TL;DR
Experimental results demonstrate that, compared with mainstream semantic segmentation models, MDeepLab significantly reduces the number of parameters while maintaining high segmentation accuracy, exhibiting promising engineering application value for automated road crack detection.
A lightweight CNN-Mamba hybrid architecture for crack segmentation as a deployment-oriented redesign of CT-CrackSeg is proposed, showing that the proposed model maintains competitive topology-aware segmentation performance while substantially improving computational efficiency.
An improved lightweight YOLOv11-based model that integrates three complementary modules for road crack detection is proposed that integrates an improved efficient multi-scale attention (iEMA) module embedded at the shallow high-resolution feature layer (P3) and the Quality Focal Loss (QFL) function is adopted to resolv...
This study presents YOLO26s, a lightweight DL model for multi-class pavement crack detection across diverse environmental and geographic conditions, and highlights the potential of efficient AI-driven inspection systems to enhance environmental and economic sustainability in civil infrastructure.
The proposed CBAM-LKC-YOLOv8-seg framework is proposed, a lightweight end-to-end framework designed for high-precision segmentation and automated quantification, providing a reliable automated tool for large-scale road maintenance.
An improved YOLOv11s-based detector for road distress recognition that provides a practical balance between detection accuracy and model compactness for automated pavement inspection is presented.
Results demonstrate that the proposed RTCS-T and RTCS-S framework provides an efficient solution for automated pavement crack detection and shows strong potential for practical road inspection applications.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
