Article Details

Abstract

Bridges hold an important position in road traffic. The detection and maintenance of bridges have experienced a transformation from the manual stage to the automatic detection based on digital image processing technology. Nowadays, Artificial Intelligence technology is also widely applied in road and bridge detection. This paper mainly reviews the applications of digital image processing technology and Machine Learning technology in bridge crack detection and conducts a comparative study. Firstly, when traditional Machine Learning methods are used for road and bridge crack detection, it is necessary to pre-process the images in advance, including image denoising and image enhancement. This paper compares the efficiencies of image denoising and image enhancement algorithms. Secondly, in bridge detection, image segmentation and splicing are key steps. This paper experimentally compares the efficiencies of image splicing algorithms. Thirdly, a method is proposed for calculating the width, length, and area of cracks, and an experimental study is carried out. Finally, the differences between traditional Machine Learning and Deep Learning in bridge crack detection are compared.

Keywords

bridge crack detection; image processing; Deep Learning

References

1. [1] Yang Guojun, Ziahui, Shi Xiuming Overview of Bridge Crack Detection Based on Digital Image Technology [J]. Journal of Jilin University: Engineering Edition, 2024, 54 (2): 313-332
2. [2] SPENCER B F，HOSKERE V，NARAZAKI Y. Advances in Computer Vision-Based Civil Infrastructure Inspection and Monitoring [J].Engineering，2019，5（2）：199-222.
3. [3] Wang Rui, Qi Taiyue Research on Crack Characteristics Based on Machine Vision Detection [J]. Journal of Civil Engineering, 2016, 49 (7): 123-128
4. [4] SHI Y，CUI L，QI Z，et al. Automatic Road Crack detection Using Random Structured Forests [J].IEEE Transactions on Intelligent Transportation Systems，2016，17（12）：3434-3445.
5. [5] Liao Yanna, Li Wan Bridge crack detection method based on convolutional neural network [J]. Computer Engineering and Design, 2021, 42 (8): 2366-2372
6. [6] ADHIKARI R S，MOSELHI O，BAGCHI A. Image-based Retrieval of Concrete Crack Properties for Bridge Inspection [J].Automation in Construction，2014，39：180-194.
7. [7] KIM H，YOON J，SIM S. Automated Bridge Component Recognition from Point Clouds Using Deep Learning [J/OL].Structural Control and Health Monitoring，2020，27：e2591（2020-06-20）.https://doi.org/10.1002/stc.2591.
8. [8] LEE J S，PARK J，RYU Y M. Semantic Segmentation of Bridge Components based on Hierarchical Point Cloud Model [J/OL].Automation in Construction，2021，130：103847（2021-07-29）.https://doi.org/10.1016/j.autcon.2021.103847.
9. [9] HSIEH Y A，TSAI Y J. Machine Learning for Crack Detection：Review and Model Performance Comparison [J/OL].Journal of Computing in Civil Engineering，2020，34（5）：04020038（2020-07-13）.https://doi.org/10.1061/（ASCE）CP.1943-5487.0000918.
10. [10] Wen Jinhui, Research on Highway Damage Detection Based on YOLOX-s [D]. Langfang: North China University of Science and Technology, 2022
11. [11] Li Ruoxing Research on Concrete Crack Detection Method Based on Machine Vision [D]. Chongqing: Chongqing University, 2018
12. [12] DORAFSHAN S，THOMAS R J，MAGUIRE M. SD-NET2018: An Annotated Image Dataset for Non-Contact Concrete Crack Detection Using Deep Convolutional Neural Networks [J].Data in Brief，2018，21：1664-1668.
13. [13] Wang Mi, Pan Jun A uniform lighting method for digital aerial images [J]. Chinese Journal of Image and Graphics, 2004, 9 (6): 744-748
14. [14] Hu Qingwu, Li Qingquan Research on Remote Sensing Image Restoration Technology Based on Mask Principle [J]. Journal of Wuhan University: Information Science Edition, 2004, 29 (4): 319-323
15. [15] Li Shuo, Wang Hui, Wang Liyong, etc Remote Sensing Image Variational Mask Adaptive Uniformity Algorithm [J]. Journal of Remote Sensing, 2018, 22 (3): 450-457
16. [16] Zhu Shulong, Zhang Zhen, Zhu Baoshan, etc Comparison of the effectiveness of correction algorithms for uneven distribution of brightness and contrast in remote sensing images [J]. Journal of Remote Sensing, 2011, 15 (1): 111-122
17. [17] Gao Lijie, Xin Wenxue, Design of a deep learning based non-uniform illumination image recognition system [J]. Information and Computer, 2023 (9): 25-27
18. [18] Jin Pingping Research on Image Splicing and Crack Extraction Methods and Their Application in Multi legged Robot Bridge Detection [D]. Guangzhou: South China University of Technology, 2015
19. [19] YU L，HE S，LIU X，et al. Engineering-Oriented Bridge Multiple-Damage Detection with Damage Integrity Using Modified Faster Region-Based Convolutional Neural Network [J].Multimedia Tools and Applications，2022，81：18279-18304.
20. [20] PARISI F，MANGINI A M，FANTI M P，et al. Automated Location of Steel Truss Bridge Damage Using Machine Learning and Raw Strain Sensor Data [J/OL].Automation in Construction，2022，138：104249（2022-04-19）.https://doi.org/10.1016/j.autcon.2022.104249.
21. [21] GARG Y，MASIH A，SHARMA U. Predicting Bridge Damage During Earthquake Using Machine Learning Algorithms [C]//2021 11th International Conference on Cloud Computing，Data Science & Engineering（Confluence）.Noida：IEEE，2021：725-728.
22. [22] POZZER S，AZAR E R，ROSA F D，et al. Semantic Segmentation of Defects in Infrared Thermographic Images of Highly Damaged Concrete Structures [J/OL].Journal of Performance of Constructed Facilities，2021，35（1）：04020131（2020-10-31）.https://doi.org/10.1061/（ASCE）CF.1943-5509.0001541.
23. [23] DROGUETT E L，TAPIA J，YANEZ C et al. Semantic Segmentation Model for Crack Images from Concrete Bridges for Mobile Devices [J].Proceedings of the Institution of Mechanical Engineers Part O Journal of Risk and Reliability，2022，236（4）：570-583.
24. [24] LI Z，ZHU H，HUANG M. A Deep Learning-based Fine Crack Segmentation Network on Full-Scale Steel Bridge Images with Complicated Backgrounds [J].IEEE Access，2021，9：114989-114997.
25. Cui Mida, Wang Chao, Chen Jinqiao, etc Real time detection system for concrete bridge cracks based on ROS and YOLOv3 [J]. Journal of Southeast University: Natural Science Edition, 2023, 53 (1): 61-66
26. [26] Du Min, Yang Guoqing, Zhang Hui Research on Bridge Crack Detection Method Based on YOLOv4 EfficientNet B7 [J]. Journal of Tianjin Urban Construction University, 2023, 29 (1): 55-61
27. [27] PELEG S，ROSENFELD A. A Min-Max Medial Axis Transformation [J].IEEE Transactions on Pattern Analysis and Machine Intelligence，1981（2）：208-210.
28. [28] Wang Longyun Research on Road Crack Detection Algorithm [D]. Nanjing: Nanjing University of Posts and Telecommunications, 2012
29. [29] ZHANG T Y，SUEN C Y. A Fast Parallel Algorithm for Thinning Digital Patterns [J].Communications of the ACM，1984，27（3）：236-239.
30. [30] Zhou Ying, Liu Tong Concrete crack recognition based on computer vision [J]. Journal of Tongji University: Natural Science Edition, 2019, 47 (9): 1277-1285
31. Tang Qianlong, Tan Yuan, Peng Limin, etc Research on the Identification Method of Tunnel Lining Cracks Based on Digital Image Technology [J]. Journal of Railway Science and Engineering, 2019, 16 (12): 3041-3049
32. [32] Shen Lihui, Wu Baoguo, Yang Nai Research on Automatic Extraction Algorithm for Main Bone Lines of Facial Features [J]. Journal of Wuhan University: Information Science Edition, 2014, 39 (7): 767-771
33. [33] Liu Yufei Multi scale structural damage recognition based on model correction and image processing [D]. Beijing: Tsinghua University, 2015
34. Yang Shifeng, Chen Huaxiang, Li Xiaobing Research on determining crack width through image grayscale [J]. Highway Transportation Technology: Application Technology Edition, 2018, 14 (3): 71-72
35. [35] Yu Xin Research and Application of Bridge Crack Detection Algorithm in Complex Background [D]. Xi'an: Chang'an University, 2021
36. Wen Jinhui, Luan Shangmin Method for calculating the intersection area of two concave polygons based on set and recursive operations [J]. Mathematical Modeling and Its Applications, 2022, 11 (1): 16-22

Funding

Langfang Science and Technology Project (2024011090)

About the authors

Jiang Xiuli (1999-), female, Han ethnicity, from Linyi, Shandong Province, is currently pursuing a master's degree in emergency informationization; Wen Jinhui (1994-), male, Han ethnicity, from Longyan, Fujian, holds a master's degree and specializes in computer vision; Luan Shangmin (1968-), male, Han nationality, from Jinan, Shandong, professor, PhD, research direction: artificial intelligence and its applications.