast encoders for object detection from point clouds[C]//Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2019: 12689-12697.
[15] XU B W, ZHANG X Y, WANG L, et al. RPFA-net: a 4D RaDAR pillar feature attention network for 3D object detection[C]//Proceedings of the 2021 IEEE International Intelligent Transportation Systems Conference. Piscataway: IEEE, 2021: 3061-3066.
[16] TAN B, MA Z X, ZHU X C, et al. 3-D object detection for multiframe 4-D automotive millimeter-wave radar point cloud[J]. IEEE Sensors Journal, 2023, 23(11): 11125-11138.
[17] WU Z H, PAN S R, CHEN F W, et al. A comprehensive survey on graph neural networks[J]. IEEE Transactions on Neural Networks and Learning Systems, 2021, 32(1): 4-24.
[18] STERGIOU A, POPPE R, KALLIATAKIS G. Refining activation downsampling with SoftPool[C]//Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2021: 10337-10346.
[19] YANG Z C, YANG D Y, DYER C, et al. Hierarchical attention networks for document classification[C]//Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Stroudsburg: ACL, 2016: 1480-1489.
[20] CHARLES R Q, HAO S, MO K C, et al. PointNet: deep learning on point sets for 3D classification and segmentation[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017: 77-85.
[21] HU J, SHEN L, SUN G. Squeeze-and-excitation networks[C]//Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2018: 7132-7141.
[22] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2016: 779-788.
[23] LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot multibox detector[C]//Proceedings of the 14th European Conference on Computer Vision. Cham: Springer, 2016: 21-37.
[24] REN S Q, HE K M, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137-1149.
[25] YAN Y, MAO Y X, LI B. SECOND: sparsely embedded convolutional detection[J]. Sensors, 2018, 18(10): 3337.
[26] LIN T Y, GOYAL P, GIRSHICK R, et al. Focal loss for dense object detection[C]//Proceedings of the 2017 IEEE International Conference on Computer Vision. Piscataway: IEEE, 2017: 2999-3007.
[27] SCHUMANN O, HAHN M, SCHEINER N, et al. RadarScenes: a real-world radar point cloud data set for automotive applications[C]//Proceedings of the 2021 IEEE 24th International Conference on Information Fusion. Piscataway: IEEE, 2021: 1-8.
[28] SHEENY M, DE PELLEGRIN E, MUKHERJEE S, et al. RADIATE: a radar dataset for automotive perception in bad weather[C]//Proceedings of the 2021 IEEE International Conference on Robotics and Automation. Piscataway: IEEE, 2021: 1-7.
[29] MEYER M, KUSCHK G. Automotive radar dataset for deep learning based 3D object detection[C]//Proceedings of the 2019 16th European Radar Conference, 2019: 129-132.
[30] GEIGER A, LENZ P, STILLER C, et al. Vision meets robotics: the KITTI dataset[J]. The International Journal of Robotics Research, 2013, 32(11): 1231-1237.
[31] SHI S S, WANG X G, LI H S. PointRCNN: 3D object proposal generation and detection from point cloud[C]//Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2019: 770-779.
[32] QI C R, YI L, SU H, et al. PointNet++: deep hierarchical feature learning on point sets in a metric space[C]//Advances in Neural Information Processing Systems 30, 2017: 5099-5108.
[33] SHI W J, RAJKUMAR R. Point-GNN: graph neural network for 3D object detection in a point cloud[C]//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2020: 1708-1716.
[34] FENT F, BAUERSCHMIDT P, LIENKAMP M. RadarGNN: transformation invariant graph neural network for radar-based perception[C]//Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Piscataway: IEEE, 2023: 182-191.