{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T12:28:50Z","timestamp":1776947330737,"version":"3.51.4"},"reference-count":263,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3456893","type":"journal-article","created":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T19:21:56Z","timestamp":1725996116000},"page":"173936-173980","source":"Crossref","is-referenced-by-count":42,"title":["Deep Learning Frontiers in 3D Object Detection: A Comprehensive Review for Autonomous Driving"],"prefix":"10.1109","volume":"12","author":[{"given":"Ambati","family":"Pravallika","sequence":"first","affiliation":[{"name":"Department of Electronics and Communication Engineering, National Institute of Technology Warangal, Warangal, India"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3808-9122","authenticated-orcid":false,"given":"Mohammad Farukh","family":"Hashmi","sequence":"additional","affiliation":[{"name":"Department of Electronics and Communication Engineering, National Institute of Technology Warangal, Warangal, India"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3128-2517","authenticated-orcid":false,"given":"Aditya","family":"Gupta","sequence":"additional","affiliation":[{"name":"Department of Information and Communication Technology, University of Agder, Grimstad, Norway"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3390\/machines5010006"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.113816"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.array.2021.100057"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00752"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461233"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2016.2578706"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3439557"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-023-02891-1"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2021.07.003"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3390\/electronics10040517"},{"key":"ref11","first-page":"1","article-title":"A comprehensive survey of deep learning multisensor fusion-based 3D object detection for autonomous driving: Methods, challenges, open issues, and future directions","volume":"2023","author":"Alaba","year":"2023","journal-title":"Authorea Preprints"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3390\/wevj15010020"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3390\/jimaging8090225"},{"key":"ref14","volume-title":"A comprehensive review: 3D object detection based on visible light camera, infrared camera, and LiDAR in dark scene","author":"Hussain","year":"2024"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2024.1212070"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00102"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01790-1"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2892405"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00620"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/MITS.2016.2583491"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8916872"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-023-03237-7"},{"key":"ref23","article-title":"Deep learning for 3D object detection and tracking in autonomous driving: A brief survey","author":"Peng","year":"2023","journal-title":"arXiv:2311.06043"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.14569\/IJACSA.2022.0131123"},{"key":"ref25","volume-title":"Waymo\u2019s Self-Driving Cars Are Being Put to Work in a Completely Driverless Ride-hailing Service in Phoenix","year":"2020"},{"key":"ref26","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.7326\/0003-4819-151-4-200908180-00135"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3005434"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3183889"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.16"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01298"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/SDF.2019.8916629"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00086"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00249"},{"issue":"10","key":"ref37","first-page":"3235","article-title":"A benchmarking of LiDAR sensors for outdoor environmental mapping","volume":"18","author":"Bijelic","year":"2018","journal-title":"Sensors"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01214"},{"key":"ref39","article-title":"Convolutional neural networks for depth estimation from stereo 360\u00b0 Panoramas","volume":"197","author":"Laga","year":"2020","journal-title":"Computer. Vis. Image Understand."},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-007-6046-2_108"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00783"},{"key":"ref42","first-page":"2287","article-title":"Stereo matching by training a convolutional neural network to compare image patches","volume":"17","author":"Zbontar","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref43","first-page":"1","article-title":"Pseudo-LiDAR++: Accurate depth for 3D object detection in autonomous driving","volume-title":"Proc. ICLR","author":"You"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018851"},{"key":"ref45","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Ren"},{"key":"ref46","first-page":"9906","article-title":"Pseudo-LiDAR++: Accurate depth for 3D object detection in autonomous driving","volume-title":"Proc. IEEE Int. Conf. Robot. Autom.","author":"You"},{"key":"ref47","first-page":"2540","article-title":"Robust stereo matching with surface normal prediction","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Zhu"},{"key":"ref48","volume-title":"Time-of-Flight Cameras: Principles, Methods and Applications","author":"Hansard","year":"2012"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2010.2101060"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1142\/S0217732310033943"},{"issue":"8","key":"ref51","first-page":"6283","article-title":"Depth-assisted sensor fusion for autonomous driving: A review","volume":"22","author":"Rathore","year":"2022","journal-title":"IEEE Sensors J."},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s00138-013-0570-5"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ITEC.2019.8790493"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.icte.2021.12.016"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907094"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00121"},{"key":"ref57","first-page":"133","article-title":"Deep learning based 3D object detection for automotive radar and camera","volume-title":"Proc. 16th Eur. Radar Conf. (EuRAD)","author":"Meyer"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.3390\/s22114208"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2016.2628914"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.3390\/electronics10091021"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw59228.2023.00026"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.3390\/s21062140"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2006.1638022"},{"key":"ref64","article-title":"Simultaneous depth completion and 3D object detection via deep learning for scene reconstruction in autonomous driving scenarios","author":"Bastico","year":"2021"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.3390\/s150923286"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01054"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00981"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00157"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197385"},{"key":"ref71","first-page":"4005","article-title":"Range adaptation for 3D object detection in LiDAR","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Ren"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793925"},{"key":"ref73","first-page":"10473","article-title":"Multi-modal fusion for 3D object detection and tracking","volume-title":"Proc. IEEE Int. Conf. Robot. Autom. (ICRA)","author":"Battra"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/IV47402.2020.9304681"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00382"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref77","first-page":"129","article-title":"Automotive radar dataset for deep learning based 3D object detection","volume-title":"Proc. 16th Eur. Radar Conf. (EuRAD)","author":"Meyer"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-323-85498-6.00003-4"},{"key":"ref79","article-title":"One thousand and one hours: Self-driving motion prediction dataset","author":"Houston","year":"2020","journal-title":"arXiv:2006.14480"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9565009"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/icftic59930.2023.10456265"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.614"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298706"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3317372"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00141"},{"issue":"7","key":"ref87","first-page":"4047","article-title":"Multi-task learning for dense prediction tasks: A survey","volume":"44","author":"Huang","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00099"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01549-6"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1177\/0278364916679498"},{"key":"ref91","volume-title":"Towards Persistent Localization and Mapping With a Continuous Appearance-Based Topology","author":"Agarwal","year":"2013"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.352"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.223"},{"key":"ref94","article-title":"One million scenes for autonomous driving: ONCE dataset","author":"Hu","year":"2022","journal-title":"arXiv:2205.03099"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02065"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.3390\/s19194093"},{"key":"ref97","first-page":"1","article-title":"Complex-YOLO: An euler-region-proposal for real-time 3D object detection on point clouds","volume-title":"Proc. Eur. Conf. Comput. Vis. (ECCV)","author":"Simon"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-018-6912-6"},{"key":"ref99","article-title":"An overview of 3D object detection","author":"Wang","year":"2020","journal-title":"arXiv:2010.15614"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.3390\/electronics10030279"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.597"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00217"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298800"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01105"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.3390\/s18103337"},{"key":"ref107","article-title":"Performance evaluation of object detection based on ROC curve","volume-title":"J. Phys., Conf. Ser.","volume":"887","author":"Shen"},{"key":"ref108","first-page":"1","article-title":"PointNet++: Deep hierarchical feature learning on point sets in a metric space","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Qi"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00472"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594049"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1016\/S0031-3203(96)00142-2"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00466"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.3390\/act11100272"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2018.8500454"},{"key":"ref115","article-title":"3D multi-object tracking: A baseline and new evaluation metrics","author":"Weng","year":"2019","journal-title":"arXiv:1907.03961"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-38822-5_14"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-021-06391-y"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-36868-w"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2023.10.1162"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref121","first-page":"21","article-title":"SSD: Single shoat multibox detector","volume-title":"Proc. ECCV","volume":"2016","author":"Liu"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858826"},{"key":"ref124","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017","journal-title":"arXiv:1704.04861"},{"key":"ref125","article-title":"YOLOv3: An incremental improvement","author":"Redmon","year":"2018","journal-title":"arXiv:1804.02767"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00972"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01204-1"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00094"},{"key":"ref129","article-title":"DSSD: Dense single shot detector","author":"Fu","year":"2017","journal-title":"arXiv:1704.04854"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref132","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Simonyan"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1611.05431"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2938758"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref137","first-page":"1292","article-title":"Multi-task learning for object detection in autonomous driving","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. Workshops (CVPRW)","author":"Rinchen"},{"key":"ref138","first-page":"5678","article-title":"Self-supervised learning for 3D object detection using point contrastive learning","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Karypidis"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_38"},{"issue":"5","key":"ref140","first-page":"1161","article-title":"3D object proposals for accurate object class detection","volume":"40","author":"Chen","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref141","first-page":"1","article-title":"3D object proposals for accurate object class detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"28","author":"Chen"},{"issue":"3","key":"ref142","first-page":"1041","article-title":"DeepMANTA: A multi-task network for monocular 3D object detection and tracking","volume":"28","author":"Li","year":"2019","journal-title":"IEEE Trans. Image Process."},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00938"},{"key":"ref144","first-page":"10320","article-title":"MonoGRNet: Monocular geometric reasoning network for 3D object detection","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Dubey"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00506"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01211"},{"key":"ref147","volume-title":"Towards model generalization for monocular 3d object detection","author":"Zhenyu"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_23"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1007\/s13177-014-0097-9"},{"key":"ref150","article-title":"MonoMAE: Enhancing monocular 3D detection through depth-aware masked autoencoders","author":"Jiang","year":"2024","journal-title":"arXiv:2405.07696"},{"key":"ref151","first-page":"1","article-title":"3D object detection and pose estimation using monocular images","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Ranasinghe"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.438"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00107"},{"key":"ref154","first-page":"1","article-title":"Vision transformers (ViTs) for multi-camera 3D object detection in autonomous vehicles","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Zhang"},{"key":"ref155","first-page":"1","article-title":"MDS Net: A one-stage monocular 3D object detection network for autonomous driving","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis. (ICCV)","author":"Song"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0275438"},{"key":"ref157","volume-title":"Computer Vision: Algorithms and Applications","author":"Szeliski","year":"2010"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1007\/s001380050120"},{"key":"ref159","volume-title":"Multiple View Geometry in Computer Vision","author":"Hartley","year":"2003"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.236"},{"key":"ref161","article-title":"STEREOBlackboxee: A stereo image-based 3D object detection system for autonomous vehicles","author":"Xu","year":"2020","journal-title":"arXiv:2004.08900"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00864"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01255"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3237579"},{"key":"ref165","first-page":"1","article-title":"TransFusion: Robust LiDAR-camera 3D object detection with transformer","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Wang"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00953"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.00178"},{"issue":"3","key":"ref168","first-page":"3169","article-title":"CIA-SSD: Confident IoU-aware single-stage object detector from point cloud","volume-title":"Proc. AAAI Conf. Artif. Intell.","volume":"35","author":"Yan"},{"issue":"1","key":"ref169","first-page":"1","article-title":"CenterPoint: Center-based 3D object detection and tracking","volume":"7","author":"Yan","year":"2022","journal-title":"IEEE Trans. Intell. Vehicles"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01426"},{"key":"ref171","first-page":"10629","article-title":"Voxel R-CNN: Efficient point cloud voxelization for 3D object detection","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Yang"},{"issue":"2","key":"ref172","first-page":"1","article-title":"CT3D: Contextual 3D object detection using multi-modal sensor fusion","volume":"24","author":"Cai","year":"2023","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref173","first-page":"2286","article-title":"Efficient point-GNN for real-time LiDAR 3D object detection","volume-title":"Proc. IEEE\/CVF Winter Conf. Appl. Comput. Vis. (WACV)","author":"Trilaksono"},{"key":"ref174","article-title":"MDRNet: Multi-level dimensionality reduction network for 3D object detection from point clouds","author":"Tong","year":"2204","journal-title":"arXiv:2204.04996"},{"key":"ref175","article-title":"VoxSter: A novel real-time and extended field-of-view LiDAR 3D object detection system","author":"Ibrahim","year":"2021","journal-title":"arXiv:2110.07712"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3015992"},{"key":"ref177","first-page":"472","article-title":"3D object detection from pseudo-labels and novel augmentations for autonomous driving","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. Workshops (CVPRW)","author":"Kozma"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00204"},{"key":"ref179","article-title":"TED: Tiny and efficient 3D object detection from point clouds","author":"Li","year":"2022","journal-title":"arXiv:2203.08781"},{"key":"ref180","article-title":"PLOT: Pillar-based lightweight object detection network for autonomous vehicles","author":"Zhang","year":"2022","journal-title":"arXiv:2205.08049"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.3390\/s19061434"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1117\/12.2663424"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1145\/3598151.3598182"},{"key":"ref184","article-title":"PMPF: Point-cloud multiple-pixel fusion for 3D object detection","author":"Liu","year":"2022","journal-title":"arXiv:2209.09483"},{"key":"ref185","article-title":"Cross-modal panoramic driving perception network for automotive multi-task learning","author":"Zhao","year":"2022","journal-title":"arXiv:2209.08639"},{"key":"ref186","article-title":"Multi-sensor 3D object detection for autonomous vehicles: Leveraging uncertainty propagation from sensors to predictions","author":"Hou","year":"2022","journal-title":"arXiv:2204.00826"},{"key":"ref187","article-title":"OD-C3DL: Object detection using camera and 3D LiDAR for autonomous vehicles","author":"Adekallu","year":"2022","journal-title":"arXiv:2205.14957"},{"key":"ref188","article-title":"DOPS: Fusing LiDAR and camera data for improving 3D object detection in autonomous vehicles","author":"Bhardwaj","year":"2021","journal-title":"arXiv:2110.03109"},{"key":"ref189","article-title":"MVMM: Multi-view mixture of modalities for 3D object detection","author":"Li","year":"2021","journal-title":"arXiv:2112.06924"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.3390\/wevj15070297"},{"key":"ref191","first-page":"4604","article-title":"PointPaintingNet: Sequential fusion for 3D object detection","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Vora"},{"key":"ref192","article-title":"CLRNet: Camera-LiDAR-radar multi-modal object detection for autonomous driving","author":"Li","year":"2021","journal-title":"arXiv:2111.07792"},{"key":"ref193","first-page":"641","article-title":"Deep continuous fusion for multi-sensor 3D object detection","volume-title":"Proc. Eur. Conf. Comput. Vis. (ECCV)","author":"Liang"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.3390\/wevj15050210"},{"issue":"8","key":"ref195","first-page":"5301","article-title":"Improving 3D object detection by fusion of LiDAR and IMU data","volume":"22","author":"Cheng","year":"2020","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref196","first-page":"1","article-title":"Robust LiDAR-IMU integration for autonomous driving: A GNSS-aided LiDAR-IMU calibration approach","volume-title":"Proc. IEEE Intell. Vehicles Symp. (IV)","author":"Wan"},{"key":"ref197","first-page":"1","article-title":"Detr3D: Delving into the efficient reading of 3D Siamese representations via industrial grade 3D detection networks","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Wang"},{"key":"ref198","article-title":"Cylindrical-attentional multi-view fusion for 3D object detection","author":"Zhu","year":"2022","journal-title":"arXiv:2205.07807"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.691"},{"key":"ref200","doi-asserted-by":"publisher","DOI":"10.1109\/iros45743.2020.9341791"},{"key":"ref201","first-page":"4981","article-title":"EPNet: Enhancing point features with edge representation for 3D object detection","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Zhang"},{"key":"ref202","first-page":"2980","article-title":"Focal loss for dense object detection","volume-title":"Proc. IEEE Int. Conf. Comput. Vis. (ICCV)","author":"Lambert"},{"key":"ref203","first-page":"12041","article-title":"TransFusion: Robust LiDAR-camera fusion for 3D object detection with transformers","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Shi"},{"key":"ref204","first-page":"10231","article-title":"Multi-view attention fusion network for 3D object detection","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis. (ICCV)","author":"Zhou"},{"key":"ref205","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref206","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref207","first-page":"1","article-title":"PointCNN: Convolution on X-transformed points","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Li"},{"key":"ref208","doi-asserted-by":"publisher","DOI":"10.1145\/3326362"},{"key":"ref209","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794195"},{"key":"ref210","first-page":"1","article-title":"Point-BERT: Pre-trained point cloud transformer for 3D vision","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Yu"},{"key":"ref211","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"ref212","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00315"},{"key":"ref213","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00827"},{"key":"ref214","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0271-y"},{"key":"ref215","first-page":"2377","article-title":"Training very deep networks","volume-title":"Proc. 28th Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Srivastava"},{"key":"ref216","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref217","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.667"},{"key":"ref218","first-page":"1","article-title":"Gather-excite: Exploiting feature context in convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Hu"},{"key":"ref219","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_17"},{"key":"ref220","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref221","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.683"},{"key":"ref222","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01011"},{"key":"ref223","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01644"},{"key":"ref224","article-title":"Theano: A Python framework for fast computation of mathematical expressions","author":"Theano Development Team","year":"2016","journal-title":"arXiv:1605.02688"},{"key":"ref225","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-2649-2"},{"key":"ref226","volume-title":"Deeplearning4j: Open Source Distributed Deep Learning for the JVM","year":"2016"},{"key":"ref227","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref228","volume-title":"Caffe: Deep Learning Framework","year":"2024"},{"key":"ref229","first-page":"1","article-title":"Torch7: A MATLAB-like environment for machine learning","volume-title":"Proc. NIPS Workshop","author":"Collobert"},{"key":"ref230","volume-title":"PyTorch: An Open-Source Deep Learning Framework","year":"2024"},{"key":"ref231","article-title":"TensorFlow: Large-scale machine learning on heterogeneous distributed systems","author":"Abadi","year":"2016","journal-title":"arXiv:1603.04467"},{"key":"ref232","volume-title":"Deep Learning With Keras","author":"Gulli","year":"2017"},{"key":"ref233","doi-asserted-by":"publisher","DOI":"10.1109\/ICACCCN.2018.8748442"},{"issue":"1","key":"ref234","first-page":"1235","article-title":"MLlib: Machine learning in Apache spark","volume":"17","author":"Meng","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref235","first-page":"610","article-title":"SINGA: Putting deep learning in the hands of multimedia users","volume-title":"Proc. 26th ACM Int. Conf. Multimedia","author":"Chen"},{"key":"ref236","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctvcm4g18.8"},{"key":"ref237","doi-asserted-by":"publisher","DOI":"10.3390\/s24134158"},{"key":"ref238","article-title":"MXNet: A flexible and efficient machine learning library for heterogeneous distributed systems","author":"Chen","year":"2015","journal-title":"arXiv:1512.01274"},{"key":"ref239","volume-title":"Neon: Nervana Systems\u2019 Deep Learning Framework"},{"issue":"3","key":"ref240","first-page":"67","article-title":"Pytorch: Tensors and dynamic neural networks in Python","volume":"6","author":"Paszke","year":"2017","journal-title":"PyTorch, Tensors Dyn. Neural Netw. Python Strong GPU Acceleration"},{"key":"ref241","volume-title":"CUDA Toolkit","year":"2024"},{"key":"ref242","volume-title":"cuDNN","year":"2024"},{"key":"ref243","volume-title":"TensorRT","year":"2024"},{"key":"ref244","first-page":"1135","article-title":"Learning both weights and connections for efficient neural network","volume-title":"Proc. NIPS","author":"Han"},{"key":"ref245","volume-title":"NVIDIA Jetson AGX Xavier"},{"key":"ref246","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-03888-4"},{"key":"ref247","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2020.106585"},{"key":"ref248","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460609"},{"key":"ref249","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau4984"},{"key":"ref250","article-title":"A deep learning approach to instance segmentation of indoor environment","author":"Tesse","year":"2022"},{"key":"ref251","first-page":"26066","article-title":"Revisiting 3D object detection from an egocentric perspective","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Deng"},{"key":"ref252","doi-asserted-by":"publisher","DOI":"10.3390\/s16081222"},{"key":"ref253","doi-asserted-by":"publisher","DOI":"10.3390\/app13074160"},{"key":"ref254","doi-asserted-by":"publisher","DOI":"10.3390\/s23020944"},{"key":"ref255","doi-asserted-by":"publisher","DOI":"10.1111\/mice.12625"},{"key":"ref256","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2021.638182"},{"key":"ref257","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2018.00100"},{"key":"ref258","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2016.2532924"},{"key":"ref259","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989165"},{"key":"ref260","doi-asserted-by":"publisher","DOI":"10.1109\/RTEICT52294.2021.9573964"},{"key":"ref261","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2020.103160"},{"key":"ref262","doi-asserted-by":"publisher","DOI":"10.5194\/isprsarchives-XLI-B5-961-2016"},{"key":"ref263","doi-asserted-by":"publisher","DOI":"10.1080\/24751839.2021.2008133"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10670385.pdf?arnumber=10670385","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:37:40Z","timestamp":1732667860000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10670385\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":263,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3456893","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}