Education, Science, Technology, Innovation and Life
Open Access
Sign In
  1. Home
  2. Journals
  3. Journal of Artificial Intelligence Practice
  4. Vol 8, Issue 4, 2025

Hybrid Detection Method for Concrete Cracks Based on Maskr-CNN and Swin Transformer

Download as PDF

DOI: 10.23977/jaip.2025.080401 | Downloads: 3 | Views: 34

Author(s)

Hongbo Luo 1,2, Xiangyuan Ma 1,2, Fan Yu 3

Affiliation(s)

1 Yangtze River Spatial Information Technology Engineering Co., Ltd. (Wuhan), Wuhan, China; Changjiang Survey, Planning, Design and Research Co., Ltd, Wuhan, China
2 Engineering Technology Research Center of Water Conservancy Information Perception and Big Data, Hubei Province Hubei, Wuhan, China; Key Laboratory of Watershed Water Security in Hubei Province, Wuhan, China
3 Beijing University of Civil Engineering and Architecture (BUCEA), Beijing, China

Corresponding Author

Hongbo Luo

ABSTRACT

This study proposes a hybrid detection model based on Mask R-CNN and Swin Transformer for the detection and segmentation of concrete cracks. This method fully utilizes the advantages of Mask R-CNN in precise object localization and pixel level segmentation, while introducing Swin Transformer to compensate for the shortcomings of traditional convolutional neural networks in capturing global contextual information, thereby improving the detection accuracy of the model in complex backgrounds and diverse crack shapes. The experimental results show that the proposed model outperforms traditional models such as U-Net, TransUNet, and Mask R-CNN in terms of Dice coefficient, accuracy, recall, and F1 Score evaluation metrics, especially in the detection and localization of complex crack images, demonstrating high robustness.

KEYWORDS

Mask R-CNN, Swin Transformer, Concrete Cracks, Precision

CITE THIS PAPER

Hongbo Luo, Xiangyuan Ma, Fan Yu, Hybrid Detection Method for Concrete Cracks Based on Maskr-CNN and Swin Transformer. Journal of Artificial Intelligence Practice (2025) Vol. 8: 1-8. DOI: http://dx.doi.org/10.23977/jaip.2025.080401.

REFERENCES

[1] Azimi M, Pekcan G. Structural health monitoring using extremely compressed data through deep learning[J]. Computer‐Aided Civil and Infrastructure Engineering, 2020, 35(6): 597-614.
[2] M. Naser, Autonomous fire resistance evaluation, Journal of Structural Engineering, 146 (2020), Article 04020103, doi: 10.1061/(ASCE)ST.1943-541X.0002641.
[3] Dung C V. Autonomous concrete crack detection using deep fully convolutional neural network[J]. Automation in Construction, 2019, 99: 52-58.
[4] Naser M Z. Enabling cognitive and autonomous infrastructure in extreme events through computer vision[J]. Innovative Infrastructure Solutions, 2020, 5(3): 99.
[5] Ewald V, Groves R, Benedictus R. Integrative approach for transducer positioning optimization for ultrasonic structural health monitoring for the detection of deterministic and probabilistic damage location[J]. Structural Health Monitoring, 2021, 20(3): 1117-1144.
[6] Taheri F, Shadlou S, Esmaeel R A. Computational Modelling of Delamination and Disbond in Adhesively Bonded Joints and the Relevant Damage Detection Approaches[J]. Reviews of Adhesion and Adhesives, 2013, 1(4): 413-458.
[7] Rao A S, Nguyen T, Palaniswami M, et al. Vision-based automated crack detection using convolutional neural networks for condition assessment of infrastructure[J]. Structural Health Monitoring, 2021, 20(4): 2124-2142.
[8] Andrushia A D, Anand N, Arulraj G P. Evaluation of thermal cracks on fire exposed concrete structures using Ripplet transform[J]. Mathematics and Computers in Simulation, 2021, 180: 93-113.
[9] Dais D, Bal I E, Smyrou E, et al. Automatic crack classification and segmentation on masonry surfaces using convolutional neural networks and transfer learning[J]. Automation in Construction, 2021, 125: 103606.
[10] Dong C Z, Catbas F N. A review of computer vision–based structural health monitoring at local and global levels[J]. Structural Health Monitoring, 2021, 20(2): 692-743.
[11] Bal I E, Dais D, Smyrou E, et al. Novel invisible markers for monitoring cracks on masonry structures[J]. Construction and Building Materials, 2021, 300: 124013.
[12] Ali R, Kang D, Suh G, et al. Real-time multiple damage mapping using autonomous UAV and deep faster region-based neural networks for GPS-denied structures[J]. Automation in Construction, 2021, 130: 103831.
[13] Mohan A, Poobal S. Crack detection using image processing: A critical review and analysis[J]. alexandria engineering journal, 2018, 57(2): 787-798.
[14] Ji A, Xue X, Wang Y, et al. An integrated approach to automatic pixel-level crack detection and quantification of asphalt pavement[J]. Automation in Construction, 2020, 114: 103176.

Subscription
E-Mail Alert
Most popular papers
Call for Special Issue
Publication Ethics & OA Statement
Plagiarism Policy
Contact Us
Downloads: 16465
Visits: 570539

Sponsors, Associates, and Links

All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.