Next Article in Journal
Development of Integrated Automatic System of Laser Cladding for Repairing of Polycrystalline Diamond Compact Bits
Next Article in Special Issue
Bust Portraits Matting Based on Improved U-Net
Previous Article in Journal
UTD-PO Solutions for the Analysis of Multiple Diffraction by Trees and Buildings When Assuming Spherical-Wave Incidence
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Electronics
Volume 12
Issue 4
10.3390/electronics12040898
electronics-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

Dense Multiscale Feature Learning Transformer Embedding Cross-Shaped Attention for Road Damage Detection

by
Chuan Xu
1,†,
Qi Zhang
1,
Liye Mei
1,†,
Sen Shen
2,
Zhaoyi Ye
1,
Di Li
1,
Wei Yang
3 and
Xiangyang Zhou
3,*
1
School of Computer Science, Hubei University of Technology, Wuhan 430068, China
2
School of Weapon Engineering, Naval Engineering University, Wuhan 430032, China
3
School of Information Science and Engineering, Wuchang Shouyi University, Wuhan 430064, China
*
Author to whom correspondence should be addressed.
†
These authors contributed equally to this work.
Electronics 2023, 12(4), 898; https://doi.org/10.3390/electronics12040898
Submission received: 15 January 2023 / Revised: 2 February 2023 / Accepted: 4 February 2023 / Published: 10 February 2023
(This article belongs to the Special Issue Computer Vision for Modern Vehicles)
Browse Figures
Review Reports Versions Notes

Abstract

Road damage detection is essential to the maintenance and management of roads. The morphological road damage contains a large number of multi-scale features, which means that existing road damage detection algorithms are unable to effectively distinguish and fuse multiple features. In this paper, we propose a dense multiscale feature learning Transformer embedding cross-shaped attention for road damage detection (DMTC) network, which can segment the damage information in road images and improve the effectiveness of road damage detection. Our DMTC makes three contributions. Firstly, we adopt a cross-shaped attention mechanism to expand the perceptual field of feature extraction, and its global attention effectively improves the feature description of the network. Secondly, we use the dense multi-scale feature learning module to integrate local information at different scales, so that we are able to overcome the difficulty of detecting multiscale targets. Finally, we utilize a multi-layer convolutional segmentation head to generalize the previous feature learning and get a final detection result. Experimental results show that our DMTC network could segment pavement pothole patterns more accurately and effectively than other methods, achieving an F1 score of 79.39% as well as an OA score of 99.83% on the cracks-and-potholes-in-road-images-dataset (CPRID).
Keywords: road damage detection; cross-shaped attention; dense multi-scale feature learning road damage detection; cross-shaped attention; dense multi-scale feature learning

Share and Cite

MDPI and ACS Style

Xu, C.; Zhang, Q.; Mei, L.; Shen, S.; Ye, Z.; Li, D.; Yang, W.; Zhou, X. Dense Multiscale Feature Learning Transformer Embedding Cross-Shaped Attention for Road Damage Detection. Electronics 2023, 12, 898. https://doi.org/10.3390/electronics12040898

AMA Style

Xu C, Zhang Q, Mei L, Shen S, Ye Z, Li D, Yang W, Zhou X. Dense Multiscale Feature Learning Transformer Embedding Cross-Shaped Attention for Road Damage Detection. Electronics. 2023; 12(4):898. https://doi.org/10.3390/electronics12040898

Chicago/Turabian Style

Xu, Chuan, Qi Zhang, Liye Mei, Sen Shen, Zhaoyi Ye, Di Li, Wei Yang, and Xiangyang Zhou. 2023. "Dense Multiscale Feature Learning Transformer Embedding Cross-Shaped Attention for Road Damage Detection" Electronics 12, no. 4: 898. https://doi.org/10.3390/electronics12040898

APA Style

Xu, C., Zhang, Q., Mei, L., Shen, S., Ye, Z., Li, D., Yang, W., & Zhou, X. (2023). Dense Multiscale Feature Learning Transformer Embedding Cross-Shaped Attention for Road Damage Detection. Electronics, 12(4), 898. https://doi.org/10.3390/electronics12040898

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop