{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,8]],"date-time":"2025-07-08T04:16:05Z","timestamp":1751948165920,"version":"3.41.2"},"reference-count":19,"publisher":"Public Library of Science (PLoS)","issue":"7","license":[{"start":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T00:00:00Z","timestamp":1751846400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Shijiazhuang Key Laboratory of Intelligent Vertical Take-off and Landing Fixed-wing UAV Research","award":["KF2024-1"],"award-info":[{"award-number":["KF2024-1"]}]},{"name":"Open Project Program of Provincial and Ministerial-Level Key Laboratories","award":["ZZKT-202301"],"award-info":[{"award-number":["ZZKT-202301"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>With the rapid expansion of railway networks globally, ensuring rail infrastructure safety through efficient detection methods has become critical. Traditional inspection systems face limitations in flexibility, adaptability to adverse weather, and multifunctional integration. This study proposes a ground-air collaborative multi-source detection system that integrates 3D light detection and ranging (LiDAR)-based point cloud imaging and deep learning-driven intrusion detection. The system employs a lightweight rail inspection vehicle equipped with dual LiDARs and an Astro camera, synchronized with an unmanned aerial vehicle (UAV) carrying industrial-grade LiDAR. We propose an improved LiDAR odometry and mapping with sliding window (LOAM-SLAM) algorithm enables real-time dynamic mapping, while an optimized iterative closest point (ICP) algorithm achieves high-precision point cloud registration and colorization. For intrusion detection, a You Only Look Once version 3 (YOLOv3)-ResNet fusion model achieves a recall rate of 0.97 and precision of 0.99. The system\u2019s innovative design and technical implementation offer significant improvements in railway track inspection efficiency and safety. This work establishes a new paradigm for adaptive railway maintenance in complex environments.<\/jats:p>","DOI":"10.1371\/journal.pone.0326951","type":"journal-article","created":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T17:50:52Z","timestamp":1751910652000},"page":"e0326951","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Air-ground collaborative multi-source orbital integrated detection system: Combining 3D imaging and intrusion recognition"],"prefix":"10.1371","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-7122-9669","authenticated-orcid":true,"given":"Mengyuan","family":"Yan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xingyu","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lifan","family":"Rong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shengbo","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan","family":"Xiong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2025,7,7]]},"reference":[{"key":"pone.0326951.ref001","volume-title":"China railway development white paper","author":"National Railway Administration","year":"2023"},{"key":"pone.0326951.ref002","volume-title":"EU rail infrastructure: safety and performance","author":"European Union Agency for Railways","year":"2023"},{"key":"pone.0326951.ref003","first-page":"91","article-title":"Development and application of onboard track condition inspection technology","volume":"10","author":"CX Ma","year":"2017","journal-title":"China Railw"},{"key":"pone.0326951.ref004","volume-title":"HORIZON 2020: research and innovation programme","author":"European Commission","year":"2023"},{"key":"pone.0326951.ref005","first-page":"3015","article-title":"Deep learning-based high-speed railway track detection","volume":"22","author":"ZY Li","year":"2021","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"pone.0326951.ref006","first-page":"104512","article-title":"LiDAR-based 3D reconstruction of railway clearance gauge","volume":"142","author":"H Zhang","year":"2022","journal-title":"Autom Constr"},{"key":"pone.0326951.ref007","first-page":"231","article-title":"Design and implementation of intelligent railway inspection robot system","volume":"6","author":"XM Li","year":"2022","journal-title":"Electron Compon Inf Technol"},{"key":"pone.0326951.ref008","first-page":"1234","article-title":"UAV-LiDAR fusion for railway clearance inspection","volume":"15","author":"J Smith","year":"2023","journal-title":"Remote Sens"},{"issue":"2","key":"pone.0326951.ref009","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1109\/34.121791","article-title":"A method for registration of 3-D shapes","volume":"14","author":"PJ Besl","year":"1992","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"pone.0326951.ref010","first-page":"679","article-title":"3D point cloud recognition algorithm based on grey relational analysis","volume":"46","author":"Z Zheng","year":"2022","journal-title":"J Nanjing Univ Sci Technol"},{"key":"pone.0326951.ref011","first-page":"4758","article-title":"LeGO-LOAM: lightweight and ground-optimized lidar odometry and mapping on variable terrain","author":"T Shan","year":"2018","journal-title":"IEEE\/RSJ Int Conf Intell Robot Syst"},{"key":"pone.0326951.ref012","doi-asserted-by":"crossref","first-page":"2901","DOI":"10.37188\/OPE.20223022.2901","article-title":"Camera pose estimation by fusing 2D images and 3D point clouds","volume":"30","author":"JL Zhou","year":"2022","journal-title":"Opt Precis Eng"},{"key":"pone.0326951.ref013","unstructured":"Redmon J, Farhadi A. YOLOv3: an incremental improvement. arXiv:1804.02767. 2018."},{"key":"pone.0326951.ref014","article-title":"Improved railway intrusion detection method based on FasterNet and YOLOv8s","author":"XJ Jiang","year":"2023","journal-title":"J Beijing Jiaotong Univ"},{"key":"pone.0326951.ref015","first-page":"567","article-title":"Real-time rail fastener detection using mobile laser scanning","volume":"14","author":"L Wang","year":"2022","journal-title":"Remote Sens"},{"key":"pone.0326951.ref016","first-page":"112","article-title":"LiDAR-based track geometry measurement","volume":"236","author":"Y Zhang","year":"2022","journal-title":"Proc Inst Mech Eng Part F J Rail Rapid Transit"},{"key":"pone.0326951.ref017","doi-asserted-by":"crossref","unstructured":"Wang CY, Bochkovskiy A, Liao HYM. YOLOv7: trainable free components set new state-of-the-art for real-time object detection. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition; 2023 Jun 18\u201322; Vancouver, BC, Canada. IEEE; 2023. p. 7464\u201375.","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"pone.0326951.ref018","first-page":"567","article-title":"UAV applications in railway safety","volume":"235","author":"J Smith","year":"2021","journal-title":"Proc Inst Mech Eng Part F J Rail Rapid Transit"},{"key":"pone.0326951.ref019","first-page":"103941","article-title":"Rail defect detection based on multimodal sensor fusion","volume":"47","author":"Q Zhang","year":"2021","journal-title":"Acta Autom Sin"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0326951","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T17:51:02Z","timestamp":1751910662000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0326951"}},"subtitle":[],"editor":[{"given":"Zhihong (Arry)","family":"Yao","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2025,7,7]]},"references-count":19,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2025,7,7]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0326951","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,7]]}}}