{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T04:54:52Z","timestamp":1783572892611,"version":"3.55.0"},"reference-count":102,"publisher":"Springer Science and Business Media LLC","issue":"20","license":[{"start":{"date-parts":[[2021,2,25]],"date-time":"2021-02-25T00:00:00Z","timestamp":1614211200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2021,2,25]],"date-time":"2021-02-25T00:00:00Z","timestamp":1614211200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61702295"],"award-info":[{"award-number":["61702295"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"the Opening Foundation of Key Laboratory of Opto-Technology and Intelligent Control (Lanzhou Jiaotong University), The Ministry of Education","award":["KFKT2020-09"],"award-info":[{"award-number":["KFKT2020-09"]}]},{"DOI":"10.13039\/501100007129","name":"Shandong Province Natural Science Foundation","doi-asserted-by":"crossref","award":["ZR2017BF023"],"award-info":[{"award-number":["ZR2017BF023"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"crossref"}]},{"name":"The Shandong Province Postdoctoral Innovation Project","award":["201703032"],"award-info":[{"award-number":["201703032"]}]},{"name":"Shandong Province Colleges and Universities Young Talents Initiation Program","award":["2019KJN047"],"award-info":[{"award-number":["2019KJN047"]}]},{"name":"the Doctoral Fund of QUST","award":["1203043003480, 010029029"],"award-info":[{"award-number":["1203043003480, 010029029"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2021,8]]},"DOI":"10.1007\/s11042-020-10475-7","type":"journal-article","created":{"date-parts":[[2021,2,25]],"date-time":"2021-02-25T07:03:33Z","timestamp":1614236613000},"page":"31297-31334","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Efficient and accurate object detection for 3D point clouds in intelligent visual internet of things"],"prefix":"10.1007","volume":"80","author":[{"given":"Hui","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junyin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lingwei","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shujun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ye","family":"Tao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,2,25]]},"reference":[{"key":"10475_CR1","first-page":"716","volume-title":"European Conference on Computer Vision","author":"W Ali","year":"2018","unstructured":"Ali W, Abdelkarim S, Zidan M, Zahran M, El Sallab A (2018) YOLO3D: End-to-End Real-Time 3D Oriented Object Bounding Box Detection from LiDAR Point Cloud. In: European Conference on Computer Vision. Springer, Cham, pp 716\u2013728"},{"key":"10475_CR2","doi-asserted-by":"crossref","unstructured":"Asvadi A, Garrote L, Premebida C, Peixoto P, Nunes UJ (2017) Depthcn: vehicle detection using 3d-lidar and convnet. In: 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC). IEEE, pp 1\u20136","DOI":"10.1109\/ITSC.2017.8317880"},{"key":"10475_CR3","doi-asserted-by":"crossref","unstructured":"Beltr\u00e1n J, Guindel C, Moreno FM, Cruzado D, Garcia F, De La Escalera A (2018) Birdnet: a 3d object detection framework from lidar information. In: 2018 21st International Conference on Intelligent Transportation Systems (ITSC). IEEE, pp 3517\u20133523","DOI":"10.1109\/ITSC.2018.8569311"},{"key":"10475_CR4","first-page":"9287","volume-title":"Proceedings of the IEEE International Conference on Computer Vision","author":"G Brazil","year":"2019","unstructured":"Brazil G, Liu X (2019) M3d-rpn: Monocular 3d region proposal network for object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp 9287\u20139296"},{"key":"10475_CR5","unstructured":"Estrach JB, Zaremba W, Szlam A, LeCun Y (2014) Spectral networks and deep locally connected networks on graphs. In 2nd International Conference on Learning Representations, ICLR 2014"},{"key":"10475_CR6","first-page":"2040","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"F Chabot","year":"2017","unstructured":"Chabot F, Chaouch M, Rabarisoa J, Teuliere C, Chateau T (2017) Deep manta: A coarse-to-fine many-task network for joint 2d and 3d vehicle analysis from monocular image. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2040\u20132049"},{"key":"10475_CR7","first-page":"424","volume":"28","author":"X Chen","year":"2015","unstructured":"Chen X, Kundu K, Zhu Y, Berneshawi AG, Ma H, Fidler S, Urtasun R (2015) 3d object proposals for accurate object class detection. Adv Neural Inf Proces Syst 28:424\u2013432","journal-title":"Adv Neural Inf Proces Syst"},{"key":"10475_CR8","first-page":"2147","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"X Chen","year":"2016","unstructured":"Chen X, Kundu K, Zhang Z, Ma H, Fidler S, Urtasun R (2016) Monocular 3d object detection for autonomous driving. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 2147\u20132156"},{"key":"10475_CR9","first-page":"1907","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"X Chen","year":"2017","unstructured":"Chen X, Ma H, Wan J, Li B, Xia T (2017) Multi-view 3d object detection network for autonomous driving. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 1907\u20131915"},{"key":"10475_CR10","first-page":"9775","volume-title":"Proceedings of the IEEE International Conference on Computer Vision","author":"Y Chen","year":"2019","unstructured":"Chen Y, Liu S, Shen X, Jia J (2019) Fast point r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision, pp 9775\u20139784"},{"key":"10475_CR11","first-page":"5828","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"A Dai","year":"2017","unstructured":"Dai A, Chang AX, Savva M, Halber M, Funkhouser T, Nie\u00dfner M (2017) Scannet: Richly-annotated 3d reconstructions of indoor scenes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 5828\u20135839"},{"key":"10475_CR12","doi-asserted-by":"crossref","unstructured":"Deng J, Czarnecki K (2019) MLOD: A multi-view 3D object detection based on robust feature fusion method. In: 2019 IEEE Intelligent Transportation Systems Conference (ITSC). IEEE, pp 279\u2013284","DOI":"10.1109\/ITSC.2019.8917126"},{"key":"10475_CR13","first-page":"5762","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Z Deng","year":"2017","unstructured":"Deng Z, Jan Latecki L (2017) Amodal detection of 3d objects: Inferring 3d bounding boxes from 2d ones in rgb-depth images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 5762\u20135770"},{"key":"10475_CR14","doi-asserted-by":"crossref","unstructured":"Dorai C, Jain AK (1995) Cosmos-a representation scheme for free-form surfaces. In: Proceedings of IEEE International Conference on Computer Vision. IEEE, pp 1024\u20131029","DOI":"10.1109\/ICCV.1995.466822"},{"key":"10475_CR15","doi-asserted-by":"crossref","unstructured":"Du X, Ang MH, Karaman S, Rus D (2018) A general pipeline for 3d detection of vehicles. In: 2018 IEEE International Conference on Robotics and Automation (ICRA). IEEE, pp 3194\u20133200","DOI":"10.1109\/ICRA.2018.8461232"},{"key":"10475_CR16","doi-asserted-by":"crossref","unstructured":"Engelcke M, Rao D, Wang DZ, Tong CH, Posner I (2017) Vote3deep: Fast object detection in 3d point clouds using efficient convolutional neural networks. In: 2017 IEEE International Conference on Robotics and Automation (ICRA). IEEE, pp 1355\u20131361","DOI":"10.1109\/ICRA.2017.7989161"},{"key":"10475_CR17","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1109\/TIP.2020.3031371","volume":"30","author":"M Feng","year":"2020","unstructured":"Feng M, Gilani SZ, Wang Y, Zhang L, Mian A (2020) Relation graph network for 3D object detection in point clouds. IEEE Trans Image Process 30:92\u2013107","journal-title":"IEEE Trans Image Process"},{"key":"10475_CR18","doi-asserted-by":"crossref","unstructured":"Garcia-Garcia A, Gomez-Donoso F, Garcia-Rodriguez J, Orts-Escolano S, Cazorla M, Azorin-Lopez J (2016) Pointnet: A 3d convolutional neural network for real-time object class recognition. In: 2016 International Joint Conference on Neural Networks (IJCNN). IEEE, pp 1578\u20131584","DOI":"10.1109\/IJCNN.2016.7727386"},{"key":"10475_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: 2012 IEEE Conference on Computer Vision and Pattern Recognition. IEEE, pp 3354\u20133361","DOI":"10.1109\/CVPR.2012.6248074"},{"issue":"11","key":"10475_CR20","doi-asserted-by":"publisher","first-page":"1231","DOI":"10.1177\/0278364913491297","volume":"32","author":"A Geiger","year":"2013","unstructured":"Geiger A, Lenz P, Stiller C, Urtasun R (2013) Vision meets robotics: The kitti dataset. Int J Robot Res 32(11):1231\u20131237","journal-title":"Int J Robot Res"},{"key":"10475_CR21","first-page":"1440","volume-title":"Proceedings of the IEEE international conference on computer vision","author":"R Girshick","year":"2015","unstructured":"Girshick R (2015) Fast r-cnn. In: Proceedings of the IEEE international conference on computer vision, pp 1440\u20131448"},{"key":"10475_CR22","doi-asserted-by":"crossref","unstructured":"Gomez-Ojeda R, Briales J, Gonzalez-Jimenez J (2016) Pl-svo: Semi-direct monocular visual odometry by combining points and line segments. In: 2016 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, pp 4211\u20134216","DOI":"10.1109\/IROS.2016.7759620"},{"key":"10475_CR23","doi-asserted-by":"crossref","unstructured":"Gonz\u00e1lez A, Villalonga G, Xu J, V\u00e1zquez D, Amores J, L\u00f3pez AM (2015) Multiview random forest of local experts combining rgb and lidar data for pedestrian detection. In: 2015 IEEE Intelligent Vehicles Symposium (IV). IEEE, pp 356\u2013361","DOI":"10.1109\/IVS.2015.7225711"},{"issue":"11","key":"10475_CR24","doi-asserted-by":"publisher","first-page":"3980","DOI":"10.1109\/TCYB.2016.2593940","volume":"47","author":"A Gonz\u00e1lez","year":"2016","unstructured":"Gonz\u00e1lez A, V\u00e1zquez D, L\u00f3pez AM, Amores J (2016) On-board object detection: Multicue, multimodal, and multiview random forest of local experts. IEEE trans Cybern 47(11):3980\u20133990","journal-title":"IEEE trans Cybern"},{"key":"10475_CR25","first-page":"3254","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"X Gu","year":"2019","unstructured":"Gu X, Wang Y, Wu C, Lee YJ, Wang P (2019) Hplflownet: Hierarchical permutohedral lattice flownet for scene flow estimation on large-scale point clouds. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 3254\u20133263"},{"key":"10475_CR26","first-page":"345","volume-title":"European conference on computer vision","author":"S Gupta","year":"2014","unstructured":"Gupta S, Girshick R, Arbel\u00e1ez P, Malik J (2014) Learning rich features from RGB-D images for object detection and segmentation. In: European conference on computer vision. Springer, Cham, pp 345\u2013360"},{"key":"10475_CR27","first-page":"626","volume-title":"European Conference on Computer Vision","author":"I Gupta","year":"2018","unstructured":"Gupta I, Rangesh A, Trivedi M (2018) 3D Bounding Boxes for Road Vehicles: A One-Stage, Localization Prioritized Approach Using Single Monocular Images. In: European Conference on Computer Vision. Springer, Cham, pp 626\u2013641"},{"key":"10475_CR28","first-page":"8409","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"T He","year":"2019","unstructured":"He T, Soatto S (2019) Mono3d++: Monocular 3d vehicle detection with two-scale 3d hypotheses and task priors. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol 33, pp 8409\u20138416"},{"key":"10475_CR29","first-page":"4421","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"J Hou","year":"2019","unstructured":"Hou J, Dai A, Nie\u00dfner M (2019) 3d-sis: 3d semantic instance segmentation of rgb-d scans. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 4421\u20134430"},{"key":"10475_CR30","first-page":"1521","volume-title":"Proceedings of the IEEE International Conference on Computer Vision","author":"W Kehl","year":"2017","unstructured":"Kehl W, Manhardt F, Tombari F, Ilic S, Navab N (2017) Ssd-6d: Making rgb-based 3d detection and 6d pose estimation great again. In: Proceedings of the IEEE International Conference on Computer Vision, pp 1521\u20131529"},{"issue":"6","key":"10475_CR31","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":"10475_CR32","doi-asserted-by":"crossref","unstructured":"Ku J, Mozifian M, Lee J, Harakeh A, Waslander SL (2018) Joint 3d proposal generation and object detection from view aggregation. In: 2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, pp 1\u20138","DOI":"10.1109\/IROS.2018.8594049"},{"issue":"3","key":"10475_CR33","doi-asserted-by":"publisher","first-page":"704","DOI":"10.3390\/s20030704","volume":"20","author":"H Kuang","year":"2020","unstructured":"Kuang H, Wang B, An J, Zhang M, Zhang Z (2020) Voxel-FPN: Multi-Scale Voxel Feature Aggregation for 3D Object Detection from LIDAR Point Clouds. Sensors 20(3):704","journal-title":"Sensors"},{"key":"10475_CR34","first-page":"12697","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"AH Lang","year":"2019","unstructured":"Lang AH, Vora S, Caesar H, Zhou L, Yang J, Beijbom O (2019) Pointpillars: Fast encoders for object detection from point clouds. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 12697\u201312705"},{"key":"10475_CR35","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1007\/978-3-319-64689-3_8","volume-title":"International Conference on Computer Analysis of Images and Patterns","author":"FJ Lawin","year":"2017","unstructured":"Lawin FJ, Danelljan M, Tosteberg P, Bhat G, Khan FS, Felsberg M (2017) Deep projective 3D semantic segmentation. In: International Conference on Computer Analysis of Images and Patterns. Springer, Cham, pp 95\u2013107"},{"issue":"7553","key":"10475_CR36","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436\u2013444","journal-title":"Nature"},{"key":"10475_CR37","doi-asserted-by":"crossref","unstructured":"Li B (2017) 3d fully convolutional network for vehicle detection in point cloud. In: 2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, pp 1513\u20131518","DOI":"10.1109\/IROS.2017.8205955"},{"key":"10475_CR38","doi-asserted-by":"crossref","unstructured":"Li B, Zhang T, Xia T (2016) Vehicle detection from 3d lidar using fully convolutional network. arXiv preprint arXiv:1608.07916","DOI":"10.15607\/RSS.2016.XII.042"},{"key":"10475_CR39","first-page":"1019","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"B Li","year":"2019","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"},{"key":"10475_CR40","first-page":"641","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"M Liang","year":"2018","unstructured":"Liang M, Yang B, Wang S, Urtasun R (2018) Deep continuous fusion for multi-sensor 3d object detection. In: Proceedings of the European Conference on Computer Vision (ECCV), pp 641\u2013656"},{"key":"10475_CR41","first-page":"7345","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"M Liang","year":"2019","unstructured":"Liang M, Yang B, Chen Y, Hu R, Urtasun R (2019) Multi-task multi-sensor fusion for 3d object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 7345\u20137353"},{"key":"10475_CR42","first-page":"2117","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"TY Lin","year":"2017","unstructured":"Lin TY, Doll\u00e1r P, Girshick R, He K, Hariharan B, Belongie S (2017) Feature pyramid networks for object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2117\u20132125"},{"key":"10475_CR43","first-page":"21","volume-title":"European conference on computer vision","author":"W Liu","year":"2016","unstructured":"Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu CY, Berg AC (2016) Ssd: Single shot multibox detector. In: European conference on computer vision. Springer, Cham, pp 21\u201337"},{"issue":"4","key":"10475_CR44","doi-asserted-by":"publisher","first-page":"950","DOI":"10.1109\/TIM.2019.2908715","volume":"69","author":"H Liu","year":"2019","unstructured":"Liu H, Hu Q, Li B, Guo Y (2019) Robust Long-Term Tracking via Instance-Specific Proposals. IEEE Trans Instrum Meas 69(4):950\u2013962","journal-title":"IEEE Trans Instrum Meas"},{"key":"10475_CR45","first-page":"529","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"X Liu","year":"2019","unstructured":"Liu X, Qi CR, Guibas LJ (2019) Flownet3d: Learning scene flow in 3d point clouds. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 529\u2013537"},{"key":"10475_CR46","first-page":"965","volume-title":"Advances in Neural Information Processing Systems","author":"Z Liu","year":"2019","unstructured":"Liu Z, Tang H, Lin Y, Han S (2019) Point-voxel cnn for efficient 3d deep learning. In: Advances in Neural Information Processing Systems, pp 965\u2013975"},{"key":"10475_CR47","unstructured":"LLC W (2019) Waymo Open Dataset: An Autonomous Driving Dataset"},{"key":"10475_CR48","first-page":"1578","volume-title":"Proceedings of the IEEE International Conference on Computer Vision","author":"J Mao","year":"2019","unstructured":"Mao J, Wang X, Li H (2019) Interpolated convolutional networks for 3d point cloud understanding. In: Proceedings of the IEEE International Conference on Computer Vision, pp 1578\u20131587"},{"key":"10475_CR49","doi-asserted-by":"crossref","unstructured":"Maturana D, Scherer S (2015) Voxnet: A 3d convolutional neural network for real-time object recognition. In: 2015 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, pp 922\u2013928","DOI":"10.1109\/IROS.2015.7353481"},{"key":"10475_CR50","first-page":"12677","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"GP Meyer","year":"2019","unstructured":"Meyer GP, Laddha A, Kee E, Vallespi-Gonzalez C, Wellington CK (2019) Lasernet: An efficient probabilistic 3d object detector for autonomous driving. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 12677\u201312686"},{"key":"10475_CR51","first-page":"7074","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"A Mousavian","year":"2017","unstructured":"Mousavian A, Anguelov D, Flynn J, Kosecka J (2017) 3d bounding box estimation using deep learning and geometry. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 7074\u20137082"},{"key":"10475_CR52","doi-asserted-by":"crossref","unstructured":"Naiden A, Paunescu V, Kim G, Jeon B, Leordeanu M (2019) Shift R-CNN: Deep monocular 3D object detection with closed-form geometric constraints. In: 2019 IEEE International Conference on Image Processing (ICIP). IEEE, pp 61\u201365","DOI":"10.1109\/ICIP.2019.8803397"},{"key":"10475_CR53","unstructured":"Ngiam J, Caine B, Han W, Yang B, Vasudevan V et al. (2019) Starnet: Targeted computation for object detection in point clouds. arXiv preprint arXiv:1908.11069"},{"key":"10475_CR54","doi-asserted-by":"crossref","unstructured":"Paigwar A, Erkent O, Wolf C, Laugier C (2019) Attentional PointNet for 3D-Object Detection in Point Clouds. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). IEEE, pp 1297\u20131306","DOI":"10.1109\/CVPRW.2019.00169"},{"key":"10475_CR55","doi-asserted-by":"crossref","unstructured":"Park Y, Lepetit V, Woo W (2008) Multiple 3d object tracking for augmented reality. In: 2008 7th IEEE\/ACM International Symposium on Mixed and Augmented Reality. IEEE, pp 117\u2013120","DOI":"10.1109\/ISMAR.2008.4637336"},{"key":"10475_CR56","first-page":"652","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"CR Qi","year":"2017","unstructured":"Qi CR, Su H, Mo K, Guibas LJ (2017) Pointnet: Deep learning on point sets for 3d classification and segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 652\u2013660"},{"key":"10475_CR57","first-page":"5099","volume":"30","author":"CR Qi","year":"2017","unstructured":"Qi CR, Yi L, Su H, Guibas LJ (2017) Pointnet++: Deep hierarchical feature learning on point sets in a metric space. Adv Neural Inf Proces Syst 30:5099\u20135108","journal-title":"Adv Neural Inf Proces Syst"},{"key":"10475_CR58","first-page":"918","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"CR Qi","year":"2018","unstructured":"Qi CR, Liu W, Wu C, Su H, Guibas LJ (2018) Frustum pointnets for 3d object detection from rgb-d data. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 918\u2013927"},{"key":"10475_CR59","first-page":"9277","volume-title":"Proceedings of the IEEE International Conference on Computer Vision","author":"CR Qi","year":"2019","unstructured":"Qi CR, Litany O, He K, Guibas LJ (2019) Deep hough voting for 3d object detection in point clouds. In: Proceedings of the IEEE International Conference on Computer Vision, pp 9277\u20139286"},{"key":"10475_CR60","first-page":"452","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Y Rao","year":"2019","unstructured":"Rao Y, Lu J, Zhou J (2019) Spherical fractal convolutional neural networks for point cloud recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 452\u2013460"},{"key":"10475_CR61","first-page":"7263","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"J Redmon","year":"2017","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"},{"key":"10475_CR62","first-page":"779","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"J Redmon","year":"2016","unstructured":"Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: Unified, real-time object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 779\u2013788"},{"issue":"6","key":"10475_CR63","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2016","unstructured":"Ren S, He K, Girshick R, Sun J (2016) 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":"10475_CR64","first-page":"1698","volume-title":"The IEEE Winter Conference on Applications of Computer Vision","author":"X Shen","year":"2020","unstructured":"Shen X, Stamos I (2020) Frustum VoxNet for 3D object detection from RGB-D or Depth images. In: The IEEE Winter Conference on Applications of Computer Vision, pp 1698\u20131706"},{"key":"10475_CR65","first-page":"1711","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"W Shi","year":"2020","unstructured":"Shi W, Rajkumar R (2020) Point-gnn: Graph neural network for 3d object detection in a point cloud. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 1711\u20131719"},{"key":"10475_CR66","first-page":"770","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"S Shi","year":"2019","unstructured":"Shi S, Wang X, Li H (2019) Pointrcnn: 3d object proposal generation and detection from point cloud. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 770\u2013779"},{"key":"10475_CR67","first-page":"10529","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"S Shi","year":"2020","unstructured":"Shi S, Guo C, Jiang L, Wang Z, Shi J, Wang X, Li H (2020) Pv-rcnn: Point-voxel feature set abstraction for 3d object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 10529\u201310538"},{"key":"10475_CR68","doi-asserted-by":"crossref","unstructured":"Shi S, Wang Z, Shi J, Wang X, Li H (2020) From points to parts: 3d object detection from point cloud with part-aware and part-aggregation network. IEEE Transactions on Pattern Analysis and Machine Intelligence","DOI":"10.1109\/TPAMI.2020.2977026"},{"key":"10475_CR69","first-page":"746","volume-title":"European conference on computer vision","author":"N Silberman","year":"2012","unstructured":"Silberman N, Hoiem D, Kohli P, Fergus R (2012) Indoor segmentation and support inference from rgbd images. In: European conference on computer vision. Springer, Berlin, Heidelberg, pp 746\u2013760"},{"key":"10475_CR70","doi-asserted-by":"crossref","unstructured":"Simon M, Amende K, Kraus A, Honer J, S\u00e4mann T, Kaulbersch H, \u2026 Gross HM (2019) Complexer-YOLO: Real-Time 3D Object Detection and Tracking on Semantic Point Clouds. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). IEEE, pp 1190\u20131199","DOI":"10.1109\/CVPRW.2019.00158"},{"key":"10475_CR71","first-page":"808","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"S Song","year":"2016","unstructured":"Song S, Xiao J (2016) Deep sliding shapes for amodal 3d object detection in rgb-d images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 808\u2013816"},{"key":"10475_CR72","first-page":"567","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"S Song","year":"2015","unstructured":"Song S, Lichtenberg SP, Xiao J (2015) Sun rgb-d: A rgb-d scene understanding benchmark suite. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 567\u2013576"},{"issue":"2","key":"10475_CR73","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1109\/34.121785","volume":"14","author":"F Stein","year":"1992","unstructured":"Stein F, Medioni G (1992) Structural indexing: Efficient 3-D object recognition. IEEE Trans Pattern Anal Mach Intell 14(2):125\u2013145","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"10475_CR74","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1016\/j.compag.2019.01.012","volume":"157","author":"Y Tian","year":"2019","unstructured":"Tian Y, Yang G, Wang Z, Wang H, Li E, Liang Z (2019) Apple detection during different growth stages in orchards using the improved YOLOV3 model. Comput Electron Agric 157:417\u2013426","journal-title":"Comput Electron Agric"},{"key":"10475_CR75","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1016\/j.neucom.2020.05.086","volume":"411","author":"Y Tian","year":"2020","unstructured":"Tian Y, Wang K, Wang Y, Tian Y, Wang Z, Wang FY (2020) Adaptive and azimuth-aware fusion network of multimodal local features for 3D object detection. Neurocomputing 411:32\u201344","journal-title":"Neurocomputing"},{"key":"10475_CR76","doi-asserted-by":"crossref","unstructured":"Wang Z, Jia K (2019) Frustum ConvNet: Sliding Frustums to Aggregate Local Point-Wise Features for Amodal. In: 2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, pp 1742\u20131749","DOI":"10.1109\/IROS40897.2019.8968513"},{"issue":"4","key":"10475_CR77","first-page":"1","volume":"36","author":"PS Wang","year":"2017","unstructured":"Wang PS, Liu Y, Guo YX, Sun CY, Tong X (2017) O-cnn: Octree-based convolutional neural networks for 3d shape analysis. ACM Trans Graph (TOG) 36(4):1\u201311","journal-title":"ACM Trans Graph (TOG)"},{"key":"10475_CR78","first-page":"2569","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"W Wang","year":"2018","unstructured":"Wang W, Yu R, Huang Q, Neumann U (2018) Sgpn: Similarity group proposal network for 3d point cloud instance segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 2569\u20132578"},{"key":"10475_CR79","first-page":"10296","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"L Wang","year":"2019","unstructured":"Wang L, Huang Y, Hou Y, Zhang S, Shan J (2019) Graph attention convolution for point cloud semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 10296\u201310305"},{"key":"10475_CR80","doi-asserted-by":"crossref","unstructured":"Weng X, Kitani K (2019) Monocular 3D Object Detection with Pseudo-LiDAR Point Cloud. In: 2019 IEEE\/CVF International Conference on Computer Vision Workshop (ICCVW). IEEE, pp 857\u2013866","DOI":"10.1109\/ICCVW.2019.00114"},{"key":"10475_CR81","doi-asserted-by":"crossref","unstructured":"Wirges S, Fischer T, Stiller C, Frias JB (2018) Object detection and classification in occupancy grid maps using deep convolutional networks. In: 2018 21st International Conference on Intelligent Transportation Systems (ITSC). IEEE, pp 3530\u20133535","DOI":"10.1109\/ITSC.2018.8569433"},{"key":"10475_CR82","first-page":"1912","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Z Wu","year":"2015","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: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1912\u20131920"},{"key":"10475_CR83","doi-asserted-by":"crossref","unstructured":"Wu B, Wan A, Yue X, Keutzer K (2018) Squeezeseg: Convolutional neural nets with recurrent crf for real-time road-object segmentation from 3d lidar point cloud. In: 2018 IEEE International Conference on Robotics and Automation (ICRA). IEEE, pp 1887\u20131893","DOI":"10.1109\/ICRA.2018.8462926"},{"key":"10475_CR84","first-page":"9621","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"W Wu","year":"2019","unstructured":"Wu W, Qi Z, Fuxin L (2019) Pointconv: Deep convolutional networks on 3d point clouds. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 9621\u20139630"},{"key":"10475_CR85","first-page":"4606","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"S Xie","year":"2018","unstructured":"Xie S, Liu S, Chen Z, Tu Z (2018) Attentional shapecontextnet for point cloud recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 4606\u20134615"},{"key":"10475_CR86","first-page":"2345","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"B Xu","year":"2018","unstructured":"Xu B, Chen Z (2018) Multi-level fusion based 3d object detection from monocular images. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2345\u20132353"},{"key":"10475_CR87","first-page":"5363","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"D Xu","year":"2017","unstructured":"Xu D, Ouyang W, Ricci E, Wang X, Sebe N (2017) Learning cross-modal deep representations for robust pedestrian detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 5363\u20135371"},{"key":"10475_CR88","first-page":"244","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"D Xu","year":"2018","unstructured":"Xu D, Anguelov D, Jain A (2018) Pointfusion: Deep sensor fusion for 3d bounding box estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 244\u2013253"},{"key":"10475_CR89","doi-asserted-by":"crossref","unstructured":"Xu L, Wang H, Gulliver TA (2020) Outage probability performance analysis and prediction for mobile IoV networks based on ICS-BP neural network. IEEE Internet of Things Journal","DOI":"10.1109\/JIOT.2020.3023694"},{"issue":"10","key":"10475_CR90","doi-asserted-by":"publisher","first-page":"3337","DOI":"10.3390\/s18103337","volume":"18","author":"Y Yan","year":"2018","unstructured":"Yan Y, Mao Y, Li B (2018) Second: Sparsely embedded convolutional detection. Sensors 18(10):3337","journal-title":"Sensors"},{"key":"10475_CR91","doi-asserted-by":"crossref","unstructured":"Yang Z, Sun Y, Liu S, Shen X, Jia J (2018) Ipod: Intensive point-based object detector for point cloud. arXiv preprint arXiv:1812.05276","DOI":"10.1109\/ICCV.2019.00204"},{"key":"10475_CR92","unstructured":"Yang Z, Sun Y, Liu S, et al (2018) Ipod: Intensive point-based object detector for point cloud[J]. arXiv preprint arXiv:1812.05276"},{"key":"10475_CR93","first-page":"3323","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"J Yang","year":"2019","unstructured":"Yang J, Zhang Q, Ni B, Li L, Liu J, Zhou M, Tian Q (2019) Modeling point clouds with self-attention and gumbel subset sampling. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 3323\u20133332"},{"key":"10475_CR94","first-page":"1951","volume-title":"Proceedings of the IEEE International Conference on Computer Vision","author":"Z Yang","year":"2019","unstructured":"Yang Z, Sun Y, Liu S, Shen X, Jia J (2019) Std: Sparse-to-dense 3d object detector for point cloud. In: Proceedings of the IEEE International Conference on Computer Vision, pp 1951\u20131960"},{"key":"10475_CR95","first-page":"11040","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Z Yang","year":"2020","unstructured":"Yang Z, Sun Y, Liu S, Jia J (2020) 3dssd: Point-based 3d single stage object detector. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 11040\u201311048"},{"key":"10475_CR96","first-page":"1631","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"M Ye","year":"2020","unstructured":"Ye M, Xu S, Cao T (2020) HVNet: Hybrid Voxel Network for LiDAR Based 3D Object Detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 1631\u20131640"},{"key":"10475_CR97","first-page":"3947","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"L Yi","year":"2019","unstructured":"Yi L, Zhao W, Wang H, Sung M, Guibas LJ (2019) Gspn: Generative shape proposal network for 3d instance segmentation in point cloud. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3947\u20133956"},{"key":"10475_CR98","unstructured":"Zarzar J, Giancola S, Ghanem B (2019) PointRGCN: Graph convolution networks for 3D vehicles detection refinement. arXiv preprint arXiv:1911.12236"},{"issue":"4","key":"10475_CR99","doi-asserted-by":"publisher","first-page":"3434","DOI":"10.1109\/LRA.2018.2852843","volume":"3","author":"Y Zeng","year":"2018","unstructured":"Zeng Y, Hu Y, Liu S, Ye J, Han Y, Li X, Sun N (2018) Rt3d: Real-time 3-d vehicle detection in lidar point cloud for autonomous driving. IEEE Robot Automation Lett 3(4):3434\u20133440","journal-title":"IEEE Robot Automation Lett"},{"key":"10475_CR100","unstructured":"Zhi S, Liu Y, Li X, Guo Y (2017) LightNet: a lightweight 3D convolutional neural network for real-time 3D object recognition. In: Proceedings of the Workshop on 3D Object Retrieval. Eurographics Association, pp 9\u201316"},{"key":"10475_CR101","unstructured":"Zhou Y, Sun P, Zhang Y, Anguelov D, Gao J, Ouyang et al (2020) End-to-end multi-view fusion for 3d object detection in lidar point clouds. In: Conference on Robot Learning. PMLR, pp 923\u2013932"},{"key":"10475_CR102","first-page":"4490","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Y Zhou","year":"2018","unstructured":"Zhou Y, Tuzel O (2018) Voxelnet: End-to-end learning for point cloud based 3d object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 4490\u20134499"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-020-10475-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-020-10475-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-020-10475-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,29]],"date-time":"2023-01-29T16:25:00Z","timestamp":1675009500000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-020-10475-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,2,25]]},"references-count":102,"journal-issue":{"issue":"20","published-print":{"date-parts":[[2021,8]]}},"alternative-id":["10475"],"URL":"https:\/\/doi.org\/10.1007\/s11042-020-10475-7","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,2,25]]},"assertion":[{"value":"15 July 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 November 2020","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 December 2020","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 February 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}