{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T16:23:31Z","timestamp":1783614211665,"version":"3.55.0"},"reference-count":68,"publisher":"Springer Science and Business Media LLC","issue":"19","license":[{"start":{"date-parts":[[2021,7,3]],"date-time":"2021-07-03T00:00:00Z","timestamp":1625270400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,7,3]],"date-time":"2021-07-03T00:00:00Z","timestamp":1625270400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"name":"National Natural Science Foundation of China under grant agreements","award":["61973250"],"award-info":[{"award-number":["61973250"]}]},{"name":"National Natural Science Foundation of China under grant agreements","award":["61802306"],"award-info":[{"award-number":["61802306"]}]},{"name":"Talent Support Project of Science Association in Shaanxi Province","award":["20180108"],"award-info":[{"award-number":["20180108"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2021,8]]},"DOI":"10.1007\/s11042-021-11137-y","type":"journal-article","created":{"date-parts":[[2021,7,3]],"date-time":"2021-07-03T21:02:16Z","timestamp":1625346136000},"page":"29617-29641","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":33,"title":["A survey of 3D object detection"],"prefix":"10.1007","volume":"80","author":[{"given":"Wei","family":"Liang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pengfei","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2518-3416","authenticated-orcid":false,"given":"Ling","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Heng","family":"Bai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,7,3]]},"reference":[{"key":"11137_CR1","doi-asserted-by":"crossref","unstructured":"Ahmed M (2020) Density based clustering for 3d object detection in point clouds. In: Conference on computer vision and pattern recognition","DOI":"10.1109\/CVPR42600.2020.01062"},{"key":"11137_CR2","doi-asserted-by":"crossref","unstructured":"Bay H, Tuytelaars T, Van Gool LJ (2006) Surf: Speeded up robust features","DOI":"10.1007\/11744023_32"},{"key":"11137_CR3","unstructured":"Belongie S (2014) microsoft coco: Common objects in context"},{"key":"11137_CR4","doi-asserted-by":"crossref","unstructured":"Beltran J, Guindel C, Moreno FM, Cruzado D, Garcia F, De La Escalera A (2018) Birdnet: a 3d object detection framework from lidar information","DOI":"10.1109\/ITSC.2018.8569311"},{"key":"11137_CR5","unstructured":"Bo L, Yan J, Wei W, Zheng Z, Hu X (2018) High performance visual tracking with siamese region proposal network. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"11137_CR6","doi-asserted-by":"crossref","unstructured":"Caesar H, Bankiti V, Lang AH, Vora S, Beijbom O (2020) nuscenes: A multimodal dataset for autonomous driving. In: 2020 IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"11137_CR7","doi-asserted-by":"crossref","unstructured":"Cai Z, Vasconcelos N (2017) Cascade r-cnn: Delving into high quality object detection","DOI":"10.1109\/CVPR.2018.00644"},{"key":"11137_CR8","doi-asserted-by":"crossref","unstructured":"Chang J, Chen Y (2018) Pyramid stereo matching network. In: 2018 IEEE\/CVF Conference on computer vision and pattern recognition, pp 5410\u20135418","DOI":"10.1109\/CVPR.2018.00567"},{"key":"11137_CR9","doi-asserted-by":"crossref","unstructured":"Chang J, Chen Y (2018) Pyramid stereo matching network","DOI":"10.1109\/CVPR.2018.00567"},{"key":"11137_CR10","doi-asserted-by":"crossref","unstructured":"Chang A, Dai A, Funkhouser T, Halber M, Niessner M, Savva M, Song S, Zeng A, Yinda Z (2017) Matterport3D: Learning from RGB-D data in indoor environments. International Conference on 3D Vision (3DV)","DOI":"10.1109\/3DV.2017.00081"},{"key":"11137_CR11","doi-asserted-by":"crossref","unstructured":"Chen X, Kundu K, Zhu Y, Ma H, Fidler S (2018) 3d object proposals using stereo imagery for accurate object class detection. IEEE Trans Pattern Anal and Mach Intell","DOI":"10.1109\/TPAMI.2017.2706685"},{"key":"11137_CR12","doi-asserted-by":"crossref","unstructured":"Chen J, Lei Bn, Song Q, Ying H, Chen D, Wu J (2020) A hierarchical graph network for 3d object detection on point clouds. CVPR: 389\u2013398","DOI":"10.1109\/CVPR42600.2020.00047"},{"key":"11137_CR13","doi-asserted-by":"crossref","unstructured":"Chen Y, Liu S, Shen X, Jia J (2019) Fast point r-cnn","DOI":"10.1109\/ICCV.2019.00987"},{"key":"11137_CR14","doi-asserted-by":"crossref","unstructured":"Chen X, Ma H, Wan J, Li B, Xia T (2016) Multi-view 3d object detection network for autonomous driving","DOI":"10.1109\/CVPR.2017.691"},{"key":"11137_CR15","doi-asserted-by":"crossref","unstructured":"Dai A, Chang A X, Savva M, Halber M, Funkhouser T, Nie\u00dfner M (2017) Scannet Richly-annotated 3d reconstructions of indoor scenes. In: 2017 IEEE Conference on computer vision and pattern recognition (CVPR), pp 2432\u20132443","DOI":"10.1109\/CVPR.2017.261"},{"issue":"2","key":"11137_CR16","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham M, Van Gool L, Williams CKI, Winn J, Zisserman A (2010) The pascal visual object classes (voc) challenge. Int J Comput Vis 88(2):303\u2013338","journal-title":"Int J Comput Vis"},{"key":"11137_CR17","doi-asserted-by":"crossref","unstructured":"Fu H, Gong M, Wang C, Batmanghelich K, Tao D (2018) Deep ordinal regression network for monocular depth estimation","DOI":"10.1109\/CVPR.2018.00214"},{"key":"11137_CR18","unstructured":"Fu CY, Liu W, Ranga A, Tyagi A, Berg AC (2017) Dssd: Deconvolutional single shot detector"},{"key":"11137_CR19","doi-asserted-by":"crossref","unstructured":"Geiger A, Lenz P, Urtasun R (2012) Are we ready for autonomous driving? the kitti vision benchmark suite. In: IEEE conference on computer vision & pattern recognition","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"11137_CR20","doi-asserted-by":"crossref","unstructured":"Girshick R, Donahue J, Darrell T, Malik J (2013) Rich feature hierarchies for accurate object detection and semantic segmentation","DOI":"10.1109\/CVPR.2014.81"},{"key":"11137_CR21","doi-asserted-by":"crossref","unstructured":"Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation, pp 580\u2013587","DOI":"10.1109\/CVPR.2014.81"},{"key":"11137_CR22","doi-asserted-by":"crossref","unstructured":"Godard C, Aodha OM, Brostow GJ (2016) Unsupervised monocular depth estimation with left-right consistency","DOI":"10.1109\/CVPR.2017.699"},{"key":"11137_CR23","doi-asserted-by":"crossref","unstructured":"Godard C, Aodha OM, Brostow GJ (2017) Unsupervised monocular depth estimation with left-right consistency. In: Computer Vision & Pattern Recognition","DOI":"10.1109\/CVPR.2017.699"},{"key":"11137_CR24","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2015) Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans Pattern Anal Mach Intell","DOI":"10.1109\/TPAMI.2015.2389824"},{"key":"11137_CR25","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"11137_CR26","unstructured":"Jrgensen E, Zach C, Kahl F (2019) Monocular 3d object detection and box fitting trained end-to-end using intersection-over-union loss"},{"key":"11137_CR27","unstructured":"Ke NY, Sukthankar R (2004) Pca-sift: a more distinctive representation for local image descriptors. In: Proceedings of the 2004 IEEE computer society conference on computer vision and pattern recognition"},{"issue":"6","key":"11137_CR28","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","volume":"60","author":"A Krizhevsky","year":"2017","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2017) Imagenet classification with deep convolutional neural networks. Commun ACM 60(6):84\u201390","journal-title":"Commun ACM"},{"key":"11137_CR29","doi-asserted-by":"crossref","unstructured":"Lahoud J, Ghanem B (2017) 2d-driven 3d object detection in rgb-d images. In: IEEE International conference on computer vision","DOI":"10.1109\/ICCV.2017.495"},{"key":"11137_CR30","doi-asserted-by":"crossref","unstructured":"Li P, Chen X, Shen S (2019) Stereo r-cnn based 3d object detection for autonomous driving","DOI":"10.1109\/CVPR.2019.00783"},{"key":"11137_CR31","doi-asserted-by":"crossref","unstructured":"Li B, Ouyang W, Sheng L, Zeng X, Wang X (2019) Gs3d: An efficient 3d object detection framework for autonomous driving. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1019\u20131028","DOI":"10.1109\/CVPR.2019.00111"},{"key":"11137_CR32","doi-asserted-by":"crossref","unstructured":"Liang M, Yang B, Zeng W, Chen Y, Hu R, Casas S, Urtasun R (2020) Pnpnet: End-to-end perception and prediction with tracking in the loop. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 11550\u201311559","DOI":"10.1109\/CVPR42600.2020.01157"},{"issue":"99","key":"11137_CR33","first-page":"2999","volume":"PP","author":"TY Lin","year":"2017","unstructured":"Lin TY, Goyal P, Girshick R, He K, Doll\u00e1r P (2017) Focal loss for dense object detection. IEEE Trans Pattern Anal Mach Intell PP(99):2999\u20133007","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"11137_CR34","doi-asserted-by":"crossref","unstructured":"Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu C-Y, Berg AC (2016) Ssd: Single shot multibox detector. Lect. Notes Comput. Sci, pp 21\u201337","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"11137_CR35","doi-asserted-by":"crossref","unstructured":"Mayer N, Ilg E, Hausser P, Fischer P, Brox T (2016) A large dataset to train convolutional networks for disparity, optical flow, and scene flow estimation. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","DOI":"10.1109\/CVPR.2016.438"},{"key":"11137_CR36","doi-asserted-by":"crossref","unstructured":"Mousavian A, Anguelov D, Flynn J, Kosecka J (2017) 3d bounding box estimation using deep learning and geometry. In: 2017 IEEE Conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR.2017.597"},{"key":"11137_CR37","doi-asserted-by":"crossref","unstructured":"Ng M, Huo Y, Yi H, Wang Z, Shi J, Lu Z, Luo P (2020) Learning depth-guided convolutions for monocular 3d object detection. In: 2020 IEEE\/CVF conference on computer vision and pattern recognition workshops (CVPRW)","DOI":"10.1109\/CVPRW50498.2020.00508"},{"key":"11137_CR38","doi-asserted-by":"crossref","unstructured":"Pang S, Morris D, Radha H (2020) Clocs: Camera-lidar object candidates fusion for 3d object detection","DOI":"10.1109\/IROS45743.2020.9341791"},{"key":"11137_CR39","doi-asserted-by":"crossref","unstructured":"Qi CR, Liu W, Wu C, Su H, Guibas LJ (2017) Frustum pointnets for 3d object detection from rgb-d data","DOI":"10.1109\/CVPR.2018.00102"},{"key":"11137_CR40","unstructured":"Qi CR, Su H, Mo K, Guibas LJ (2016) Pointnet: Deep learning on point sets for 3d classification and segmentation"},{"key":"11137_CR41","unstructured":"Qi CR, Yi L, Su H, Guibas LJ (2017) Pointnet++: Deep hierarchical feature learning on point sets in a metric space"},{"key":"11137_CR42","doi-asserted-by":"crossref","unstructured":"Qian R, Garg D, Wang Y, You Y, Chao WL (2020) End-to-end pseudo-lidar for image-based 3d object detection. In: 2020 IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR42600.2020.00592"},{"key":"11137_CR43","doi-asserted-by":"crossref","unstructured":"Redmon J, Farhadi A (2017) Yolo9000: better, faster, stronger. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7263\u20137271","DOI":"10.1109\/CVPR.2017.690"},{"key":"11137_CR44","unstructured":"Redmon J, Farhadi A (2018) Yolov3: An incremental improvement"},{"issue":"6","key":"11137_CR45","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren S, He K, Girshick R, Sun J (2017) Faster r-cnn: Towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 39(6):1137\u20131149","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"11137_CR46","doi-asserted-by":"crossref","unstructured":"Shafiee MJ, Chywl B, Li F, Wong A (2017) Fast yolo: A fast you only look once system for real-time embedded object detection in video","DOI":"10.15353\/vsnl.v3i1.171"},{"key":"11137_CR47","doi-asserted-by":"crossref","unstructured":"Shi S, Guo C, Li J, Wang Z, Li H (2020) Pv-rcnn: Point-voxel feature set abstraction for 3d object detection. In: 2020 IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR42600.2020.01054"},{"key":"11137_CR48","doi-asserted-by":"crossref","unstructured":"Shi W, Rajkumar R (2020) Point-gnn: Graph neural network for 3d object detection in a point cloud. In: 2020 IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR42600.2020.00178"},{"key":"11137_CR49","doi-asserted-by":"crossref","unstructured":"Shi S, Wang X, Li H (2018) Pointrcnn: 3d object proposal generation and detection from point cloud","DOI":"10.1109\/CVPR.2019.00086"},{"key":"11137_CR50","doi-asserted-by":"crossref","unstructured":"Silberman N, Hoiem D, Kohli P, Fergus R (2012) Indoor segmentation and support inference from rgbd images. In: European conference on computer vision","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"11137_CR51","doi-asserted-by":"crossref","unstructured":"Sindagi VA, Zhou Y, Tuzel O (2019) Mvx-net: Multimodal voxelnet for 3d object detection","DOI":"10.1109\/ICRA.2019.8794195"},{"key":"11137_CR52","doi-asserted-by":"crossref","unstructured":"Song S, Lichtenberg SP, Xiao J (2015) Sun rgb-d: A rgb-d scene understanding benchmark suite","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"11137_CR53","doi-asserted-by":"crossref","unstructured":"Su H, Jampani V, Sun D, Maji S, Kalogerakis E, Yang M-H, Kautz J (2018) Splatnet: Sparse lattice networks for point cloud processing, pp 2530\u20132539","DOI":"10.1109\/CVPR.2018.00268"},{"key":"11137_CR54","doi-asserted-by":"crossref","unstructured":"Sun J, Chen L, Xie Y, Zhang S, Jiang Q, Zhou X, Bao H (2020) Disp r-cnn: Stereo 3d object detection via shape prior guided instance disparity estimation","DOI":"10.1109\/CVPR42600.2020.01056"},{"key":"11137_CR55","doi-asserted-by":"crossref","unstructured":"Wang Y, Chao W-L, Garg D, Hariharan B, Campbell M, Weinberger KQ (2018) Pseudo-lidar from visual depth estimation: Bridging the gap in 3d object detection for autonomous driving","DOI":"10.1109\/CVPR.2019.00864"},{"key":"11137_CR56","doi-asserted-by":"crossref","unstructured":"Wang Y, Chen X, You Y, Li E, Hariharan B, Campbell M, Weinberger KQ, Chao WL (2020) Train in Germany, test in the USA Making 3d object detectors generalize. In: 2020 IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR42600.2020.01173"},{"key":"11137_CR57","doi-asserted-by":"crossref","unstructured":"Wang X, Han TX, Yan S (2010) An hog-lbp human detector with partial occlusion handling. In: 2009 IEEE 12th international conference on computer vision","DOI":"10.1109\/ICCV.2009.5459207"},{"key":"11137_CR58","doi-asserted-by":"crossref","unstructured":"Wang Z, Jia K (2019) Frustum convnet: Sliding frustums to aggregate local point-wise features for amodal 3d object detection","DOI":"10.1109\/IROS40897.2019.8968513"},{"key":"11137_CR59","doi-asserted-by":"crossref","unstructured":"Wang X, Shrivastava A, Gupta A (2017) Hard positive generation via adversary for object detection. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","DOI":"10.1109\/CVPR.2017.324"},{"issue":"99","key":"11137_CR60","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/ACCESS.2019.2900225","volume":"PP","author":"J Wang","year":"2019","unstructured":"Wang J, Zhu M, Sun D, Bo W, Wei H (2019) Mcf3d: Multi-stage complementary fusion for multi-sensor 3d object detection. IEEE Access PP(99):1\u20131","journal-title":"IEEE Access"},{"key":"11137_CR61","unstructured":"LLC W (2019) Waymo open dataset: An autonomous driving dataset"},{"key":"11137_CR62","unstructured":"Wu Z, Song S, Khosla A, Yu F, Zhang L, Tang X, Xiao J (2015) 3d shapenets: A deep representation for volumetric shapes. In: 2015 IEEE conference on computer vision and pattern recognition (CVPR)"},{"key":"11137_CR63","doi-asserted-by":"crossref","unstructured":"Xu D, Anguelov D, Jain A (2017) Pointfusion: Deep sensor fusion for 3d bounding box estimation","DOI":"10.1109\/CVPR.2018.00033"},{"key":"11137_CR64","doi-asserted-by":"crossref","unstructured":"Xu B, Chen Z (2018) Multi-level fusion based 3d object detection from monocular images. In: 2018 IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR.2018.00249"},{"key":"11137_CR65","doi-asserted-by":"crossref","unstructured":"Yang B, Luo W, Urtasun R (2018) Pixor: Real-time 3d object detection from point clouds","DOI":"10.1109\/CVPR.2018.00798"},{"key":"11137_CR66","doi-asserted-by":"crossref","unstructured":"Zhou J, Lu X, Tan X, Shao Z, Ding S, Ma L (2019) Fvnet: 3d front-view proposal generation for real-time object detection from point clouds. arXiv:1903.10750","DOI":"10.1109\/CISP-BMEI48845.2019.8965844"},{"key":"11137_CR67","doi-asserted-by":"crossref","unstructured":"Zhou Y, Tuzel O (2017) Voxelnet: End-to-end learning for point cloud based 3d object detection","DOI":"10.1109\/CVPR.2018.00472"},{"issue":"3","key":"11137_CR68","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1016\/j.cviu.2008.08.006","volume":"113","author":"H Zhou","year":"2009","unstructured":"Zhou H, Yuan Y, Shi C (2009) Object tracking using sift features and mean shift. Computer Vision & Image Understanding 113(3):345\u2013352","journal-title":"Computer Vision & Image Understanding"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-021-11137-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-021-11137-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-021-11137-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,8,19]],"date-time":"2021-08-19T18:23:42Z","timestamp":1629397422000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-021-11137-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,3]]},"references-count":68,"journal-issue":{"issue":"19","published-print":{"date-parts":[[2021,8]]}},"alternative-id":["11137"],"URL":"https:\/\/doi.org\/10.1007\/s11042-021-11137-y","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,7,3]]},"assertion":[{"value":"27 September 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 January 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 June 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 July 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}