基于计算机视觉技术的结构表面裂缝检测方法研究
|
摘要
计算机视觉技术用于混凝土结构表面裂缝检测,具有现场检测方便、效率高、客观性强的特点,但图像数据分析是该技术的核心,其中裂缝提取与定量测量较为复杂。为提高裂缝图像处理效率和准确率,将深度学习和数字图像处理技术相结合,提出一种裂缝检测方法。建立基于深度卷积神经网络的裂缝识别模型,在图像上自动定位裂缝并结合图像局域阈值分割方法提取裂缝。在裂缝宽度定量测量方面,采用双边滤波算法和三段线性变换对裂缝图像进行预处理,提高了裂缝边缘识别的精确度。通过改进边缘梯度法,实现裂缝最大宽度的定位和裂缝最大宽度的自动获取。该研究为全自动识别裂缝图像及高精度测量裂缝宽度提供了一种解决方法。
The application of computer vision technology to the surface crack detection of concrete structure is a new detection method, which has the characteristics of convenient site detection, high efficiency and strong objectivity. The image data analysis is the core of the technology, and image processing and crack detection are complex. In order to improve the efficiency and accuracy of image processing, a method based on deep learning and digital image processing is proposed in this paper. The deep convolution neural network(CNN) is used to establish the crack recognition model. The cracks are automatically located on the image and the image local threshold segmentation method is used to extract the cracks. For the measurement of crack width, the bilateral filtering algorithm and the three segment linear transformation are used to preprocess the crack image to improve the accuracy of crack edge recognition. By improving the edge gradient method, the maximum width of cracks can be located and the maximum width of cracks can be automatically acquired. This study provides a solution to automatic identification of crack images and quantitative measurement of crack width.
The application of computer vision technology to the surface crack detection of concrete structure is a new detection method, which has the characteristics of convenient site detection, high efficiency and strong objectivity. The image data analysis is the core of the technology, and image processing and crack detection are complex. In order to improve the efficiency and accuracy of image processing, a method based on deep learning and digital image processing is proposed in this paper. The deep convolution neural network(CNN) is used to establish the crack recognition model. The cracks are automatically located on the image and the image local threshold segmentation method is used to extract the cracks. For the measurement of crack width, the bilateral filtering algorithm and the three segment linear transformation are used to preprocess the crack image to improve the accuracy of crack edge recognition. By improving the edge gradient method, the maximum width of cracks can be located and the maximum width of cracks can be automatically acquired. This study provides a solution to automatic identification of crack images and quantitative measurement of crack width.
引文
[1] 彭玲丽,黄少旭,张申申,李乾. 浅谈无人机在桥梁检测中的应用与发展[J].交通科技, 2015(6):42-44. (PENG Lingli, HUANG Shaoxu, ZHANG Shenshen, LI Qian. Discussion on UAV application and development in bridge inspection[J]. Transportation Science & Technology, 2015(6): 42- 44. (in Chinese))
[2] SANKARASRINIVASAN S, BALASUBRAMANIAN E, KARTHIK K, CHANDRASEKAR U, GUPTA R. Health monitoring of civil structures with integrated UAV and image processing system [J]. Procedia Computer Science, 2015, 54: 508-515.
[3] LIM R S, LA H M, SHENG W. A robotic crack inspection and mapping system for bridge deck maintenance [J]. IEEE Transactions on Automation Science and Engineering, 2014, 11(2): 367-378.
[4] PHAM N H, LA H M. Design and implementation of an autonomous robot for steel bridge inspection[C]//Fifty-fourth Annual Allerton Conference on Communication, Control, and Computing. New York, USA:IEEE, 2016: 556-562.
[5] 耿飞,解建光,钱春香. 图像分析技术对混凝土裂缝的定量评价[J]. 混凝土, 2005 (5): 78-94.(GENG Fei, XIE Jianguang, QIAN Chunxiang. Image analysis for quantitative evalution of cracks in concrete [J]. Concrete, 2005 (5): 78-94. (in Chinese))
[6] YU T, ZHU A, CHEN Y. Efficient crack detection method for tunnel linning surface cracks baesd on infrared images[J]. Journal of Computing in Civil Engineering, 2016, 31(3): 1-11.
[7] PRASANNA P, DANA K J, GUCUNSKI N, BASILY B B, LA H M, LIM R S, PARVARDEH H. Automated crack detection on concrete bridges [J]. IEEE Transactions on Automation Science and Engineering, 2016, 13(2): 591-600.
[8] WANG S, QIU S, WANG W, et al. Cracking classification using minimum rectangular cover-based support vector machine[J]. Journal of Computing in Civil Engineering, 2017, 31(5): 04017027.
[9] KONSTANTINOS M E, PROTOPAPADAKIS A, DOULAMIS N. Deep convolutional neural networks for efficient vision based tunnel inspection[C]//IEEE International Conference on Intelligent Computer Communication & Proccessing. New York:IEEE, 2015:335-342.
[10] JE-KANG P, KWON B K, PARK J H, KANG D J. Machine learning-based imaging system for defect inspection[J]. International Journal of Precision Engineering and Manufacturing-Green Technology, 2016, 3(3): 303-310.
[11] YOKOYAMA S, MATSUMOTO T. Development of an automatic detector of cracks in concrete using machine learning [J].Procedia Engineering,2017,171:1250-1255.
[12] CHA Y J, CHOI W. Deep learning-based crack damage detection using convolutional neural networks [J]. Computer-Aided Civil and Infrastructure Engineering, 2017, 32(5): 361-378.
[13] WEISS K, KHOSHGOFTAAR T M, WANG D. A survey of transfer learning [J]. Journal of Big Data, 2016: DOI 10.1186/S40537-016-0043-6.
[14] GOODFELLOWM I, BENGIO Y, COURVILLE A. Deep learning [M]. Cambridge,Msachusetts:The MIT Press, 2016.
[15] YOSINSKI J, CLUNE J, BENGIO Y, LIPSON H. How transferable are features in deep neural networks?[J] Advances in Neural Information Processing Systems,2014, 27: 3320-3328.
[16] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks [C]//International Conference on Neural Information Processing Systems.Red Hook,NY,USA:Curran Associates Inc,2012:1097-1105.
[17] DENG J, DONG W, SOCHER R, et al. ImageNet: a large-scale hierarchical image database[C]//IEEE Conference on Computer Vision & Pattern Recognition. New York:IEEE, 2009: 248-255.
[18] GARETH J, DANIELA W, TREVOR H, ROBERT T. An Introduction to statistical learning [M]. New York: Spinger, 2013.
[19] 冈萨雷斯. 数字图像处理[M]. 3版. 北京:电子工业出版社, 2013: 88-93.(GONZALEZ R C. Digital image processing [M]. 3rd ed. Beijing: Publishing House of Electronics Industry, 2013: 88-93.(in Chinese))
[2] SANKARASRINIVASAN S, BALASUBRAMANIAN E, KARTHIK K, CHANDRASEKAR U, GUPTA R. Health monitoring of civil structures with integrated UAV and image processing system [J]. Procedia Computer Science, 2015, 54: 508-515.
[3] LIM R S, LA H M, SHENG W. A robotic crack inspection and mapping system for bridge deck maintenance [J]. IEEE Transactions on Automation Science and Engineering, 2014, 11(2): 367-378.
[4] PHAM N H, LA H M. Design and implementation of an autonomous robot for steel bridge inspection[C]//Fifty-fourth Annual Allerton Conference on Communication, Control, and Computing. New York, USA:IEEE, 2016: 556-562.
[5] 耿飞,解建光,钱春香. 图像分析技术对混凝土裂缝的定量评价[J]. 混凝土, 2005 (5): 78-94.(GENG Fei, XIE Jianguang, QIAN Chunxiang. Image analysis for quantitative evalution of cracks in concrete [J]. Concrete, 2005 (5): 78-94. (in Chinese))
[6] YU T, ZHU A, CHEN Y. Efficient crack detection method for tunnel linning surface cracks baesd on infrared images[J]. Journal of Computing in Civil Engineering, 2016, 31(3): 1-11.
[7] PRASANNA P, DANA K J, GUCUNSKI N, BASILY B B, LA H M, LIM R S, PARVARDEH H. Automated crack detection on concrete bridges [J]. IEEE Transactions on Automation Science and Engineering, 2016, 13(2): 591-600.
[8] WANG S, QIU S, WANG W, et al. Cracking classification using minimum rectangular cover-based support vector machine[J]. Journal of Computing in Civil Engineering, 2017, 31(5): 04017027.
[9] KONSTANTINOS M E, PROTOPAPADAKIS A, DOULAMIS N. Deep convolutional neural networks for efficient vision based tunnel inspection[C]//IEEE International Conference on Intelligent Computer Communication & Proccessing. New York:IEEE, 2015:335-342.
[10] JE-KANG P, KWON B K, PARK J H, KANG D J. Machine learning-based imaging system for defect inspection[J]. International Journal of Precision Engineering and Manufacturing-Green Technology, 2016, 3(3): 303-310.
[11] YOKOYAMA S, MATSUMOTO T. Development of an automatic detector of cracks in concrete using machine learning [J].Procedia Engineering,2017,171:1250-1255.
[12] CHA Y J, CHOI W. Deep learning-based crack damage detection using convolutional neural networks [J]. Computer-Aided Civil and Infrastructure Engineering, 2017, 32(5): 361-378.
[13] WEISS K, KHOSHGOFTAAR T M, WANG D. A survey of transfer learning [J]. Journal of Big Data, 2016: DOI 10.1186/S40537-016-0043-6.
[14] GOODFELLOWM I, BENGIO Y, COURVILLE A. Deep learning [M]. Cambridge,Msachusetts:The MIT Press, 2016.
[15] YOSINSKI J, CLUNE J, BENGIO Y, LIPSON H. How transferable are features in deep neural networks?[J] Advances in Neural Information Processing Systems,2014, 27: 3320-3328.
[16] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks [C]//International Conference on Neural Information Processing Systems.Red Hook,NY,USA:Curran Associates Inc,2012:1097-1105.
[17] DENG J, DONG W, SOCHER R, et al. ImageNet: a large-scale hierarchical image database[C]//IEEE Conference on Computer Vision & Pattern Recognition. New York:IEEE, 2009: 248-255.
[18] GARETH J, DANIELA W, TREVOR H, ROBERT T. An Introduction to statistical learning [M]. New York: Spinger, 2013.
[19] 冈萨雷斯. 数字图像处理[M]. 3版. 北京:电子工业出版社, 2013: 88-93.(GONZALEZ R C. Digital image processing [M]. 3rd ed. Beijing: Publishing House of Electronics Industry, 2013: 88-93.(in Chinese))