道路係國家重要公共交通設施，為保障人民用路權益及行車安全，定期執行道路鋪面巡檢作業以及養護道路鋪面乃有其必要性。道路鋪面大多由於交通載重、天氣或施工不良等因素產生破壞，於眾多道路破壞中，坑洞影響尤為嚴重，許導致重大交通事故。目前坑洞偵測方式係由巡查人員親臨現場量測，耗費人力且具危險性。近年，車載光達系統(Mobile Laser Systems, MLS)發展逐漸成熟，透過光達(Light Detection and Ranging, LiDAR)系統收集三維點雲空間資訊，用以獲取道路鋪面資訊。
本研究利用車載光達系統獲得大面積之三維點雲資訊作於偵測坑洞，原始車載點雲資料以Iterative Discretization Method Normal Distributions Transform (IDM-NDT)演算法執行點雲拼接，重建三維空間場景。使用最佳擬合平面演算法(Best Fitting Plane)計算道路鋪面凹陷處，並以坑洞垂直深度篩選、坑洞視線偵測篩選與最小面積篩選三種方法加以篩選，初探坑洞偵測之成果。本研究於臺南地區於30處實驗區收集總共41個坑洞，誤判偵測個數為56個，漏判偵測個數為5個，召回率為58.33%，精確率為11.11%。

Roads are important public transportation facilities in the country. In order to protect the rights and interests of people using roads and driving safety, it is necessary to carry out regular road pavement inspections and maintain road pavements. Road pavement is mostly damaged due to factors such as traffic load, weather, or poor construction. Among the many types of pavement distresses, potholes are significantly serious, which may lead to major traffic accidents. The current method of pothole detection is that inspection personnel come to the site to measure, which is labor-intensive and dangerous. The development of mobile laser system (MLS) has gradually matured in recent years. The Light Detection and Ranging (LiDAR) system is used to collect 3D point cloud to obtain road pavement information. In this research, a large area of 3D point cloud information is obtained by using the MLS to detect potholes. The original MLS point cloud data is matched to reconstruct the 3D scene. Use the Best Fitting Plane algorithm to calculate the road pavement depressions, and filter by pothole vertical depth filter, pothole sightline filter, and minimum area filter to obtain pothole detection results. In this research, a total of 41 potholes were collected in 30 experimental areas in Tainan. The proposed method has a recall of 0.58 and a precision of 0.02.

交通部(2019)，交通部公路總局公路養護手冊，臺北市：交通部。

交通部(2019)，交通部公路總局受理挖掘公路作業程序手冊，臺北市：交通部。

陳建旭, 孟繁萱, 李政德, & 陳志軒. (2018). 柔性鋪面生命週期成本分析. 鋪面工程, 16(4), 9-19.

Arjapure, S., & Kalbande, D. R. (2021, June). Deep learning model for pothole detection and area computation. In 2021 International Conference on Communication information and Computing Technology (ICCICT) (pp. 1-6). IEEE.

ASTM, A. (2020). D6433-20; Standard Practice for Roads and Parking Lots Pavement Condition Index Surveys. ASTM International: West Conshohocken, PA, USA.

Baek, J. W., & Chung, K. (2020). Pothole classification model using edge detection in road image. Applied Sciences, 10(19), 6662.

Besl, P. J., & McKay, N. D. (1992, April). Method for registration of 3-D shapes. In Sensor fusion IV: control paradigms and data structures (Vol. 1611, pp. 586-606). Spie.

Biber, P., & Straßer, W. (2003, October). The normal distributions transform: A new approach to laser scan matching. In Proceedings 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2003)(Cat. No. 03CH37453) (Vol. 3, pp. 2743-2748). IEEE.

Chen, Y., & Medioni, G. (1992). Object modelling by registration of multiple range images. Image and vision computing, 10(3), 145-155.

Cheng, L., Chen, S., Liu, X., Xu, H., Wu, Y., Li, M., & Chen, Y. (2018). Registration of laser scanning point clouds: A review. Sensors, 18(5), 1641.

Chiu, Y. T., Srinara, S., Tsai, M. L., & Chiang, K. W. (2022). IMPROVEMENT OF LiDAR-SLAM-BASED 3D NDT LOCALIZATION USING FAULT DETECTION AND EXCLUSION ALGORITHM. International Archives of the Photogrammetry, Remote Sensing & Spatial Information Sciences.

De Blasiis, M. R., Di Benedetto, A., & Fiani, M. (2020). Mobile laserscanning data for the evaluation of pavement surface distress. RemoteSensing, 12(6), 942

Dhiman, A., & Klette, R. (2019). Pothole detection using computer vision and learning. IEEE Transactions on Intelligent Transportation Systems, 21(8), 3536-3550.

Du, R., Qiu, G., Gao, K., Hu, L., & Liu, L. (2020). Abnormal road surface recognition based on smartphone acceleration sensor. Sensors, 20(2), 451.

Guan, J., Yang, X., Ding, L., Cheng, X., Lee, V. C., & Jin, C. (2021). Automated pixel-level pavement distress detection based on stereo vision and deep learning. Automation in Construction, 129, 103788.

Haq, M. U. U., Ashfaque, M., Mathavan, S., Kamal, K., & Ahmed, A. (2019). Stereo-based 3D reconstruction of potholes by a hybrid, dense matching scheme. IEEE Sensors Journal, 19(10), 3807-3817.

He, L., Ren, X., Gao, Q., Zhao, X., Yao, B., & Chao, Y. (2017). The connected-component labeling problem: A review of state-of-the-art algorithms. Pattern Recognition, 70, 25-43.

Kim, T., & Ryu, S. K. (2014). Review and analysis of pothole detection methods. Journal of Emerging Trends in Computing and Information Sciences, 5(8), 603-608.

Kim, Y. M., Kim, Y. G., Son, S. Y., Lim, S. Y., Choi, B. Y., & Choi, D. H. (2022). Review of Recent Automated Pothole-Detection Methods. Applied Sciences, 12(11), 5320.

Li, J., Chen, B., Yuan, M., Zhao, Q., Luo, L., & Gao, X. (2022). Matching Algorithm for 3D Point Cloud Recognition and Registration Based on Multi-Statistics Histogram Descriptors. Sensors, 22(2), 417.

Magnusson, M., Duckett, T., Elsrud, R., & Skagerlund, L. E. (2005). 3d modelling for underground mining vehicles. In SimSafe 2005, Proceedings of the Conference on Modeling and Simulation for Public Safety.

Magnusson, M., Lilienthal, A., & Duckett, T. (2007). Scan registration for autonomous mining vehicles using 3D‐NDT. Journal of Field Robotics, 24(10), 803-827.

Magnusson, M., Vaskevicius, N., Stoyanov, T., Pathak, K., & Birk, A. (2015, May). Beyond points: Evaluating recent 3D scan-matching algorithms. In 2015 IEEE International Conference on Robotics and Automation (ICRA) (pp. 3631-3637). IEEE.

Mohod, M. V., & Kadam, K. N. (2016). A comparative study on rigid and flexible pavement: A review. IOSR Journal of Mechanical and Civil Engineering (IOSR-JMCE), 13(3), 84-88.

Pang, S., Kent, D., Cai, X., Al-Qassab, H., Morris, D., & Radha, H. (2018, August). 3d scan registration based localization for autonomous vehicles-a comparison of ndt and icp under realistic conditions. In 2018 IEEE 88th vehicular technology conference (VTC-Fall) (pp. 1-5). IEEE.

Pereira, V., Tamura, S., Hayamizu, S., & Fukai, H. (2018, July). A deep learning-based approach for road pothole detection in timor leste. In 2018 IEEE international conference on service operations and logistics, and informatics (SOLI) (pp. 279-284). IEEE.

Ping, P., Yang, X., & Gao, Z. (2020, August). A deep learning approach for street pothole detection. In 2020 IEEE Sixth International Conference on Big Data Computing Service and Applications (BigDataService) (pp. 198-204). IEEE.

Ravi, R., Bullock, D., & Habib, A. (2020). Highway and Airport Runway Pavement Inspection Using Mobile LiDAR. The International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, 43, 349-354.

Ravi, R., Habib, A., & Bullock, D. (2020). Pothole Mapping and PatchingQuantity Estimates using LiDAR-Based Mobile Mapping Systems.Transportation Research Record, 2674(9), 124-134

Soille, P. (1999). Morphological image analysis: principles and applications (Vol. 2, No. 3, pp. 170-171). Berlin: Springer.

Spagnolo, F., Perri, S., & Corsonello, P. (2019). An efficient hardware-oriented single-pass approach for connected component analysis. Sensors, 19(14), 3055.

Takeuchi, E., & Tsubouchi, T. (2006, October). A 3-D scan matching using improved 3-D normal distributions transform for mobile robotic mapping. In 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems (pp. 3068-3073). IEEE.

Van Der Horst, B. B., Lindenbergh, R. C., & Puister, S. W. J. (2019). Mobile laser scan data for road surface damage detection. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 42, 1141-1148.

Vigneshwar, K., & Kumar, B. H. (2016, December). Detection and counting of pothole using image processing techniques. In 2016 IEEE International Conference on Computational Intelligence and Computing Research (ICCIC) (pp. 1-4). IEEE.

Wu, C., Wang, Z., Hu, S., Lepine, J., Na, X., Ainalis, D., & Stettler, M. (2020). An automated machine-learning approach for road pothole detection using smartphone sensor data. Sensors, 20(19), 5564.

Ye, W., Jiang, W., Tong, Z., Yuan, D., & Xiao, J. (2021). Convolutional neural network for pothole detection in asphalt pavement. Road materials and pavement design, 22(1), 42-58.

Zhang, D., Zou, Q., Lin, H., Xu, X., He, L., Gui, R., & Li, Q. (2018). Automatic pavement defect detection using 3D laser profiling technology. Automation in Construction, 96, 350-365.

Zhang, W., Qi, J., Wan, P., Wang, H., Xie, D., Wang, X., & Yan, G. (2016). An easy-to-use airborne LiDAR data filtering method based on cloth simulation. Remote sensing, 8(6), 501.