Pavement Damage Recognition Based on Deep Learning

Road surface disease detection is a vital component of road maintenance. Traditional deep learning-based detection methods face challenges such as low detection accuracy, high false alarm rates in complex scenarios, and significant missed detection rates for small targets like potholes. To address t...

Full description

Saved in:
Bibliographic Details
Published inInternational journal of advanced network, monitoring, and controls Vol. 10; no. 2; pp. 74 - 84
Main Authors Ning, Mingbo, Yang, Shengquan
Format Journal Article
LanguageEnglish
Published Xi'an Sciendo 16.06.2025
De Gruyter Poland
Subjects
Accuracy
Algorithms
Computer vision
Cracks
Deep Learning
Defects
Efficiency
Highway construction
Inspections
Lmbablock
Repair & maintenance
Road Surface Disease Detection
Roads & highways
RT-DETR
Semantics
STEP
Transportation planning
Online AccessGet full text

Cover

More Information
Summary:Road surface disease detection is a vital component of road maintenance. Traditional deep learning-based detection methods face challenges such as low detection accuracy, high false alarm rates in complex scenarios, and significant missed detection rates for small targets like potholes. To address these limitations, this paper proposes an improved pavement disease detection algorithm based on RT-DETR. First, a lightweight backbone network named LMBANet is constructed by integrating DRB and ADown modules. This network enhances feature extraction capabilities without increasing computational overhead during inference, preserving local details of low-level features while expanding the receptive field to capture long-range semantic information and reduce false detection of diverse defects in complex scenes. Second, an small-target enhanced feature pyramid network is designed using SPDConv and OmniKernel. By feeding large-scale feature maps extracted by the backbone into a feature fusion layer and enhancing multi-scale feature representation through EFKM, this network resolves the high missed detection rate of small targets in the original model. Experimental results demonstrate that on the RDD2020 dataset, the improved network achieves an mAP of 69.2%, representing a 2.1 percentage point improvement over the original network, while simultaneously reducing parameters and computational costs.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2470-8038
2470-8038
DOI:10.2478/ijanmc-2025-0018