臺灣博碩士論文加值系統

近年為了延長結構物之壽命與避免受到天然災害之二次損傷，結構健康監測於實務上日益重要，透過即時與自動化之方式將結構物之健康資訊傳遞給居民，亦或是工程師以利後續之補強工程。而傳統之結構健康監測方式為利用有線感測器傳遞電子訊號至主機，再由主機從感測器所提供之資訊進行結構健康監測。而本研究目的為提出一自動化方式，有別於一般有線感測器，以無線之影像量測、電腦視覺與深度學習判斷混凝土構件表面之裂縫性質，以非破壞性檢測裂縫之方式，提供裂縫相關資訊使非專業人士也能夠判斷混凝土構件之健康情況。

本研究首先利用基於人工智慧中深度學習以及遷移學習的方式，藉由學習訓練資料中每張影像特徵，訓練出屬於本研究之裂縫辨識模型。訓練完畢後，透過其架構能夠自動卷積每張影像提取特徵，進而自動化地判斷影像中混凝土表面裂縫之有無與將其位置框選出，隨後將深度學習所判斷裂縫之位置，進行影像處理，經過電腦視覺之方法，將混凝土表面上的裂縫萃取出，最後利用影像量測之方式，計算混凝土表面之裂縫長度、寬度。

本研究利用現場拍攝不同混凝土構件表面之裂縫影像，來評估方法的可靠性。利用事先校正好之雙相機模型於現場拍攝裂縫影像，將其輸入至本研究方法中，經由量測裂縫實際長度與寬度作為驗證，本研究方法所計算結果與實際值相當，顯示本研究方法能夠成功地判斷裂縫性質。而該方法能藉由非破壞性的檢測方式，進一步了解混凝土構件的破壞程度，可作為結構健康監測方法之一。

Structural health monitoring becomes more and more important in practice because this technology can elongate the structural life cycle as well as protect structures against natural hazards. Moreover, structural health monitoring systems can automatically inform residents and users for the current condition of structures and engineers for the current performance. In past, structural health monitoring relies on the contact sensors to acquire structural responses and then diagnoses structures in accordance with the measurements. In this research, a new method is developed to detect and quantify the concrete cracks based on the noncontact image measurements. This method integrates computer vision and deep learning to identify the crack existence and geometry. The identified cracks can provide indirect information for experts to further investigate the structural conditions.

This study exploits deep learning and transfer learning, e.g., the tools in the category of artificial intelligence, to train and establish a concrete segmentation model that can identify the locations of cracks in images. In this model, the crack features can be obtained from the convolutional neural network and then automatically identify whether the cracks are present and where the cracks are. Then, the image processing and computer vision are implemented to highlight and extract these cracks from images. Finally, the geometry of these cracks (i.e., lengths and widths) can be calculated by image measurement techniques.

To verify the proposed method, this study employs the images of concrete surface cracks obtained from the real-world structures and then evaluate the reliability of this method. In the verification, the pre-calibrated stereo camera model with a two-camera setup is used to verify the actual lengths and widths of cracks. The calculated results are compared with the actual measurements. As a result, the proposed method can successfully determine crack geometry. Moreover, the method also benefits users to obtain crack information and to turn into performance evaluation of concrete structures for structural health monitoring.

口試委員會審定書 #
誌謝 I
摘要 III
Abstract V
目錄 VII
圖目錄 XI
表目錄 XVI
第一章 緒論 1
1.1 研究動機 1
1.2 文獻回顧 2
1.2.1 電腦視覺與影像量測於結構健康監測應用 2
1.2.2 深度學習於結構健康監測之應用 3
1.3 本文內容 4
第二章 數位影像量測分析 6
2.1 前言 6
2.2 相機成像原理 6
2.2.1 針孔相機成像原理 6
2.2.2 座標系統間之幾何轉換關係 7
2.3 相機校正 11
2.3.1 張氏校正法 11
2.3.2 計算單應矩陣 12
2.3.3 計算內、外參數矩陣 13
2.3.4 最大似然法估計 15
2.4 雙相機模型 15
2.4.1 雙相機幾何關係 16
2.4.2 基礎矩陣 16
2.4.3 求解基礎矩陣 18
2.5 立體視覺模型 19
2.5.1 雙平行相機 19
2.5.2 深度計算 21
2.6 小結 22
第三章 電腦視覺處理分析 23
3.1 前言 23
3.2 數位影像種類 23
3.2.1 彩色影像 23
3.2.2 灰階影像 24
3.3 影像滲濾法 25
3.3.1 裂縫偵測 25
3.3.2 滲濾法結果 28
3.3.3 移除光影效果 30
3.3.4 增加裂縫對比度 33
3.4 除噪與分群 36
3.4.1 中值濾波器 36
3.4.2 分群 37
3.5 小結 40
第四章 深度學習於影像辨識之應用 41
4.1 前言 41
4.2 機器學習 41
4.2.1 監督與非監督式學習 41
4.3 深度學習 44
4.3.1 卷積神經網路 45
4.3.2 線性整流函數 49
4.3.3 池化層 50
4.3.4 全連接層 51
4.3.5 訓練過程 60
4.4 物體偵測 61
4.4.1 R-CNN 61
4.4.2 Fast R-CNN 62
4.4.3 Faster R-CNN 63
4.5 遷移式學習 65
4.6 小結 67
第五章 裂縫辨識與影像量測 68
5.1 前言 68
5.2 實驗步驟 68
5.3 實驗儀器與硬體配置 70
5.4 資料準備與訓練 74
5.4.1 標籤影像 74
5.4.2 訓練模型 74
5.4.3 模型訓練 80
5.4.4 校正雙相機參數矩陣 85
5.5 實驗結果與分析 88
5.6 小結 104
第六章 結論與未來展望 106
6.1 結論 106
6.2 未來展望 108
參考文獻 109

[1] Abdel-Qader, I., Abudayyeh, O., Kelly, M.E. (2003), “Analysis of edge-detection techniques for crack identification in bridges,” Journal of Computing Civil Engineering , 17(4), 255-63.
[2] Kim, H., Ahn, E., Cho, S., Shin, M., Sim S.H. (2017), “Comparative analysis of image binarization methods for crack identification in concrete structures,” Cement Concrete Research, 99, 53-61.
[3] Yamaguchi, T., Hashimoto, S. (2006), “ Automated crack detection for concrete surface image using percolation model and edge information,” IECON 2006 - 32nd Annual Conference on IEEE Industrial Electronics, 3355-3360.
[4] Yamaguchi, T., Nakamura, S., Hashimoto, S. (2008), “An efficient crack detection method using percolation-based image processing,” 2008 3rd IEEE Conference on Industrial Electronics and Applications, 1875-1880.
[5] Yamaguchi, T., Hashimoto, S. (2010), “Fast crack detection method for large-size concrete surface images using percolation-based image processing,” Machine Vision and Application, 21(5), 797-809.
[6] Zhu, Z., German, S., Brilakis, I. (2011), “Visual retrieval of concrete crack properties for automated post-earthquake structural safety evaluation,” Automation in Constructtion, 20(7), 874-83.
[7] Nishikawa, T., Yoshida, J., Sugiyama, T., Fujino, Y. (2012), “Concrete crack detection by multiple sequential image filtering,” Computer-Aided Civil And Infrastructure Engineering, 27(1), 29-47.
[8] Jahanshahi, M.R., Kelly, J.S., Masri, S.F., Sukhatme, G.S. (2009), “A survey and evaluation of promising approaches for automatic image-based defect detection of bridge structures,” Structure and Infrastructre Engineering, 5(6), 455-486.
[9] Jahanshahi, M.R., Masri, S.F. (2013), “A new methodology for non-contact accurate crack width measurement through photogrammetry for automated structural safety evaluation,” Smart Materials Structures, 22(3), 035019.
[10] Adhikari, R.S., Moselhi, O., Bagchi, A. (2014), “Image-based retrieval of concrete crack properties for bridge inspection,” Automation in Construction, 39, 180-194.
[11] Zhang, W., Zhang, Z., Qi, D., Liu, Y. (2014), “Automatic crack detection and classification method for subway tunnel safety monitoring,” Sensors(Basel), 14 (10), 19307–19328.
[12] LeCun, Y., Bengio, Y., Hinton, G. (2015), ”Deep learning,” Nature, 521(7553), 436–44.
[13] Bojarski, M., Del, T.D., Dworakowski, D., Firner, B., Flepp, B., Goyal, P., et al. (2016), “End to end learning for self-driving cars,” arXiv, 1604.07316v1.
[14] Litjens, G., Kooi, T., Bejnordi, BE, Setio A.A.A., Ciompi, F., Ghafoorian, M., et al. (2017), “A survey on deep learning in medical image analysis,” Med Image Anal, 42, 60–88.
[15] Xu, Y., Bao, Y., Chen, J., Zuo, W., Li, H. (2018), “Surface fatigue crack identification in steel box girder of bridges by a deep fusion convolutional neural network based on consumer-grade camera images,” Structural Health Monitoring, 18(3), 653-674.
[16] Zhang, L., Yang, F., Zhang, Y.D., Zhu, Y.J. (2016), “Road crack detection using deep convolutional neural network,” 2016 IEEE International Conference on Image Processing, 3708-3712.
[17] Zhang, A., Wang, K.C.P., Li, B., Yang, E., Dai, X., Peng, Y., et al.(2017), “Automated pixel-level pavement crack detection on 3D asphalt surfaces using a deep-learning network,” Computer-Aided Civil Infrastructure Engineering, 32(10), 805-819.
[18] Cha, Y.J., Choi, W., Büyüköztürk, O. (2017), “Deep learning-based crack damage detection using convolutional neural networks,” Computer-Aided Civil Infrastructure Engineering, 32(5), 361–378.
[19] Kim, H., Ahn, E., Shin, M., Sim, S.H. (2018), “Crack and noncrack classification from concrete surface images using machine learning,” Structural Health Monitoring, Apr 23.
[20] Kim, B., Cho, S. (2018), “Automated vision-based detection of cracks on concrete surfaces using a deep learning technique,” Sensors (Basel), 18(10), 3452.
[21] Kim, B., Cho, S. (2018), “Automated and practical vision-based crack detection of concrete structures using deep learning,” Computer-Aided Civil Infrastructure Engineering, In press.
[22] Cha, Y.J., Choi, W., Suh, G., Mahmoudkhani, S., Büyüköztürk, O. (2018), “Autonomous structural visual inspection using region-based deep learning for detecting multiple damage types,” Computer-Aided Civil Infrastructure Engineering, 33(9), 731–47.
[23] Zhang, Z.Y. (2000), “A Flexible New Technique for Camera Calibration,” IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(11), 1330-1334.
[24] Christopher, L.H. (1981), “A computer algorithm for reconstructing a scene fromtwo projections,” Nature, 5828(291), 133-135.
[25] Fujita, Y., Hamamoto, Y. (2010), “A robust automatic crack detection method from noisy concrete surfaces,” Machine Vision and Applications, 22(2), 245-254.
[26] Krizhevsky, A., Sutskever, I., Hinton, G.E. (2017), “ImageNet classification with deep convolutional neural networks,” Communications of the ACM, 60(6), 84–90.
[27] Werbos, P.J. (1974), “Beyond regression: New tools for prediction and analysis in the behavioral sciences,” PhD thesis, Harvard University.
[28] Girshick, R., Donahue, J., Darrell, T., Malik, J. (2014), “Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation,” 2014 IEEE Conference on Computer Vision and Pattern Recognition.
[29] Uijlings, J.R.R., van de Sande, K.E.A., Gevers, T., Smeulders, A.W.M. (2013), “Selective Search for Object Recognition,” International Journal of Computer Vision, 104(2), 154-171.
[30] Felzenszwalb, P.F., Huttenlocher, D.P. (2004), “Efficient Graph-Based Image Segmentation,” International Journal of Computer Vision, 59(2), 167-181.
[31] Girshick, R. (2015), “Fast R-CNN,” IEEE International Conference on Computer Vision (ICCV), 1440-1448.
[32] Ren, S., He, K., Girshick, R., Sun, J. (2017), “Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks,” IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(6), 1137-1149.
[33] Canziani, A., Paszke, A., Culurciello, E. (2017), “An Analysis of Deep Neural Network Models for Practical Applications,” Computer Vision and Pattern Recognition, arXiv:1605.07678.
[34] Szegedy, C., Wei, L., Jia, Y., Sermanet, P., Reed, S., et al. (2015), “Going deeper with convolutions,” 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), arXiv:1409.4842.
[35] Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z. (2016), “Rethinking the Inception Architecture for Computer Vision,” 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), arXiv:1512.00567.