Road damage detection for autonomous driving vehicles using YOLOv8 and salp swarm algorithm
Road accidents are one of the leading causes of death and serious injury in Malaysia, often resulting from human errors and poor road conditions. Autonomous vehicles aim to reduce accidents by mitigating human errors. Therefore, improving the road damage detection model in autonomous vehicles is cru...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Arqii Publication
2025
|
| Subjects: | |
| Online Access: | http://umpir.ump.edu.my/id/eprint/43710/ http://umpir.ump.edu.my/id/eprint/43710/1/729-2470-10.pdf |
| _version_ | 1848826941851828224 |
|---|---|
| author | Nik Ahmad Farihin, Mohd Zulkifli Zuriani, Mustaffa Mohd Herwan, Sulaiman |
| author_facet | Nik Ahmad Farihin, Mohd Zulkifli Zuriani, Mustaffa Mohd Herwan, Sulaiman |
| author_sort | Nik Ahmad Farihin, Mohd Zulkifli |
| building | UMP Institutional Repository |
| collection | Online Access |
| description | Road accidents are one of the leading causes of death and serious injury in Malaysia, often resulting from human errors and poor road conditions. Autonomous vehicles aim to reduce accidents by mitigating human errors. Therefore, improving the road damage detection model in autonomous vehicles is crucial for enhancing their decision-making capabilities and reducing road accidents. Finding suitable sets of hyperparameters for this task is time-consuming. Consequently, this paper proposes a method to improve the detection accuracy of You Only Look Once version 8 (YOLOv8) using Salp Swarm Algorithm (SSA) for hyperparameter optimization, focusing on eight key parameters. The model is trained using the Czech data in Road Damage Dataset RDD2022 from the Crowdsensing-based Road Damage Detection Challenge (CRDDC’2022), with 80% of the data used for training and 20% for validation. The YOLOv8n model is trained with SSA on the RDD2022 dataset, specifically using data from India and China, to find the optimal parameters. The model is then retrained using the hyperparameters identified by SSA. The YOLOv8 models optimized using SSA are compared with the original YOLOv8 and other YOLO versions (YOLOv5, YOLOv9, and YOLOv10), demonstrating a 3.5% improvement in accuracy after hyperparameter optimization in detecting road damage. |
| first_indexed | 2025-11-15T03:52:49Z |
| format | Article |
| id | ump-43710 |
| institution | Universiti Malaysia Pahang |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T03:52:49Z |
| publishDate | 2025 |
| publisher | Arqii Publication |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | ump-437102025-02-04T02:11:47Z http://umpir.ump.edu.my/id/eprint/43710/ Road damage detection for autonomous driving vehicles using YOLOv8 and salp swarm algorithm Nik Ahmad Farihin, Mohd Zulkifli Zuriani, Mustaffa Mohd Herwan, Sulaiman QA75 Electronic computers. Computer science TK Electrical engineering. Electronics Nuclear engineering Road accidents are one of the leading causes of death and serious injury in Malaysia, often resulting from human errors and poor road conditions. Autonomous vehicles aim to reduce accidents by mitigating human errors. Therefore, improving the road damage detection model in autonomous vehicles is crucial for enhancing their decision-making capabilities and reducing road accidents. Finding suitable sets of hyperparameters for this task is time-consuming. Consequently, this paper proposes a method to improve the detection accuracy of You Only Look Once version 8 (YOLOv8) using Salp Swarm Algorithm (SSA) for hyperparameter optimization, focusing on eight key parameters. The model is trained using the Czech data in Road Damage Dataset RDD2022 from the Crowdsensing-based Road Damage Detection Challenge (CRDDC’2022), with 80% of the data used for training and 20% for validation. The YOLOv8n model is trained with SSA on the RDD2022 dataset, specifically using data from India and China, to find the optimal parameters. The model is then retrained using the hyperparameters identified by SSA. The YOLOv8 models optimized using SSA are compared with the original YOLOv8 and other YOLO versions (YOLOv5, YOLOv9, and YOLOv10), demonstrating a 3.5% improvement in accuracy after hyperparameter optimization in detecting road damage. Arqii Publication 2025-01-01 Article PeerReviewed pdf en cc_by_4 http://umpir.ump.edu.my/id/eprint/43710/1/729-2470-10.pdf Nik Ahmad Farihin, Mohd Zulkifli and Zuriani, Mustaffa and Mohd Herwan, Sulaiman (2025) Road damage detection for autonomous driving vehicles using YOLOv8 and salp swarm algorithm. Applications of Modelling and Simulation, 9. pp. 1-11. ISSN 2600-8084. (Published) http://arqiipubl.com/ojs/index.php/AMS_Journal/article/view/729 |
| spellingShingle | QA75 Electronic computers. Computer science TK Electrical engineering. Electronics Nuclear engineering Nik Ahmad Farihin, Mohd Zulkifli Zuriani, Mustaffa Mohd Herwan, Sulaiman Road damage detection for autonomous driving vehicles using YOLOv8 and salp swarm algorithm |
| title | Road damage detection for autonomous driving vehicles using YOLOv8 and salp swarm algorithm |
| title_full | Road damage detection for autonomous driving vehicles using YOLOv8 and salp swarm algorithm |
| title_fullStr | Road damage detection for autonomous driving vehicles using YOLOv8 and salp swarm algorithm |
| title_full_unstemmed | Road damage detection for autonomous driving vehicles using YOLOv8 and salp swarm algorithm |
| title_short | Road damage detection for autonomous driving vehicles using YOLOv8 and salp swarm algorithm |
| title_sort | road damage detection for autonomous driving vehicles using yolov8 and salp swarm algorithm |
| topic | QA75 Electronic computers. Computer science TK Electrical engineering. Electronics Nuclear engineering |
| url | http://umpir.ump.edu.my/id/eprint/43710/ http://umpir.ump.edu.my/id/eprint/43710/ http://umpir.ump.edu.my/id/eprint/43710/1/729-2470-10.pdf |