Accurate highway area recognition is essential for intelligent transportation planning and digital infrastructure management. This paper addresses the challenge of automatic highway extraction from high-resolution remote sensing images, particularly in complex backgrounds, by proposing a semantic segmentation approach based on the DeepLab V3+ model. A high-quality pixel-level annotated dataset was constructed, and model hyperparameters were optimized. Experimental results indicate that DeepLab V3+ achieves strong performance, with an IoU of 87.36% and a Dice coefficient of 86.76%. Visual analysis further confirms robust performance across diverse scenes. The results demonstrate that the proposed method can provide reliable support for intelligent transportation systems and digital infrastructure management.
Yang Yang, Ke Li, Lei Wang et al.· International Conference on...· 0 citations
To address the challenge that the diversity and complex morphology of pavement distresses make it difficult for traditional detection methods to simultaneously achieve high accuracy and real-time performance, a multi-class pavement distress detection approach based on the YOLO26 model is proposed. Seven common types of distresses, including block cracking, longitudinal cracking, transverse cracking, potholes, strip patching, block patching, and raveling, are considered as detection targets. A high-quality annotated dataset comprising 12,451 images is constructed. Experimental results show that YOLO26 achieves a precision of 0.80, a recall of 0.81, and an mAP@0.5 of 0.79 on the test set. These results outperform those of the comparative models, including YOLOv5, YOLOv8, and YOLO11. In particular, YOLO26 improves mAP@0.5 by 1.3% compared to YOLO11, while maintaining real-time inference speed. Visualization results further validate the model’s capability for accurate localization and classification of multiple distress types. This study provides a reliable and efficient technical solution for precise multi-class pavement distress detection.
Xiaoning Chao, Jiajia Wu, Ke Li et al.· International Conference on...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
