臺灣博碩士論文加值系統

隧道的襯砌異狀檢測採用了許多技術，其中以光達為最有效裂縫的辨識，光達所獲得的點雲可以手動處理但資料量極為龐大。自動化數據處理在確定裂縫的存在時無法提供足夠的功能；此外，在目前的裂縫辨識軟體中，大多以影像處理或深度學習法進行辨識，在這樣的模式下，需耗費長時間訓練及檢測且準確率僅有80%左右，因此如何改善光達在裂縫辨識上所面臨的問題為一重要課題。
為了提高隧道襯砌中點雲的自動檢測效率，本研究建立了一套程序，襯砌點雲經濾除、修剪並挑選明顯裂縫處轉存為影像型式，再以影像處理搭配主成分分析法、物件式影像分析、地理物件式影像分析等三種方法進行裂縫影像辨識，接著將辨識結果進行裂縫量測，獲得的量測結果再與實際大小比較，以瞭解誤差情形。本研究使用的襯砌型式分別為混凝土式及磚式之襯砌隧道，經三種檢測法辨識後，依據混淆矩陣衍生的準確率、錯誤率、誤報率、漏報率及KAPPA進行評估。
三種方法中，以地理物件式影像分析的結果最為良好，原因是以自動化決定分割尺度將影像分割，而分類除了像元外還納入其它屬性，比起像元式分類能有更佳的辨識能力，其處理程序為影像分割、物件初步訓練、知識模型建立及規則設置，透過物件初步訓練與建立知識模型進行第二次的分類，來提高分類結果。兩種襯砌的辨識結果，準確率皆達95%以上、Kappa皆達0.85以上。在量測方面，辨識結果的長度最大誤差約4%-34%、寬度最大誤差約23%-88%，檢測最小寬度為1.1公釐。

The inspection of tunnel lining conditions is have been carried out with many technologies, among which LiDAR is the most efficiency method for crack detection. However, it collects an immense amount of point cloud data, which could be handled manually. Automatic data processing didn’t provide enough function in determining the existence of cracks. Moreover, a majority of current tunnel crack detection software use image processing or deep learning to detect abnormalities. These methods require extensive training and time-consuming detection for accuracy of only approximately 80%. Therefore, it is an important issue to ameliorate the problems faced by LiDAR in tunnel crack detection. To improve the efficiency of auto-detection via point clouds form at tunnel linings, a combined routine is established. The point cloud data are then filtered and cropped for visibly discernible cracks to translate into image format. Image recognition for crack detection was then performed by combining image processing with three detection methods: Principal Component Analysis (PCA), Object-Based Image Analysis (OBIA), and Geographic Object-Based Image Analysis (GEOBIA). Crack measurements were produced from these image recognition results and then compared with the actual measurements to determine the level of error. The types of tunnel lining examined in this study are concrete tunnel linings and brick tunnel linings, which were evaluated using the accuracy rate, error rate, false-positive rate, false-negative rate, and Kappa coefficient after recognition via the three detection methods. From the three applied methods, GEOBIA produced the best results. This is because of its automated selection of the scale of image segmentation, along with its image recognition capability that outperforms pixel-based classification due to its implementation of elements in addition to pixels. The identification results of the two types of lining have consistent accuracy rates of over 95% and Kappa coefficients of over 0.85. In terms of measurements, the maximum error of length in the recognition results was between 4–34% and the maximum error of width was between 23–88%; the minimum width detected was 1.1 mm.

摘要 I
Abstract II
致謝 VI
目錄 VII
圖目錄 X
表目錄 XII
第1章 緒論 1
1.1 前言 1
1.2 研究動機與目的 2
1.3 研究流程 3
第2章 文獻回顧 5
2.1 裂縫檢測 5
2.2 隧道檢測 10
2.3 影像分類 14
2.4 雷射掃描儀介紹 14
2.4.1 商用系統介紹 17
2.4.2 光達系統之隧道應用 18
2.5 檢測方法簡介 21
2.5.1 主成分分析 21
2.5.2 物件式影像分析 22
2.5.3 地理物件式影像分析 23
第3章 研究方法 25
3.1 研究資料與工具 25
3.1.1 研究資料說明 25
3.1.2 研究工具 25
3.2 點雲初步處理 26
3.2.1 混凝土式壁面 26
3.2.2 磚式壁面 27
3.3 主成分分析 31
3.3.1 影像前處理 31
3.3.2 影像處理 33
3.3.3 主成分分析 35
3.3.4 特徵值辨識 37
3.4 物件式影像分析 37
3.4.1 影像分割 38
3.4.2 區塊分類 39
3.5 地理物件式影像分析 41
3.5.1 影像分割 41
3.5.2 區塊分類 42
3.5.3 提取特徵屬性 42
3.5.4 知識分類模型 43
3.5.5 設置分類規則 45
3.6 準確度評估 46
3.7 裂縫量測 48
3.7.1 主成分分析之裂縫量測 49
3.7.2 物件式影像分析、地理物件式影像分析之裂縫量測 51
第4章 研究成果及討論 54
4.1 主成分分析檢測結果 54
4.1.1 灰階化 54
4.1.2 對比增強 55
4.1.3 影像平滑 56
4.1.4 底帽變換 57
4.1.5 二值化 57
4.1.6 物件聯通 59
4.1.7 去除微小物件 59
4.1.8 主成分分析 60
4.1.9 特徵值辨識 61
4.1.10 檢測結果 62
4.2 物件式影像分析檢測結果 66
4.2.1 影像分割 66
4.2.2 物件分類 67
4.2.3 檢測結果 68
4.3 地理物件式影像分析 71
4.3.1 影像分割 71
4.3.2 物件分類 72
4.3.3 建立知識分類模型 73
4.3.4 設置分類規則 74
4.3.5 檢測結果 75
4.4 裂縫量測 78
4.4.1 主成分分析 78
4.4.2 物件式影像分析、地理物件式影像分析 78
4.5 討論 80
4.5.1 各檢測法比較 80
4.5.2 特徵因子 81
4.5.3 光達解析度 84
4.5.4 檢測結果探討 87
4.5.5 裂縫量測誤差探討 88
第5章 結論與建議 89
5.1 結論 89
5.2 建議 90
參考文獻 91
附錄 96

丁亞中、官群倫(2012) 物件導向多尺度分割之探討－以裸露地分類為例，中華民國地圖學會會刊，22(2)，49-62。
李佳翰(2013)，山岳隧道襯砌異狀肇因診斷技術研究，國立臺北科技大學，臺北。
盧家鋒(2013)，多變數分析:主成分分析法。國立陽明大學，檢自：
http://www.ym.edu.tw/~cflu/MedSigProcess_Class09_CFLu.pdf
黃仲偉、紀乃文、陳北亭、楊元森、林詠彬(2016)，影像量測於結構監測之應用。 土木水利，43(1)，66-74。
江怡萱(2014)，雷射掃描技術於隧道內空變位監測之應用，國立臺灣大學，台北。
經緯航太科技股份有限公司(2018)，106 及107 年度發展車載移動測繪系統(MMS)作業-工作總報告
邱顯晉、林金城(2015)，3D 雷射掃描應用於鐵路隧道空間資訊與檢測之案例探討，2015 電子計算機於土木水利工程應用研討會，臺中。
蕭牟淵、游本志、王泰典、蕭興臺(2010)，台灣公路隧道安全檢測及評估之研究。臺灣公路工程，36(5)，25-44。
王泰典、邱雅筑、李佳翰、陳正勳、黃燦輝(2015)，從我國岩石隧道檢修經驗探討營運期間結構行為演化及維護管理，土木水利，42(1)，14-25。
王慶雄、林蔚然(2015)，山區隧道損壞之檢測調查 — 以台20 線嘉寶隧道為例。中國土木水利工程學會，42(1)，54-63。
Abdel-Qader, I., Abudayyeh, O., ＆ Kelly, M. E. (2003). Analysis of Edge-Detection Techniques for Crack Identification in Bridges. Journal of Computing in Civil
Engineering, 17(4), 255-263.
Baatz, M., ＆ Schäpe, A. (2000). Multiresolution segmentation: an optimization approach for high quality multi-scale image segmentation,58,12-23.
Balaguer, C.,Montero, R.,Victores, J.G.,Martínez, S., ＆ Jardón, A.,(2014) Towards fully automated tunnel inspection: A survey and future trends. In ISARC.Proceedings of the International Symposium on Automation and Robotics in Construction. IAARC Publications,31,19-33.
Benz, U. C., Hofmann, P., Willhauck, G., Lingenfelder, I., ＆ Heynen, M. (2004).Multi-resolution, object-oriented fuzzy analysis of remote sensing data for GIS-ready information. ISPRS journal of photogrammetry and remote sensing,58(3-4), 239-258.
Blaschke, T., Hay, G. J., Kelly, M., Lang, S., Hofmann, P., Addink, E., Feitosa, R.Q.,Van der Meer, F., Van der Werff, H., Van Coillie, F. (2014). Geographic object based image analysis–towards a new paradigm. ISPRS journal of photogrammetry and remote sensing, 87, 180- 191.
Bose, K., ＆ Kumar Bandyopadhyay, S.(2016). Crack Detection and Classification in Concrete Structure. Journal for Research, 2(4), 29-38.
Bramer, M. (2007). Principles of Data Mining. 1sted., 41-50. London:Springer-Verlag.
Cha, Y. J., Choi, W., ＆ Buyukozturk, O. (2017). Deep Learning-Based Crack Damage Detection Using Convolutional Neural Networks. Computer-Aided Civil and Infrastructure Engineering, 32(5), 361-378.
Clark, P. J., ＆ Evans, F. C. (1954). Distance to nearest neighbor as a measure of spatial relationships in populations. Ecology, 35, 445-453.
Dhital, D., ＆ Lee, J. R. (2012). A Fully Non-Contact Ultrasonic Propagation Imaging System for Closed Surface Crack Evaluation. Experimental Mechanics, 52,1111-1122.
Drăguţ, L., Csillik, O., Eisank, C., ＆ Tiede, D.(2014). Automated parameterisation for multi-scale image segmentation on multiple layers. ISPRS journal of photogrammetry and remote sensing, 88, 119-127.
Faroudja, Y. C. (1988). NTSC AND BEYOND. IEEE Transactions on Consumer Electronic, 34(1), 166-178.
Fisher, R.B., Perkins, S., Walker, A., ＆ Wolfart, E. (1996). Hypermedia Image Processing Reference. England: John Wiley ＆ Sons Ltd.
Haack, A., Schreyer, J., ＆ Jackel, G. (1995). State-of-the-art of Non-destructive Testing Methods for Determining the State of a Tunnel Lining. Tunnelling and
Underground Space Technology incorporating Trenchless Technology Research, 4(10), 413-431.
Haralick, R. M., Sternberg, S. R., ＆ Zhuang, X.(1987). Image analysis using mathematical morphology. IEEE transactions on pattern analysis and machine intelligence, (4), 532-550.
Han, J.-Y., Guo, J., ＆ Jiang, Y.-S. (2013a).Monitoring tunnel deformations by means of multi-epoch dispersed 3D LiDAR point clouds: An improved approach.Tunnelling and Underground Space Technology, 38, 385-389.
Han, J.-Y., Guo, J., ＆ Jiang, Y.-S. (2013b).Monitoring tunnel profile by means of multi-epoch dispersed 3-D LiDAR point clouds. Tunnelling and Underground Space Technology, 33, 186-192.
Hay, G. J., ＆ Castilla, G.(2008). Geographic Object-Based Image Analysis (GEOBIA): A new name for a new discipline. In Blaschke, T., Lang, S.,Hay,G.J., (Eds.), Object-Based Image Analysis: Spatial Concepts for Knowledge-Driven Remote Sensing Applications(pp.75-89). London:Springer-Verlag.
Heritage, G. L., ＆ Large, A. R. G. (2009). Principles of 3D Laser Scanning. In Heritage, G. L., ＆ Large, A. R. G.(Eds.), Laser Scanning For the Envirormental Sciences(pp.21-34). New Jersey: John Wiley ＆ Sons Ltd.
Iyer, S., ＆ Sinha, S. K. (2005). A robust approach for automatic detection and segmentation of cracks in underground pipeline images. Image and Vision Computing, 23(10), 921-933.
Kim, M., Warner, T. A., Madden, M., ＆ Atkinson, D. S. (2011). Multi-scale GEOBIA with very high spatial resolution digital aerial imagery: scale, texture and
image objects. International Journal of Remote Sensing, 32(10), 2825-2850.
Kohavi, R., ＆ Provost, F. (Eds.),(1998). Machine learning: Special issue on application of machine learning and knowledge discovery process. Machine
Learning, 30(2/3),271–274.
Liu, Z., Suandi, S. A., Ohashi, T., ＆ Ejima, T. (2002). Tunnel crack detection and classification system based on image processing. In Machine Vision Applications in Industrial Inspection X , 4664, pp.145-153.
Lee, I. -M., Bae, G. -J., Lee, S. -W., ＆ Lee, J. G. (2004). Soundness Evaluation of a Tunnel Concrete Lining by Using the Hammer Impact-Induced Sound Wave.Key Engineering Materials,270-273, pp.1500-1505.
Marques, A. G. C. S., ＆ Correia, P. L. (2012). Automatic road pavement crack detection using SVM. Lisbon, Portugal: Dissertation for the Master of Science
Degree in Electrical and Computer Engineering at Instituto Superior Técnico.
McHugh, M. L. (2012). Interrater reliability: the kappa statistic. Biochemia medica:Biochemia medica, 22(3), 276-282.
Menendez, E., Victores, J. G., Montero, R., Martínez, S., ＆ Balaguer, C. (2018).Tunnel structural inspection and assessment using an autonomous robotic system. Automation in Construction, 87, 117-126.
Mohan, A., ＆ Poobal, S. (2018). Crack detection using image processing: A critical review and analysis. Alexandria Engineering Journal, 57(2), 787-798.
Murakami, T., Saito, N., Komachi, Y., Michikawa, T., Sakashita, M., Kogure, S.,Kase,K., Wada ,S., ＆ Midorikawa, K. (2018). High spatial resolution LIDAR
for detection of cracks on tunnel surfaces. In CLEO: Applications and Technology. Optical Society of America.
Myint, S. W., Gober, P., Brazel, A., Grossman-Clarke, S., ＆ Weng, Q. (2011). Perpixel vs. object-based classification of urban land cover extraction using high
spatial resolution imagery. Remote sensing of environment, 115(5), 1145-1161.
Neeraj Bhargava, G.S., Bhargava, R., ＆ Mathuria, M. (2013). Decision Tree Analysis on J48 Algorithm for Data Mining. International Journal of Advanced Research in Computer Science and Software Engineering, 3(6), 1114-1119.
Nieniewski, M., Chmielewski, L., Jozwik, A., ＆ Sklodowski, M. (1999).Morphological detection and feature-based classification of cracked cegions in
ferrites. Machine Graphics and Vision, 8(4), 699-712.
Protopapadakis, E., Makantasis, K., Kopsiaftis, G., Doulami, N., ＆ Amditis, A.(2016). Crack Identification Via User Feedback, Convolutional Neural Networks and Laser Scanners for Tunnel Infrastructures. Imaging and
Computer Graphics Theory and Applications, 4, 725-734.
Rajan, K. (2005) Materials informatics. Materials Today,8(10), 38-45.
Rejaur Rahman, M., ＆ Saha, S. K. (2009). Multi-resolution segmentation for objectbased classification and accuracy assessment of land use/land cover classification using remotely sensed data. Journal of the Indian Society of Remote Sensing, 36(2), 189-201.
Richards, J.A. (1998). Inspection, maintenance and repair of tunnels: International lessons and practice. Tunnelling and Underground Space Technology, 13(4),369-375.
Rodarmel, C., ＆ Shan, J. (2002). Principal component analysis for hyperspectral image classification.Surveying and Land Information Science, 62(2), 115-122.
Silva, W. R. L. D., ＆ Lucena, D. S. D. (2018).Concrete Cracks Detection Based on Deep Learning Image Classification. Proceedings, 2(8), 489.
Sinha, S. K., ＆ Fieguth, P. W. (2006). Automated detection of cracks in buried concrete pipe images. Automation in Construction, 15(1), 58-72.
Talab, A. M. A., Huang, Z., Xi, F., ＆ HaiMing, L. (2016). Detection crack in image using Otsu method and multiple filtering in image processing techniques.Optik-International Journal for Light and Electron Optics,127(3), 1030-1033.
Van Gosliga, R., Lindenbergh, R., ＆ Pfeifer, N.(2006). Deformation analysis of a bored tunnel bored tunnel by means of terrestaial laser scanning.
Viera, A. J., ＆ Garrett, J. M. (2005). Understanding interobserver agreement: the kappa statistic. Fam med, 37(5), 360-363.
Wang, B., Li, Y., Zhao, W., Zhang, Z., Zhang, Y., ＆ Wang, Z. (2019). Effective Crack Damage Detection Using Multilayer Sparse Feature Representation and Incremental Extreme Learning Machine. Applied Sciences, 9(3), 614.
Wehr, A., ＆ Lohr, U. (1999). Airborne laser scanning—an introduction and overview.ISPRS Journal of photogrammetry and remote sensing, 54(2-3), 68-82.
Wei, S., Chao, Z., Yang, J. Y., Wu, H. G.,Chen,M. J., Yue, A. Z.,Zhang, Y. N.,Sun,Chongli. (2010). Knowledge-based object oriented land cover classification using SPOT5 imagery in forest-agriculture ecotones. Sensor Letters, 8(1), 22-31.
Yoon, J. S., Sagong, M., ＆ Lee, J. S. (2007). Development of damage detection method on the tunnel lining from the laser scanning data. In Proceedings of the World Tunnel Congress 2007 and 33rd ITA/AITES Annual General Assembly,1469-1474.
Yoon, J. S., Sagong, M., Lee, J. S., ＆ Lee, K. S. (2009). Feature extraction of a concrete tunnel liner from 3D laser scanning data. Ndt ＆ E International,
42(2), 97-105.
Zhang, A., Wang, K. C. P., Li, B. X., Yang, E. H., Dai, X. X., Peng, Y., Yue, F., Yang,L., Li, J.Q., ＆ Chen, C. (2017). Automated Pixel-Level Pavement Crack Detection on 3D Asphalt Surfaces Using a Deep-Learning Network.Computer-Aided Civil and Infrastructure Engineering, 32(10), 805-819.
Zhang, W., Zhang, Z., Qi, D., ＆ Liu, Y. (2014).
Automatic crack detection and classification method for subway tunnel safety monitoring. Sensors, 14(10),19307-19328.
Zhong, Q., Bai, L., An, S. Q., Ju, F. R., ＆ Liu, L. (2016).Lining seam elimination algorithm and surface crack detection in concrete tunnel lining. Journal of
Electronic Imaging, 25(6).