The Application of Close-Range Digital Photogrammetry Based on the Neural Network in Crack-Monitoring

Abstract:

Based on the two-dimensional Direct Linear Transformation (DLT) principle of close-range digital photogrammetry and mathematical principle of the linear neuron, the equivalent relationship between linear neural network and the two-dimensional DLT of close-range digital photogrammetry is discussed. A neural network with 2 linear neurons, 6 input parameters and 2 output parameters is established to simulate the two-dimensional DLT. The network can be trained using a set of grid points in the control coordinate system with known world coordinates and pixel coordinates. The weights and biases of trained network contain camera interior and exterior parameters. A new digital photographic technique is put forward combined camera self-calibration based on neural network with non-linear pixel coordinates correction of lens distortion. The indoor survey test indicates that measurement is more accuracy. Meanwhile, the new technology is successfully used in crack monitor of a bridge pier.

• Periodical: Applied Mechanics and Materials (Volumes 90-93)
• Pages: 2875-2880
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.90-93.2875
• Online since: September 2011
• Authors: Ming Ming Li, Jian Gong Chen, Yong Xing Zhang
• Keywords: Close-Range Digital Photography, Crack-Monitoring, Direct Linear Transformation (DLT), Neural Network (NN)

References

[1] Rossip.New method for detecting cracks in concrete using fiber optics [J].Material and structures,1989,22(13): 437-442.

[2] Ansari F.Real-time monitoring or concrete structures on embedded optical fiber[J].ASCE,1992,3:49-59.

[3] Mingquan Zhong. Influence of Fatigue Loading on the Stress of Non-Prestressed Reinforcement, Crack Width and Static Strength in PPC Beams[J]. Journal of Southwest Jiaotong University,1995, 30(3):283-290. (in Chinese)

[4] Jianguo Nie, Jumin Shen.Experimental Study on Long-Term Diagonal Crack Width of Reinforced Concret-e Beams[J].Journal of Building Structures,1995,16(3):4-9. (in Chinese)

[5] Jianglong Wu,Xingang Zhou. Method of measuring dynamic cracks on concrete structures[J].Journal of Shandong Institute of Architecture and Engineering,1999,14(2):12-15. (in Chinese)

[6] Wright, C. A., Weijers,L., Davis,E. J., Mayerhofer, M.: "Under staining hydraulic fracture growth: tricky but not hopeless. "SPE paper 56724 presented at the 1999 Annual Technical conference and Exhibition.Honston.oct.3-6.

DOI: 10.2118/56724-ms

[7] Yi Jiang, Christopher K. Y. Leung. Distributed fiber optical crack sensor[J].Piezoelectrics & Acoustooptics,2004,26(1):10-12. (in Chinese)

[8] Jing Wang, Hongqi Li, Dongmei Xing, Bo Jin, Jingwei Tong, Linan Li. Application of digital image corr-elation method in bridge cracks measurement[J].Chine-se Quarterly of Mechanics,2003,24(4):512-516. (in Chinese)

[9] Fei Geng, Chunxiang Qian. Image analysis techniquefor quantitative testing and evaluation of plastic shrinkage cracks in concrete[J].Journal of Southeast Universi-ty,2003,33(6):774-776. (in Chinese)

[10] Shuming Shi, Xiumin Chu, Rongben Wang. Resear-ch on asphalt pavement surface distress image measuring method[J]. Journal of Highway and Transportation Research and Development,2004,21(7):12-16. (in Chinese)

[11] Yiqun Zou, Guicang Hou, Feng Yang. A Surface cr-ack inspection algorithm based on digital image processing techniques[J]. Control & Automation,2004,20(4). (in Chinese)

[12] Dere Lin, Zhaobao Zheng. Analytic Photogrammetry[M]. Beijing:Surveying and Mapping Press,1992. (in Chinese)

[13] Jianqing Zhang, Li Pan, Shugen Wang.Photogrammetry [M].Wuhan:Wuhan University Publishing Pre ss, 2002. (in Chinese)

[14] Wenhao Feng. Close-rang Photogrammetry [M]. Wuhan:Wuhan University Publishing Press,2002. (in Chinese)

[15] Jiguang Chen, Qiangyong Zhang, Shucai Li. The application of direct linear transformation based on theneural network in geomechanics model test[J] .Rock and Soil Mechanics,2008,29(4):897-900. (in Chinese)