近年來台灣道路平整度議題經常被提出來討論，其中一項就是孔蓋的正常與否。每年都需要花費大量的人力在孔蓋巡檢上。為保證巡檢品質與第二年作業需求，需要檢查作業人員拍攝回來之照片，其中包含著門牌以及閥栓近遠照等照片。路面平整度的另一個議題是路面破損，而目前路面破損之檢測如同閥栓巡檢一般依靠了大量的人力。為了減少大量人力需求，本研究將設計一快速且準確之閥栓分辨系統以及一道路破損辨識系統。

本研究中以YOLOv3-tiny及作為基礎，建置一快速分辨閥栓以及門牌之系統。在實驗結果中，本研究在近照之閥栓分辨結果中，達到了Precision 99.33%、Recall 98.89%之高精度。在門牌與街牌辨識的部分，也達到了Precision 95.96%、Recall 93.45%之精度。

道路破損辨識的部分，本研究使用YOLOv3類神經網路進行訓練，並使用一簡單之分割操作，提升了辨識準確率。並希望在未來使用其餘類神經網路以及各種技術，改善此一辨識率。

Road flatness plays a key role in traffic safety, the manhole covers placed on roads often reduce the flatness and cause traffic accident. In order to guarantee the traffic safety, it is necessary for government to do manhole-cover inspection every year. A lot of pictures, including doorplates, street signs, and manhole cover of valves and hydrants, will be reproduced in manhole-cover inspection, and it takes a large amount of time to check these pictures manually. Another important issue of traffic safety is road crack, and the inspection of this problem is also labor-intensive work. The objective of this study is to design an automatic inspection system of manhole-cover and road crack to reduce the workload.

The manhole-cover inspection system proposed in this study is based on YOLOv3-tiny network. Experimental results show that the system has high efficiency with precision of 99.33%, and recall of 98.89%. In terms of road-crack detection, this study applies YOLOv3 network to road-crack detection system, and uses simple image segmentation to detect the pictures, which increases system recall. In the future, we hope to improve the performance of detection by using other networks and operations.

萬國法律事務所，交通部公路總局-「道路工程引發國家賠償案件之研究分析」研究報告，https://www.aac.moj.gov.tw/ct.asp?xItem=442841&ctNode=44532&mp=289
C. Mertz, “Continuous road damage detection using regular service vehicles,” Proceedings of the ITS world congress, pp. 5-8, 2011.
A. Mednis, G. Strazdins, R. Zviedris, G. Kanonirs, and L. Selavo, “Real time pothole detection using android smartphones with accelerometers,” 2011 International conference on distributed computing in sensor systems and workshops (DCOSS), IEEE, pp. 1-6, Jun. 2011.
I. Abdel-Qader, O. Abudayyeh, and M. E. Kelly, “Analysis of edge-detection techniques for crack identification in bridges,” Journal of Computing in Civil Engineering, vol. 17, no. 4, pp. 255-263, Oct. 2003.
Y. Shi, L. Cui, Z. Qi, F. Meng, and Z. Chen, ‘‘Automatic road crack detection using random structured forests,’’ IEEE Transactions on Intelligent Transportation Systems, vol. 17, no. 12, pp. 3434–3445, Dec. 2016.
H. Oliveira and P. L. Correia, ‘‘Automatic road crack detection and characterization,’’ IEEE Transactions on Intelligent Transportation Systems, vol. 14, no. 1, pp. 155–168, Mar. 2013.
L. Zhang, F. Yang, Y. D. Zhang, and Y. J. Zhu, ‘‘Road crack detection using deep convolutional neural network,’’ 2016 IEEE international conference on image processing (ICIP), IEEE, pp. 3708-3712, Sep. 2016.
Y.-J. Cha, W. Choi, and O. Buy¨ uk¨ ozt ¨ urk, “Deep learning-based crack ¨ damage detection using convolutional neural networks,” Computer‐Aided Civil and Infrastructure Engineering, vol. 32, no. 5, pp. 361–378, Mar. 2017.
新北市路平報馬仔，https://rdm.ntpc.gov.tw/Road/NewCase.aspx
labelImg https://github.com/tzutalin/labelImg
J. Redmon, "Darknet: Open Source Neural Networks in C," http://pjreddie.com/darknet/, 2013~2016.
R. Girshick, J. Donahue, T. Darrell, and J. Malik, “Rich feature hierarchies for accurate object detection and semantic segmentation,” Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 580-587, Jun. 2014.
K. He, X. Zhang, S. Ren, and J. Sun, “Spatial pyramid pooling in deep convolutional networks for visual recognition,” IEEE transactions on pattern analysis and machine intelligence, vol. 37, no. 9, pp. 1904–1916, Sep. 2015.
R. Girshick, “Fast r-cnn,” Proceedings of the IEEE international conference on computer vision, pp. 1440-1448, 2015.
S. Ren, K. He, R. Girshick, and J. Sun, “Faster R-CNN: Towards real-time object detection with region proposal networks,” Advances in neural information processing systems, pp. 91-99, 2015.
J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You only look once: Unified, real-time object detection,” Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 779-788, 2016.
J. Redmon and A. Farhadi, “YOLO9000: better, faster, stronger,” Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 7263-7271, 2017.
J. Redmon and A. Farhadi, “Yolov3: An incremental improvement,” 2018, arXiv:1804.02767.
W. Liu, D. Anguelov, D. Erhan, C. Szegedy, and S. Reed, “SSD: Single shot multibox detector,” arXiv:1512.02325, 2015.
H. Oliveira and P. L. Correia, ‘‘Automatic road crack segmentation using entropy and image dynamic thresholding,’’ 2009 17th European Signal Processing Conference, IEEE, pp. 622-626, Aug. 2009.
H. Ma, N. Lu, L. Ge, Q. Li, X. You, and X. Li, “Automatic road damage detection using high-resolution satellite images and road maps,” Geoscience and Remote Sensing Symposium (IGARSS), 2013 IEEE International, pp. 3718–3721, 2013.
F.-C. Chen and M. R. Jahanshahi, "NB-CNN: Deep Learning-Based Crack Detection Using Convolutional Neural Network and Naïve Bayes Data Fusion," IEEE Transactions on Industrial Electronics, vol. 65, no. 5, pp. 4392-4400, 2018.
H. Maeda, Y. Sekimoto, T. Seto, T. Kashiyama, and H. Omata, “Road damage detection and classification using deep neural networks with smartphone images,” Computer‐Aided Civil and Infrastructure Engineering , vol. 33, no. 12, pp. 1127-1141, 2018.
T.-Y. Lin, P. Dollár, R. Girshick, K. He, B. Hariharan, and S. Belongie, “Feature pyramid networks for object detection,” Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 2117-2125, 2017.
K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770-778, 2016.
H. Law and J. Deng, “Cornernet: Detecting objects as paired keypoints,” Proceedings of the European Conference on Computer Vision (ECCV), pp. 734-750, 2018.
Y. Chen, H. Fang, B. Xu, Z. Yan, Y. Kalantidis et al., “Drop an octave: Reducing spatial redundancy in convolutional neural networks with octave convolution,” arXiv:1904.05049, 2019.