{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,25]],"date-time":"2025-05-25T04:04:03Z","timestamp":1748145843586,"version":"3.41.0"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"18","license":[{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100013058","name":"Jiangsu Provincial Key Research and Development Program","doi-asserted-by":"publisher","award":["U22A20100"],"award-info":[{"award-number":["U22A20100"]}],"id":[{"id":"10.13039\/501100013058","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U22A20100"],"award-info":[{"award-number":["U22A20100"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-024-19807-3","type":"journal-article","created":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T09:02:36Z","timestamp":1721034156000},"page":"19273-19288","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Vehicle-infrastructure cooperative 3D target detection based on Feature Prediction Atrous Spatial Pyramid Pooling Net"],"prefix":"10.1007","volume":"84","author":[{"given":"Shaohua","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7568-9101","authenticated-orcid":false,"given":"Yunxiang","family":"Gan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yicheng","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kecheng","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,7,15]]},"reference":[{"key":"19807_CR1","unstructured":"3D object detection based on point cloud in automatic driving scene | Multimedia Tools and Applications. Accessed: 06 Feb 2024. [Online]. Available: https:\/\/link.springer.com\/article\/10.1007\/s11042-023-15963-0"},{"key":"19807_CR2","doi-asserted-by":"crossref","unstructured":"Mao J, Shi S, Wang X, Li H (2023) 3D Object detection for autonomous driving: a comprehensive survey. arXiv. Accessed: 10 Jan 2024. [Online]. Available: http:\/\/arxiv.org\/abs\/2206.09474","DOI":"10.1007\/s11263-023-01790-1"},{"key":"19807_CR3","unstructured":"Multi-modal information fusion for LiDAR-based 3D object detection framework | Multimedia Tools and Applications. Accessed: 06 Feb 2024. [Online]. Available: https:\/\/link.springer.com\/article\/10.1007\/s11042-023-15452-4"},{"issue":"3","key":"19807_CR4","doi-asserted-by":"publisher","first-page":"1852","DOI":"10.1109\/TITS.2020.3028424","volume":"23","author":"E Arnold","year":"2022","unstructured":"Arnold E, Dianati M, De Temple R, Fallah S (2022) Cooperative perception for 3d object detection in driving scenarios using infrastructure sensors. IEEE Trans Intell Transp Syst 23(3):1852\u20131864. https:\/\/doi.org\/10.1109\/TITS.2020.3028424","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"19807_CR5","doi-asserted-by":"publisher","unstructured":"Lang AH, Vora S, Caesar H, Zhou L, Yang J, Beijbom O (2019) PointPillars: fast encoders for object detection from point clouds, in 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA: IEEE, pp. 12689\u201312697. https:\/\/doi.org\/10.1109\/CVPR.2019.01298","DOI":"10.1109\/CVPR.2019.01298"},{"key":"19807_CR6","doi-asserted-by":"crossref","unstructured":"Xu R, Xiang H, Xia X, Han X, Li J, Ma J (2022) OPV2V: An Open benchmark dataset and fusion pipeline for perception with vehicle-to-vehicle communication. arXiv. Accessed: 10 Jan 2024. [Online]. Available: http:\/\/arxiv.org\/abs\/2109.07644","DOI":"10.1109\/ICRA46639.2022.9812038"},{"key":"19807_CR7","doi-asserted-by":"crossref","unstructured":"Xu R, Xiang H, Tu Z, Xia X, Yang M-H, Ma J (2022) V2X-ViT: vehicle-to-everything cooperative perception with vision transformer. arXiv. Accessed: 10 Jan 2024. [Online]. Available: http:\/\/arxiv.org\/abs\/2203.10638","DOI":"10.1007\/978-3-031-19842-7_7"},{"key":"19807_CR8","unstructured":"Ren S, Chen S, Zhang W (2022) Collaborative perception for autonomous driving: current status and future trend. arXiv. Accessed: 20 Jan 2024. [Online]. Available: http:\/\/arxiv.org\/abs\/2208.10371"},{"key":"19807_CR9","unstructured":"Wang T-H et al (2024) V2VNet: vehicle-to-vehicle communication for joint perception and prediction. arXiv. Accessed: 10 Jan 2024. [Online]. Available: http:\/\/arxiv.org\/abs\/2008.07519"},{"key":"19807_CR10","unstructured":"Li Y, Ren S, Wu P, Chen S, Feng C, Zhang W (2022) Learning distilled collaboration graph for multi-agent perception. arXi. Accessed: 10 Jan 2024. [Online]. Available: http:\/\/arxiv.org\/abs\/2111.00643"},{"key":"19807_CR11","unstructured":"Yu H et al (2023) Vehicle-Infrastructure Cooperative 3D Object Detection via Feature Flow Prediction. arXiv. Accessed: 10 Jan 2024. [Online]. Available: http:\/\/arxiv.org\/abs\/2303.10552"},{"key":"19807_CR12","doi-asserted-by":"publisher","unstructured":"Zhao H, Jiang L, Jia J, Torr P, Koltun V (2021) Point transformer. In 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada: IEEE, pp 16239\u201316248. https:\/\/doi.org\/10.1109\/ICCV48922.2021.01595","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"19807_CR13","doi-asserted-by":"publisher","unstructured":"Qi CR, Liu W, Wu C, Su H, Guibas LJ (218) Frustum PointNets for 3D object detection from RGB-D data. In 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA: IEEE, pp 918\u2013927. https:\/\/doi.org\/10.1109\/CVPR.2018.00102","DOI":"10.1109\/CVPR.2018.00102"},{"key":"19807_CR14","doi-asserted-by":"crossref","unstructured":"Hu Q et al (2020) RandLA-Net: Efficient semantic segmentation of large-scale point clouds. arXiv. Accessed: 10 Jan 2024. [Online]. Available: http:\/\/arxiv.org\/abs\/1911.11236","DOI":"10.1109\/CVPR42600.2020.01112"},{"key":"19807_CR15","doi-asserted-by":"publisher","unstructured":"Graham B, Engelcke M, Maaten LVD (2018) 3D semantic segmentation with submanifold sparse convolutional networks. In 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA: IEEE, pp 9224\u20139232. https:\/\/doi.org\/10.1109\/CVPR.2018.00961","DOI":"10.1109\/CVPR.2018.00961"},{"key":"19807_CR16","doi-asserted-by":"crossref","unstructured":"Li J, Luo C, Yang X (2023) PillarNeXt: Rethinking network designs for 3D object detection in LiDAR point clouds. arXiv. Accessed: 10 Jan 2024. [Online]. Available: http:\/\/arxiv.org\/abs\/2305.04925","DOI":"10.1109\/CVPR52729.2023.01685"},{"key":"19807_CR17","unstructured":"Yang Z, Sun Y, Liu S, Shen X, Jia J (2018) IPOD: intensive point-based object detector for point cloud. arXiv. Accessed: 10 Jan 2024. [Online]. Available: http:\/\/arxiv.org\/abs\/1812.05276"},{"key":"19807_CR18","doi-asserted-by":"publisher","unstructured":"Yang Z, Sun Y, Liu S, Shen X, Jia J (2019) STD: Sparse-to-dense 3D object detector for point cloud. In 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), Seoul, Korea (South): IEEE, pp 1951\u20131960. https:\/\/doi.org\/10.1109\/ICCV.2019.00204","DOI":"10.1109\/ICCV.2019.00204"},{"key":"19807_CR19","doi-asserted-by":"publisher","unstructured":"Zhou Y, Tuzel O (2018) VoxelNet: End-to-end learning for point cloud based 3D object detection. In 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA: IEEE, pp 4490\u20134499. https:\/\/doi.org\/10.1109\/CVPR.2018.00472","DOI":"10.1109\/CVPR.2018.00472"},{"key":"19807_CR20","doi-asserted-by":"publisher","unstructured":"Charles RQ, Su H, Kaichun M, Guibas LJ (2017) PointNet: Deep learning on point sets for 3D classification and segmentation. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI: IEEE, pp 77\u201385. https:\/\/doi.org\/10.1109\/CVPR.2017.16","DOI":"10.1109\/CVPR.2017.16"},{"key":"19807_CR21","unstructured":"Qi CR, Yi L, Su H, Guibas LJ (2017) PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space. arXiv. Accessed: 10 Jan 2024. [Online]. Available: http:\/\/arxiv.org\/abs\/1706.02413"},{"key":"19807_CR22","doi-asserted-by":"crossref","unstructured":"Yin J, Shen J, Guan C, Zhou D, Yang R (2020) LiDAR-based online 3D video object detection with graph-based message passing and spatiotemporal transformer attention.\u201d arXiv, Apr. Accessed: 10 Jan 2024. [Online]. Available: http:\/\/arxiv.org\/abs\/2004.01389","DOI":"10.1109\/CVPR42600.2020.01151"},{"issue":"10","key":"19807_CR23","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. https:\/\/doi.org\/10.3390\/s18103337","journal-title":"Sensors"},{"key":"19807_CR24","doi-asserted-by":"publisher","unstructured":"Ye M, Xu S, Cao T (2020) HVNet: Hybrid voxel network for LiDAR based 3D object detection. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA: IEEE, pp 1628\u20131637. https:\/\/doi.org\/10.1109\/CVPR42600.2020.00170","DOI":"10.1109\/CVPR42600.2020.00170"},{"key":"19807_CR25","doi-asserted-by":"publisher","unstructured":"Shi S, Wang X, Li H (2019) PointRCNN: 3D Object proposal generation and detection from point cloud. In 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA: IEEE, pp 770\u2013779. https:\/\/doi.org\/10.1109\/CVPR.2019.00086","DOI":"10.1109\/CVPR.2019.00086"},{"key":"19807_CR26","unstructured":"Qian G et al (2022) PointNeXt: Revisiting POINTNET++ with improved training and scaling strategies. arXiv. Accessed: 10 Jan 2024. [Online]. Available: http:\/\/arxiv.org\/abs\/2206.04670"},{"key":"19807_CR27","doi-asserted-by":"crossref","unstructured":"Yang Z, Sun Y, Liu S, Jia J (2020) 3DSSD: Point-based 3D single stage object detector. arXiv. Accessed: 10 Jan 2024. [Online]. Available: http:\/\/arxiv.org\/abs\/2002.10187","DOI":"10.1109\/CVPR42600.2020.01105"},{"issue":"12","key":"19807_CR28","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1109\/MCOM.2015.7355568","volume":"53","author":"L Hobert","year":"2015","unstructured":"Hobert L, Festag A, Llatser I, Altomare L, Visintainer F, Kovacs A (2015) Enhancements of V2X communication in support of cooperative autonomous driving. IEEE Commun Mag 53(12):64\u201370. https:\/\/doi.org\/10.1109\/MCOM.2015.7355568","journal-title":"IEEE Commun Mag"},{"key":"19807_CR29","doi-asserted-by":"publisher","unstructured":"Lin T-Y, Dollar P, Girshick R, He K, Hariharan B, Belongie S (2017) Feature pyramid networks for object detection. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI: IEEE, pp 936\u2013944. https:\/\/doi.org\/10.1109\/CVPR.2017.106","DOI":"10.1109\/CVPR.2017.106"},{"key":"19807_CR30","doi-asserted-by":"publisher","unstructured":"Yu H et al (2022) DAIR-V2X: A large-scale dataset for vehicle-infrastructure cooperative 3D object detection. In 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA: IEEE, pp 21329\u201321338. https:\/\/doi.org\/10.1109\/CVPR52688.2022.02067","DOI":"10.1109\/CVPR52688.2022.02067"},{"key":"19807_CR31","doi-asserted-by":"publisher","unstructured":"Valiente R, Zaman M, Ozer S, Fallah YP (2019) Controlling steering angle for cooperative self-driving vehicles utilizing CNN and LSTM-based deep networks. In 2019 IEEE Intelligent Vehicles Symposium (IV), Paris, France: IEEE, pp 2423\u20132428. https:\/\/doi.org\/10.1109\/IVS.2019.8814260","DOI":"10.1109\/IVS.2019.8814260"},{"key":"19807_CR32","doi-asserted-by":"crossref","unstructured":"Lei Z, Ren S, Hu Y, Zhang W, Chen S (2022) Latency-Aware Collaborative Perception. arXiv. Accessed: 10 Jan 2024. [Online]. Available: http:\/\/arxiv.org\/abs\/2207.08560","DOI":"10.1007\/978-3-031-19824-3_19"},{"key":"19807_CR33","doi-asserted-by":"publisher","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, Providence, RI: IEEE, pp 3354\u20133361. https:\/\/doi.org\/10.1109\/CVPR.2012.6248074","DOI":"10.1109\/CVPR.2012.6248074"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-024-19807-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-024-19807-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-024-19807-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,24]],"date-time":"2025-05-24T10:27:44Z","timestamp":1748082464000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-024-19807-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,15]]},"references-count":33,"journal-issue":{"issue":"18","published-online":{"date-parts":[[2025,5]]}},"alternative-id":["19807"],"URL":"https:\/\/doi.org\/10.1007\/s11042-024-19807-3","relation":{},"ISSN":["1573-7721"],"issn-type":[{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2024,7,15]]},"assertion":[{"value":"6 February 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 May 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 July 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 July 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}