Pavement pothole detection system based on deep learning and binocular vision

Due to strong vibrations and the impact on high-speed vehicles, road potholes may cause discomfort to passengers, damaging the durability of the suspension and the integrity of the cargo. Therefore, a road pothole detection system is proposed, which uses deep learning and binocular vision for precis...

Full description

Saved in:
Bibliographic Details
Main Authors: Tian Guan, Jianyuan Cai, Yu Wang, Wei Yang, Xiaobo Chang, Yi Han
Format: Article
Language:English
Published: KeAi Communications Co., Ltd. 2025-08-01
Series:Journal of Traffic and Transportation Engineering (English ed. Online)
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2095756425001126
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849406302555471872
author Tian Guan
Jianyuan Cai
Yu Wang
Wei Yang
Xiaobo Chang
Yi Han
author_facet Tian Guan
Jianyuan Cai
Yu Wang
Wei Yang
Xiaobo Chang
Yi Han
author_sort Tian Guan
collection DOAJ
description Due to strong vibrations and the impact on high-speed vehicles, road potholes may cause discomfort to passengers, damaging the durability of the suspension and the integrity of the cargo. Therefore, a road pothole detection system is proposed, which uses deep learning and binocular vision for precise detection in the front. 6,848 road surface pothole condition recognition datasets were constructed using a vehicle mounted binocular camera. The group attention shuffle block (GASB) is designed to enhance the expression of channel and spatial feature information in road images, while improving the existing shuffling network (ShuffleNetv2). This establishes a ShuffleNetv2 (GASB-ShuffleNetv2) model based on mixed attention for recognizing the state of road potholes. The experimental results show that the model has better accuracy than the basic model and can effectively detect road potholes. In addition, we replaced the ordinary convolution in the CenterNet feature extraction network with pyramid convolution with multiple receptive fields, and designed a feature fusion module in the same network to fuse low-level and high-level features related to holes, thus establishing a PF-CenterNet that combines pyramid convolution with feature fusion to detect areas containing road potholes. A pothole distance estimation model based on binocular vision was established by analyzing the stereo ranging model and semi-global block matching algorithm. After parameter calibration, images were rectified and stereo-matched to generate a disparity map. This map was optimized using a weighted least squares filter to fill blank areas. The 3D coordinates are then calculated based on the disparity provided with distance information. Finally, vehicle experiments were conducted to verify the effectiveness of the algorithm in meeting detection requirements while considering long-range perception accuracy. The experimental results show that the system can meet the needs of unmanned vehicles, enabling them to perceive potholes in advance, thereby issuing timely warnings to drivers.
format Article
id doaj-art-85fb5793ec084dfb9f303667085634e8
institution Kabale University
issn 2095-7564
language English
publishDate 2025-08-01
publisher KeAi Communications Co., Ltd.
record_format Article
series Journal of Traffic and Transportation Engineering (English ed. Online)
spelling doaj-art-85fb5793ec084dfb9f303667085634e82025-08-20T03:36:26ZengKeAi Communications Co., Ltd.Journal of Traffic and Transportation Engineering (English ed. Online)2095-75642025-08-011241100112310.1016/j.jtte.2024.08.001Pavement pothole detection system based on deep learning and binocular visionTian Guan0Jianyuan Cai1Yu Wang2Wei Yang3Xiaobo Chang4Yi Han5School of Automobile, Chang'an University, Xi'an 710064, ChinaSchool of Automobile, Chang'an University, Xi'an 710064, ChinaSchool of Automobile, Chang'an University, Xi'an 710064, ChinaSchool of Automobile, Chang'an University, Xi'an 710064, China; Corresponding author.China National Heavy Duty Truck Group Co., Ltd., Jinan 250000, ChinaSchool of Automobile, Chang'an University, Xi'an 710064, ChinaDue to strong vibrations and the impact on high-speed vehicles, road potholes may cause discomfort to passengers, damaging the durability of the suspension and the integrity of the cargo. Therefore, a road pothole detection system is proposed, which uses deep learning and binocular vision for precise detection in the front. 6,848 road surface pothole condition recognition datasets were constructed using a vehicle mounted binocular camera. The group attention shuffle block (GASB) is designed to enhance the expression of channel and spatial feature information in road images, while improving the existing shuffling network (ShuffleNetv2). This establishes a ShuffleNetv2 (GASB-ShuffleNetv2) model based on mixed attention for recognizing the state of road potholes. The experimental results show that the model has better accuracy than the basic model and can effectively detect road potholes. In addition, we replaced the ordinary convolution in the CenterNet feature extraction network with pyramid convolution with multiple receptive fields, and designed a feature fusion module in the same network to fuse low-level and high-level features related to holes, thus establishing a PF-CenterNet that combines pyramid convolution with feature fusion to detect areas containing road potholes. A pothole distance estimation model based on binocular vision was established by analyzing the stereo ranging model and semi-global block matching algorithm. After parameter calibration, images were rectified and stereo-matched to generate a disparity map. This map was optimized using a weighted least squares filter to fill blank areas. The 3D coordinates are then calculated based on the disparity provided with distance information. Finally, vehicle experiments were conducted to verify the effectiveness of the algorithm in meeting detection requirements while considering long-range perception accuracy. The experimental results show that the system can meet the needs of unmanned vehicles, enabling them to perceive potholes in advance, thereby issuing timely warnings to drivers.http://www.sciencedirect.com/science/article/pii/S2095756425001126Image processingUnmanned vehiclesDeep learningPavement pothole detectionBinocular vision
spellingShingle Tian Guan
Jianyuan Cai
Yu Wang
Wei Yang
Xiaobo Chang
Yi Han
Pavement pothole detection system based on deep learning and binocular vision
Journal of Traffic and Transportation Engineering (English ed. Online)
Image processing
Unmanned vehicles
Deep learning
Pavement pothole detection
Binocular vision
title Pavement pothole detection system based on deep learning and binocular vision
title_full Pavement pothole detection system based on deep learning and binocular vision
title_fullStr Pavement pothole detection system based on deep learning and binocular vision
title_full_unstemmed Pavement pothole detection system based on deep learning and binocular vision
title_short Pavement pothole detection system based on deep learning and binocular vision
title_sort pavement pothole detection system based on deep learning and binocular vision
topic Image processing
Unmanned vehicles
Deep learning
Pavement pothole detection
Binocular vision
url http://www.sciencedirect.com/science/article/pii/S2095756425001126
work_keys_str_mv AT tianguan pavementpotholedetectionsystembasedondeeplearningandbinocularvision
AT jianyuancai pavementpotholedetectionsystembasedondeeplearningandbinocularvision
AT yuwang pavementpotholedetectionsystembasedondeeplearningandbinocularvision
AT weiyang pavementpotholedetectionsystembasedondeeplearningandbinocularvision
AT xiaobochang pavementpotholedetectionsystembasedondeeplearningandbinocularvision
AT yihan pavementpotholedetectionsystembasedondeeplearningandbinocularvision