{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T14:50:58Z","timestamp":1784299858871,"version":"3.55.0"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031918124","type":"print"},{"value":"9783031918131","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-91813-1_2","type":"book-chapter","created":{"date-parts":[[2025,5,24]],"date-time":"2025-05-24T12:41:48Z","timestamp":1748090508000},"page":"16-33","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["RP3D: A Roadside Perception Framework for\u00a03D Object Detection via\u00a0Multi-view Sensor Fusion"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4622-3985","authenticated-orcid":false,"given":"Shaowu","family":"Zheng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0586-1195","authenticated-orcid":false,"given":"Ruyi","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5991-2421","authenticated-orcid":false,"given":"Yuan","family":"Ji","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6623-8976","authenticated-orcid":false,"given":"Ming","family":"Ye","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7493-1399","authenticated-orcid":false,"given":"Weihua","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,5,12]]},"reference":[{"issue":"3","key":"2_CR1","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.: Cooperative perception for 3D object detection in driving scenarios using infrastructure sensors. IEEE Trans. Intell. Transp. Syst. 23(3), 1852\u20131864 (2022). https:\/\/doi.org\/10.1109\/TITS.2020.3028424","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"2_CR2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3390552","author":"Z Bai","year":"2024","unstructured":"Bai, Z., et al.: Pillar attention encoder for adaptive cooperative perception. IEEE Internet Things J. (2024). https:\/\/doi.org\/10.1109\/JIOT.2024.3390552","journal-title":"IEEE Internet Things J."},{"key":"2_CR3","doi-asserted-by":"publisher","unstructured":"Carrillo, J., Waslander, S.: UrbanNet: leveraging urban maps for long range 3D object detection. In: 2021 IEEE International Intelligent Transportation Systems Conference (ITSC), pp. 3799\u20133806. IEEE (2021). https:\/\/doi.org\/10.1109\/ITSC48978.2021.9564840","DOI":"10.1109\/ITSC48978.2021.9564840"},{"key":"2_CR4","doi-asserted-by":"publisher","unstructured":"Chen, M., Wu, Y., Gao, B., Zheng, K.: Vehicle target oriented bidirectional matching handover method for multi camera on roadside. Autom. Eng. 43(10), 1435\u20131441 (2019). https:\/\/doi.org\/10.19562\/j.chinasae.qcgc.2021.10.003","DOI":"10.19562\/j.chinasae.qcgc.2021.10.003"},{"key":"2_CR5","doi-asserted-by":"publisher","unstructured":"Chen, Y., Liu, J., Zhang, X., Qi, X., Jia, J.: VoxelNeXt: fully sparse VoxelNet for 3D object detection and tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21674\u201321683 (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.02076","DOI":"10.1109\/CVPR52729.2023.02076"},{"key":"2_CR6","unstructured":"Contributors, M.: MMDetection3D: OpenMMLab next-generation platform for general 3D object detection (2020). https:\/\/github.com\/open-mmlab\/mmdetection3d"},{"key":"2_CR7","doi-asserted-by":"publisher","unstructured":"Deng, J., Shi, S., Li, P., Zhou, W., Zhang, Y., Li, H.: Voxel R-CNN: towards high performance voxel-based 3D object detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a035, pp. 1201\u20131209 (2021). https:\/\/doi.org\/10.1609\/aaai.v35i2.16207","DOI":"10.1609\/aaai.v35i2.16207"},{"key":"2_CR8","doi-asserted-by":"publisher","unstructured":"Fleck, T., Ochs, S., Zofka, M.R., Zollner, J.M.: Robust tracking of reference trajectories for autonomous driving in intelligent roadside infrastructure. In: 2020 IEEE Intelligent Vehicles Symposium (IV), pp. 1337\u20131342 (2020). https:\/\/doi.org\/10.1109\/IV47402.2020.9304620","DOI":"10.1109\/IV47402.2020.9304620"},{"key":"2_CR9","doi-asserted-by":"publisher","unstructured":"Hao, R., et al.: RCooper: a real-world large-scale dataset for roadside cooperative perception. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 22347\u201322357 (2024). https:\/\/doi.org\/10.48550\/arXiv.2403.10145","DOI":"10.48550\/arXiv.2403.10145"},{"issue":"1\u20132","key":"2_CR10","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1002\/nav.3800020109","volume":"2","author":"HW Kuhn","year":"1955","unstructured":"Kuhn, H.W.: The Hungarian method for the assignment problem. Naval Res. Logist. Q. 2(1\u20132), 83\u201397 (1955). https:\/\/doi.org\/10.1002\/nav.3800020109","journal-title":"Naval Res. Logist. Q."},{"key":"2_CR11","doi-asserted-by":"publisher","unstructured":"Lang, A.H., Vora, S., Caesar, H., Zhou, L., Yang, J., Beijbom, O.: PointPillars: fast encoders for object detection from point clouds. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12697\u201312705 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.01298","DOI":"10.1109\/CVPR.2019.01298"},{"key":"2_CR12","doi-asserted-by":"publisher","unstructured":"Li, X., Yin, J., Li, W., Xu, C., Yang, R., Shen, J.: DI-V2X: learning domain-invariant representation for vehicle-infrastructure collaborative 3d object detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 3208\u20133215 (2024). https:\/\/doi.org\/10.1609\/aaai.v38i4.28105","DOI":"10.1609\/aaai.v38i4.28105"},{"issue":"02","key":"2_CR13","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1109\/TPAMI.2018.2858826","volume":"42","author":"TY Lin","year":"2020","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Dollar, P.: Focal loss for dense object detection. IEEE Trans. Pattern Anal. Mach. Intell. 42(02), 318\u2013327 (2020). https:\/\/doi.org\/10.1109\/TPAMI.2018.2858826","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"W Liu","year":"2016","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., Berg, A.C.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21\u201337. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2"},{"key":"2_CR15","doi-asserted-by":"publisher","unstructured":"Masi, S., Xu, P., Bonnifait, P., Ieng, S.: Augmented perception with cooperative roadside vision systems for autonomous driving in complex scenarios. In: 2021 IEEE International Intelligent Transportation Systems Conference (ITSC), pp. 1140\u20131146 (2021). https:\/\/doi.org\/10.1109\/ITSC48978.2021.9564833","DOI":"10.1109\/ITSC48978.2021.9564833"},{"key":"2_CR16","unstructured":"RangiLyu: Nanodet-plus: Super fast and high accuracy lightweight anchor-free object detection model. https:\/\/github.com\/RangiLyu\/nanodet\/. Accessed 9 Sept 2022"},{"key":"2_CR17","doi-asserted-by":"publisher","unstructured":"Shi, G., Li, R., Ma, C.: PillarNet: Real-time and high-performance pillar-based 3D object detection. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol 13670, pp. 35\u201352. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20080-9_3","DOI":"10.1007\/978-3-031-20080-9_3"},{"key":"2_CR18","doi-asserted-by":"publisher","unstructured":"Shi, S., et al.: 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 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.01054","DOI":"10.1109\/CVPR42600.2020.01054"},{"issue":"2","key":"2_CR19","doi-asserted-by":"publisher","first-page":"531","DOI":"10.1007\/s11263-022-01710-9","volume":"131","author":"S Shi","year":"2023","unstructured":"Shi, S., et al.: PV-RCNN++: point-voxel feature set abstraction with local vector representation for 3d object detection. Int. J. Comput. Vision 131(2), 531\u2013551 (2023). https:\/\/doi.org\/10.1007\/s11263-022-01710-9","journal-title":"Int. J. Comput. Vision"},{"key":"2_CR20","doi-asserted-by":"publisher","unstructured":"Shi, S., Wang, X., Li, H.: PointRCNN: 3D object proposal generation and detection from point cloud. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 770\u2013779 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00086","DOI":"10.1109\/CVPR.2019.00086"},{"key":"2_CR21","doi-asserted-by":"publisher","unstructured":"Shi, S., Wang, Z., Wang, X., Li, H.: Part-A2 net: 3D part-aware and aggregation neural network for object detection from point cloud. arXiv:1907.03670, vol. 3, no. 2 (2019). https:\/\/doi.org\/10.48550\/arXiv.1907.03670","DOI":"10.48550\/arXiv.1907.03670"},{"key":"2_CR22","doi-asserted-by":"publisher","unstructured":"Sun, P., Sun, C., Wang, R., Zhao, X.: Object detection based on roadside LiDAR for cooperative driving automation: a review. Sensors 22(23) (2022). https:\/\/doi.org\/10.3390\/s22239316","DOI":"10.3390\/s22239316"},{"key":"2_CR23","unstructured":"Team, O.D.: OpenPCDet: an open-source toolbox for 3D object detection from point clouds (2020). https:\/\/github.com\/open-mmlab\/OpenPCDet"},{"key":"2_CR24","doi-asserted-by":"publisher","unstructured":"Wen, T., Xiao, Z., Jiang, K., Yang, M., Li, K., Yang, D.: High precision target positioning method for RSU in cooperative perception. In: 2019 IEEE 21st International Workshop on Multimedia Signal Processing (MMSP), pp.\u00a01\u20136 (2019). https:\/\/doi.org\/10.1109\/MMSP.2019.8901755","DOI":"10.1109\/MMSP.2019.8901755"},{"key":"2_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-01234-2_1","volume-title":"Computer Vision \u2013 ECCV 2018","author":"S Woo","year":"2018","unstructured":"Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: CBAM: convolutional block attention module. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 3\u201319. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_1"},{"key":"2_CR26","doi-asserted-by":"publisher","unstructured":"Yan, Y., Mao, Y., Li, B.: SECOND: sparsely embedded convolutional detection. Sensors 18(10), 3337 (2018). https:\/\/doi.org\/10.3390\/s18103337","DOI":"10.3390\/s18103337"},{"key":"2_CR27","doi-asserted-by":"publisher","unstructured":"Yang, H., et al.: GD-MAE: generative decoder for MAE pre-training on lidar point clouds. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9403\u20139414 (2023). https:\/\/doi.org\/10.48550\/arXiv.2212.03010","DOI":"10.48550\/arXiv.2212.03010"},{"key":"2_CR28","doi-asserted-by":"publisher","unstructured":"Yang, L., et al.: BEVHeight: a robust framework for vision-based roadside 3D object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 21611\u201321620 (2023). https:\/\/doi.org\/10.48550\/arXiv.2303.08498","DOI":"10.48550\/arXiv.2303.08498"},{"key":"2_CR29","doi-asserted-by":"publisher","unstructured":"Ye, X., et al.: Rope3D: the roadside perception dataset for autonomous driving and monocular 3D object detection task. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 21341\u201321350 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.02065","DOI":"10.1109\/CVPR52688.2022.02065"},{"key":"2_CR30","doi-asserted-by":"publisher","unstructured":"Yin, T., Zhou, X., Krahenbuhl, P.: Center-based 3D object detection and tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11784\u201311793 (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.01161","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"2_CR31","doi-asserted-by":"publisher","unstructured":"Yu, H., et\u00a0al.: DAIR-V2X: a large-scale dataset for vehicle-infrastructure cooperative 3D object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21361\u201321370 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.02067","DOI":"10.1109\/CVPR52688.2022.02067"},{"key":"2_CR32","doi-asserted-by":"publisher","unstructured":"Yu, H., et al.: V2X-seq: a large-scale sequential dataset for vehicle-infrastructure cooperative perception and forecasting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5486\u20135495 (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.00531","DOI":"10.1109\/CVPR52729.2023.00531"},{"issue":"3","key":"2_CR33","doi-asserted-by":"publisher","first-page":"408","DOI":"10.1049\/itr2.12151","volume":"16","author":"C Zhang","year":"2022","unstructured":"Zhang, C., Wei, J., Hu, A.S., Fu, P.: A novel method for calibration and verification of roadside millimetre-wave radar. IET Intel. Transp. Syst. 16(3), 408\u2013419 (2022). https:\/\/doi.org\/10.1049\/itr2.12151","journal-title":"IET Intel. Transp. Syst."},{"key":"2_CR34","doi-asserted-by":"publisher","unstructured":"Zhang, C., et al.: A roadside cooperative perception system with multi-camera fusion at an intersection. In: 2023 IEEE 26th International Conference on Intelligent Transportation Systems (ITSC), pp. 642\u2013649 (2023). https:\/\/doi.org\/10.1109\/ITSC57777.2023.10422029","DOI":"10.1109\/ITSC57777.2023.10422029"},{"key":"2_CR35","doi-asserted-by":"publisher","unstructured":"Zheng, S., Xie, C., Huang, R., Yu, S., Ye, M., Li, W.: V2X-based cooperative positioning for connected vehicles in GNSS-denied environments. In: 2023 IEEE 26th International Conference on Intelligent Transportation Systems (ITSC), pp. 4953\u20134959 (2023). https:\/\/doi.org\/10.1109\/ITSC57777.2023.10422687","DOI":"10.1109\/ITSC57777.2023.10422687"},{"key":"2_CR36","doi-asserted-by":"publisher","unstructured":"Zheng, S., Xie, C., Yu, S., Ye, M., Huang, R., Li, W.: A robust strategy for roadside cooperative perception based on multi-sensor fusion. In: 2022 International Conference on Sensing, Measurement and Data Analytics in the era of Artificial Intelligence (ICSMD), pp.\u00a01\u20136 (2022). https:\/\/doi.org\/10.1109\/ICSMD57530.2022.10058282","DOI":"10.1109\/ICSMD57530.2022.10058282"},{"key":"2_CR37","doi-asserted-by":"publisher","unstructured":"Zimmer, W., et al.: InfraDet3D: multi-modal 3D object detection based on roadside infrastructure camera and lidar sensors. In: 2023 IEEE Intelligent Vehicles Symposium (IV), pp.\u00a01\u20138 (2023). https:\/\/doi.org\/10.1109\/IV55152.2023.10186723","DOI":"10.1109\/IV55152.2023.10186723"},{"key":"2_CR38","doi-asserted-by":"publisher","unstructured":"Zimmer, W., Wardana, G.A., Sritharan, S., Zhou, X., Song, R., Knoll, A.C.: TUMTraf V2X cooperative perception dataset. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, p.\u00a010 (2024). https:\/\/doi.org\/10.48550\/arXiv.2403.01316","DOI":"10.48550\/arXiv.2403.01316"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-91813-1_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,24]],"date-time":"2025-05-24T12:41:52Z","timestamp":1748090512000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-91813-1_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031918124","9783031918131"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-91813-1_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"12 May 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}