OEM-HWNet: A Prior Knowledge-Guided Network for Pavement Interlayer Distress Detection Based on Computer Vision Using GPR

Accurate detection of interlayer distress based on ground-penetrating radar has been widely adopted for in-service asphalt pavement condition assessment to improve maintenance efficiency and reduce costs. However, accurate interlayer distress locating is challenging with limited adaptability to thei...

Full description

Saved in:
Bibliographic Details
Main Authors: Congde Lu, Senguo Cao, Xiao Wang, Guanglai Jin, Siqi Wang, Wenlong Cai
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/17/9/1554
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850135954441895936
author Congde Lu
Senguo Cao
Xiao Wang
Guanglai Jin
Siqi Wang
Wenlong Cai
author_facet Congde Lu
Senguo Cao
Xiao Wang
Guanglai Jin
Siqi Wang
Wenlong Cai
author_sort Congde Lu
collection DOAJ
description Accurate detection of interlayer distress based on ground-penetrating radar has been widely adopted for in-service asphalt pavement condition assessment to improve maintenance efficiency and reduce costs. However, accurate interlayer distress locating is challenging with limited adaptability to their large-scale variations, which significantly weakens the detection performance. This study proposed a novel automatic detection network based on YOLOv5s to detect interlayer distresses in asphalt pavement named OEM-HWNet. Firstly, an object enhancement module based on prior knowledge was designed to locate the regions of interlayer distress and enhance their characteristics. Then, wavelet convolution was added to increase the receptive field of the network and enhance the ability to capture low-frequency information. Finally, an additional detection head was added to improve the detection capability of interlayer distress with different sizes. Experiments demonstrated that the proposed network achieves a mean average precision (mAP) of 89.6%, outperforming other advanced models, such as YOLOv5s, YOLOv8s, YOLOv11s, and Faster R-CNN. Incorporating prior knowledge into deep learning networks could provide an effective solution to detect interlayer distress of asphalt pavement.
format Article
id doaj-art-d22006f53e3c440c943fb10bb02a4564
institution OA Journals
issn 2072-4292
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-d22006f53e3c440c943fb10bb02a45642025-08-20T02:31:16ZengMDPI AGRemote Sensing2072-42922025-04-01179155410.3390/rs17091554OEM-HWNet: A Prior Knowledge-Guided Network for Pavement Interlayer Distress Detection Based on Computer Vision Using GPRCongde Lu0Senguo Cao1Xiao Wang2Guanglai Jin3Siqi Wang4Wenlong Cai5School of Mechanical and Electrical Engineering, Chengdu University of Technology, Chengdu 610059, ChinaSchool of Mechanical and Electrical Engineering, Chengdu University of Technology, Chengdu 610059, ChinaSchool of Mechanical and Electrical Engineering, Chengdu University of Technology, Chengdu 610059, ChinaJiangsu Sinoroad Engineering Technology Research Institute Co., Ltd., Nanjing 211800, ChinaSchool of Transportation, Southeast University, Nanjing 211189, ChinaJiangsu Sinoroad Engineering Technology Research Institute Co., Ltd., Nanjing 211800, ChinaAccurate detection of interlayer distress based on ground-penetrating radar has been widely adopted for in-service asphalt pavement condition assessment to improve maintenance efficiency and reduce costs. However, accurate interlayer distress locating is challenging with limited adaptability to their large-scale variations, which significantly weakens the detection performance. This study proposed a novel automatic detection network based on YOLOv5s to detect interlayer distresses in asphalt pavement named OEM-HWNet. Firstly, an object enhancement module based on prior knowledge was designed to locate the regions of interlayer distress and enhance their characteristics. Then, wavelet convolution was added to increase the receptive field of the network and enhance the ability to capture low-frequency information. Finally, an additional detection head was added to improve the detection capability of interlayer distress with different sizes. Experiments demonstrated that the proposed network achieves a mean average precision (mAP) of 89.6%, outperforming other advanced models, such as YOLOv5s, YOLOv8s, YOLOv11s, and Faster R-CNN. Incorporating prior knowledge into deep learning networks could provide an effective solution to detect interlayer distress of asphalt pavement.https://www.mdpi.com/2072-4292/17/9/1554interlayer distressground penetrating radarobject detectionprior knowledgeCanny operator
spellingShingle Congde Lu
Senguo Cao
Xiao Wang
Guanglai Jin
Siqi Wang
Wenlong Cai
OEM-HWNet: A Prior Knowledge-Guided Network for Pavement Interlayer Distress Detection Based on Computer Vision Using GPR
Remote Sensing
interlayer distress
ground penetrating radar
object detection
prior knowledge
Canny operator
title OEM-HWNet: A Prior Knowledge-Guided Network for Pavement Interlayer Distress Detection Based on Computer Vision Using GPR
title_full OEM-HWNet: A Prior Knowledge-Guided Network for Pavement Interlayer Distress Detection Based on Computer Vision Using GPR
title_fullStr OEM-HWNet: A Prior Knowledge-Guided Network for Pavement Interlayer Distress Detection Based on Computer Vision Using GPR
title_full_unstemmed OEM-HWNet: A Prior Knowledge-Guided Network for Pavement Interlayer Distress Detection Based on Computer Vision Using GPR
title_short OEM-HWNet: A Prior Knowledge-Guided Network for Pavement Interlayer Distress Detection Based on Computer Vision Using GPR
title_sort oem hwnet a prior knowledge guided network for pavement interlayer distress detection based on computer vision using gpr
topic interlayer distress
ground penetrating radar
object detection
prior knowledge
Canny operator
url https://www.mdpi.com/2072-4292/17/9/1554
work_keys_str_mv AT congdelu oemhwnetapriorknowledgeguidednetworkforpavementinterlayerdistressdetectionbasedoncomputervisionusinggpr
AT senguocao oemhwnetapriorknowledgeguidednetworkforpavementinterlayerdistressdetectionbasedoncomputervisionusinggpr
AT xiaowang oemhwnetapriorknowledgeguidednetworkforpavementinterlayerdistressdetectionbasedoncomputervisionusinggpr
AT guanglaijin oemhwnetapriorknowledgeguidednetworkforpavementinterlayerdistressdetectionbasedoncomputervisionusinggpr
AT siqiwang oemhwnetapriorknowledgeguidednetworkforpavementinterlayerdistressdetectionbasedoncomputervisionusinggpr
AT wenlongcai oemhwnetapriorknowledgeguidednetworkforpavementinterlayerdistressdetectionbasedoncomputervisionusinggpr