3D Object Detection Based on Convolutional Neural Networks: A Survey
WANG Yadong1, TIAN Yonglin2,3, LI Guoqiang1, WANG Kunfeng1, LI Dazi1
1. College of Information Science and Technology, Beijing University of Chemical Technology, Beijing 100029; 2. Department of Automation, University of Science and Technology of China, Hefei 230022; 3. The State Key Laboratory of Management and Control of Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190
Abstract Three-dimensional(3D) object detection plays a critical role in the fields of autonomous driving and robotics, since deep learning methods can offer possible solutions for accurate object detection, especially convolutional neural networks. The research progresses of convolutional neural network-based 3D object detection are reviewed comprehensively. Firstly, the practical value, basic procedures and challenges of 3D object detection are summarized. Next, the preliminary knowledge of convolutional neural networks, typical 2D object detection network structures, some widely-used open source datasets and point cloud representations is introduced. Then, progresses on the application of convolutional neural networks in 3D object detection are presented, and the methods are sorted out and analyzed according to different data modalities and method commonalities. Finally, issues in the existing research of 3D object detection are discussed, and future research trends are prospected.
Fund:National Key Research and Development Program of China(No.2020YFC2003900), National Natural Science Foundation of China(No.62076020), Fundamental Research Funds for the Central Universities(No.buctrc201933)
Corresponding Authors:
WANG Kunfeng, Ph.D., professor. His research interests include computer vision, machine learning and intelligent unmanned systems.
About author:: WANG Yadong, Ph.D. candidate. His research interests include computer vision and deep learning. TIAN Yonglin, Ph.D. candidate. His research interests include computer vision and intelligent transportation systems. LI Guoqiang, master student. His research interests include computer vision and deep learning. LI Dazi, Ph.D., professor. Her research interests include pattern recognition and reinforcement learning.
[1] LI B Y, OUYANG W L, SHENG L, et al. GS3D: An Efficient 3D Object Detection Framework for Autonomous Driving // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2019: 1019-1028. [2] ZHOU Y, TUZEL O.VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2018: 4490-4499. [3] KU J, MOZIFIFIAN M, LEE J, et al. Joint 3D Proposal Generation and Object Detection from View Aggregation // Proc of the IEEE/RSJ International Conference on Intelligent Robots and Systems. Washington, USA: IEEE, 2018. DOI: 10.1109/IROS.2018.8594049. [4] ARNOLD E, AL-JARRAH O Y, DIANATI M, et al. A Survey on 3D Object Detection Methods for Autonomous Driving Applications. IEEE Transactions on Intelligent Transportation Systems, 2019, 20(10): 3782-3795. [5] 张慧,王坤峰,王飞跃.深度学习在目标视觉检测中的应用进展与展望.自动化学报, 2017, 43(8): 1289-1305. (ZHANG H, WANG K F, WANG F Y.Advances and Perspectives on Applications of Deep Learning in Visual Object Detection. Acta Automatica Sinica, 2017, 43(8): 1289-1305.) [6] REN Z, SUDDERTH E B.Three-Dimensional Object Detection and Layout Prediction Using Clouds of Oriented Gradients // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington,USA: IEEE, 2016: 1525-1533. [7] ALI W, ABDELKARIM S, ZAHRAN M, et al. YOLO3D: End-to-End Real-Time 3D Oriented Object Bounding Box Detection from LiDAR Point Cloud // Proc of the European Conference on Computer Vision. Springer, Germany: Springer, 2018: 716-728. [8] RODDICK T, KENDALL A, CIPOLLA R.Orthographic Feature Transform for Monocular 3D Object Detection[C/OL]. [2021-05-20].https://arxiv.org/pdf/1811.08188.pdf. [9] LAHOUD J, GHANEM B.2D-Driven 3D Object Detection in RGB-D Images // Proc of the IEEE International Conference on Computer Vision. Washington, USA: IEEE, 2017: 4632-4640. [10] CHEN Y L, LIU S, SHEN X Y, et al. Fast Point R-CNN // Proc of the IEEE/CVF International Conference on Computer Vision. Washington, USA: IEEE, 2019: 9774-9783. [11] LIANG M, YANG B, CHEN Y, et al. URTASU: Multi-task Multi-sensor Fusion for 3D Object Detection // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2019: 7337-7345. [12] LAMPERT C H, BLASCHKO M B, HOFMANN T.Beyond Sli-ding Windows: Object Localization by Efficient Subwindow Search // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2008. DOI: 10.1109/CVPR.2008.4587586.. [13] DALAL N, TRIGGS B. Histograms of Oriented Gradients for Human Detection // Proc of the IEEE Society Conference on Compu-ter Vision and Pattern Recognition. Washington, USA:IEEE, 2005, I: 886-893. [14] LEIBE B, LEONARDIS A, SCHIELE B.Robust Object Detection with Interleaved Categorization and Segmentation. International Journal of Computer Vision, 2008, 77: 259-289. [15] SHOTTON J, WINN J, ROTHER C, et al. TextonBoost: Joint Appearance, Shape and Context Modeling for Multi-class Object Recognition and Segmentation // Proc of the European Conference on Computer Vision. Berlin, Germany: Springer, 2006: 1-15. [16] 吴帅,徐勇,赵东宁.基于深度卷积网络的目标检测综述.模式识别与人工智能, 2018, 31(4): 335-346. (WU S, XU Y, ZHAO D N.Survey of Object Detection Based on Deep Convolutional Network.Pattern Recognition and Artificial Intelligence, 2018, 31(4): 335-346.) [17] LECUN Y, BOTTOU L, BENGIO Y, et al. Gradient-Based Lear-ning Applied to Document Recognition. Proceeding of the IEEE, 1998, 86(11): 2278-2324. [18] KRIZHEVSKY A, SUTSKEVER I, HINTON G E.ImageNet Cla-ssification with Deep Convolutional Neural Networks. Communications of the ACM, 2017, 60(6): 84-90. [19] SIMONYA K, ZISSERMAN A. Very Deep Convolutional Networks for Large-Scale Image Recognition[C/OL]. [2021-05-20]. https://arxiv.org/pdf/1409.1556.pdf. [20] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation // Proc of the IEEE Conference on Computer Vision and Pa-ttern Recognition. Washington, USA: IEEE, 2014: 580-587. [21] HE K M, ZHANG X Y, REN S Q, et al. Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014, 37(9): 1904-1916. [22] GIRSHICK R.Fast R-CNN // Proc of the IEEE International Conference on Computer Vision. USA: IEEE, 2015: 1440-1448. [23] REN S Q, HE K M, GIRSHICK R, et al. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137-1149. [24] 王浩,单文静,方宝富.基于多层上下文卷积神经网络的目标检测算法.模式识别与人工智能, 2020, 33(2): 113-120. (WANG H, SHAN W J, FANG B F.Multi-layers Context Convolutional Neural Network for Object Detection. Pattern Recognition and Artificial Intelligence, 2020, 33(2): 113-120.) [25] 张绳昱,董士风,焦林,等.基于有效感受野的区域推荐网络.模式识别与人工智能, 2020, 33(5): 393-400. (ZHANG S Y, DONG S F, JIAO L, et al. Region Proposal Network Based on Effective Receptive Field. Pattern Recognition and Artificial Intelligence, 2020, 33(5): 393-400.) [26] LIU W, ANGUELOV D, ERHAN D, et al. SSD: Single Shot Multi-box Detector // Proc of the European Conference on Computer Vision. Berlin, Germany: Springer, 2016: 21-37. [27] 储珺,朱晓阳,冷璐,等.引入通道注意力和残差学习的目标检测器.模式识别与人工智能, 2020, 33(10): 889-897. (CHU J, ZHU X Y, LENG L, et al. Target Detector with Channel Attention and Residual Learning. Pattern Recognition and Artificial Intelligence, 2020, 33(10): 889-897.) [28] REDMON J, FARHADI A.YOLO9000: Better, Faster, Stronger // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2017: 6517-6525. [29] LIN T Y, GOYAL P, GIRSHICK R, et al. Focal Loss for Dense Object Detection // Proc of the IEEE International Conference on Computer Vision. Washington, USA: IEEE, 2017: 2999-3007. [30] ZHOU X Y, WANG D Q, KRÄHENBÜHL P. Objects as Points[C/OL].[2021-05-20]. https://arxiv.org/pdf/1904.07850.pdf. [31] BELTRÁN J, GUINDEL C, MORENO F M, et al. BirdNet: A 3D Object Detection Framework from LiDAR Information // Proc of the 21st International Conference on Intelligent Transportation Systems. Washington, USA: IEEE, 2018: 3517-3523. [32] QI C R, SU H, KAICHUN M, et al. PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2017: 77-85. [33] SHI S S, GUO C X, JIANG L, et al. PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2020: 10526-10535 [34] LIMAYE A, MATHEW M, NAGORI S, et al. SS3D: Single Shot 3D Object Detector[C/OL].[2021-05-20]. https://arxiv.org/ftp/arxiv/papers/2004/2004.14674.pdf. [35] LANG A H, VORA S, CAESAR H, et al. PointPillars: Fast Encoders for Object Detection from Point Clouds // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2019: 12689-12697. [36] YANG Z T, SUN Y N, LIU S, et al. 3DSSD: Point-Based 3D Single Stage Object Detector // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . Washington,USA: IEEE, 2020: 11037-11045. [37] QI C R, LIU W, WU C X, et al. GUIBAS: Frustum PointNets for 3D Object Detection from RGB-D Data[C/OL].[2021-05-20]. https://arxiv.org/pdf/1711.08488.pdf. [38] SHI S S, WANG X G, LI H S.Point RCNN: 3D Object Proposal Generation and Detection from Point Cloud // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2019: 770-779. [39] ZHOU Y, SUN P, ZHANG Y, et al. End-to-End Multi-view Fusion for 3D Object Detection in LiDAR Point Clouds. Proceedings of the Conference on Robot Learning, 2020, 100: 923-932. [40] KUANG H W, WANG B, AN J P, et al. Voxel-FPN: Multi-scale Voxel Feature Aggregation for 3D Object Detection from LIDAR Point Clouds. Sensors, 2020, 20(3). DOI: 10.3390/s20030704. [41] SHI W J, RAJKUMAR R.Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloud // Proc of the IEEE International Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2020: 1711-1719. [42] GEIGER A, LENZ P, URTASUN R.Are We Ready for Autonomous Driving? The KITTI Vision Benchmark Suite // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2012: 3354-3361. [43] HUANG X Y, WANG P, CHENG X J, et al. The ApolloScape Open Dataset for Autonomous Driving and Its Application. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(10): 2702-2719. [44] SUN P, KRETZSCHMAR H, DOTIWALLA X.Scalability in Perception for Autonomous Driving: Waymo Open Dataset // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2020: 2443-2451. [45] CHOI Y, KIM N, HWANG S, et al. KAIST Multi-spectral Day/Night Data Set for Autonomous and Assisted Driving. IEEE Tran-sactions on Intelligent Transportation Systems, 2018, 19(3): 934-948. [46] CAESAR H, BANKITI V, LANG A H, et al. nuScenes: A Multimodal Dataset for Autonomous Driving // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2020: 11618-11628. [47] GÄHLERT N, JOURDAN N, CORDTS M, et al. Cityscapes 3D: Dataset and Benchmark for 9 DoF Vehicle Detection[C/OL].[2020-05-20]. https://arxiv.org/pdf/2006.07864v1.pdf. [48] SILBERMAN N, HOIEM D, KOHLI P, et al. Indoor Segmentation and Support Inference from RGB-D Images // Proc of the European Conference on Computer Vision. Berlin, Germany: Springer, 2012: 746-760. [49] JANOCH A, KARAYEV S, JIA Y Q, et al. A Category-Level 3D Object Dataset: Putting the Kinect to Work // FOSSATI A, GALLHELMUT J, XIAOFENG G, et al, eds. Consumer Depth Cameras for Computer Vision. Berlin, Germany: Springer, 2013: 141-165. [50] XIAO J X, OWENS A, TORRALBA A.SUN3D: A Database of Big Spaces Reconstructed Using SFM and Object Labels // Proc of the IEEE International Conference on Computer Vision. Washington, USA: IEEE, 2013: 1625-1632. [51] SONG S R, LICHTENBERG S P, XIAO J X.SUN RGB-D: A RGB-D Scene Understanding Benchmark Suite // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2015: 567-576. [52] DAI A, CHANG A X, SAVVA M, et al. ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2017: 2432-2443. [53] LIU L H, LU J W, XU C J, et al. Deep Fitting Degree Scoring Network for Monocular 3D Object Detection // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2019: 1057-1066. [54] LIU Z C, WU Z Z, TOTH R.SMOKE: Single-Stage Monocular 3D Object Detection via Keypoint Estimation // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Washington, USA: IEEE, 2020: 4289-4298. [55] LUO Q H, MA H F, TANG L, et al. 3D-SSD: Learning Hierarchical Features from RGB-D Images for Amodal 3D Object Detection. Neurocomputing, 2020, 378: 364-374. [56] BEKER D, KATO H, MORARIU M A, et al. Monocular Differentiable Rendering for Self-Supervised 3D Object Detection // Proc of the European Conference on Computer Vision. Berlin, Germany: Springer, 2020: 514-529. [57] CHEN X Z, KUNDU K, ZHU Y K, et al. 3D Object Proposals for Accurate Object Class Detection // Proc of the 28th International Conference on Neural Information Processing Systems. Cambridge, USA: The MIT Press, 2015, I: 424-432. [58] CHEN X Z, KUNDU K, ZHANG Z Y, et al. Monocular 3D Object Detection for Autonomous Driving // Proc of the IEEE Confe-rence on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2016: 2147-2156. [59] LI P L, CHEN X Z, SHEN S J.Stereo R-CNN Based 3D Object Detection for Autonomous Driving // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2019: 7636-7644. [60] 迟旭然,裴伟,朱永英, 等.Fast Stereo-RCNN三维目标检测算法[J/OL]. [2021-05-20]. http://kns.cnki.net/kcms/detail/21.1106.TP.20210818.0939.018.html. (CHI X R, PEI W, ZHU Y Y, et al. Fast Stereo-RCNN 3D Target Detection Algorithm[J/OL]. [2021-05-20]. http://kns.cnki.net/kcms/detail/21.1106.TP.20210818.0939.018.html [61] BAO W T, XU B, CHEN Z Z, et al. MonoFENet: Monocular 3D Object Detection with Feature Enhancement Networks. IEEE Tran-sactions on Image Processing, 2020, 29: 2753-2765. [62] KUNDU A, LI Y, REHG J M.3D-RCNN: Instance-Level 3D Object Reconstruction via Render-and-Compare // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2018: 3559-3568. [63] HE K M, ZHANG X Y, REN S Q, et al. Deep Residual Learning for Image Recognition // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2016: 770-778. [64] WANG Y, CHAO W L, GARG D, et al. Pseudo-LiDAR from Vi-sual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2019: 8437-8445. [65] GUIZILINI V, AMBRUS R, PILLAI S, et al. 3D Packing for Self-Supervised Monocular Depth Estimation // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2020: 2482-2491. [66] SUN J M, CHEN L H, XIE Y M, et al. Disp R-CNN: Stereo 3D Object Detection via Shape Prior Guided Instance Disparity Estimation // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2020: 10545-10554. [67] PLAUT E, YAACOV E B, EL SHLOMO B.Monocular 3D Object Detection in Cylindrical Images from Fisheye Cameras[C/OL]. [2020-05-20].https://arxiv.org/pdf/2003.03759.pdf. [68] AL HAKIM E.3D YOLO: End-to-End 3D Object Detection Using Point Clouds. Master Dissertation. Stockholm, Sweden: KTH Ro-yal Institute of Technology, 2018. [69] YE M S, XU S J, CAO T Y.HVNet: Hybrid Voxel Network for LiDAR Based 3D Object Detection[C/OL]. [2020-05-20].https://arxiv.org/pdf/2003.00186.pdf. [70] QI C R, YI L, SU H, et al. PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space // Proc of the 31st International Conference on Neural Information Processing Systems. Cambridge, USA: The MIT Press, 2017: 5105-5114. [71] QI C R, LITANY O, HE K M, et al. Deep Hough Voting for 3D Object Detection in Point Clouds // Proc of the IEEE/CVF International Conference on Computer Vision. Washington, USA: IEEE, 2019: 9276-9285. [72] NOH J, LEE S, HAM B.HVPR: Hybrid Voxel-Point Representation for Single-Stage 3D Object Detection // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2021: 14605-14614. [73] MEYER G P, LADDHA A, KEE E, et al. LaserNet: An Efficient Probabilistic 3D Object Detector for Autonomous Driving // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2019: 12677-12686. [74] CHEN Q, SUN L, WANG Z X, et al. Object as Hotspots: An Anchor-Free 3D Object Detection Approach via Firing of Hotspots // Proc of the European Conference on Computer Vision. Berlin, Germany: Springer, 2020: 68-84. [75] 刘斌平,周越.一种新颖的无锚框三维目标检测器.中国体视学与图像分析, 2020, 25(1): 65-71. (LIU B P, ZHOU Y.A Novel Anchor-Free 3D Detector. Chinese Journal of Stereology and Image Analysis, 2020, 25(1): 65-71.) [76] BARRERA A, GUINDE C, BELTRÁN J. BirdNet+: End-to-End 3D Object Detection in LiDAR Bird's Eye View // Proc of the 23rd IEEE International Conference on Intelligent Transportation Systems. Washington, USA: IEEE, 2020. DOI: 10.1109/ITSC45102.2020.9294293. [77] LEHNER J, MITTERECKER A, ADLER T, et al. Patch Refinement-Localized 3D Object Detection[C/OL].[2021-05-20]. https://arxiv.org/pdf/1910.04093.pdf. [78] YANG Z T, SUN Y N, LIU S, et al. STD: Sparse-to-Dense 3D Object Detector for Point Cloud // Proc of the IEEE/CVF International Conference on Computer Vision. Washington, USA: IEEE, 2019: 1951-1960. [79] HE C H, ZENG H, HUANG J Q, et al. Structure Aware Single-Stage 3D Object Detection from Point Cloud // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2020: 11870-11879. [80] LI J L, LUO S J, ZHU Z Q, et al. 3D IOU-Net: IOU Guided 3D Object Detector for Point Clouds[C/OL].[2021-05-20]. https://arxiv.org/pdf/2004.04962.pdf. [81] REN Z L, SUDDERTH E B.3D Object Detection with Latent Su-pport Surfaces // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2018: 937-946. [82] 季一木,陈治宇,田鹏浩,等.无人驾驶中3D目标检测方法研究综述.南京邮电大学学报(自然科学版), 2019, 39(4): 72-79. (JI Y M, CHEN Z Y, TIAN P H, et al. A Survey of 3D Target Detection Methods in Unmanned Driving. Journal of Nanjing University of Posts and Telecommunications (Natural Science Edition), 2019, 39(4): 72-79.) [83] CUI Y D, CHEN R, CHU W B, et al. Deep Learning for Image and Point Cloud Fusion in Autonomous Driving: A Review. IEEE Transactions on Intelligent Transportation Systems, 2021. DOI: 10.1109/TITS.2020.3023541.2021.. [84] FENG D, HAASE-SCHUETZ C, ROSENBAUM L, et al. Deep Multi-modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges. IEEE Tran-sactions on Intelligent Transportation Systems, 2021, 22(3): 1341-1360. [85] SINDAGI V A, ZHOU Y, TUZEL O.MVX-Net: Multimodal Voxelnet for 3D Object Detection // Proc of the International Confe-rence on Robotics and Automation. Washington, USA: IEEE, 2019: 7276-7282. [86] RUSSAKOVSKY O, DENG J, SU H, et al. ImageNet Large Scale Visual Recognition Challenge. International Journal of Computer Vision, 2015, 115(3): 211-252. [87] MEYER G P, CHARLAND J, HEGDE D, et al. Sensor Fusion for Joint 3D Object Detection and Semantic Segmentation // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Washington, USA: IEEE, 2019: 1230-1237. [88] XU D F, ANGUELOV D, JAIN A.PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimation // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2018: 244-253. [89] YOO J H, KIM Y, KIM J S, et al. 3D-CVF: Generating Joint Camera and LiDAR Features Using Cross-View Spatial Feature Fusion for 3D Object Detection // Proc of the European Conference on Computer Vision. Berlin, Germany: Springer, 2020: 720-736. [90] 王刚,王沛.基于深度学习的三维目标检测方法研究.计算机应用与软件, 2020, 37(12): 164-168. (WANG G, WANG P.3D Object Detection Method Based on Deep Learning. Computer Applications and Software, 2020, 37(12): 164-168.) [91] CHEN X Z, MA H M, WAN J, et al. Multi-view 3D Object Detection Network for Autonomous Driving // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2017: 6526-6534. [92] 周晓蕾. 基于激光雷达和相机的三维目标检测算法研究.硕士学位论文.北京:华北电力大学, 2020. (ZHOU X L.Research on 3D Object Detection Algorithms Based on Lidar and Camera. Master Dissertation. Beijing, China: North China Electric Power University, 2020.) [93] LIANG M, YANG B, WANG S L, et al. Deep Continuous Fusion for Multi-sensor 3D Object Detection // Proc of the European Conference on Computer Vision. Berlin, Germany: Springer, 2018: 663-678. [94] TIAN Y L, WANG K F, WANG Y, et al. Adaptive and Azimuth-Aware Fusion Network of Multimodal Local Features for 3D Object Detection. Neurocomputing, 2020, 411: 32-44. [95] QI C R, CHEN X L, LITANY O, et al. ImVoteNet: Boosting 3D Object Detection in Point Clouds with Image Votes // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2020: 4403-4412. [96] 黄漫,黄勃,高永彬.引入深度补全与实例分割的三维目标检测.传感器与微系统, 2021, 40(1): 129-132. (HUANG M, HUANG B, GAO Y B.3D Target Detection Incorporating with Depth Completion and Instance Segmentation. Transducer and Microsystem Technologies, 2021, 40(1): 129-132.) [97] ZHANG Y D, BAI M R, KOHLI P, et al. DeepContext: Context-Encoding Neural Pathways for 3D Holistic Scene Understanding[C/OL].[2021-05-20]. https://arxiv.org/pdf/1603.04922v4.pdf. [98] TORRALBA A, EFROS A A.Unbiased Look at Dataset Bias // Proc of the IEEE Conference on Computer Vision and Pattern Re-cognition. Washington, USA: IEEE, 2011: 1521-1528. [99] ZHENG Y T, HUANG D, LIU S T, et al. Cross-Domain Object Detection Through Coarse-to-Fine Feature Adaptation // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2020: 13763-13772. [100] 田永林,沈宇,李强,等. 平行点云:虚实互动的点云生成与三维模型进化方法.自动化学报, 2020, 46(12): 2572-2582. (TIAN Y L, SHEN Y, LI Q, et al. Parallel Point Clouds: Point Clouds Generation and 3D Model Evolution via Virtual-Real Interaction. Acta Automatica Sinica, 2020, 46(12): 2572-2582.) [101] NGIAM J, CAINE B, HAN W, et al. StarNet: Targeted Computation for Object Detection in Point Clouds[C/OL].[2021-05-20]. https://arxiv.org/pdf/1908.11069.pdf. [102] LI X, WANG K F, TIAN Y L, et al. The Parallel Eye Dataset: A Large Collection of Virtual Images for Traffic Vision Research. IEEE Transactions on Intelligent Transportation Systems, 2019, 20(6): 2072-2084. [103] PFEUFFER A, DIETMAYER K.Optimal Sensor Data Fusion Architecture for Object Detection in Adverse Weather Conditions // Proc of the 21st International Conference on Information Fusion. Washington, USA: IEEE, 2018. DOI: 10.23919/ICIF.2018.8455757. [104] KIM J, KOH J, KIM Y, et al. Robust Deep Multi-modal Lear-ning Based on Gated Information Fusion Network // Proc of the Asian Conference on Computer Vision. Berlin, Germany: Sprin-ger, 2018: 90-106. [105] MENG Q H, WANG W G, ZHOU T F, et al. Weakly Supervised 3D Object Detection from LiDAR Point Cloud // Proc of the European Conference on Computer Vision. Berlin, Germany: Springer, 2020: 515-531. [106] LIANG Z D, ZHANG M, ZHANG Z H, et al. RangeRCNN: Towards Fast and Accurate 3D Object Detection with Range Image Representation[C/OL].[2021-05-20]. https://arxiv.org/pdf/2009.00206.pdf. [107] TIAN Y L, HUANG L C, LI X S, et al. Context-Aware Dynamic Feature Extraction for 3D Object Detection in Point Clouds[C/OL].[2021-05-20]. https://arxiv.org/pdf/1912.04775.pdf.
2021, Vol. 34 
