文章详情

题名 · 作者 · 摘要 · 关键词 · DOI · 参考文献

基于单目场景的车辆三维目标检测方法综述

唐心瑶1，2，王伟3

（1.华南理工大学 电子与信息学院，广东 广州 510640；2.广电运通集团股份有限公司，广东 广州 510663； 3.长安大学 信息工程学院，陕西 西安 710018）

栏目：人工智能 · 第 2025 年第 9 期 · 页码：16-24,31 · 2096-4706（2025）09-0016-10 · 中图分类号：TP391.4 · 文献标识码：A · DOI：10.19850/j.cnki.2096-4706.2025.09.004

摘要

近年来，车辆三维目标检测在自动驾驶等智能交通领域备受关注。相较于二维检测，三维检测可精确估计目标在三维空间中的位置、尺寸与姿态等信息。因单目相机具备成本低、数据处理效率高等优势，在实际应用中占据主导地位。文章聚焦单目场景下的三维目标检测方法，系统梳理其发展脉络。首先，依据先验信息来源，将检测方法分为基于几何信息、二维目标检测与几何信息约束、三维特征估计三类，并分别剖析了每类方法中代表性算法的核心思想及其优缺点。其次，介绍领域内常用的公共数据集与评价指标，并在KITTI数据集上对典型算法的实验结果进行量化对比。最后，结合当前研究现状，剖析该领域现存的主要问题，并展望未来发展趋势。

关键词

智能交通；单目相机；三维目标检测；深度学习

参考文献

  1. [1] ASEEM B，OMID H J，SIVA K M，et al. Bounding Boxes, Segmentations and Object Coordinates: How Important is Recognition for 3D Scene Flow Estimation in Autonomous Driving Scenarios? [C]//2017 IEEE International Conference on Computer Vision(ICCV).Venice：IEEE，2017：2593-2602.
  2. [2] MA X Z，WANG Z H，LI H J，et al. Accurate Monocular 3D Object Detection Via Color-Embedded 3D Reconstruction for Autonomous Driving [C]//2019 IEEE /CVF International Conference on Computer Vision(ICCV).Seoul：IEEE，2019：6850-6859.
  3. [3] 曹培.面向自动驾驶的双传感器信息融合目标检测及姿态估计 [D].哈尔滨：哈尔滨工业大学，2019.
  4. [4] ZHANG H R，CAO Q X. Texture-Less Object Detection and 6D Pose Estimation in RGB-D Images [J].Robotics and Autonomous Systems，2017，95：64-79.
  5. [5] DAVID J T，NASSIR N，FEDERICO T. 6D Object Pose Estimation with Depth Images: A Seamless Approach for Robotic Interaction and Augmented Reality [J/OL].arXiv:1709.01459 [cs.CV].[2024-12-18].https://arxiv.org/abs/1709.01459.
  6. [6] JORGE B，CARLOS G，FRANCISCO M M，et al. Birdnet: A 3D Object Detection Framework from LiDAR Information [C]//2018 21st International Conference on Intelligent Transportation Systems(ITSC).Maui：IEEE，2018：3517-3523.
  7. [7] LI B，ZHANG T L，XIA T. Vehicle Detection from 3D Lidar Using Fully Convolutional Network [J/OL].arXiv:1608.07916 [cs.CV].[2024-12-19].https://arxiv.org/abs/1608.07916.
  8. [8] SHI S S，WANG X G，LI H S. Pointrcnn: 3D Object Proposal Generation and Detection from Point Cloud [C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).Long Beach：IEEE，2019：770-779.
  9. [9] ZHOU Y，ONCEL T. Stereo Imagery: End-to-end Learning for Point Cloud Based 3D Object Detection [C]//2018 IEEE Conference on Computer Vision and Pattern Recognition.Salt Lake City：IEEE，2018：4490-4499.
  10. [10] GUPTA S，GIRSHICK R，ARBELÁEZ P，et al. Learning Rich Features from RGB-D Images for Object Detection and Segmentation [J].CoRR，2014：345-360.
  11. [11] CHEN X Z，KAUSTAV K，ZHU Y K，et al. 3D Object Proposals Using Stereo Imagery for Accurate Object Class Detection [J].IEEE Transactions on Pattern Analysis & Machine Intelligence，2018，40（5）：1259-1272.
  12. [12] XU B，CHEN Z Z. Multi-Level Fusion Based 3D Object Detection from Monocular Images [C]//2018 IEEE Conference on Computer Vision and Pattern Recognition.Salt Lake City：IEEE，2018：2345-2353.
  13. [13] QI C R，YI L，SU H，et al. PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space [J/OL].arXiv:1706.02413 [cs.CV].[2024-12-19].https://arxiv.org/abs/1706.02413.
  14. [14] CHEN X Z，MA H M，WAN J，et al. Multi-View 3D Object Detection Network for Autonomous Driving [C]//2017 IEEE Conference on Computer Vision and Pattern Recognition.Honolulu：IEEE，2017：6526-6534.
  15. [15] QI C R，LIU W，WU C X，et al. Frustum PointNets for 3D Object Detection from RGB-D Data [C]//2018 IEEE Conference on Computer Vision and Pattern Recognition.Salt Lake City：IEEE，2018：918-927.
  16. [16] CHU H，MA W C，KAUSTAV K，et al. Surfconv: Bridging 3D and 2D Convolution for RGBD Images [C]//2018 IEEE Conference on Computer Vision and Pattern Recognition.Salt Lake City：IEEE，2018：3002-3011.
  17. [17] QIN Z Y，WANG J L，LU Y. Triangulation Learning Network: From Monocular to Stereo 3D Object Detection [C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).Long Beach：IEEE，2019：7607-7615.
  18. [18] LI P L，CHEN X Z，SHEN S J. Stereo R-CNN Based 3D Object Detection for Autonomous Driving [C]//2019 IEEE Conference on Computer Vision and Pattern Recognition(CVPR).Long Beach：IEEE，2019：7636-7644.
  19. [19] HU H N，CAI Q Z，WANG D Q，et al. Joint Monocular 3D Vehicle Detection and Tracking [C]//2019 IEEE/CVF International Conference on Computer Vision(ICCV).Seoul：IEEE，2019：5389-5398.
  20. [20] QIN Z Y，WANG J L，LU Y. Monogrnet: A Geometric Reasoning Network for Monocular 3D Object Localization [J].Proceedings of the AAAI Conference on Artificial Intelligence，2019，33：8851-8858.
  21. [21] THOMAS R，ALEX K，ROBERTO C. Orthographic Feature Transform for Monocular 3D Object Detection [J/OL].arXiv:1811.08188 [cs.CV].[2024-12-19].https://arxiv.org/abs/1811.08188.
  22. [22] KU J，PON A D，WASLANDER S L. Monocular 3D Object Detection Leveraging Accurate Proposals and Shape Reconstruction [C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).Long Beach：IEEE，2019：11859-11868.
  23. [23] XIANG Y，CHOI W G，LIN Y Q，et al. Subcategory Aware Convolutional Neural Networks for Object Proposals and Detection [C]//2017 IEEE Winter Conference on Applications of Computer Vision (WACV).Santa Rosa：IEEE，2017：924-933.
  24. [24] LI C，ZIA M Z，TRAN Q H，et al. Deep Supervision with Shape Concepts for Occlusion-Aware 3D Object Parsing [C]//2017 IEEE Conference on Computer Vision and Pattern Recognition.Honolulu：IEEE，2017：388-397.
  25. [25] ZIA M Z，MICHAEL S，BERNT S，et al. Detailed 3D Representations for Object Recognition and Modeling [J].IEEE Transactions on Pattern Analysis & Machine Intelligence，2013，35（11）：2608-2623.
  26. [26] DUBSKÁ M，HEROUT A，SOCHOR J. Automatic Camera Calibration for Traffic Understanding [EB/OL].[2024-12-19].https://www.bmva-archive.org.uk/bmvc/2014/papers/paper013/index.html.
  27. [27] ultralytics. YOLOv5 [EB/OL].[2024-12-19].https://github.com/ultralytics/yolov5.
  28. [28] ZHOU X Y，WANG D Q，KRHENBHL P. Objects as Points [J/OL].arXiv:1904.07850 [cs.CV].[2024-12-20].https://arxiv.org/abs/1904.07850.
  29. [29] LIU W，ANGUELOV D，ERHAN D，et al. SSD: Single Shot MultiBox Detector [J/OL].arXiv:1512.02325 [cs.CV].[2024-12-20].https://arxiv.org/abs/1512.02325.
  30. [30] LIU L J，LU J W，XU C J，et al. Deep Fitting Degree Scoring Network for Monocular 3D Object Detection [C]//2019 IEEE Conference on Computer Vision and Pattern Recognition.Long Beach：IEEE，2019：1057-1066.
  31. [31] CHEN X Z，KAUSTAV K，ZHANG Z Y，et al. Monocular 3D Object Detection for Autonomous Driving [C]//2016 IEEE Conference on Computer Vision and Pattern Recognition(CVPR).Las Vegas：IEEE，2016：2147-2156.
  32. [32] MOUSAVIAN A，ANGUELOV D，FLYNN J，et al. 3D Bounding Box Estimation Using Deep Learning and Geometry [C]//2017 IEEE Conference on Computer Vision and Pattern Recognition.Honolulu：IEEE，2017：5632-5640.
  33. [33] CHABOT F，CHAOUCH M，RABARISOA J，et al. Deep MANTA: A Coarse-to-Fine Many-Task Network for Joint 2D and 3D Vehicle Analysis from Monocular Image [C]//2017 IEEE Conference on Computer Vision and Pattern Recognition(CVPR).Honolulu：IEEE，2017：1827-1836.
  34. [34] YANG S C，SCHERER S. CubeSLAM: Monocular 3-D Object SLAM [J].IEEE Transactions on Robotics，2019，35（4）：925-938.
  35. [35] HE T，SOATTO S. Mono3D++: Monocular 3D Vehicle Detection with Two-Scale 3D Hypotheses and Task Priors [J/OL].arXiv:1901.03446 [cs.CV].[2024-12-19].https://arxiv.org/abs/1901.03446.
  36. [36] MANHARDT F，KEHL W，GAIDON A. ROI-10D: Monocular Lifting of 2D Detection to 6D Pose and Metric Shape [C]//2019 IEEE Conference on Computer Vision and Pattern Recognition（CVPR）.Long Beach：IEEE，2019：2064-2073.
  37. [37] DING M Y，HUO Y Q，YI H W，et al. Learning Depth-Guided Convolutions for Monocular 3D Object Detection [C]//2020 IEEE Conference on Computer Vision and Pattern Recognition.Seattle：IEEE，2020：11669-11678.
  38. [38] M RAD，VINCENT L. BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects without Using Depth [C]//2017 IEEE International Conference on Computer Vision.Venice：IEEE，2017：3848-3856.
  39. [39] WADIM K，FABIAN M，FEDERICO T，et al. SSD-6D: Making RGB-Based 3D Detection and 6D Pose Estimation Great Again [C]//2017 IEEE International Conference on Computer Vision.Venice：IEEE，2017：1530-1538.
  40. [40] BUGRA T，SUDIPTA N S，PASCAL F. Real-Time Seamless Single Shot 6D Object Pose Prediction [C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Salt Lake City：IEEE，2018：292-301.
  41. [41] ISHAN G，AKSHAY R，MOHAN T. 3D Bounding Boxes for Road Vehicles: A One-Stage, Localization Prioritized Approach Using Single Monocular Images [EB/OL].[2024-12-19]. https://openaccess.thecvf.com/content_eccv_2018_workshops/w29/html/Gupta_3D_Bounding_Boxes_for_Road_Vehicles_A_One-Stage_Localization_Prioritized_ECCVW_2018_paper.html.
  42. [42] LI B Y，OUYANG W L，SHENG L，et al. GS3D: An EFFicient 3D Object Detection Framework for Autonomous Driving [C]//2019 IEEE Conference on Computer Vision and Pattern Recognition.Long Beach：IEEE，2019：1019-1028.
  43. [43] LI P X，ZHAO H C，LIU P F，et al. RTM3D： Real-Time Monocular 3D Detection from Object Keypoints for Autonomous Driving [J/OL].arXiv:2001.03343 [cs.CV].[2024-12-19].https://arxiv.org/abs/2001.03343v1.
  44. [44] IVAN B，ALEXEY A，EVGENY B，et al. Monocular 3D Object Detection via Geometric Reasoning on Keypoints [J/OL].arXiv:1905.05618 [cs.CV].[2024-12-19].https://arxiv.org/abs/1905.05618.
  45. [45] ANDREAS G，PHILIP L，RAQUEL U. Are we Ready for Autonomous Driving? The KITTI Vision Benchmark Suite [C]//2012 IEEE Conference on Computer Vision and Pattern Recognition.Providence：IEEE，2012：3354-3361.
  46. [46] XIANG Y，ROOZBEH M，SILVIO S. Beyond PASCAL: A Benchmark for 3D Object Detection in the Wild [C]//IEEE Winter Conference on Applications of Computer Vision.Steamboat Springs：IEEE，2014：75-82.
  47. [47] HUANG X Y，WANG P，CHENG X J，et al. The ApolloScape Open Dataset for Autonomous Driving and Its Application [J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2018，42（10）：2702-2719.
  48. [48] SUN P，HENRIK K，XERXES D，et al. Scalability in Perception for Autonomous Driving: Waymo Open Dataset [C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).Seattle：IEEE，2020：2443-2451.
  49. [49] CAESAR H，BANKITI V，LANG A H，et al. NuScenes: A Multimodal Dataset for Autonomous Driving [C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).Seattle：IEEE，2020：11618-11628.

基金项目

陕西省自然科学基础研究计划项目（2023-JC-YB-600）

作者简介

唐心瑶（1996—），女，汉族，江苏苏州人，算法工程师，博士，研究方向：计算机视觉、智能交通。