Academic Journal
Real-time detection of rare roadside obstacles using YOLOv8-n in autonomous vehicles.
| Τίτλος: | Real-time detection of rare roadside obstacles using YOLOv8-n in autonomous vehicles. |
|---|---|
| Συγγραφείς: | Tanveer AB; Faculty of Computing and Informatics (FCI), Multimedia University, Cyberjaya, Malaysia.; Department of Software Engineering, National University of Technology, Islamabad, Pakistan., Kamal MA; Faculty of Computing and Informatics (FCI), Multimedia University, Cyberjaya, Malaysia.; Department of Computer Science, DHA Suffa University, Karachi, Pakistan., Alam MM; Faculty of Computing and Informatics (FCI), Multimedia University, Cyberjaya, Malaysia.; Department of Computer Science and Software Engineering, Riphah International University, Islamabad, Pakistan., Su'ud MM; Faculty of Computing and Informatics (FCI), Multimedia University, Cyberjaya, Malaysia. |
| Πηγή: | PloS one [PLoS One] 2026 Jun 12; Vol. 21 (6), pp. e0350732. Date of Electronic Publication: 2026 Jun 12 (Print Publication: 2026). |
| Τύπος έκδοσης: | Journal Article |
| Γλώσσα: | English |
| Στοιχεία περιοδικού: | Publisher: Public Library of Science Country of Publication: United States NLM ID: 101285081 Publication Model: eCollection Cited Medium: Internet ISSN: 1932-6203 (Electronic) Linking ISSN: 19326203 NLM ISO Abbreviation: PLoS One Subsets: MEDLINE |
| Imprint Name(s): | Original Publication: San Francisco, CA : Public Library of Science |
| Ιατρικοί όροι (MeSH): | Image Processing, Computer-Assisted*/methods , Detection Algorithms* , Autonomous Vehicles* |
| Περίληψη: | 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. (Copyright: © 2026 Tanveer et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.) |
| Competing Interests: | The authors have declared that no competing interests exist. |
| References: | Sensors (Basel). 2025 Aug 04;25(15):. (PMID: 40807965) Sensors (Basel). 2025 Feb 20;25(5):. (PMID: 40096028) Sensors (Basel). 2024 Sep 29;24(19):. (PMID: 39409360) Sensors (Basel). 2024 Sep 25;24(19):. (PMID: 39409249) Sensors (Basel). 2023 Oct 14;23(20):. (PMID: 37896564) |
| Entry Date(s): | Date Created: 20260612 Date Completed: 20260612 Latest Revision: 20260813 |
| Update Code: | 20260813 |
| PubMed Central ID: | PMC13262933 |
| DOI: | 10.1371/journal.pone.0350732 |
| PMID: | 42284357 |
| Βάση Δεδομένων: | MEDLINE |
| ISSN: | 1932-6203 |
|---|---|
| DOI: | 10.1371/journal.pone.0350732 |