在各類道路基礎設施中，桿柱為沿路設置的常見類型，如路燈、道路交通號誌及路牌標誌。然而伴隨長期使用，這些桿柱可能因外力導致桿柱傾斜，嚴重時可能危害車輛駕駛人及行人使用道路時的安全性。
隨著移動測繪系統的發展，許多研究提出了以車載光達點雲自動巡檢桿柱傾斜的方法，然而這些方法面臨的挑戰為若在缺乏參考桿柱資料的情況下，在大範圍空間下搜尋桿柱位置不僅需花費大量時間，且萃取桿柱點雲之結果通常較不理想，如何穩健的萃取與樹木相鄰之桿柱點雲更是一大挑戰。
為改善上述限制，本研究提出一種結合高精地圖與車載光達系統巡檢桿柱傾斜之流程。演算法中結合了高精地圖提供的桿柱位置向量檔，因此得以省略桿柱檢測的步驟，並降低桿柱檢測失敗的可能性。本研究結合高精地圖所提供的桿柱坐標進行資料前處理，並透過CANUPO (CAractérisation de NUages de POints) (Brodu & Lague, 2012) 留下具有桿柱特徵的點雲，接著藉由隨機抽樣一致算法(Random Sample Consensus, RANSAC) (Fischler & Bolles, 1981) 和DBSCAN(Density-based spatial clustering of applications with noise) (Ester et al., 1996) 萃取桿柱點雲，最後通過擬合桿柱並設置門檻值來決定有效圓心，即可計算出桿柱傾角。本研究的實驗部分分為模擬實驗及實地實驗，在模擬實驗中以路燈桿、交通燈桿及標誌桿三種不同類型的桿柱模型測試不同車速、行駛車道、傾斜方向及傾角對桿柱傾角計算的影響，最後進一步加入兩種樹木模型討論桿柱與樹木距離及桿柱相對於樹木之傾斜方向對桿柱傾斜巡檢之影響，模擬實驗成果展示，本研究提出流程不僅適用於傾斜角度60度以下桿柱之巡檢，且能有效應用於與樹木相鄰之桿柱傾斜巡檢，克服過往相關研究受樹木點雲影響桿柱萃取之挑戰。在實地資料實驗中則以兩台64線車載光達於實驗區域收集桿柱點雲資料，並以人工數化方式萃取高精地圖點雲中的桿柱部分計算傾角，做為參考資料計算RMSE值，高度7公尺以上之桿柱之RMSE值為0.5度，4~7公尺高之桿柱為3.09度，4公尺以下之桿柱為4.13度。實地實驗成果展示，本研究提出流程應用於現實道路環境之複雜場景，仍能有效偵測並計算桿柱傾斜角度，提供良好成果。

This study proposes a workflow that combines HD map with MLS for inspecting pole tilts. The workflow preprocesses data by merging pole coordinates from HD maps, utilizes CANUPO for retaining point clouds with pole features, employs Random Sample Consensus (RANSAC) and DBSCAN for pole point cloud selection, and applies thresholding to determine the effective center, ultimately calculating pole tilt angles. Simulated experiments using HELIOS++ evaluate the method's performance across various parameters such as vehicle speeds, lanes, tilt directions, and angles, including pole-to-tree distance and relative tilt direction to trees. Results show a detection rate exceeding 90% for tilts below 60°, with RMSE values below 3° for streetlight and traffic light poles and varying between 4° to 13° for sign poles. Field data experiments involve two mobile LiDARs collecting pole point clouds, with manual digitization on high-precision map point clouds serving as reference data. The proposed workflow demonstrates effectiveness, yielding RMSE values of 0.5° for poles above 7 meters, 3.09° for poles between 4 and 7 meters, and 4.13° for poles below 4 meters. Overall, the study establishes the proposed method as reliable for extracting pole features and inspecting pole inclinations in practical applications.

台灣資通產業標準協會(2019)。高精地圖製圖作業指引v2
交通部電信總局(1995)。電信架空線路立桿、拉線及撐桿施工規範
Alam, M. M., Zhu, Z., Eren Tokgoz, B., Zhang, J., & Hwang, S. (2020). Automatic Assessment and Prediction of the Resilience of Utility Poles Using Unmanned Aerial Vehicles and Computer Vision Techniques. International Journal of Disaster Risk Science, 11(1), 119-132.
Biber, P., & Strasser, W. (2003, 27-31 Oct. 2003). The normal distributions transform: a new approach to laser scan matching. Paper presented at the Proceedings 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2003) (Cat. No.03CH37453).
Brodu, N., & Lague, D. (2012). 3D terrestrial lidar data classification of complex natural scenes using a multi-scale dimensionality criterion: Applications in geomorphology. ISPRS journal of photogrammetry and remote sensing, 68, 121-134.
Cabo, C., Ordoñez, C., García-Cortés, S., & Martínez, J. (2014). An algorithm for automatic detection of pole-like street furniture objects from Mobile Laser Scanner point clouds. ISPRS Journal of Photogrammetry and Remote Sensing, 87, 47-56.
Chen, L., Chang, J., Xu, J., & Yang, Z. (2023). Automatic Measurement of Inclination Angle of Utility Poles Using 2D Image and 3D Point Cloud. Applied Sciences, 13(3).
El-Halawany, S. I., & Lichti, D. D. (2013). Detecting road poles from mobile terrestrial laser scanning data. GIScience & Remote Sensing, 50(6), 704-722.
Ester, M., Kriegel, H.-P., Sander, J., & Xu, X. (1996). A density-based algorithm for discovering clusters in large spatial databases with noise. Paper presented at the Proceedings of the Second International Conference on Knowledge Discovery and Data Mining, Portland, Oregon.
Fischler, M. A., & Bolles, R. C. (1981). Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM, 24(6), 381–395.
Gomes, M., Silva, J., Gonçalves, D., Zamboni, P., Perez, J., Batista, E., . . . Gonçalves, W. (2020). Mapping Utility Poles in Aerial Orthoimages Using ATSS Deep Learning Method. Sensors, 20(21).
Guan, H., Yan, W., Yu, Y., Zhong, L., & Li, D. (2018). Robust Traffic-Sign Detection and Classification Using Mobile LiDAR Data With Digital Images. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 11(5), 1715-1724.
Ha, T., & Chaisomphob, T. (2020). Automated Localization and Classification of Expressway Pole-Like Road Facilities from Mobile Laser Scanning Data. Advances in Civil Engineering, 2020, 1-18.
Hearst, M. A., Dumais, S. T., Osuna, E., Platt, J., & Scholkopf, B. (1998). Support vector machines. IEEE Intelligent Systems and their applications, 13(4), 18-28.
Hosseini, M. M., Umunnakwe, A., Parvania, M., & Tasdizen, T. (2020). Intelligent Damage Classification and Estimation in Power Distribution Poles Using Unmanned Aerial Vehicles and Convolutional Neural Networks. IEEE Transactions on Smart Grid, 11(4), 3325-3333.
Huang, J., & You, S. (2015). Pole-like object detection and classification from urban point clouds. Paper presented at the 2015 IEEE International Conference on Robotics and Automation (ICRA).
Javanmardi, E., Javanmardi, M., Gu, Y., & Kamijo, S. (2021). Pre-Estimating Self-Localization Error of NDT-Based Map-Matching From Map Only. IEEE Transactions on Intelligent Transportation Systems, 22(12), 7652-7666.
Kang, Z., Yang, J., Zhong, R., Wu, Y., Shi, Z., & Lindenbergh, R. (2018). Voxel-Based Extraction and Classification of 3-D Pole-Like Objects From Mobile LiDAR Point Cloud Data. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 11(11), 4287-4298.
Kim, J., Kamari, M., Lee, S., & Ham, Y. (2021). Large-Scale Visual Data–Driven Probabilistic Risk Assessment of Utility Poles Regarding the Vulnerability of Power Distribution Infrastructure Systems. Journal of Construction Engineering and Management, 147(10), 04021121.
Liu, R., Wang, J., & Zhang, B. (2020). High Definition Map for Automated Driving: Overview and Analysis. The Journal of Navigation, 73(2), 324-341.
Luo, D.-a., & Wang, Y.-m. (2008). Rapid extracting pillars by slicing point clouds. Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci, 37, 215-218.
Maćkiewicz, A., & Ratajczak, W. (1993). Principal components analysis (PCA). Computers & Geosciences, 19(3), 303-342.
Rusu, R. B., & Cousins, S. (2011, 9-13 May 2011). 3D is here: Point Cloud Library (PCL). Paper presented at the 2011 IEEE International Conference on Robotics and Automation.
Shi, Z., Kang, Z., Lin, Y., Liu, Y., & Chen, W. (2018). Automatic Recognition of Pole-Like Objects from Mobile Laser Scanning Point Clouds. Remote Sensing, 10(12).
Takeuchi, E., & Tsubouchi, T. (2006, 9-15 Oct. 2006). A 3-D Scan Matching using Improved 3-D Normal Distributions Transform for Mobile Robotic Mapping. Paper presented at the 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems.
Talebi Nahr, S., Saadatseresht, M., & Talebi, J. (2017). DETECTION OF STREET LIGHT POLES IN ROAD SCENES FROM MOBILE LIDAR MAPPING DATA FOR ITS APPLICATIONS. ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XLII-4/W4, 265-270.
Wang, J., Lindenbergh, R., & Menenti, M. (2017). SigVox–A 3D feature matching algorithm for automatic street object recognition in mobile laser scanning point clouds. ISPRS Journal of Photogrammetry and Remote Sensing, 128, 111-129.
Winiwarter, L., Pena, A. M. E., Weiser, H., Anders, K., Sánchez, J. M., Searle, M., & Höfle, B. (2022). Virtual laser scanning with HELIOS++: A novel take on ray tracing-based simulation of topographic full-waveform 3D laser scanning. Remote Sensing of Environment, 269, 112772.
Yan, L., Li, Z., Liu, H., Tan, J., Zhao, S., & Chen, C. (2017). Detection and classification of pole-like road objects from mobile LiDAR data in motorway environment. Optics & Laser Technology, 97, 272-283.
Yu, Y., Li, J., Guan, H., Wang, C., & Yu, J. (2014). Semiautomated extraction of street light poles from mobile LiDAR point-clouds. IEEE Transactions on Geoscience and Remote Sensing, 53(3), 1374-1386.
Zhang, W., Witharana, C., Li, W., Zhang, C., Li, X., & Parent, J. (2018). Using Deep Learning to Identify Utility Poles with Crossarms and Estimate Their Locations from Google Street View Images. Sensors, 18(8).
Ziegler, J., Bender, P., Schreiber, M., Lategahn, H., Strauss, T., Stiller, C., . . . Zeeb, E. (2014). Making Bertha Drive—An Autonomous Journey on a Historic Route. IEEE Intelligent Transportation Systems Magazine, 6(2), 8-20.