{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T17:59:31Z","timestamp":1781287171608,"version":"3.54.1"},"reference-count":33,"publisher":"Public Library of Science (PLoS)","issue":"6","license":[{"start":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T00:00:00Z","timestamp":1781222400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Rare road obstacles, including traffic cones, fallen trees, debris, barrels, and rocks, pose significant safety risks to autonomous vehicles. This paper presents a lightweight real-time detection framework using YOLOv8-n to accurately identify such obstacles on resource-constrained hardware. Multiple open source datasets containing annotated images of rare objects were combined and curated into a unified dataset. The model was refined using transfer learning, and its resilience to changing illumination and partial occlusion was enhanced by data augmentation techniques such brightness fluctuation, rotation, flipping, and geometric distortion. On a mid-range NVIDIA P100 GPU, the model maintained an inference speed of 68 frames per second while achieving a precision of 95.4%, recall of 93.9%, F1-score of 94.6%, and mean average precision (mAP@0.5) of 98.1%. These findings show that the framework is appropriate for edge-based autonomous driving systems where low latency and computational efficiency are crucial since it provides precise real-time detection without the need for expensive hardware.<\/jats:p>","DOI":"10.1371\/journal.pone.0350732","type":"journal-article","created":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T17:47:23Z","timestamp":1781286443000},"page":"e0350732","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Real-time detection of rare roadside obstacles using YOLOv8-n in autonomous vehicles"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-3321-0142","authenticated-orcid":true,"given":"Afeera Bint-e","family":"Tanveer","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muhammad Ayoub","family":"Kamal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5773-7140","authenticated-orcid":true,"given":"Muhammad Mansoor","family":"Alam","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mazliham Mohd","family":"Su\u2019ud","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,6,12]]},"reference":[{"key":"pone.0350732.ref001","doi-asserted-by":"crossref","unstructured":"Afdhal A, Saddami K, Sugiarto S, Fuadi Z, Nasaruddin N. Real-time object detection performance of YOLOv8 models for self-driving cars in a mixed traffic environment. In: 2023 2nd International Conference on Computer System, Information Technology, and Electrical Engineering (COSITE). 2023. pp. 260-5. Available from: https:\/\/ieeexplore.ieee.org\/document\/10249521","DOI":"10.1109\/COSITE60233.2023.10249521"},{"key":"pone.0350732.ref002","unstructured":"Reis D, Kupec J, Hong J, Daoudi A. Real-time flying object detection with YOLOv8. arXiv preprint. 2023. Available from: http:\/\/arxiv.org\/abs\/2305.09972"},{"key":"pone.0350732.ref003","unstructured":"Bochkovskiy A, Wang CY, Liao HYM. YOLOv4: Optimal speed and accuracy of object detection. arXiv preprint. 2020. Available from: http:\/\/arxiv.org\/abs\/2004.10934"},{"key":"pone.0350732.ref004","unstructured":"Real-time object detection method based on improved YOLOv4-tiny. 2020. Available from: https:\/\/www.researchgate.net\/publication\/345653552"},{"issue":"19","key":"pone.0350732.ref005","doi-asserted-by":"crossref","first-page":"6209","DOI":"10.3390\/s24196209","article-title":"SOD-YOLOv8-enhancing YOLOv8 for small object detection in aerial imagery and traffic scenes","volume":"24","author":"B Khalili","year":"2024","journal-title":"Sensors (Basel)"},{"issue":"12","key":"pone.0350732.ref006","first-page":"25345","article-title":"Edge YOLO: Real-time intelligent object detection system based on edge-cloud cooperation in autonomous vehicles","volume":"23","author":"S Liang","year":"2022","journal-title":"arXiv preprint"},{"issue":"2","key":"pone.0350732.ref007","first-page":"1","article-title":"Detection of small object based on improved YOLOv8","volume":"6","author":"Y Tan","year":"2024","journal-title":"Front Comput Inf Sci"},{"issue":"5","key":"pone.0350732.ref008","first-page":"1355","article-title":"Impact of LoRA and 5G on smart manufacturing from automation perspective","volume":"18","author":"MA Kamal","year":"2025","journal-title":"IEEE Access"},{"issue":"2","key":"pone.0350732.ref009","doi-asserted-by":"crossref","first-page":"10135","DOI":"10.48084\/etasr.10135","article-title":"Cost-effective real-time obstacle detection and avoidance for AGVs using YOLOv8 and RGB-D sensors","volume":"15","author":"A Medjaldi","year":"2025","journal-title":"Eng Technol Appl Sci Res"},{"issue":"13","key":"pone.0350732.ref010","doi-asserted-by":"crossref","first-page":"7275","DOI":"10.3390\/app15137275","article-title":"YOLOv8 with post-processing for small object detection enhancement","volume":"15","author":"J Ryu","year":"2025","journal-title":"Appl Sci"},{"key":"pone.0350732.ref011","article-title":"Small object detection in UAV images based on YOLOv8n","author":"LYZ Xu","year":"2024","journal-title":"J Image Graph"},{"issue":"12","key":"pone.0350732.ref012","doi-asserted-by":"crossref","first-page":"2263","DOI":"10.3390\/agriculture14122263","article-title":"Improved field obstacle detection algorithm based on YOLOv8","volume":"14","author":"XWC Zhou","year":"2024","journal-title":"Agriculture"},{"issue":"3","key":"pone.0350732.ref013","first-page":"234","article-title":"Lightweight multi-scale object detection method for edge devices based on YOLOv8","volume":"45","author":"J Hao","year":"2025","journal-title":"J Comput Appl"},{"issue":"3","key":"pone.0350732.ref014","doi-asserted-by":"crossref","first-page":"1186","DOI":"10.32520\/stmsi.v14i3.5081","article-title":"Object detection using YOLOv8\u00a0: a systematic review","volume":"14","author":"NA Megantara","year":"2025","journal-title":"SISTEMASI"},{"key":"pone.0350732.ref015","unstructured":"Verma U, Kalia A, Sood S. YOLOv8: an enhanced object detection model for distance estimation. 2024 Int J Intell Syst Appl Eng. 2024."},{"issue":"3","key":"pone.0350732.ref016","first-page":"45","article-title":"Road obstacle object detection based on improved YOLO V4","volume":"11","author":"X Zuo","year":"2021","journal-title":"Int J Automat Networked Control"},{"key":"pone.0350732.ref017","doi-asserted-by":"crossref","unstructured":"Pham V, Dong Thi Ngoc L, Bui DL. Optimizing YOLO Architectures for Optimal Road Damage Detection and Classification: A Comparative Study from YOLOv7 to YOLOv10. arXiv preprint arXiv:241008409. 2024. Available from: https:\/\/arxiv.org\/abs\/2410.08409","DOI":"10.1109\/BigData62323.2024.10825509"},{"issue":"5","key":"pone.0350732.ref018","doi-asserted-by":"crossref","first-page":"1287","DOI":"10.3390\/s25051287","article-title":"Deep learning-based algorithm for road defect detection","volume":"25","author":"S Li","year":"2025","journal-title":"Sensors (Basel)"},{"issue":"4","key":"pone.0350732.ref019","first-page":"1680","article-title":"A comprehensive review of YOLO architectures in computer vision: From YOLOv1 to YOLOv8 and YOLO-NAS","volume":"5","author":"J Terven","year":"2023","journal-title":"arXiv preprint"},{"key":"pone.0350732.ref020","doi-asserted-by":"crossref","first-page":"135036","DOI":"10.1016\/j.conbuildmat.2024.135036","article-title":"An end-to-end computer vision system based on deep learning for pavement distress detection and quantification","volume":"416","author":"S Cano-Ortiz","year":"2024","journal-title":"Construct Build Mater"},{"issue":"12","key":"pone.0350732.ref021","doi-asserted-by":"crossref","first-page":"2413","DOI":"10.3390\/electronics13122413","article-title":"Road surface defect detection algorithm based on YOLOv8","volume":"13","author":"Z Sun","year":"2024","journal-title":"Electronics"},{"issue":"19","key":"pone.0350732.ref022","doi-asserted-by":"crossref","first-page":"6319","DOI":"10.3390\/s24196319","article-title":"Object detection and classification framework for analysis of video data acquired from Indian roads","volume":"24","author":"A Padia","year":"2024","journal-title":"Sensors (Basel)"},{"key":"pone.0350732.ref023","doi-asserted-by":"crossref","unstructured":"S SJ, P ER. LittleYOLO-SPP: A delicate real-time vehicle detection algorithm. arXiv preprint. 2020. 165818. http:\/\/arxiv.org\/abs\/2011.05940","DOI":"10.1016\/j.ijleo.2020.165818"},{"issue":"12","key":"pone.0350732.ref024","first-page":"2250","article-title":"An advanced approach to object detection and tracking in robotics and autonomous vehicles using YOLOv8 and LiDAR data fusion","volume":"13","year":"2023","journal-title":"Electronics"},{"key":"pone.0350732.ref025","doi-asserted-by":"crossref","unstructured":"LEAD-YOLO: A lightweight and accurate network for small object detection in autonomous driving. 2024. Available from: https:\/\/www.mdpi.com\/1424-8220\/25\/15\/4800","DOI":"10.3390\/s25154800"},{"key":"pone.0350732.ref026","doi-asserted-by":"crossref","unstructured":"AMW-YOLOv8n: Road scene object detection based on an improved YOLOv8. 2023. Available from: https:\/\/www.mdpi.com\/2079-9292\/13\/20\/4121","DOI":"10.3390\/electronics13204121"},{"key":"pone.0350732.ref027","doi-asserted-by":"crossref","unstructured":"Object detection in adverse weather for autonomous driving through data merging and YOLOv8; 2023. Available from: https:\/\/www.mdpi.com\/1424-8220\/23\/20\/8471","DOI":"10.3390\/s23208471"},{"key":"pone.0350732.ref028","doi-asserted-by":"crossref","unstructured":"A study on the performance improvement of a conical bucket detection algorithm based on YOLOv8s; 2023. Available from: https:\/\/www.mdpi.com\/2032-6653\/15\/6\/238","DOI":"10.3390\/wevj15060238"},{"issue":"10","key":"pone.0350732.ref029","doi-asserted-by":"crossref","first-page":"3782","DOI":"10.1109\/TITS.2019.2892405","article-title":"A survey on 3D object detection methods for autonomous driving applications","volume":"20","author":"E Arnold","year":"2019","journal-title":"IEEE Trans Intell Transport Syst"},{"key":"pone.0350732.ref030","doi-asserted-by":"crossref","first-page":"125122","DOI":"10.1109\/ACCESS.2023.3330844","article-title":"DS-YOLOv8-based object detection method for remote sensing images","volume":"11","author":"L Shen","year":"2023","journal-title":"IEEE Access"},{"key":"pone.0350732.ref031","unstructured":"What is YOLOv8: An in-depth exploration of the internal features of the next-generation object detector. 2024. Available from: https:\/\/arxiv.org\/html\/2408.15857"},{"key":"pone.0350732.ref032","unstructured":"Choe TE, Choi S, Lee H, Kim M. HazardNet: Road Debris Detection by Augmentation of Synthetic Models. arXiv preprint arXiv:230307547. 2023. Available from: https:\/\/arxiv.org\/abs\/2303.07547"},{"key":"pone.0350732.ref033","doi-asserted-by":"crossref","unstructured":"Khare OM, Gandhi S, Rahalkar AM, Mane S. YOLOv8-Based Visual Detection of Road Hazards: Potholes, Sewer Covers, and Manholes. arXiv preprint arXiv:231100073. 2023. Available from: https:\/\/arxiv.org\/abs\/2311.00073","DOI":"10.1109\/PuneCon58714.2023.10449999"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0350732","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T17:47:34Z","timestamp":1781286454000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0350732"}},"subtitle":[],"editor":[{"given":"Ryan Wen","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,6,12]]},"references-count":33,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2026,6,12]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0350732","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,12]]}}}