TMENet: Multimodal Road Crack Segmentation Network for Complex Scenarios
IEEE Transactions on Intelligent Transportation Systems · 2026-02 · 27 (2) · 2488-2503
DOI: 10.1109/tits.2025.3634352 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Intelligent Transportation Systems, 2026-02. Verfasst von Ruoli Yang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 74 Literaturangaben.
Abstract (Originalsprache)
Road crack detection in complex scenarios is challenged by road surface backgrounds such as water stains, oil stains, and printed road signs. To better address these issues, we propose a Multimodal Road Crack Segmentation Network–TMENet, based on complex scenes. In this article, we introduced text guidance in road crack segmentation tasks to supplement more detailed crack features. Firstly, we designed the Textual Crack Enhancer module(TCE Module) to fine-tune the Text Transformer in the Clipseg model to enhance its ability to parse specific crack descriptions. Secondly, we designed a multiscale Mamba module(Ms-Mamba Module) that integrates multiscale composite convolution and residual connections to improve the sensitivity of the model to local and multiscale details and enhance the network’s ability to recover lost features. Then, we designed a Laplacian edge detection module (LED module) that combines deep visual features and high-frequency edge information to enhance the crack edge detection capability in complex scenes through a refined feature adjustment mechanism. Finally, TMENet achieved the best results in comparative testing with seven state-of-the-art segmentation networks on the CampCrack800, AsphaltCrack300, Crackseg9K, and CRKWH100 datasets. In addition, TMENet has achieved excellent results in actual road testing, and the test results show that TMENet is an effective auxiliary method to improve the accuracy of road safety detection.
Zitieren
APA
Yang, R., Jiang, J., Zhan, L., Wan, B., Qi, R., & Zhou, G. (2026). TMENet: Multimodal Road Crack Segmentation Network for Complex Scenarios. IEEE Transactions on Intelligent Transportation Systems, 27(2), 2488-2503. https://doi.org/10.1109/tits.2025.3634352
Vancouver
Yang R, Jiang J, Zhan L, Wan B, Qi R, Zhou G. TMENet: Multimodal Road Crack Segmentation Network for Complex Scenarios. IEEE Transactions on Intelligent Transportation Systems. 2026;27(2):2488-2503. doi:10.1109/tits.2025.3634352
BibTeX
@article{Yang2026,
author = {Yang, Ruoli and Jiang, Jie and Zhan, Lixin and Wan, Baiyan and Qi, Rui and Zhou, Guoxiong},
title = {TMENet: Multimodal Road Crack Segmentation Network for Complex Scenarios},
journal = {IEEE Transactions on Intelligent Transportation Systems},
year = {2026},
volume = {27},
number = {2},
pages = {2488--2503},
doi = {10.1109/tits.2025.3634352}
}
EUVIMED