Deep Learning-Based Algorithm for Road Defect Detection

With the increasing demand for road defect detection, existing deep learning methods have made significant progress in terms of accuracy and speed. However, challenges remain, such as insufficient detection precision for detection precision for road defect recognition and issues of missed or false d...

Full description

Saved in:
Bibliographic Details
Main Authors: Shaoxiang Li, Dexiang Zhang
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/5/1287
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850052813355220992
author Shaoxiang Li
Dexiang Zhang
author_facet Shaoxiang Li
Dexiang Zhang
author_sort Shaoxiang Li
collection DOAJ
description With the increasing demand for road defect detection, existing deep learning methods have made significant progress in terms of accuracy and speed. However, challenges remain, such as insufficient detection precision for detection precision for road defect recognition and issues of missed or false detections in complex backgrounds. These issues reduce detection reliability and hinder real-world deployment. To address these challenges, this paper proposes an improved YOLOv8-based model, RepGD-YOLOV8W. First, it replaces the C2f module in the GD mechanism with the improved C2f module based on RepViTBlock to construct the Rep-GD module. This improvement not only maintains high detection accuracy but also significantly enhances computational efficiency. Subsequently, the Rep-GD module was used to replace the traditional neck part of the model, thereby improving multi-scale feature fusion, particularly for detecting small targets (e.g., cracks) and large targets (e.g., potholes) in complex backgrounds. Additionally, the introduction of the Wise-IoU loss function further optimized the bounding box regression task, enhancing the model’s stability and generalization. Experimental results demonstrate that the improved REPGD-YOLOV8W model achieved a 2.4% increase in mAP50 on the RDD2022 dataset. Compared with other mainstream methods, this model exhibits greater robustness and flexibility in handling road defects of various scales.
format Article
id doaj-art-c75a3df23e954a7e9be47eea326e19b1
institution DOAJ
issn 1424-8220
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-c75a3df23e954a7e9be47eea326e19b12025-08-20T02:52:42ZengMDPI AGSensors1424-82202025-02-01255128710.3390/s25051287Deep Learning-Based Algorithm for Road Defect DetectionShaoxiang Li0Dexiang Zhang1School of Electrical Engineering and Automation, Anhui University, Hefei 230601, ChinaSchool of Electrical Engineering and Automation, Anhui University, Hefei 230601, ChinaWith the increasing demand for road defect detection, existing deep learning methods have made significant progress in terms of accuracy and speed. However, challenges remain, such as insufficient detection precision for detection precision for road defect recognition and issues of missed or false detections in complex backgrounds. These issues reduce detection reliability and hinder real-world deployment. To address these challenges, this paper proposes an improved YOLOv8-based model, RepGD-YOLOV8W. First, it replaces the C2f module in the GD mechanism with the improved C2f module based on RepViTBlock to construct the Rep-GD module. This improvement not only maintains high detection accuracy but also significantly enhances computational efficiency. Subsequently, the Rep-GD module was used to replace the traditional neck part of the model, thereby improving multi-scale feature fusion, particularly for detecting small targets (e.g., cracks) and large targets (e.g., potholes) in complex backgrounds. Additionally, the introduction of the Wise-IoU loss function further optimized the bounding box regression task, enhancing the model’s stability and generalization. Experimental results demonstrate that the improved REPGD-YOLOV8W model achieved a 2.4% increase in mAP50 on the RDD2022 dataset. Compared with other mainstream methods, this model exhibits greater robustness and flexibility in handling road defects of various scales.https://www.mdpi.com/1424-8220/25/5/1287road defect detectionYOLOv8GD mechanismRepViTBlockWise-IoU loss function
spellingShingle Shaoxiang Li
Dexiang Zhang
Deep Learning-Based Algorithm for Road Defect Detection
Sensors
road defect detection
YOLOv8
GD mechanism
RepViTBlock
Wise-IoU loss function
title Deep Learning-Based Algorithm for Road Defect Detection
title_full Deep Learning-Based Algorithm for Road Defect Detection
title_fullStr Deep Learning-Based Algorithm for Road Defect Detection
title_full_unstemmed Deep Learning-Based Algorithm for Road Defect Detection
title_short Deep Learning-Based Algorithm for Road Defect Detection
title_sort deep learning based algorithm for road defect detection
topic road defect detection
YOLOv8
GD mechanism
RepViTBlock
Wise-IoU loss function
url https://www.mdpi.com/1424-8220/25/5/1287
work_keys_str_mv AT shaoxiangli deeplearningbasedalgorithmforroaddefectdetection
AT dexiangzhang deeplearningbasedalgorithmforroaddefectdetection