Image Mosaic Using SIFT for Bridge Cable Surface Flaw Detection

Abstract:

A machine vision system is developed to detect the cable surface damage of cable-stayed bridge. In the system, four cameras are employed to acquire images around the cable surface. So the same one defect may be split into several images. Image mosaic had to be done to obtain a complete defect image for further process. The feature of cable surface image is simple and its illumination is heterogeneous. So the Scale Invariant Feature Transform (SIFT) feature matching algorithm is suitable for the image mosaic. Firstly, cable surface images should be preprocessed. Secondly, the SIFT algorithm achieves the detection, extraction, description and matching of feature points for defect images. Finally, image fusion is implemented to acquire the integrated image and a complete defect will be showed in the image. Experimental results show that using SIFT for the cable defect image mosaic has good effect on improving the detection accuracy and integrity for cable surface defects.

• Periodical: Applied Mechanics and Materials (Volumes 333-335)
• Pages: 1654-1658
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.333-335.1654
• Online since: July 2013
• Authors: Xin Ke Li, Chao Gao, Yong Cai Guo, Yan Hua Shao, Fu Liang He
• Keywords: Bridge Cable, Image Mosaic, Machine Vision, SIFT, Surface Damage Detection

References

[1] Gao Chao, Li Xinke, Guo Yongcai and He Fuliang, Cable Health Monitoring System for Long-span Cable-stayed Bridge,. Disaster Advances, vol. 4, No. 1, pp.130-135, (2011).

[2] Lee J. -J., Kim K. -D., Ho H. -N., A vision-based damage detection of cable exterior in cable-stayed bridges,. The Sixth International Conference on Bridge Maintenance, Safety and Management, Stresa, Lake Maggiore, Italy. pp.1138-1145, (2012).

DOI: 10.1201/b12352-159

[3] Mahmoud Al-Hader, Ahmad Rodzi, Mohd Hasmadi Ismail, Alias Mohd Sood, Utilization of the Dynamic Laser Scanning Technology for Monitoring, locating and Classification of the City Trees, International Journal of Information Processing and Management, Vol. 2, No. 1, pp.148-159, (2011).

DOI: 10.4156/ijipm.vol2.issue1.17

[4] Lowe David, Distinctive Image Features from Scale-in-variant Keypoints, ．International Journal of Computer Vision, Vol. 60, No. 1, pp.91-110, 2004.

DOI: 10.1023/b:visi.0000029664.99615.94

[5] Zetao Jiang, Jiping Wu, Tongmin Liu, Dejing Cui, Stitching Method for Distorted Image Based on SIFT Feature Matching, Journal of Communication and Information Science, Vol. 3, No. 1, pp.1-8, (2013).

[6] Zhang Xue-wu, Ding Yan-qiong, Lv Yan-yun, Shi Ai-ye, Liang Rui-yu, A vision inspection system for the surface defects of strongly reflected metal based on multi-class SVM,. Expert Systems with Applications, vol. 38, pp.5930-5939, (2011).

DOI: 10.1016/j.eswa.2010.11.030

[7] Jaka Katrasnik, Franjo Pernus, Bostjan Likar, A Survey of Mobile Robots for Distribution Power Line Inspection,. IEEE Transactions on Power Delivery, Vol. 25, No. 1, pp.485-493, (2010).

DOI: 10.1109/tpwrd.2009.2035427

[8] Reza Javanmard Alitappeh, Kossar Jeddi Saravi and Fariborz Mahmoudi, A New Illumination Invariant Feature Based on SIFT Descriptor in Color Space,. Engineering Procedia, vol. 41, pp.305-311, (2012).

DOI: 10.1016/j.proeng.2012.07.177

[9] Lowe David, Object recognition from local scale-invariant features. International Conference on Computer Vision, Corfu, Greece, pp.1150-1157. (1999).

DOI: 10.1109/iccv.1999.790410

[10] Beis J. S. and Lowe David, Shape indexing using approximate nearest-neighbour search in highdimensional spaces,. Conference on Computer Visionand Pattern Recognition, Puerto Rico, pp.1000-1006, (1997).

DOI: 10.1109/cvpr.1997.609451