What question did this study set out to answer?

This research aims to improve the segmentation of cracks in road pavements using a new model called DCP-TransUNet.

February 9, 2026Sensors0 citationsOpen Access

DCP-TransUNet: An Approach for Crack Segmentation on Roads

YLYing LiuShenyang Pharmaceutical University XDXu DuChangchun University of Science and Technology WLWeiguang LIResearch Institute of Wood Industry

Key Points

This research aims to improve the segmentation of cracks in road pavements using a new model called DCP-TransUNet.
Introduced DCP-TransUNet with a hybrid encoder for segmentation tasks.
Integrated a DSE-CNN module and CLMA-Transformer block to enhance feature extraction.
Designed a PPA bottleneck module to capture discriminative features from images.
Achieved mIoU of 79.12%, Recall of 87.96%, F1 score of 87.06%, and Precision of 86.21% on a public dataset.
Attained mIoU of 68.83%, Recall of 74.42%, F1 score of 77.57%, and Precision of 81.67% on a private dataset.
Demonstrated superior accuracy and effectiveness compared to other segmentation models.

Abstract

For cement pavements on vast road networks, cracking has become one of the principal distresses threatening structural integrity and traffic safety. This study introduces DCP-TransUNet, a model featuring a new hybrid encoder that enhances the continuity of crack extraction under complex conditions through a DSE-CNN module and a CLMA-Transformer block. To further strengthen learning and interpretability for challenging crack imagery, a PPA bottleneck module is designed to capture additional discriminative features. Experimental results indicate strong performance: on the public dataset, DCP-TransUNet achieves mIoU 79.12%, Recall 87.96%, F1 87.06%, and Precision 86.21%; on the private dataset, it attains mIoU 68.83%, Recall 74.42%, F1 77.57%, and Precision 81.67%. Compared with other models, these outcomes demonstrate the method’s accuracy and effectiveness for crack segmentation.

Ask AI

Helpful

Bookmark

View Full Paper