{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T15:54:25Z","timestamp":1791474865888,"version":"4.3.4"},"reference-count":33,"publisher":"Public Library of Science (PLoS)","issue":"6","license":[{"start":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T00:00:00Z","timestamp":1750982400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Open Project of Shandong Key Laboratory of Smart Transportation","award":["2021SDKLST004"],"award-info":[{"award-number":["2021SDKLST004"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["52472337 and 52302491"],"award-info":[{"award-number":["52472337 and 52302491"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2023T160129"],"award-info":[{"award-number":["2023T160129"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Research Funds for the Interdisciplinary Projects, CHU","award":["300104240911"],"award-info":[{"award-number":["300104240911"]}]},{"DOI":"10.13039\/501100017596","name":"Natural Science Basic Research Program of Shaanxi Province","doi-asserted-by":"publisher","award":["2023-JC-YB-523"],"award-info":[{"award-number":["2023-JC-YB-523"]}],"id":[{"id":"10.13039\/501100017596","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100015401","name":"Key Research and Development Program of Shaanxi","doi-asserted-by":"crossref","award":["2023-YBGY-119"],"award-info":[{"award-number":["2023-YBGY-119"]}],"id":[{"id":"10.13039\/501100015401","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Key Science and Technology Project of Ministry of Transport","award":["2022-ZD6-079"],"award-info":[{"award-number":["2022-ZD6-079"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Aiming at the problem that small and irregular detection targets such as cyclists have low detection accuracy and inaccurate recognition by existing 3D target detection algorithms, MAT-PointPillars (Multi-scale Attention and Transformer PointPillars), a 3D object detection algorithm, extends PointPillars with multi-scale vision Transformers and attention mechanisms. First, the algorithm employs pillar coding for semantic point cloud encoding and introduces an attention mechanism to refine the backbone\u2019s upsampling process. Furthermore, the Transformer Encoder is introduced to improve the upsampling structure of the third stage of the backbone. On the KITTI dataset, our algorithm achieved 3D average detection accuracy (AP3D) of 81.15%, 62.02%, and 58.68% across three difficulty levels. Compared with the baseline model, the proposed algorithm improves AP3D by 2.44%, 1.19%, and 1.23% respectively. The real-time 3D object detection system is built based on ROS, and average running frames per second of the system is 22.63, which is higher than the sampling frequency of conventional LiDAR. By ensuring sufficient detection speed, the MAT-PointPillars algorithm can increase detection accuracy of cyclists in real-world scenarios.<\/jats:p>","DOI":"10.1371\/journal.pone.0325373","type":"journal-article","created":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T17:52:08Z","timestamp":1751046728000},"page":"e0325373","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":2,"title":["MAT-PointPillars: Enhanced PointPillars algorithm based on multi-scale attention mechanisms and transformer"],"prefix":"10.1371","volume":"20","author":[{"given":"Xinpeng","family":"Yao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2989-6322","authenticated-orcid":true,"given":"Peiyuan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingmei","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zijian","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Songhua","family":"Fan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuchen","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,6,27]]},"reference":[{"key":"pone.0325373.ref001","first-page":"259","article-title":"A survey on 3D object detection methods based on LiDAR point clouds","volume":"50","author":"J Qing","year":"2023","journal-title":"Computer Sci"},{"key":"pone.0325373.ref002","doi-asserted-by":"crossref","unstructured":"Yang Z, Sun Y, Liu S, Jia J. 3DSSD: point-based 3D single stage object detector. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. Seattle, DC, USA; 2020: 11040\u20138.","DOI":"10.1109\/CVPR42600.2020.01105"},{"key":"pone.0325373.ref003","doi-asserted-by":"crossref","unstructured":"Shi S, Guo C, Jiang L, Wang Z, Shi J, Wang X. PV-RCNN: point-voxel feature set abstraction for 3D object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. Seattle, WA, USA; 2020: 10529\u201338.","DOI":"10.1109\/CVPR42600.2020.01054"},{"key":"pone.0325373.ref004","doi-asserted-by":"crossref","first-page":"108954","DOI":"10.1016\/j.patcog.2022.108954","article-title":"Towards generalizable person re-identification with a bi-stream generative model","volume":"132","author":"X Xu","year":"2022","journal-title":"Pattern Recognition"},{"issue":"10","key":"pone.0325373.ref005","doi-asserted-by":"crossref","first-page":"105023","DOI":"10.1088\/1361-6501\/ad633d","article-title":"Enhanced feature extraction YOLO industrial small object detection algorithm based on receptive-field attention and multi-scale features","volume":"35","author":"H Tao","year":"2024","journal-title":"Meas Sci Technol"},{"key":"pone.0325373.ref006","doi-asserted-by":"crossref","first-page":"419","DOI":"10.1016\/j.isatra.2024.12.023","article-title":"End-to-end multi-scale residual network with parallel attention mechanism for fault diagnosis under noise and small samples","volume":"157","author":"Y Sun","year":"2025","journal-title":"ISA Trans"},{"key":"pone.0325373.ref007","unstructured":"Qi CR, Su H, Mo K, Guibas LJ. PointNet: deep learning on point sets for 3D classification and segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI, USA; 2017: 652\u201360."},{"key":"pone.0325373.ref008","unstructured":"Qi CR, Yi L, Su H, Guibas LJ. PointNet: deep hierarchical feature learning on point sets in a metric space. In: Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook, NY, USA; 2017: 5105\u201314."},{"key":"pone.0325373.ref009","doi-asserted-by":"crossref","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. Long Beach, CA, USA; 2019: 770\u20139.","DOI":"10.1109\/CVPR.2019.00086"},{"key":"pone.0325373.ref010","doi-asserted-by":"crossref","unstructured":"Yang Z, Sun Y, Liu S, Shen X, Jia J. STD: Sparse-to-dense 3D object detector for point cloud. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV). 2019: 1951\u201360.","DOI":"10.1109\/ICCV.2019.00204"},{"key":"pone.0325373.ref011","doi-asserted-by":"crossref","unstructured":"Zhou Y, Tuzel O. VoxelNet: end-to-end learning for point cloud based 3D object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City, UT, USA; 2018: 4490\u20139.","DOI":"10.1109\/CVPR.2018.00472"},{"issue":"2","key":"pone.0325373.ref012","doi-asserted-by":"crossref","first-page":"1201","DOI":"10.1609\/aaai.v35i2.16207","article-title":"Voxel R-CNN: towards high performance voxel-based 3D object detection","volume":"35","author":"J Deng","year":"2021","journal-title":"AAAI"},{"issue":"10","key":"pone.0325373.ref013","doi-asserted-by":"crossref","first-page":"3337","DOI":"10.3390\/s18103337","article-title":"SECOND: sparsely embedded convolutional detection","volume":"18","author":"Y Yan","year":"2018","journal-title":"Sensors (Basel)"},{"key":"pone.0325373.ref014","doi-asserted-by":"crossref","unstructured":"Li J, Luo C, Yang X. PillarNeXt: rethinking network designs for 3D object detection in LiDAR point clouds. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2023: 17567\u201376. doi: 10.1109\/cvpr52729.2023.01685","DOI":"10.1109\/CVPR52729.2023.01685"},{"key":"pone.0325373.ref015","doi-asserted-by":"crossref","unstructured":"Lang AH, 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. Long Beach, CA, USA; 2019: 12697\u2013705.","DOI":"10.1109\/CVPR.2019.01298"},{"key":"pone.0325373.ref016","first-page":"1","article-title":"PointPillars: Improvement method based on density clustering and dual attention mechanism","author":"QX Yang","year":"2024","journal-title":"Laser Optoelectronics Progress"},{"key":"pone.0325373.ref017","doi-asserted-by":"crossref","unstructured":"Chen X, Ma H, Wan J, Li B, Xia T. Multi-view 3D object detection network for autonomous driving. In: Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI, USA; 2017: 6526\u201334.","DOI":"10.1109\/CVPR.2017.691"},{"key":"pone.0325373.ref018","doi-asserted-by":"crossref","unstructured":"Ku J, Mozifian M, Lee J, Harakeh A, Waslander SL. Joint 3D proposal generation and object detection from view aggregation. In: Proceedings of the 2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems. Madrid, Spain; 2018: 1\u20138.","DOI":"10.1109\/IROS.2018.8594049"},{"key":"pone.0325373.ref019","doi-asserted-by":"crossref","unstructured":"Liang M, Yang B, Chen Y, Hu R, Urtasun R. Multi-task multi-sensor fusion for 3D object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, CA, USA; 2019: 7345\u201353.","DOI":"10.1109\/CVPR.2019.00752"},{"key":"pone.0325373.ref020","doi-asserted-by":"crossref","unstructured":"Liang M, Yang B, Wang S, Urtasun R. Deep continuous fusion for multi-sensor 3D object detection. In: Proceedings of the European Conference on Computer Vision. Munich, Germany; 2018: 641\u201356.","DOI":"10.1007\/978-3-030-01270-0_39"},{"key":"pone.0325373.ref021","doi-asserted-by":"crossref","unstructured":"Qi CR, Liu W, Wu C, Su H, Guibas LJ. Frustum PointNets for 3D object detection from RGB-D data. In: Proceedings of the 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Salt Lake City, UT, USA: 2018: 918\u201327.","DOI":"10.1109\/CVPR.2018.00102"},{"key":"pone.0325373.ref022","doi-asserted-by":"crossref","unstructured":"Xu D, Anguelov D, Jain A. PointFusion: deep sensor fusion for 3D bounding box estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, UT, USA; 2018: 244\u201353.","DOI":"10.1109\/CVPR.2018.00033"},{"key":"pone.0325373.ref023","doi-asserted-by":"crossref","unstructured":"Paigwar A, Sierra-Gonzalez D, Erkent \u00d6. Frustum-PointPillars: a multi-stage approach for 3D object detection using RGB camera and LiDAR. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. Montreal, BC, Canada; 2021: 2926\u201333.","DOI":"10.1109\/ICCVW54120.2021.00327"},{"key":"pone.0325373.ref024","first-page":"492","article-title":"3D object detection method for autonomous vehicle based on sparse color point cloud","volume":"43","author":"Y Luo","year":"2021","journal-title":"Automotive Engineering"},{"key":"pone.0325373.ref025","first-page":"268","article-title":"An attention-based PointPillars 3D object detection","volume":"41","author":"W Zhan","year":"2020","journal-title":"J Jiangsu University (Natural Science Edition)"},{"issue":"10","key":"pone.0325373.ref026","first-page":"1028012","article-title":"Lidar 3D target detection based on improved PointPillars","volume":"60","author":"D Chen","year":"2023","journal-title":"Laser Optoelectronics Progress"},{"key":"pone.0325373.ref027","doi-asserted-by":"crossref","unstructured":"Liu Z, Lin Y, Cao Y. Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. Montreal, QC, Canada; 2021: 10012\u201322.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"pone.0325373.ref028","doi-asserted-by":"crossref","unstructured":"Woo S, Park J, Lee JY, Kweon IS. CBAM: convolutional block attention module. In: Proceedings of the European Conference on Computer Vision. Munich, Germany; 2018: 3\u201319.","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"pone.0325373.ref029","doi-asserted-by":"crossref","unstructured":"Hou Q, Zhou D, Feng J. Coordinate attention for efficient mobile network design. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. Nashville, TN, USA; 2021: 13713\u201322.","DOI":"10.1109\/CVPR46437.2021.01350"},{"key":"pone.0325373.ref030","unstructured":"Vaswani A, Shazeer N, Parmar N. Attention is all you need. In: Proceedings of the Advances in Neural Information Processing Systems. Long Beach, CA, USA; 2017: 5998\u20136008."},{"key":"pone.0325373.ref031","doi-asserted-by":"crossref","unstructured":"Zhu X, Lyu S, Wang X, Zhao Q. TPH-YOLOv5: improved YOLOv5 based on transformer prediction head for object detection on drone-captured scenarios. In: 2021 IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW). Montreal, BC, Canada; 2021: 2778\u201388. doi: 10.1109\/iccvw54120.2021.00312","DOI":"10.1109\/ICCVW54120.2021.00312"},{"key":"pone.0325373.ref032","article-title":"Open3D: a modern library for 3D data processing","author":"QY Zhou","year":"2018","journal-title":"arXiv"},{"key":"pone.0325373.ref033","doi-asserted-by":"crossref","unstructured":"Geiger A, Lenz P, Urtasun R. Are we ready for autonomous driving? The KITTI vision benchmark suite. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition. Providence, RI, USA; 2012: 3354\u201361. doi: 10.1109\/cvpr.2012.6248074","DOI":"10.1109\/CVPR.2012.6248074"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0325373","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T17:52:19Z","timestamp":1751046739000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0325373"}},"subtitle":[],"editor":[{"given":"Xin","family":"Xu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,6,27]]},"references-count":33,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2025,6,27]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0325373","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,27]]}}}