2026· Academic Journal of Architecture and Geotechnical Engineering· 0 citations· 2 references
TL;DR
The HPA (Hybrid Pooling Attention) module in the YOLOv8n Neck stage is introduced, which combines average pooling and max pooling with cross space learning to enhance the transmission and fusion of multi-scale crack features and alleviate information attenuation in feature propagation.
Abstract
: The detection of road and cracks is crucial for the safe operation and maintenance of infrastructure, but in practical scenarios, complex backgrounds and multi-scale morphological changes lead to insufficient detection accuracy of YOLOv8n baseline model. In response to this issue, this article introduces the HPA (Hybrid Pooling Attention) module in the YOLOv8n Neck stage, which combines average pooling and max pooling with cross space learning to enhance the transmission and fusion of multi-scale crack features and alleviate information attenuation in feature propagation. The improved model significantly improves the detection rate and positioning accuracy of small cracks in complex backgrounds while maintaining real-time performance, providing an efficient solution for intelligent detection of road and cracks.
The lightweight model reduces model complexity but also exhibits a non-negligible decrease in detection accuracy, demonstrating an explicit accuracy-complexity trade-off rather than accuracy-preserving compression.
Q. Peng, P. Zhong, C.-R. Yang· Advanced Electromagnetics· 0 citations
Analysis of the performance of the YOLO26l model as a baseline model in detecting four categories of road damage such as potholes, alligator cracking, lateral cracking, and longitudinal cracking using the Road Damage Indonesia Dataset showed that the model was able to identify all four categories of road damage well.
Mohammad Alwi Nanda Saputra, F. Alzami, Christy Atika Sari· JOURNAL OF APPLIED INFORMATI...· 0 citations
Pavement surface distress detection is an important task in road maintenance and intelligent infrastructure inspection. In practical vehicle-mounted inspection images, cracks and other distress targets often present weak edges, irregular shapes, large scale variations, and strong background interference, which makes st...
Peng Li, Tianyang Wang, Lu-Sheng Liu et al.· International Conference on...· 0 citations
Due to the low detection accuracy of current steel surface defect detection methods, this paper proposes an SSB-YOLO11-based detection method. Three attention mechanisms, namely SimAM, CBAM, and ECA, are incorporated into the YOLO11 model. Experimental results demonstrate that the SimAM module achieves superior perform...
Asphalt deterioration is a major problem for road safety and infrastructure maintenance, as it can shorten pavement lifespans, increase driver risks, and cause traffic disruptions. This study applies YOLOv8, a recent object-recognition algorithm, to detect asphalt deterioration across seven classes: Crack, Patch-Crack,...
Muhammet Fatih Sadak, A. Lav· Canadian journal of civil en...· 0 citations
To address the poor detection performance of existing models for coal mine conveyor belts under low illumination, an improved algorithm based on YOLOv8n (You Only Look Once version 8 nano) is proposed to reduce false and missed detections of slender metallic objects, small targets, and objects with background-similar t...
Lin-Xuan Li· 2026 International Conferenc...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
