使用U-net全卷積神經網路實現橋梁塗層缺陷識別自動化

AUTOMATED BRIDGE COATING DEFECT RECOGNITION USING U-NET FULLY CONVOLUTIONAL NEURAL NETWORKS

10.6652/JoCICHE.202112_33(8).0002

黃一峰(I-Feng Huang)；陳柏翰(Po-Han Chen)；陳思愷(Su-Kai Chen)

鏽蝕 ； 深度學習 ； U-net ； 語義分割 ； deep learning ； rust ； U-net ； pixel-level

中國土木水利工程學刊

33卷8期（2021 / 12 / 01）

605 - 617

繁體中文

台灣的氣候大部分時間多為暖和與潮濕，導致了鋼橋較易生鏽之情形。鋼材鏽蝕往往是鋼橋在維養上的關鍵議題，加上橋梁是大多數國家的重要基礎設施，故有效的鋼橋鏽蝕檢測方法，有助於維護鋼橋的健康，亦可同時降低鋼橋的生命週期成本。過往的研究曾提出了一些鋼橋檢測相關之影像處理技術（IPTs），以快速有效地進行鏽蝕影像識別。鏽蝕識別的關鍵在於辨識真實的鏽斑，並排除類鏽斑之雜訊及處理亮度不均等問題。為了更有效及更快速地辨識鋼橋鏽蝕，本文探索了一個以深度學習為基礎之全卷積神經網路U-Net，開發了影像語義分割模型，及提供像素等級精度之嶄新鏽蝕影像辨識方法。

As the weather in Taiwan is mostly warm and humid, steel bridges get rusted easily. For rusting is one of the most significant factors in steel bridge maintenance, together with the crucial role that steel bridges play in most countries, it is important to develop effective steel bridge rust detection methods to enhance steel bridge health and safety, and lower the lifecycle cost of steel bridges. Some image processing techniques (IPTs) have been developed in prior research to quickly and effectively detect rust defects of steel bridges. The keys to rust defect recognition are the discrimination of rust spots from the background that may contain rust-like noises and the handling of non-uniform illumination. In order to detect rust spots in a more effective and efficient fashion, this paper explored a new rust recognition method that integrates a deep-learning-based fully convolutional neural network, namely U-net, and a newly developed image semantic segmentation model, to provide pixel-wise steel bridge rust defect recognition.

1. Baidu Library. https://wenku.baidu.com/view/eb2d600dbb68a98271fefadc.html.
2. AbdelRazig, Y. A.(1999).United States,Purdue University.
3. AbdelRazig, Y. A.(1999).Department of Civil Engineering, Purdue University.
4. Agarwal, K.,Chen, X.,Pan, L.,Yeo, S.(2011).Multiple signal classification algorithm for Nondestructive imaging of reinforcement bars and empty ducts in circular concrete columns.General Assembly & Scientific Symposium,Istanbul, Turkey:
5. Buda, M.,Maki, A.,Mazurowski, M. A..A systematic study of the class imbalance problem in convolutional neural networks.Neural Netw,106,249-259.
6. Caelli, T,Reye, D.(1993).On the classification of image regions by colour, texture and shape.Pattern Recognition,26(4),461-470.
7. Chen, P. H.,Chang, L. M.(2003).Artificial intelligence application to bridge painting assessment.Automation in Construction,12(4),431-445.
8. Chen, P. H.,Chang, Y. C.,Chang, L. M.,Doerschuk, P. C.(2002).Application of multiresolution pattern classification to steel bridge coating assessment.Journal of Computing in Civil Engineering,16(4),244-251.
9. Chen, P. H.,Yang, Y. C.,Chang, L. M.(2009).Automated bridge coating defect recognition using adaptive Ellipse approach.Automation in Construction,18(5),632-643.
10. Dass, R.,Priyanka,Devi, S.(2012).Image segmentation techniques.IJECT,3(1),66-70.
11. Dosovitskiy, A.,Springenberg, J. T.,Riedmiller, M.,Brox, T.(2014).Discriminative un-supervised feature learning with convolutional neural networks.NIPS
12. Esgiar, A. N.,Naguib, R. N.,Sharif, B. S.,Bennett, M. K.,Murry, A.(1998).Microscopic image analysis for quantitative measurement and feature identification of normal and cancerous colonic mucosa.IEEE Transactions on Information Technology in Biomedicine,2(3),197-203.
13. Fang, X.,Luo, H.,Tang, J.(2005).Structural damage detection using neural network with learning rate improvement.Computer & Structures,25,2150-2161.
14. Freeman, H.(1961).On the encoding of arbitrary geometric configurations.IRE Transactions on Electronic Computers,EC–10(2),260-268.
15. Frey, B. J.,Dueck, D.(2014).Clustering by passing messages between data points.Science,315,972-976.
16. Günsel, B.,Murat Tekalp, A.(1998).Shape similarity matching for query-by-example.Pattern Recognition,31(7),931-944.
17. Han, J.,Ma, K. K.(2002).Fuzzy color histogram and its use in color image retrieval.IEEE Transactions on Image Processing,11(8),944-952.
18. Haralick, R.,Shanmugam, K.,Dinstein, I.(1973).Textural features for image classification.IEEE Transactions on Systems,SMC–3(6),610-621.
19. Jain, A. K.,Vailaya, A.(1996).Image retrieval using color and shape.Pattern Recognition,29(8),1233-1244.
20. Jhanwar, N.,Chaudhuri, S.,Seetharaman, G.,Zavidovique, B.(2004).Content based image retrieval using motif cooccurrence matrix.Image and Vision Computing,22(14),1211-1220.
21. Jumb, V.,Sohani, M.,Shrivas, A.(2014).Color image segmentation using K-means clustering and Otsu’s adaptive thresholding.Int. J. Innov. Technol. Explor. Eng.,3(9),72-76.
22. Khan, A.,Ullah, J.,Jaffar, M. A.,Choi, T. S.(2014).Color image segmentation: a novel spatial fuzzy genetic algorithm.SIViP,8(7),1233-1243.
23. Kingma, Diederik,Ba, Jimmy(2014).,未出版
24. LeCun, Y.,Bengio, Y.,Hinton, G..Deep learning.Nature,7553,436-444.
25. Lee, S.,Chang, L. M.,Chen, P. H.(2005).Performance comparison of bridge coating defect recognition methods.Corrosion,61(1),12-20.
26. Li, D.,Cong, A.,Guo, S..Sewer damage detection from imbalanced cctv inspection data using deep convolutional neural networks with hierarchical classification.Autom. Constr.,101,199-208.
27. Liao, K. W.,Lee, Y. T.(2016).Detection of rust defects on steel bridge coatings via digital image recognition.Automation in Construction,71,294-306.
28. Liu, Z.,Cao, Y.,Wang, Y.,Wang, W.(2019).Computer vision-based concrete crack detection using U-net fully convolutional networks.Automation in Construction,104,129-139.
29. M.O.T.C, Statics of Ministry of Transportation and Communications, http://www.motc.gov.tw/ch/home.jsp?id=64&parentpath=0,6 (2016).
30. Maeda, H.,Sekimoto, Y.,Seto, T.(2016).Lightweight road manager: Smartphone-based automatic determination of road damage status by deep neural network.ACM SIGSPATIAL International Workshop on Mobile Geographic Information Systems
31. Nair, V.,Hinton, G.(2010).Rectified linear units improve restricted Boltzmann machines.Proceedings of the 27th International Conference on Machine Learning, Vol. ICML-10
32. Nishida, H.(2002).Structural feature indexing for retrieval of partially visible shapes.Pattern Recognition,35(1),55-67.
33. Ronneberger, O.,Fischer, P.,Brox, T.(2017).U-net: Convolutional networks for biomedical image segmentation.International Conference on Medical Image Computing and Computer-Assisted Intervention
34. Scherer, D.,Muller, A.,Behnke, S.(2010).Evaluation of pooling operations in convolutional architectures for object recognition.Artificial Neural Networks–ICANN
35. Shen, H. K.,Chen, P. H.,Chang, L. M.(2018).Humanvisual-perception-like intensity recognition for color rust images based on artificial neural network.Automation in Construction,90,178-187.
36. Shih, P. C.,Liu, C. J.(2005).Comparative assessment of content-based face image retrieval in Different color spaces.International Journal of Pattern Recognition and Artificial Intelligence,19(7),873-893.
37. Shitong H,Dong, B.,Wang, H. C.,Wu, G.(2020).Inspection of surface defects on stay cables using a robot and transfer learning.Automation in Construction,119,103382.
38. Swain, M. J.,Ballard, D. H.(1991).Color indexing.International Journal of Computer Vision,7(1),11-32.
39. Szegedy, C.,Liu, W.,Jia, Y.,Sermanet, P.,Reed, S.,Anguelov, D.,Rabinovich, A.(2014).Going deeper with convolutions.Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
40. Torre, V.,Poggio, T.(2009).On edge detection.IEEE Trans. Pattern Anal. Mach. Intell
41. Wu, X.,Ghaboussi, J.,Garrett, J.(1992).Use of neural networks in detection of structural damage.Computer & Structures,42,578-581.
42. 王坤賢(2001)。新竹，國立交通大學土木工程學系。
43. 卓益民(2003)。臺南，遠東科技大學研究所。
44. 曹又仁(2005)。高雄，國立中山大學機械與機電工程學系研究所。
45. 陳俐穎(2003)。臺南，成功大學統計學系。
46. 陳建文(2002)。臺南，國立成功大學測量工程學系。
47. 賴明皇(2004)。桃園，中央大學土木工程研究所。
48. 戴安琦(2003)。臺北，私立淡江大學資訊工程學系研究所。
49. 戴佳信(2003)。新竹，國立交通大學土木工程學系。