Road Perception for Autonomous Driving: Pothole Detection in Complex Environments Based on Improved YOLOv8

Road surface pothole detection is crucial for ensuring the driving safety and path planning of autonomous vehicles. However, existing detection methods are often affected by variations in lighting, weather conditions, and complex environments, resulting in lower detection precision and recall rates....

Full description

Saved in:
Bibliographic Details
Main Authors: Siyuan Kong, Qiao Meng, Xin Li, Zhijie Wang, Xin Liu, Bingyu Li
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10985758/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850136171076648960
author Siyuan Kong
Qiao Meng
Xin Li
Zhijie Wang
Xin Liu
Bingyu Li
author_facet Siyuan Kong
Qiao Meng
Xin Li
Zhijie Wang
Xin Liu
Bingyu Li
author_sort Siyuan Kong
collection DOAJ
description Road surface pothole detection is crucial for ensuring the driving safety and path planning of autonomous vehicles. However, existing detection methods are often affected by variations in lighting, weather conditions, and complex environments, resulting in lower detection precision and recall rates. To address this, this paper proposes an innovative improved algorithm, which is based on the YOLOv8 model, and introduces the MSF-HFEB module in the innovative design. By cleverly blending the strengths of Convolutional Neural Network (CNN) and the Transformer architecture, the algorithm accomplishes multi-scale feature extraction and fusion for both local and global aspects of road potholes. This design significantly improves the robustness of the algorithm under different lighting and complex environmental conditions. Additionally, the algorithm incorporates the LSKA attention mechanism and an integrated MHSA_CGLU module. By utilizing large-scale convolutional kernels for weighted feature screening, it further enhances the capability of multi-scale feature extraction and the richness of nonlinear feature representation. Experiments on public datasets have validated the effectiveness of our approach: compared to the original YOLOv8 model, the detection precision and recall rate of our algorithm have been improved by 9.8% and 11.6% respectively, and the F1 score has reached 84.9%. The outcomes of this research not only enhance the driving safety and comfort of autonomous vehicles in complex environments but also offer robust technical support for obstacle avoidance and path planning in self-driving vehicles.
format Article
id doaj-art-9341a449c88a4531823f4cdebfd09f79
institution OA Journals
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-9341a449c88a4531823f4cdebfd09f792025-08-20T02:31:12ZengIEEEIEEE Access2169-35362025-01-0113809148092910.1109/ACCESS.2025.356694410985758Road Perception for Autonomous Driving: Pothole Detection in Complex Environments Based on Improved YOLOv8Siyuan Kong0https://orcid.org/0009-0001-9234-0162Qiao Meng1https://orcid.org/0009-0004-7529-4127Xin Li2Zhijie Wang3Xin Liu4Bingyu Li5School of Computer Technology and Application, Qinghai University, Xining, Qinghai, ChinaSchool of Computer Technology and Application, Qinghai University, Xining, Qinghai, ChinaSchool of Computer Technology and Application, Qinghai University, Xining, Qinghai, ChinaSchool of Computer Technology and Application, Qinghai University, Xining, Qinghai, ChinaSchool of Computer Technology and Application, Qinghai University, Xining, Qinghai, ChinaSchool of Computer Technology and Application, Qinghai University, Xining, Qinghai, ChinaRoad surface pothole detection is crucial for ensuring the driving safety and path planning of autonomous vehicles. However, existing detection methods are often affected by variations in lighting, weather conditions, and complex environments, resulting in lower detection precision and recall rates. To address this, this paper proposes an innovative improved algorithm, which is based on the YOLOv8 model, and introduces the MSF-HFEB module in the innovative design. By cleverly blending the strengths of Convolutional Neural Network (CNN) and the Transformer architecture, the algorithm accomplishes multi-scale feature extraction and fusion for both local and global aspects of road potholes. This design significantly improves the robustness of the algorithm under different lighting and complex environmental conditions. Additionally, the algorithm incorporates the LSKA attention mechanism and an integrated MHSA_CGLU module. By utilizing large-scale convolutional kernels for weighted feature screening, it further enhances the capability of multi-scale feature extraction and the richness of nonlinear feature representation. Experiments on public datasets have validated the effectiveness of our approach: compared to the original YOLOv8 model, the detection precision and recall rate of our algorithm have been improved by 9.8% and 11.6% respectively, and the F1 score has reached 84.9%. The outcomes of this research not only enhance the driving safety and comfort of autonomous vehicles in complex environments but also offer robust technical support for obstacle avoidance and path planning in self-driving vehicles.https://ieeexplore.ieee.org/document/10985758/Autonomous drivingLSKA attention mechanismMSF-HFEBmulti-scale feature extractionYOLOv8
spellingShingle Siyuan Kong
Qiao Meng
Xin Li
Zhijie Wang
Xin Liu
Bingyu Li
Road Perception for Autonomous Driving: Pothole Detection in Complex Environments Based on Improved YOLOv8
IEEE Access
Autonomous driving
LSKA attention mechanism
MSF-HFEB
multi-scale feature extraction
YOLOv8
title Road Perception for Autonomous Driving: Pothole Detection in Complex Environments Based on Improved YOLOv8
title_full Road Perception for Autonomous Driving: Pothole Detection in Complex Environments Based on Improved YOLOv8
title_fullStr Road Perception for Autonomous Driving: Pothole Detection in Complex Environments Based on Improved YOLOv8
title_full_unstemmed Road Perception for Autonomous Driving: Pothole Detection in Complex Environments Based on Improved YOLOv8
title_short Road Perception for Autonomous Driving: Pothole Detection in Complex Environments Based on Improved YOLOv8
title_sort road perception for autonomous driving pothole detection in complex environments based on improved yolov8
topic Autonomous driving
LSKA attention mechanism
MSF-HFEB
multi-scale feature extraction
YOLOv8
url https://ieeexplore.ieee.org/document/10985758/
work_keys_str_mv AT siyuankong roadperceptionforautonomousdrivingpotholedetectionincomplexenvironmentsbasedonimprovedyolov8
AT qiaomeng roadperceptionforautonomousdrivingpotholedetectionincomplexenvironmentsbasedonimprovedyolov8
AT xinli roadperceptionforautonomousdrivingpotholedetectionincomplexenvironmentsbasedonimprovedyolov8
AT zhijiewang roadperceptionforautonomousdrivingpotholedetectionincomplexenvironmentsbasedonimprovedyolov8
AT xinliu roadperceptionforautonomousdrivingpotholedetectionincomplexenvironmentsbasedonimprovedyolov8
AT bingyuli roadperceptionforautonomousdrivingpotholedetectionincomplexenvironmentsbasedonimprovedyolov8