Comparing Automated Image-Based Crack Detection Techniques in the Spatial and Frequency Domains

Cracks are ubiquitous phenomena in concrete structures, especially in road pavements and bridge decks. Locating and measuring the concrete cracks are among the most time-consuming practices in structural health monitoring and bridge inspection. Similar to other aspects of living in the modern era, many structural inspection practices are improving thorough automation. One common approach is to equip ground/aerial platforms with visual cameras and capture inspection images from the structure of interest. The number of acquired images can be burdensome and, due to their size and complexity, they require an excessive amount of manual post-processing to count, measure and classify the cracking on the structure. Developing and selecting a post-processing algorithm(s) to automatically discover cracks can solve the issues with large datasets and excessive inspection times. In this paper three popular edge detectors, Sobel and Roberts edge detectors in spatial domain, and Gaussian high pass filter method in frequency domain, are implemented in a Matlab program to detect cracks in 100 captured images by an Unmanned Aerial Vehicle from bridge decks (50 defected and 50 sound). The Sobel method provided the most accurate results with 92% successful detection while this number was 83% and 81% for Gaussian and Roberts, respectively. In terms of sensitivity, the minimum crack width detectable by Sobel method was 2.5 pixels which was 0.5 pixel less than Gaussian and 1 pixel less than Roberts. Another perks of using Sobel method was its speed. With 0.95 second per image, Sobel was slightly faster than Roberts, with 0.98 second per image, and significantly faster than Gaussian high pass filter with 1.33 seconds per images. Therefore, the Sobel edge detector was the most appropriate edge detector among the studied methods for crack detection in concrete structures.

References

[1] T. W. Ryan, H. R. A., M. J. Eric and D. L. j., "Bridge inspector’s reference manual," U.S. Department of Transportation, 2012.

[2] FHWA, "fhwa.dot.gov," 31 12 2015. [Online]. Available: https://www.fhwa.dot.gov/bridge/nbi/no10/wearing15.cfm. [Accessed 30 12 2016].

[3] T. Dorsey, 27 03 2016. [Online]. Available: http://www.aashtojournal.org/Pages/NewsReleaseDetail.aspx?NewsReleaseID=1466. [Accessed 2016 23 08].

[4] FHWA, 13 04 2014. [Online]. Available: https://www.fhwa.dot.gov/research/tfhrc/programs/infrastructure/structures/ltbp/ltbpresearch/rabit/index.cfm.

[5] R. S. Lim, H. M. La and W. Sheng, "A robotic crack inspection and mapping system for bridge deck maintenance," IEEE Transactions on Automation Science and Engineering, pp. 367-378, 2014.

[6] N. Gucunski, S. H. Kee, H. La, B. Basily, A. Maher and H. Ghasemi, "Implementation of a fully autonomous platform for assessment of concrete bridge decks RABIT," Structures Congress, pp. 23-25, 2015.

[7] S. Dorafshan and M. Maguire, "Unmanned Aieral Vehicle Bridge Inspection-Phase 1," Idaho Transportation Department, Boise, 2016.

[8] FAA, 10 10 2016. [Online]. Available: https://www.faa.gov/uas/media/Part_107_Summary.pdf.

[9] B. Jahne, Practical handbook on Image Processing for Scientific and Technical Applications, Boca Raton, FL: CRC Press Inc, 2004.

[10] J. Kittler, R. Marik, M. Mirmehdi, M. Petrou and J. Song, "Detection of Defects in Clour Textures Surfaces," in MVA, Guildford, 1994.

[11] I. Abdel-Qader, O. Abudayyeh and E. Michael, "Analysis of Edge-Detection Techniques for Crack," Journal of Computing in Civil Engineering, pp. 255-263, 2003.

[12] I. Abdel-Qader, S. Pashaie-Rad, O. Abudayyeh and S. Yehia, "PCA-Based algorithm for unsupervised bridge crack detection," Advances in Engineering Software, vol. 37, no. 12, pp. 771-778, 2007.

[13] T. Yamaguchi, S. Nakamura, R. Saegusa and S. Hashimoto, "Image-Based Crack Detection for Real Concrete Surfaces," IEEJ Transactions on Electrical and Electronic Engineering, vol. 3, no. 1, pp. 128-135, 2008.

[14] H.-G. Moon and J.-H. Kim, "Inteligent Crack Detecting Algorithm On The Concrete Crack Image Using Neural Network," in 28th ISARC, Seoul, 2011.

[15] H. Wang, Z. Chen and L. Sun, "Image Preprocessing Methods to Identify Micro-cracks of Road Pavement," Optics and Photonics Journal, vol. 3, no. 02, pp. 99-102, 2013.

[16] J.-W. Kim, S.-B. Kim, J.-C. Park and J.-W. Nam, "Development of Crack Detection System with Unmanned Aerial Vehicles and Digital Image Processing," in Advances in structural engineering and mechanics (ASEM15), Inchoen, Korea, 2015.

[17] A. Rimkus, A. Podviezko and V. Gribniak, "Processing digital images for crack localization in reinforced concrete members," Procedia Engineering, vol. 122, pp. 239-243, 2015.

[18] M. A. Talab, Z. Huanga, X. Fan and H. Liu, "Detection crack in image using Otsu method and multiple filtering inimage processing techniques," Optik-International Journal for Light and Electron Optics, vol. 127, no. 3, pp. 1030-1033, 2015.

[19] S. Dorafshan, M. Maguire and X. Qi, "Automatic Surface Crack Detection in Concrete Structures Using OTSU Thresholding and Morphological Operations," Utah State University, Logan, Utah, USA, 2016.

[20] R. C. Gonzalez and R. E. Woods, Digital image processing, 2008.

[21] N. Otsu, "A Threshold Selection Method from Gray-Level Histograms," IEEE Transactions on Systems, Man, and Cybernetics, pp. 62-66, 1979.

[22] L. S. Davis, "A survey of edge detection techniques," Computer graphics and image processing, pp. 248-270, 1975.

[23] H. Blinchikoff and H. Krause, Filtering in the time and frequency domains, The Institution of Engineering and Technology, 2001.

Metrics
Usage Shares
Total Views
40 Page Views
Total Shares
0 Tweets
40
0 PDF Downloads
0
0 Facebook Shares
Total Usage
40