台灣由於河流眾多，橋梁已成為不可或缺的交通基礎設施，因此對既有橋梁的劣化進行評估，不僅是為了維持兩地的聯絡，更是為廣大交通安全提供一個保障。最基本的工作是對橋梁的劣化情況進行監測，傳統上，橋梁檢查是通過人工現場目視進行的，過程中不僅存在高風險，同時也是一項勞動密集型的任務。近年由於無人機（Unmanned Aerial Vehicle, UAV）的高機動性，其被廣泛地應用於基礎設施的檢查。本研究亦將使用無人機搭載消費型相機以進行橋梁影像蒐集，同時藉著深度學習(Deep Learning)來完成對影像的語意分割(Semantic Segmentation)，實現以人工智慧進行橋梁劣化檢測的目標。此外，無人機在實際拍攝影像的過程中，很容易受到現場環境的影響造成影像模糊。由於模糊的影像不利於後續的應用，需予以剔除。然而以人工方式進行模糊影像篩選工作不僅費時，同時視覺上亦很難辨認一張影像的模糊程度且缺乏評估標準。因此本研究同樣嘗試以深度學習的方式，來偵測影像中的模糊區域。
本研究使用全卷積神經網路(Fully Convolutional Neural Network, FCN)以及Deeplab V3+對四種常見的橋梁劣化(裂縫、鏽蝕、剝落以及白華)和影像模糊進行訓練。過程中，將以人工方式對影像進行標註，作為進行訓練的基本資料，並透過不斷調整訓練參數來得到最佳的模型。在模型精度評估方面，將各模型對驗證集的資料進行驗證後，本研究使用多項精度指標從各方面解釋模型的預測能力，並根據模型於精度評估指標上的表現，提出該模型在語意分割任務中的適用性，同時比較兩種神經網路在各種橋梁劣化類別上的偵測結果。最終FCN在裂縫、鏽蝕、剝落以及白華的總體準確度(Overall Accuracy)分別為0.9386、0.4167、0.577和0.5175；而Deeplab V3+則分別為0.9865、0.9315、0.9042及0.8006。顯示Deeplab V3+在橋梁劣化的偵測上具有優勢，而FCN僅在裂縫類別上有較佳的表現。影像模糊方面，模型的總體準確度達到0.8076，確認藉由深度學習來尋找影像中的模糊區是一項可行的方式。

Due to the large number of rivers in Taiwan, bridges have become indispensable transportation infrastructure. Therefore, to evaluate the deterioration of existing bridges is to provide a guarantee for traffic safety. In this study, we use Unmanned Aerial Vehicle (UAV) to collect bridge images, and appeal deep learning to complete semantic segmentation of images, so as to achieve the goal of using artificial intelligence to detect bridge deterioration. In addition, when the drone is shooting, it is easy to be affected by the environment and cause blurry images. However, the process of manually removing blurred images is time-consuming. Therefore, this research also tries to detect blurry areas in images by means of deep learning.
In this study, Full Convolution Neural Network (FCN) and Deeplab V3+ were used to train four common bridge deteriorations and image blur model. In the process, the images will be labeled manually as the basic data for training. Finally, according to the performance of the model in each accuracy evaluation index, the applicability of the model in semantic segmentation task is proposed. The results show that Deeplab V3+ has advantages in the detection of bridge deterioration, and the overall accuracy is over 80%, while FCN only has better performance in the crack category. In terms of image blur, the overall accuracy of the model reaches 0.8076. It is confirmed that deep learning is a feasible way to find the blurred area in the image.

Badrinarayanan, V., Kendall, A., Cipolla, R., 2017. SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation. IEEE Trans Pattern Anal Mach Intell 39, 2481-2495.

Bottou, L., 2012. Stochastic gradient descent tricks, Neural networks: Tricks of the trade. Springer, pp. 421-436.

Cha, Y.-J., Choi, W., Büyüköztürk, O., 2017. Deep Learning-Based Crack Damage Detection Using Convolutional Neural Networks. Computer-Aided Civil and Infrastructure Engineering 32, 361-378.

Chen, L.-C., Papandreou, G., Schroff, F., Adam, H., 2017. Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587.

Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H., 2018. Encoder-decoder with atrous separable convolution for semantic image segmentation, Proceedings of the European conference on computer vision (ECCV), pp. 801-818.

Dong, Y., Wang, J., Wang, Z., Zhang, X., Gao, Y., Sui, Q., Jiang, P., 2019. A Deep-Learning-Based Multiple Defect Detection Method for Tunnel Lining Damages. IEEE Access 7, 182643-182657.

Duchi, J., Hazan, E., Singer, Y., 2011. Adaptive subgradient methods for online learning and stochastic optimization. Journal of machine learning research 12.

Gao, Y., Guo, S., Huang, K., Chen, J., Gong, Q., Zou, Y., Bai, T., Overett, G., 2017. Scale optimization for full-image-CNN vehicle detection, 2017 IEEE Intelligent Vehicles Symposium (IV). IEEE, pp. 785-791.

He, K., Zhang, X., Ren, S., Sun, J., 2016. Deep residual learning for image recognition, Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770-778.

Hinton, G.E., Osindero, S., Teh, Y.-W., 2006. A fast learning algorithm for deep belief nets. Neural computation 18, 1527-1554.

Hosmer Jr, D.W., Lemeshow, S., Sturdivant, R.X., 2013. Applied logistic regression. John Wiley & Sons.

Huang, R., Feng, W., Fan, M., Wan, L., Sun, J., 2018. Multiscale blur detection by learning discriminative deep features. Neurocomputing 285, 154-166.

Khaloo, A., Lattanzi, D., Cunningham, K., Dell’Andrea, R., Riley, M., 2018. Unmanned aerial vehicle inspection of the Placer River Trail Bridge through image-based 3D modelling. Structure and Infrastructure Engineering 14, 124-136.

Kim, I.H., Jeon, H., Baek, S.C., Hong, W.H., Jung, H.J., 2018. Application of Crack Identification Techniques for an Aging Concrete Bridge Inspection Using an Unmanned Aerial Vehicle. Sensors (Basel) 18.

Kingma, D.P., Ba, J., 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.

Kruachottikul, P., Cooharojananone, N., Phanomchoeng, G., Chavarnakul, T., Kovitanggoon, K., Trakulwaranont, D., Atchariyachanvanich, K., 2019. Bridge Sub Structure Defect Inspection Assistance by using Deep Learning, 2019 IEEE 10th International Conference on Awareness Science and Technology (iCAST). IEEE, pp. 1-6.

LeCun, Y., Bengio, Y., Hinton, G., 2015. Deep learning. Nature 521, 436-444.

LeCun, Y., Bottou, L., Bengio, Y., Haffner, P., 1998. Gradient-based learning applied to document recognition. Proceedings of the IEEE 86, 2278-2324.

Liu, W., Wang, Z., Liu, X., Zeng, N., Liu, Y., Alsaadi, F.E., 2017. A survey of deep neural network architectures and their applications. Neurocomputing 234, 11-26.

Long, J., Shelhamer, E., Darrell, T., 2015. Fully convolutional networks for semantic segmentation, Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 3431-3440.

Ma, K., Fu, H., Liu, T., Wang, Z., Tao, D., 2018. Deep blur mapping: Exploiting high-level semantics by deep neural networks. IEEE Transactions on Image Processing 27, 5155-5166.

Nair, V., Hinton, G.E., 2010. Rectified linear units improve restricted boltzmann machines, Icml.

Narazaki, Y., Hoskere, V., Hoang, T.A., Spencer Jr, B.F., 2018. Automated vision-based bridge component extraction using multiscale convolutional neural networks. arXiv preprint arXiv:1805.06042.

Radovic, M., Adarkwa, O., Wang, Q., 2017. Object recognition in aerial images using convolutional neural networks. Journal of Imaging 3, 21.

Ronneberger, O., Fischer, P., Brox, T., 2015. U-net: Convolutional networks for biomedical image segmentation, International Conference on Medical image computing and computer-assisted intervention. Springer, pp. 234-241.

Simonyan, K., Zisserman, A., 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.

Song, W., Jia, G., Zhu, H., Jia, D., Gao, L., 2020. Automated Pavement Crack Damage Detection Using Deep Multiscale Convolutional Features. Journal of Advanced Transportation 2020.

Su, B., Lu, S., Tan, C.L., 2011. Blurred image region detection and classification, Proceedings of the 19th ACM international conference on Multimedia, pp. 1397-1400.

Tieleman, T., Hinton, G., 2012. Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude. COURSERA: Neural networks for machine learning 4, 26-31.

Xu, H., Su, X., Xu, H., Li, H., 2019. Autonomous Bridge Crack Detection Using Deep Convolutional Neural Networks, 3rd International Conference on Computer Engineering, Information Science & Application Technology (ICCIA 2019). Atlantis Press.

Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J., 2017. Pyramid scene parsing network, Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 2881-2890.

Zou, Q., Zhang, Z., Li, Q., Qi, X., Wang, Q., Wang, S., 2018. Deepcrack: Learning hierarchical convolutional features for crack detection. IEEE Transactions on Image Processing 28, 1498-1512.

国土交通省橋梁維持管理部会, 2015。次世代社会インフラ用ロボット開発・導入の推進。

姚乃嘉, 2015。建立行動裝置3D橋梁檢測應用程式之研究。國立中央大學營建管理研究所。科技部計畫報告。

姚乃嘉, 黃榮堯, 楊智斌, 蔡閔光, 葉啟章, 許文科, 任以永, 廖先格, 莊友涵, 廖艾貞, 2015。第二代臺灣地區橋梁管理資訊系統建置規劃。國立中央大學營建管理研究所。交通部運輸研究所計畫報告。

姚乃嘉, 蔡閔光, 陳明正, 葉啟章, 吳明諺, 白耀升, 廖先格, 莊友涵, 廖艾貞, 2017。 橋梁檢測工具效能提升計畫。國立中央大學營建管理研究所。交通部運輸研究所計畫報告。

孫浩庭, 2020。無人飛行載具於橋梁檢測之研究-以黎霧橋及蘭陽大橋為例。國立宜蘭大學土木工程學系研究所碩士論文。

張智安, 2017。以影像特徵自動化估計影像模糊指標。國立交通大學土木工程學系研究所。

連冠婷, 2018。以全卷積網路結合物件導向影像分類進行橋梁裂縫偵測。國立成功大學測量及空間資訊學系研究所碩士論文。

詹凱智, 張智安, 2015。無人載具遙測影像之移動模糊偵測及影像修復。國立交通大學土木工程學系研究所碩士論文。

蕭凱文, 饒見有, 王瑞麟, 2017。利用多軸無人機影像萃取橋梁劣化區三維空間資訊。航測及遙測學刊23(3)：205-211。