{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,10]],"date-time":"2026-10-10T20:56:22Z","timestamp":1791665782746,"version":"4.3.4"},"reference-count":41,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2023,2,16]],"date-time":"2023-02-16T00:00:00Z","timestamp":1676505600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004731","name":"Natural Science Foundation of Zhejiang Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neurorobot."],"abstract":"<jats:p>Lidar-based 3D object detection and classification is a critical task for autonomous driving. However, inferencing from exceedingly sparse 3D data in real-time is a formidable challenge. Complex-YOLO solves the problem of point cloud disorder and sparsity by projecting it onto the bird\u2019s-eye view and realizes real-time 3D object detection based on LiDAR. However, Complex-YOLO has no object height detection, a shallow network depth, and poor small-size object detection accuracy. To address these issues, this paper has made the following improvements: (1) adds a multi-scale feature fusion network to improve the algorithm\u2019s capability to detect small-size objects; (2) uses a more advanced RepVGG as the backbone network to improve network depth and overall detection performance; and (3) adds an effective height detector to the network to improve the height detection. Through experiments, we found that our algorithm\u2019s accuracy achieved good performance on the KITTI dataset, while the detection speed and memory usage were very superior, 48FPS on RTX3070Ti and 20FPS on GTX1060, with a memory usage of 841Mib.<\/jats:p>","DOI":"10.3389\/fnbot.2023.1092564","type":"journal-article","created":{"date-parts":[[2023,2,16]],"date-time":"2023-02-16T11:21:34Z","timestamp":1676546494000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":21,"title":["Efficient three-dimensional point cloud object detection based on improved Complex-YOLO"],"prefix":"10.3389","volume":"17","author":[{"given":"Yongxin","family":"Shao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhetao","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aihong","family":"Tan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianhong","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2023,2,16]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"1053124","DOI":"10.3389\/fnbot.2022.1053124","article-title":"A detection method of the rescue targets in the marine casualty based on improved YOLOv5s.","volume":"16","author":"Bai","year":"2022","journal-title":"Front. Neurorobot."},{"key":"B2","article-title":"Yolov4: Optimal speed and accuracy of object detection.","author":"Bochkovskiy","year":"2020","journal-title":"arXiv"},{"key":"B3","doi-asserted-by":"publisher","first-page":"1907","DOI":"10.1109\/CVPR.2017.691","article-title":"Multi-view 3d object detection network for autonomous driving","author":"Chen","year":"2017","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition"},{"key":"B4","doi-asserted-by":"publisher","first-page":"1030707","DOI":"10.3389\/fncom.2022.1030707","article-title":"Invariance of object detection in untrained deep neural networks.","volume":"16","author":"Cheon","year":"2022","journal-title":"Front. Comput. Neurosci."},{"key":"B5","doi-asserted-by":"publisher","first-page":"1201","DOI":"10.1609\/aaai.v35i2.16207","article-title":"Voxel r-cnn: Towards high performance voxel-based 3d object detection.","volume":"35","author":"Deng","year":"2021","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"B6","doi-asserted-by":"publisher","first-page":"13733","DOI":"10.1109\/CVPR46437.2021.01352","article-title":"Repvgg: Making vgg-style convnets great again","author":"Ding","year":"2021","journal-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition"},{"key":"B7","doi-asserted-by":"publisher","first-page":"6569","DOI":"10.1109\/ICCV.2019.00667","article-title":"Centernet: Keypoint triplets for object detection","author":"Duan","year":"2019","journal-title":"Proceedings of the IEEE\/CVF international conference on computer vision"},{"key":"B8","doi-asserted-by":"publisher","first-page":"3354","DOI":"10.1109\/CVPR.2012.6248074","article-title":"Are we ready for autonomous driving? the kitti vision benchmark suite","author":"Geiger","year":"2012","journal-title":"Proceedings of the 2012 IEEE conference on computer vision and pattern recognition"},{"key":"B9","doi-asserted-by":"publisher","first-page":"2068","DOI":"10.3390\/s22052068","article-title":"Real-time object detection and classification by UAV equipped with SAR.","volume":"22","author":"Gromada","year":"2022","journal-title":"Sensors (Basel)"},{"key":"B10","doi-asserted-by":"publisher","first-page":"770","DOI":"10.1109\/CVPR.2016.90","article-title":"Deep residual learning for image recognition","author":"He","year":"2016","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition"},{"key":"B11","doi-asserted-by":"publisher","first-page":"4700","DOI":"10.1109\/CVPR.2017.243","article-title":"Densely connected convolutional networks","author":"Huang","year":"2017","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition"},{"key":"B12","doi-asserted-by":"publisher","first-page":"1663","DOI":"10.3390\/s22041663","article-title":"Evaluation of 3D vulnerable objects\u2019 detection using a multi-sensors system for autonomous vehicles.","volume":"22","author":"Khatab","year":"2022","journal-title":"Sensors (Basel)"},{"key":"B13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/IROS.2018.8594049","article-title":"Joint 3d proposal generation and object detection from view aggregation","author":"Ku","year":"2018","journal-title":"Proceedings of the 2018 IEEE\/RSJ international conference on intelligent robots and systems (IROS)"},{"key":"B14","doi-asserted-by":"publisher","first-page":"12697","DOI":"10.1109\/CVPR.2019.01298","article-title":"Pointpillars: Fast encoders for object detection from point clouds","author":"Lang","year":"2019","journal-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition"},{"key":"B15","doi-asserted-by":"publisher","first-page":"2117","DOI":"10.1109\/CVPR.2017.106","article-title":"Feature pyramid networks for object detection","author":"Lin","year":"","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition"},{"key":"B16","doi-asserted-by":"publisher","first-page":"2980","DOI":"10.1109\/ICCV.2017.324","article-title":"Focal loss for dense object detection","author":"Lin","year":"","journal-title":"Proceedings of the IEEE international conference on computer vision"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2022.3210592","author":"Liu","year":"","journal-title":"A control strategy of robot eye-head coordinated gaze behavior achieved for minimized neural transmission noise."},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1016\/j.isatra.2022.09.002","article-title":"The opening workspace control strategy of a novel manipulator-driven emission source microscopy system.","author":"Liu","year":"","journal-title":"ISA Trans."},{"key":"B19","doi-asserted-by":"publisher","first-page":"2949","DOI":"10.1109\/ICCV48922.2021.00294","article-title":"Group-free 3d object detection via transformers","author":"Liu","year":"2021","journal-title":"Proceedings of the IEEE\/CVF international conference on computer vision"},{"key":"B20","doi-asserted-by":"publisher","first-page":"2453","DOI":"10.3390\/s22072453","article-title":"Unifying obstacle detection, recognition, and fusion based on the polarization color stereo camera and LiDAR for the ADAS.","volume":"22","author":"Long","year":"2022","journal-title":"Sensors (Basel)"},{"key":"B21","doi-asserted-by":"publisher","first-page":"2315","DOI":"10.3390\/s22062315","article-title":"SHEL5K: An extended dataset and benchmarking for safety helmet detection.","volume":"22","author":"Otgonbold","year":"2022","journal-title":"Sensors (Basel)"},{"key":"B22","doi-asserted-by":"publisher","first-page":"821","DOI":"10.1109\/CVPR.2019.00091","article-title":"Libra r-cnn: Towards balanced learning for object detection","author":"Pang","year":"2019","journal-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition"},{"key":"B23","doi-asserted-by":"publisher","first-page":"471","DOI":"10.3390\/s22020471","article-title":"High-performance image acquisition and processing for stereoscopic diagnostic systems with the application of graphical processing units.","volume":"22","author":"Perek","year":"2022","journal-title":"Sensors (Basel)"},{"key":"B24","doi-asserted-by":"publisher","first-page":"9277","DOI":"10.1109\/ICCV.2019.00937","article-title":"Deep hough voting for 3d object detection in point clouds","author":"Qi","year":"2019","journal-title":"Proceedings of the IEEE\/CVF international conference on computer vision"},{"key":"B25","first-page":"652","article-title":"Pointnet: Deep learning on point sets for 3d classification and segmentation","author":"Qi","year":"","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition"},{"key":"B26","first-page":"30","article-title":"Pointnet++: Deep hierarchical feature learning on point sets in a metric space","author":"Qi","year":"","journal-title":"Proceedings of the 31st international conference on neural information processing systems"},{"key":"B27","doi-asserted-by":"crossref","first-page":"6039","DOI":"10.1109\/LRA.2021.3089999","article-title":"Multi-sensor guided hand gesture recognition for a teleoperated robot using a recurrent neural network.","volume":"6","author":"Qi","year":"2021","journal-title":"IEEE Robot. Autom. Lett."},{"key":"B28","first-page":"7263","article-title":"YOLO9000: Better, faster, stronger","author":"Redmon","year":"2017","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition"},{"key":"B29","first-page":"91","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks.","volume":"28","author":"Ren","year":"2015","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"B30","first-page":"10529","article-title":"Pv-rcnn: Point-voxel feature set abstraction for 3d object detection","author":"Shi","year":"","journal-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition"},{"key":"B31","first-page":"2647","article-title":"From points to parts: 3d object detection from point cloud with part-aware and part-aggregation network.","volume":"43","author":"Shi","year":"","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"B32","first-page":"770","article-title":"Pointrcnn: 3d object proposal generation and detection from point cloud","author":"Shi","year":"2019","journal-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition"},{"key":"B33","doi-asserted-by":"crossref","first-page":"518","DOI":"10.3390\/s22020518","article-title":"Sym3DNet: Symmetric 3D prior network for single-view 3D reconstruction.","volume":"22","author":"Siddique","year":"2022","journal-title":"Sensors (Basel)"},{"key":"B34","first-page":"197","article-title":"Complex-yolo: An euler-region-proposal for real-time 3d object detection on point clouds","author":"Simony","year":"2018","journal-title":"Proceedings of the European conference on computer vision (ECCV) workshops"},{"key":"B35","first-page":"5998","article-title":"Attention is all you need.","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"B36","doi-asserted-by":"crossref","first-page":"1039645","DOI":"10.3389\/fpsyg.2022.1039645","article-title":"Design and implementation of real-time object detection system based on single-shoot detector and OpenCV.","volume":"13","author":"Wahab","year":"2022","journal-title":"Front. Psychol."},{"key":"B37","doi-asserted-by":"crossref","first-page":"10495","DOI":"10.3934\/math.2022585","article-title":"An intelligent recognition framework of access control system with anti-spoofing function.","volume":"7","author":"Wang","year":"2022","journal-title":"AIMS Maths."},{"key":"B38","first-page":"3","article-title":"Cbam: Convolutional block attention module","author":"Woo","year":"2018","journal-title":"Proceedings of the European conference on computer vision (ECCV)"},{"key":"B39","first-page":"1","article-title":"A novel dual-modal emotion recognition algorithm with fusing hybrid features of audio signal and speech context.","author":"Xu","year":"2022","journal-title":"Complex Intell. Syst."},{"key":"B40","doi-asserted-by":"crossref","first-page":"3337","DOI":"10.3390\/s18103337","article-title":"Second: Sparsely embedded convolutional detection.","volume":"18","author":"Yan","year":"2018","journal-title":"Sensors (Basel)"},{"key":"B41","first-page":"4490","article-title":"Voxelnet: End-to-end learning for point cloud based 3d object detection","author":"Zhou","year":"2018","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition"}],"container-title":["Frontiers in Neurorobotics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2023.1092564\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,16]],"date-time":"2023-02-16T11:21:56Z","timestamp":1676546516000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2023.1092564\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,16]]},"references-count":41,"alternative-id":["10.3389\/fnbot.2023.1092564"],"URL":"https:\/\/doi.org\/10.3389\/fnbot.2023.1092564","relation":{},"ISSN":["1662-5218"],"issn-type":[{"value":"1662-5218","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,16]]},"article-number":"1092564"}}