{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T10:07:31Z","timestamp":1774519651973,"version":"3.50.1"},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2023,6,13]],"date-time":"2023-06-13T00:00:00Z","timestamp":1686614400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,6,13]],"date-time":"2023-06-13T00:00:00Z","timestamp":1686614400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Transportation Science and Technology Fund of Tianjin"},{"name":"Basic Research Fund of Central-level Nonprofit Scientific Research Institutes"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2024,1]]},"DOI":"10.1007\/s11042-023-15452-4","type":"journal-article","created":{"date-parts":[[2023,6,13]],"date-time":"2023-06-13T13:02:20Z","timestamp":1686661340000},"page":"7995-8012","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Multi-modal information fusion for LiDAR-based 3D object detection framework"],"prefix":"10.1007","volume":"83","author":[{"given":"Ruixin","family":"Ma","sequence":"first","affiliation":[]},{"given":"Yong","family":"Yin","sequence":"additional","affiliation":[]},{"given":"Jing","family":"Chen","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5384-0212","authenticated-orcid":false,"given":"Rihao","family":"Chang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,6,13]]},"reference":[{"key":"15452_CR1","doi-asserted-by":"crossref","unstructured":"Barrera A, Guindel C, Beltr\u00e1n J, Garc\u00eda F (2020) Birdnet+: end-to-end 3d object detection in lidar bird\u2019s eye view. In: 2020 IEEE 23rd international conference on intelligent transportation systems (ITSC). IEEE, pp 1\u20136","DOI":"10.1109\/ITSC45102.2020.9294293"},{"issue":"1","key":"15452_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1456650.1456651","volume":"41","author":"J Bleiholder","year":"2009","unstructured":"Bleiholder J, Naumann F (2009) Data fusion. ACM Comput Surv (CSUR) 41(1):1\u201341","journal-title":"ACM Comput Surv (CSUR)"},{"key":"15452_CR3","first-page":"81","volume":"11","author":"W Chang-jun","year":"2022","unstructured":"Chang-jun W, Cheng P, Yong L (2022) Multi-feature fusion ship target detection algorithm in complex environment. Comput Modern 11:81","journal-title":"Comput Modern"},{"issue":"10","key":"15452_CR4","doi-asserted-by":"publisher","first-page":"18855","DOI":"10.1109\/TITS.2022.3161977","volume":"23","author":"J Chen","year":"2022","unstructured":"Chen J, Wang Q, Peng W, Xu H, Li X, Xu W (2022) Disparity-based multiscale fusion network for transportation detection. IEEE Trans Intell Transp Syst 23(10):18855\u201318863","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"15452_CR5","doi-asserted-by":"crossref","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","DOI":"10.1109\/CVPR.2017.691"},{"key":"15452_CR6","unstructured":"Collignon A, Maes F, Delaere D, Vandermeulen D, Suetens P, Marchal G (1995) Automated multi-modality image registration based on information theory. In: Information processing in medical imaging, vol 3, pp 263\u2013274"},{"key":"15452_CR7","doi-asserted-by":"crossref","unstructured":"da Silva BRF, Nogueira M B, Alsina P J, de Albuquerque GLA, Dantas Jo ao BD, de Medeiros Adelardo AD, Santiago G S (2017) Study on detection of boats using satellite imagery for use on unmanned aerial vehicles. In: 2017 Latin American robotics symposium (LARS) and 2017 Brazilian symposium on robotics (SBR). IEEE, pp 1\u20135","DOI":"10.1109\/SBR-LARS-R.2017.8215300"},{"issue":"12","key":"15452_CR8","doi-asserted-by":"publisher","first-page":"1925","DOI":"10.1109\/LGRS.2016.2618604","volume":"13","author":"H Dai","year":"2016","unstructured":"Dai H, Du L, Wang Y, Wang Z (2016) A modified cfar algorithm based on object proposals for ship target detection in sar images. IEEE Geosci Remote Sens Lett 13(12):1925\u20131929","journal-title":"IEEE Geosci Remote Sens Lett"},{"key":"15452_CR9","doi-asserted-by":"crossref","unstructured":"Engelcke M, Rao D, Wang D Z, Tong C H, 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":"15452_CR10","doi-asserted-by":"crossref","unstructured":"Fan L, Xiong X, Wang F, Wang N, Zhang Z (2021) Rangedet: in defense of range view for lidar-based 3d object detection. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 2918\u20132927","DOI":"10.1109\/ICCV48922.2021.00291"},{"key":"15452_CR11","unstructured":"Ge Z, Liu S, Wang F, Li Z, Sun J (2021) Yolox: exceeding yolo series in 2021. arXiv:2107.08430"},{"issue":"11","key":"15452_CR12","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":"15452_CR13","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"},{"key":"15452_CR14","doi-asserted-by":"crossref","unstructured":"Girshick R (2015) Fast r-cnn. In: Proceedings of the IEEE international conference on computer vision, pp 1440\u20131448","DOI":"10.1109\/ICCV.2015.169"},{"key":"15452_CR15","doi-asserted-by":"crossref","unstructured":"Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 580\u2013587","DOI":"10.1109\/CVPR.2014.81"},{"key":"15452_CR16","doi-asserted-by":"crossref","unstructured":"Gonz\u00e1lez A, Villalonga G, Xu J, V\u00e1zquez D, Amores J, L\u00f3pez A M (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"},{"key":"15452_CR17","doi-asserted-by":"crossref","unstructured":"He K, Gkioxari G, Doll\u00e1r P, Girshick R (2017) Mask r-cnn. In: Proceedings of the IEEE international conference on computer vision, pp 2961\u20132969","DOI":"10.1109\/ICCV.2017.322"},{"key":"15452_CR18","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"issue":"9","key":"15452_CR19","first-page":"1841","volume":"43","author":"J Huang","year":"2017","unstructured":"Huang J, Jiang Z, Zhang H, Yao Y (2017) Ship object detection in remote sensing images using convolutional neural networks. Journal of Beijing University of Aeronautics and Astronautics 43(9):1841","journal-title":"Journal of Beijing University of Aeronautics and Astronautics"},{"key":"15452_CR20","doi-asserted-by":"crossref","unstructured":"Kidono K, Naito T, Miura J (2012) Reliable pedestrian recognition combining high-definition lidar and vision data. In: 2012 15th International IEEE conference on intelligent transportation systems. IEEE, pp 1783\u20131788","DOI":"10.1109\/ITSC.2012.6338657"},{"key":"15452_CR21","doi-asserted-by":"crossref","unstructured":"K\u00f6nigshof H, Salscheider N O, Stiller C (2019) Realtime 3d object detection for automated driving using stereo vision and semantic information. In: 2019 IEEE Intelligent transportation systems conference (ITSC). IEEE, pp 1405\u20131410","DOI":"10.1109\/ITSC.2019.8917330"},{"key":"15452_CR22","doi-asserted-by":"crossref","unstructured":"K\u00f6nigshof H, Stiller C (2020) Learning-based shape estimation with grid map patches for realtime 3d object detection for automated driving. In: 2020 IEEE 23rd International conference on intelligent transportation systems (ITSC), pp 1\u20136","DOI":"10.1109\/ITSC45102.2020.9294743"},{"key":"15452_CR23","unstructured":"Krizhevsky A, Sutskever I, Hinton G E (2012) Imagenet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems, 25"},{"key":"15452_CR24","doi-asserted-by":"crossref","unstructured":"Li S, Liu Z, Shen Z, Cheng K-T (2022) Stereo neural vernier caliper. In: AAAI Conference on artificial intelligence","DOI":"10.1609\/aaai.v36i2.20026"},{"key":"15452_CR25","unstructured":"Li Y, Bu R, Sun M, Wu W, Di X, Chen B (2018) Pointcnn: convolution on x-transformed points. Advances in Neural Information Processing Systems, 31"},{"key":"15452_CR26","doi-asserted-by":"crossref","unstructured":"Lin T-Y, 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","DOI":"10.1109\/CVPR.2017.106"},{"key":"15452_CR27","doi-asserted-by":"crossref","unstructured":"Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu C-Y, Berg A C (2016) Ssd: single shot multibox detector. In: European conference on computer vision. Springer, pp 21\u201337","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"15452_CR28","doi-asserted-by":"crossref","unstructured":"Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z, Lin S, Guo B (2021) Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 10012\u201310022","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"15452_CR29","doi-asserted-by":"crossref","unstructured":"Ma R, Yin Y, Li Z, Chen J, Bao K (2020) Research on active intelligent perception technology of vessel situation based on multisensor fusion. Math Probl Eng, 2020","DOI":"10.1155\/2020\/9146727"},{"key":"15452_CR30","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1016\/j.inffus.2019.12.001","volume":"57","author":"T Meng","year":"2020","unstructured":"Meng T, Jing X, Yan Z, Pedrycz W (2020) A survey on machine learning for data fusion. Inform Fus 57:115\u2013129","journal-title":"Inform Fus"},{"key":"15452_CR31","doi-asserted-by":"publisher","first-page":"28","DOI":"10.2112\/SI73-006.1","volume":"73","author":"C Mi","year":"2015","unstructured":"Mi C, Shen Y, Mi W, Huang Y (2015) Ship identification algorithm based on 3d point cloud for automated ship loaders. J Coastal Res 73:28\u201334","journal-title":"J Coastal Res"},{"key":"15452_CR32","doi-asserted-by":"crossref","unstructured":"Nie W, Ren M, Liu A, Mao Z, Nie J (2020) M-gcn: multi-branch graph convolution network for 2d image-based on 3d model retrieval. IEEE Trans Multimedia","DOI":"10.1109\/TMM.2020.3006371"},{"key":"15452_CR33","doi-asserted-by":"crossref","unstructured":"Nie W, Ren M, Nie J, Zhao S (2020) C-gcn: correlation based graph convolutional network for audio-video emotion recognition. IEEE Trans Multimedia","DOI":"10.1109\/TMM.2020.3032037"},{"issue":"9","key":"15452_CR34","first-page":"2561","volume":"40","author":"X Nie","year":"2020","unstructured":"Nie X, Liu W, Wu W (2020) Ship detection based on enhanced yolov3 under complex environments. J Comput Applic 40(9):2561","journal-title":"J Comput Applic"},{"key":"15452_CR35","unstructured":"Qi C R, Su H, Mo K, Guibas L J (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":"15452_CR36","doi-asserted-by":"crossref","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","DOI":"10.1109\/CVPR.2016.91"},{"key":"15452_CR37","unstructured":"Ren S, He K, Girshick R, Sun J (2015) Faster r-cnn: towards real-time object detection with region proposal networks. arXiv:1506.01497"},{"key":"15452_CR38","doi-asserted-by":"crossref","unstructured":"Simon M, Amende K, Kraus A, Honer J, Samann T, Kaulbersch H, Milz S, Michael Gross H (2019) Complexer-yolo: real-time 3d object detection and tracking on semantic point clouds. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition workshops, pp 0\u20130","DOI":"10.1109\/CVPRW.2019.00158"},{"key":"15452_CR39","doi-asserted-by":"crossref","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","DOI":"10.1109\/CVPR.2016.94"},{"key":"15452_CR40","doi-asserted-by":"crossref","unstructured":"Tulldahl H M, Pettersson M (2007) Lidar for shallow underwater target detection. In: Electro-optical remote sensing, detection, and photonic technologies and their applications, vol 6739. International Society for Optics and Photonics, p 673906","DOI":"10.1117\/12.737872"},{"issue":"6","key":"15452_CR41","doi-asserted-by":"publisher","first-page":"620","DOI":"10.3390\/rs11060620","volume":"11","author":"J Wang","year":"2019","unstructured":"Wang J, Zheng T, Lei P, Bai X (2019) A hierarchical convolution neural network (cnn)-based ship target detection method in spaceborne sar imagery. Rem Sens 11(6):620","journal-title":"Rem Sens"},{"issue":"5","key":"15452_CR42","doi-asserted-by":"publisher","first-page":"057207","DOI":"10.1117\/1.3578402","volume":"50","author":"J Wu","year":"2011","unstructured":"Wu J, Mao S, Wang X, Zhang T (2011) Ship target detection and tracking in cluttered infrared imagery. Opt Eng 50(5):057207","journal-title":"Opt Eng"},{"key":"15452_CR43","unstructured":"You Y, Wang Y, Chao W-L, Garg D, Pleiss G, Hariharan B, Campbell M, Weinberger K Q (2020) Pseudo-lidar++: accurate depth for 3d object detection in autonomous driving. In: International conference on learning representations (ICLR)"},{"key":"15452_CR44","doi-asserted-by":"publisher","first-page":"214","DOI":"10.1016\/j.neuroimage.2014.12.061","volume":"108","author":"W Zhang","year":"2015","unstructured":"Zhang W, Li R, Deng H, Wang L, Lin W, Ji S, Shen D (2015) Deep convolutional neural networks for multi-modality isointense infant brain image segmentation. Neuroimage 108:214\u2013224","journal-title":"Neuroimage"},{"key":"15452_CR45","doi-asserted-by":"crossref","unstructured":"Zhang W, Zhou H, Sun S, Wang Z, Shi J, Loy C C (2019) Robust multi-modality multi-object tracking. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 2365\u20132374","DOI":"10.1109\/ICCV.2019.00245"},{"issue":"12","key":"15452_CR46","doi-asserted-by":"publisher","first-page":"2002","DOI":"10.3390\/rs10122002","volume":"10","author":"Y Zhang","year":"2018","unstructured":"Zhang Y, Xiong W, Dong X, Hu C, Sun Y (2018) Grft-based moving ship target detection and imaging in geosynchronous sar. Rem Sens 10 (12):2002","journal-title":"Rem Sens"},{"key":"15452_CR47","doi-asserted-by":"publisher","first-page":"100004","DOI":"10.1016\/j.array.2019.100004","volume":"3","author":"T Zhou","year":"2019","unstructured":"Zhou T, Ruan S, Canu S (2019) A review: deep learning for medical image segmentation using multi-modality fusion. Array 3:100004","journal-title":"Array"},{"key":"15452_CR48","doi-asserted-by":"crossref","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","DOI":"10.1109\/CVPR.2018.00472"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-15452-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-023-15452-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-15452-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,8]],"date-time":"2024-01-08T07:26:35Z","timestamp":1704698795000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-023-15452-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,13]]},"references-count":48,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2024,1]]}},"alternative-id":["15452"],"URL":"https:\/\/doi.org\/10.1007\/s11042-023-15452-4","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,13]]},"assertion":[{"value":"15 April 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 January 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 April 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 June 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}