請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/98194完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 曾惠斌 | zh_TW |
| dc.contributor.advisor | Hui-Ping Tserng | en |
| dc.contributor.author | 陳羿清 | zh_TW |
| dc.contributor.author | Yi-Ching Chen | en |
| dc.date.accessioned | 2025-07-30T16:17:24Z | - |
| dc.date.available | 2025-07-31 | - |
| dc.date.copyright | 2025-07-30 | - |
| dc.date.issued | 2025 | - |
| dc.date.submitted | 2025-07-23 | - |
| dc.identifier.citation | [1] 劉翠溶. 八十年來臺灣的都市發展. 經濟論文, 20(2):1–35, 1991.
[2] Ministry of Transportation and Communications (MOTC). 全國橋梁統計資訊網. https://bss.iot.gov.tw/bss/public/public/login/, 2025. [資料取得日期：2025 年6 月6 日]. [3] 中央通訊社. 南方澳大橋斷裂事故調查報告出爐監造單位疏失釀禍, 11 2020. 最後查閱日期：2025-02-14. [4] P. C. Chang, A. Flatau, and S. C. Liu. Review paper: Health monitoring of civil infrastructure. Structural Health Monitoring, 2(3):257–267, 2003. [5] C. R. Farrar and K. Worden. An introduction to structural health monitoring. Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, 365(1851):303–315, 2007. [6] J. M. W. Brownjohn. Structural health monitoring of civil infrastructure. Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, 365(1851):589–622, 2007. [7] C. M. Yeum and S. J. Dyke. Vision-based automated crack detection for bridge inspection. Computer-Aided Civil and Infrastructure Engineering, 30(10):759–770, 2015. [8] Y. J. Cha, W. Choi, and O. Büyüköztürk. Deep learning-based crack damage detection using convolutional neural networks. Computer-Aided Civil and Infrastructure Engineering, 32(5):361–378, 2017. [9] Mahta Zakaria, Enes Karaaslan, and F. Necati Catbas. Advanced bridge visual inspection using real-time machine learning in edge devices. Advances in Bridge Engineering, 3(1):27, 2022. [10] NVIDIA Corporation. Edge computing with nvidia jetson: Enabling real-time ai at the edge, 2024. [11] M. Mandirola, C. Casarotti, S. Peloso, I. Lanese, E. Brunesi, and I. Senaldi. Use of uas for damage inspection and assessment of bridge infrastructures. International Journal of Disaster Risk Reduction, 72:102824, 2022. [12] American Association of State Highway and Transportation Officials. Drones: Improving safety and cutting costs for bridge inspections. Technical report, Asphalt Magazine, 2016. [13] Alon Oring. Fast and robust structural damage analysis of civil infrastructure using uav imagery. arXiv preprint arXiv:2110.04806, 2021. [14] Sina Tavasoli, Xiao Pan, T. Y. Yang, Saudah Gazi, and Mohsen Azimi. Autonomous damage assessment of structural columns using low-cost micro aerial vehicles and multi-view computer vision. arXiv preprint arXiv:2308.16278, 2023. [15] NEXCO 東日本. 介紹使用無人機(uav) 拍攝的影片進行鋼橋檢查, 2024. Accessed: 2025-02-14. [16] 交通部運輸研究所. 橋梁檢測工具效能提升計畫, 2024. [17] 交通部. 無人機搭配ai 影像辨識應用於橋梁檢測之研究(2/2). Technical report, 交通部, 2024. [18] 交通部. 無人機搭配ai 影像辨識應用於橋梁檢測之研究(1/2). Technical report, 交通部, 2022. [19] Emesent. Routine bridge inspection using slam, 2024. [20] 交通部. 公路橋梁檢測及補強規範, 2018. [21] 臺北市政府工務局新建工程處. 橋梁檢測成果, 2024. [22] Ikhlas Abdel-Qader, Osama Abudayyeh, and Michael E. Kelly. Analysis of edge-detection techniques for crack identification in bridges. Journal of Computing in Civil Engineering, 17(4):255–263, 2003. [23] Qin Zou, Zheng Zhang, Qingquan Li, Xianbiao Qi, Qian Wang, and Song Wang. Deepcrack: Learning hierarchical convolutional features for crack detection. IEEE Transactions on Image Processing, 28(3):1498–1512, 2019. [24] Billie F. Spencer, Vedhus Hoskere, and Yasutaka Narazaki. Advances in computer vision-based civil infrastructure inspection and monitoring. Engineering, 5(2):199–222, 2019. [25] Wenjun Wang and Chao Su. Automatic concrete crack segmentation model based on transformer. Automation in Construction, 139:104275, 2022. [26] Philipp Hüthwohl, Ruodan Lu, and Ioannis Brilakis. Multi-classifier for reinforced concrete bridge defects. Automation in Construction, 105:102824, 2019. [27] Martin Mundt, Sagnik Majumder, Sreenivas Murali, Panagiotis Panetsos, and Visvanathan Ramesh. Meta-learning convolutional neural architectures for multi-target concrete defect classification with the concrete defect bridge image dataset. In 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 11188–11197, 2019. [28] Jingdao Chen and Yong Kwon Cho. Crackembed: Point feature embedding for crack segmentation from disaster site point clouds with anomaly detection. Advanced Engineering Informatics, 52:101550, 2022. [29] Joseph Redmon, Santosh Divvala, Ross Girshick, and Ali Farhadi. You only look once: Unified, real-time object detection, 2016. [30] Alexey Bochkovskiy, Chien-Yao Wang, and Hong-Yuan Mark Liao. Yolov4: Optimal speed and accuracy of object detection, 2020. [31] Chien-Yao Wang, I-Hau Yeh, and Hong-Yuan Mark Liao. Yolov9: Learning what you want to learn using programmable gradient information, 2024. [32] Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. Faster r-cnn: Towards real-time object detection with region proposal networks, 2016. [33] Rahmat Ali, Dongho Kang, Gahyun Suh, and Young-Jin Cha. Real-time multiple damage mapping using autonomous uav and deep faster region-based neural networks for gps-denied structures. Automation in Construction, 130:103831, 2021. [34] Chaobo Zhang, Chih-chen Chang, and Maziar Jamshidi. Concrete bridge surface damage detection using a single-stage detector. Computer-Aided Civil and Infrastructure Engineering, 35(4):389–409, 2020. [35] Lucas Prado Osco, José Marcato Junior, Ana Paula Marques Ramos, Lúcio André de Castro Jorge, Sarah Narges Fatholahi, Jonathan de Andrade Silva, Edson Takashi Matsubara, Hemerson Pistori, Wesley Nunes Gonçalves, and Jonathan Li. A review on deep learning in uav remote sensing. International Journal of Applied Earth Observation and Geoinformation, 102:102456, 2021. [36] 王姿樺(Zi-Hua Wang), 高書屏(Szu-Pyng Kao), and 林志憲(Jhih-Sian Lin). 應用深度學習技術輔助橋梁裂縫辨識. 航測及遙測學刊, 27(4):247–257, Dec 2022. [37] 張永辰(Yung-Chen Chang), 高書屏(Szu-Pyng Kao), 王豐良(Feng-Liang Wang), and 林志憲(Jhih-Sian Lin). 應用uav 影像及深度學習技術輔助橋梁裂縫量化分析. volume 11, pages 15–33. 中華民國地籍測量學會, Jan 2023. [38] 蔡宜真. 以無人機建立即時自動化橋梁裂縫影像辨識系統. 碩士論文, 國立臺灣大學, 2024. [39] Szu-Pyng Kao, Feng-Liang Wang, Jhih-Sian Lin, Jichiang Tsai, Yi-De Chu, and Pen-Shan Hung. Bridge crack inspection efficiency of an unmanned aerial vehicle system with a laser ranging module. Sensors, 22(12), 2022. [40] A. Ellenberg, A. Kontsos, F. Moon, and I. Bartoli. Bridge deck delamination identification from unmanned aerial vehicle infrared imagery. Automation in Construction, 72:155–165, 2016. [41] Francesco Nex and Fabio Remondino. Uav for 3d mapping applications: a review. Applied Geomatics, 6(1):1–15, 03 2014. [42] Neshat Bolourian and Amin Hammad. Lidar-equipped uav path planning considering potential locations of defects for bridge inspection. Automation in Construction, 117:103250, 2020. [43] Sofia Tilon, Francesco Nex, George Vosselman, Irene Llave, and Norman Kerle. Towards improved unmanned aerial vehicle edge intelligence: A road infrastructure monitoring case study. Remote Sensing, 14:4008, 08 2022. [44] Yiching Lin, Chin-Yu Hsiao, Jian-Hua Tong, Chih-Pin Liao, Shin-Tai Song, Hsin-Chu Tsai, and Jui-Lin Wang. Application of edge computing in structural health monitoring of simply supported pci girder bridges. Sensors, 22:8711, 11 2022. [45] Daniel Jozi, Nima Shirzad-Ghaleroudkhani, Garvit Luhadia, Shaghayegh Abtahi, and Mustafa Gül. Rapid post-disaster assessment of residential buildings using unmanned aerial vehicles. International Journal of Disaster Risk Reduction, 111:104707, 2024. [46] Raj Hakani and Abhishek Rawat. Edge computing-driven real-time drone detection using yolov9 and nvidia jetson nano. Drones, 8(11), 2024. [47] Jui-Sheng Chou and Chi-Yun Liu. Optimized lightweight edge computing platform for uav-assisted detection of concrete deterioration beneath bridge decks. Journal of Computing in Civil Engineering, 39(1):04024045, 2025. [48] Cesar Cadena, Luca Carlone, Henry Carrillo, Yasir Latif, Davide Scaramuzza, José Neira, Ian Reid, and John J. Leonard. Past, present, and future of simultaneous localization and mapping: Toward the robust-perception age. IEEE Transactions on Robotics, 32(6):1309–1332, 2016. [49] Andréa Macario Barros, Maugan Michel, Yoann Moline, Gwenolé Corre, and Frédérick Carrel. A comprehensive survey of visual slam algorithms. Robotics, 11(1), 2022. [50] Ethan Rublee, Vincent Rabaud, Kurt Konolige, and Gary Bradski. Orb: An efficient alternative to sift or surf. In 2011 International Conference on Computer Vision, pages 2564–2571, 2011. [51] Raúl Mur-Artal, J. M. M. Montiel, and Juan D. Tardós. Orb-slam: A versatile and accurate monocular slam system. IEEE Transactions on Robotics, 31(5):1147–1163, 2015. [52] Carlos Campos, Richard Elvira, Juan J. Gómez Rodríguez, José M. M. Montiel, and Juan D. Tardós. Orb-slam3: An accurate open-source library for visual, visual–inertial, and multimap slam. IEEE Transactions on Robotics, 37(6):1874–1890, 2021. [53] Liang Zhang, Leqi Wei, Peiyi Shen, Wei Wei, Guangming Zhu, and Juan Song. Semantic slam based on object detection and improved octomap. IEEE Access, 6:75545–75559, 2018. [54] Fangwei Zhong, Sheng Wang, Ziqi Zhang, China Chen, and Yizhou Wang. Detectslam: Making object detection and slam mutually beneficial. In 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), pages 1001–1010, 2018. [55] Chu-Qiao Feng, Bao-Luo Li, Yu Fei Liu, Zhizhong Fu, Yonghong Yan, and Junqi Fan. Crack assessment using multi-sensor fusion simultaneous localization and mapping (slam) and image super-resolution for bridge inspection. Automation in Construction, 155:105047, nov 2023. [56] Huitong Xu, Meng Wang, Cheng Liu, Yongchao Guo, Zihan Gao, and Changqing Xie. Tunnel crack assessment using simultaneous localization and mapping (slam) and deep learning segmentation. Automation in Construction, 171:105977, 2025. [57] Zhengyi Chen, Changhao Song, Boyu Wang, Xingyu Tao, Xiao Zhang, Fangzhou Lin, and Jack C.P. Cheng. Automated reality capture for indoor inspection using bim and a multi-sensor quadruped robot. Automation in Construction, 170:105930, 2025. [58] Tao Lu, Sonja Tervola, Xiaoshu Lü, Charles Kibert, Qunli Zhang, Tong Li, and Zhitong Yao. A novel methodology for the path alignment of visual slam in indoor construction inspection. Automation in Construction, 127:103723, 07 2021. [59] Xiao Pan, Sina Tavasoli, T. Y. Yang, and Sina Poorghasem. Post-disaster building indoor damage and survivor detection using autonomous path planning and deep learning with unmanned aerial vehicles, 2025. [60] 交通部. 公路橋梁檢測及補強規範. https://www.motc.gov.tw/ch/app/divpubreg_list/view?module=divpubreg&id=740&serno=425, 2023. [61] Roboflow. Defects-6bfhc dataset [data set]. https://universe.roboflow.com/x-i0m9x/defects-6bfhc, 2024. [62] Roboflow. Bridge-ssz3a dataset [data set]. https://universe.roboflow.com/peccunb/bridge-ssz3a, 2024. [63] B. Dwyer, J. Nelson, and T. Hansen. Roboflow (version 1.0). https://roboflow.com, 2024. [64] Alex Krizhevsky, Ilya Sutskever, and Geoffrey E. Hinton. Imagenet classification with deep convolutional neural networks. Commun. ACM, 60(6):84–90, May 2017. [65] Raul Mur-Artal and Juan D. Tardos. Orb-slam2: An open-source slam system for monocular, stereo, and rgb-d cameras. IEEE Transactions on Robotics, 33(5):1255–1262, October 2017. [66] Jakob Engel, Thomas Schöps, and Daniel Cremers. LSD-SLAM: Large-scale direct monocular slam. In David Fleet, Tomas Pajdla, Bernt Schiele, and Tinne Tuytelaars, editors, Computer Vision – ECCV 2014, pages 834–849, Cham, 2014. Springer International Publishing. [67] Chien-Yao Wang, Alexey Bochkovskiy, and Hong-Yuan Mark Liao. Yolov7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors, 2022. [68] Sanghyun Park. Yolov9 ros. https://github.com/SanghyunPark01/yolov9_ros, 2024. [69] Christoph Zauner. Implementation and benchmarking of perceptual image hash functions. 2010. [70] WongKinYiu. Yolov9: Learning what you want to learn using programmable gradient information. https://github.com/WongKinYiu/yolov9, 2024. [71] Zhaohui Zheng, Ping Wang, Wei Liu, Jinze Li, Rongguang Ye, and Dongwei Ren. Distance-iou loss: Faster and better learning for bounding box regression, 2019. [72] Mark Everingham, S. M. Ali Eslami, Luc Van Gool, Christopher K. I. Williams, John Winn, and Andrew Zisserman. The pascal visual object classes challenge: A retrospective. International Journal of Computer Vision, 111(1):98–136, 2015. [73] Thien Nguyen. orb_slam3_ros: A ros implementation of orb-slam3. https://github.com/thien94/orb_slam3_ros, 2021. [74] Johannes Schönberger and Jan-Michael Frahm. Structure-from-motion revisited. 06 2016. [75] S. Ullman and Sydney Brenner. The interpretation of structure from motion. Proceedings of the Royal Society of London. Series B. Biological Sciences, 203(1153):405–426, 1979. [76] Michael Goesele, Noah Snavely, Brian Curless, Hugues Hoppe, and Steven Seitz. Multi-view stereo for community photo collections. pages 1–8, 11 2007. [77] CloudCompare Development Team. CloudCompare (version 2.X) [GPL software]. http://www.cloudcompare.org/, 2025. [78] Qian-Yi Zhou, Jaesik Park, and Vladlen Koltun. Open3d: A modern library for 3d data processing, 2018. [79] P.J. Besl and Neil D. McKay. A method for registration of 3-d shapes. IEEE Transactions on Pattern Analysis and Machine Intelligence, 14(2):239–256, 1992. [80] C. Bane Sullivan and Alexander A. Kaszynski. Pyvista: 3d plotting and mesh analysis through a streamlined interface for the visualization toolkit (vtk). Journal of Open Source Software, 4(37):1450, May 2019. [81] Jon Louis Bentley. Multidimensional binary search trees used for associative searching. Commun. ACM, 18(9):509–517, September 1975. [82] Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. Attention is all you need, 2023. [83] Abhinav Shrivastava, Abhinav Gupta, and Ross Girshick. Training region-based object detectors with online hard example mining, 2016. [84] Chao Dong, Chen Change Loy, Kaiming He, and Xiaoou Tang. Image superresolution using deep convolutional networks, 2015. | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/98194 | - |
| dc.description.abstract | 橋梁作為交通運輸系統中關鍵的基礎建設，其結構安全攸關公眾生命財產之保障與基礎設施之永續運作。隨著橋梁使用年限逐漸提高，結構劣化問題日益嚴重，傳統仰賴人力進行的橋梁檢測方法，存在檢測效率低落、人力成本高昂、作業環境危險及檢測結果主觀性高等諸多限制，難以因應大量橋梁設施的日常維護需求。面對此一挑戰，如何發展具即時性、自動化、低成本與高準確率之橋梁檢測技術，已成為當前土木工程領域的重要研究議題。
為解決上述問題，本研究提出一套結合深度學習影像辨識與同步定位與地圖建構（Simultaneous Localization and Mapping, SLAM）之無人機（Unmanned Aerial Vehicle, UAV）智慧檢測系統。系統架構包含前端影像蒐集、中段即時推論與定位、以及後端三維建模與資料整合等模組。前端部分以無人機搭載光學相機進行橋梁影像拍攝，並以 NVIDIA Jetson Orin Nano 作為邊緣運算平台，即時執行影像辨識及同步定位與地圖建構。 影像辨識模組採用 YOLOv9 進行多類別劣化偵測，針對常見缺陷類型如裂縫、剝落與白華進行訓練與評估，訓練資料來自公開資料集，測試資料則為實地拍攝之影像，並透過灰階轉換與超參數調整優化模型性能。同步定位與地圖建構部分，採用 ORB-SLAM3 作為核心演算法，於飛行過程中估算無人機姿態並同步建立稀疏地圖。後續則結合其輸出的關鍵幀與相機外參資訊，匯入 COLMAP 進行稠密點雲重建。為實現缺陷資訊於三維空間中的準確標註與視覺化展示，本研究進一步整合建築資訊模型（Building Information Modeling, BIM），並透過點雲配準技術進行空間對齊，最終輸出包含缺陷位置、構件對應、TWD97 坐標與影像標註之結構化檢測報告。 實驗結果顯示，最終 YOLOv9 模型於本研究自建測試集上達到 mAP@0.5 為 0.657，於道南橋進行之現地飛行測試中，可穩定完成即時辨識與定位作業，成功標註 25 處劣化並建立完整三維點雲模型，Micro F1-score 達 0.656，驗證系統整合效能與即時性優勢。整體而言，本研究所提出之系統具備高度模組化、即時運作、低成本與高擴充性等特性，能有效協助橋梁管理單位進行結構檢測與缺陷紀錄，提升傳統檢測流程之智慧化與作業效率，並提供具實務應用潛力之技術解決方案。 | zh_TW |
| dc.description.abstract | Bridges are critical components of transportation infrastructure, and their structural integrity is essential for public safety and long-term serviceability. As aging structures face increasing deterioration, traditional manual inspections have proven inefficient, costly, hazardous, and prone to subjective errors—making them unsuitable for large-scale routine monitoring. Addressing these challenges requires an automated, real-time, and accurate inspection solution.
This study proposes a UAV-based intelligent inspection system integrating deep learning and Simultaneous Localization and Mapping (SLAM). The system consists of three modules: image acquisition via UAVs, real-time inference and localization using the NVIDIA Jetson Orin Nano, and 3D reconstruction and defect annotation. YOLOv9 is employed to detect common defects such as cracks, spalling, and efflorescence. The model is trained on public datasets and tested with field-collected images, with performance enhanced through grayscale preprocessing and hyperparameter tuning. For localization, ORB-SLAM3 estimates the UAV’s pose and generates sparse maps in real time. Keyframes and camera poses are then used in COLMAP to reconstruct dense point clouds. These are aligned with Building Information Modeling (BIM) via point cloud registration to produce accurate 3D annotations and structured inspection reports containing defect locations, component IDs, and TWD97 coordinates. Experimental results show that the optimized YOLOv9 model achieved an mAP@0.5 of 0.657. Field tests at Daonan Bridge demonstrated real-time detection and mapping of 25 defects with a micro F1-score of 0.656. The proposed system is modular, low-cost, and scalable, offering an effective solution for automating bridge inspection and enhancing maintenance workflows. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2025-07-30T16:17:24Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2025-07-30T16:17:24Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | 謝辭 i
摘要 ii Abstract iv 目次 vii 圖次 xiii 表次 xv 符號列表 xvii 第一章 緒論 1 1.1 研究背景與動機 1 1.2 研究目的 3 1.3 論文架構與研究流程 5 第二章 文獻回顧 7 2.1 橋梁檢測定義與國內規範 7 2.1.1 檢測制度與評估指標 7 2.1.2 橋梁檢測類型分類 8 2.1.3 RC橋梁表面劣化項目與辨識標準 8 2.2 劣化辨識技術的發展 9 2.2.1 離線影像辨識與多目標劣化檢測 9 2.2.2 即時物件檢測與多重缺陷辨識 10 2.2.3 性能比較與挑戰 11 2.3 無人機影像辨識應用於土木工程 12 2.3.1 橋梁缺陷檢測與裂縫辨識 13 2.3.2 三維測繪與缺陷可視化 13 2.3.3 災後即時應變與邊緣運算技術 14 2.3.4 技術整合與實務應用推動 15 2.3.5 系統比較與應用挑戰 15 2.4 視覺SLAM技術之發展 16 2.4.1 視覺SLAM的核心概念與主要演算法 16 2.4.2 動態環境與複雜場景下的SLAM應用 17 2.5 SLAM在土木工程等領域中的應用 18 2.5.1 橋梁與隧道巡檢 18 2.5.2 室內建築與施工場域 18 2.5.3 災後快速應變 19 2.6 小結 19 第三章 系統建構方法 21 3.1 硬體與系統架構 22 3.1.1 硬體設備組成 22 3.1.2 系統流程概述 24 3.2 橋梁劣化資料集 27 3.2.1 劣化型式說明 27 3.2.2 資料蒐集與分割 29 3.3 影像擷取與前處理 30 3.3.1 影像來源與ROS輸入 30 3.3.2 影像增強與轉換 31 3.4 劣化偵測：YOLOv9 33 3.4.1 模型結構概述 33 3.4.2 YOLOv9之ROS模組 35 3.4.3 訓練方法與流程 37 3.4.4 評估指標 38 3.5 同步定位與地圖構建：ORB-SLAM3 39 3.5.1 系統架構概述 40 3.5.2 相機內參標定 42 3.5.3 ORB-SLAM3之ROS模組 42 3.6 相機外參與時間戳對應 45 3.7 點雲獲取 46 3.7.1 稠密點雲重建（COLMAP） 46 3.7.2 BIM模型轉點雲 48 3.8 點雲配準與相機位姿變換 49 3.8.1 點雲配準目的與流程 49 3.8.2 相機位姿變換與更新 51 3.9 劣化資訊展示與互動應用 52 3.9.1 三維視覺化展示 53 3.9.2 三維量測與位置查驗 53 3.9.3 劣化標註表與報告書 54 3.10 系統應用情境分析 57 3.11 小結 59 第四章 系統驗證與實測 61 4.1 劣化辨識模型 61 4.1.1 實驗環境與系統設定 61 4.1.2 模型選擇與實驗設計 62 4.1.3 基礎訓練參數設定 62 4.1.4 測試集設計與評估原則 63 4.1.5 模型比較與超參數調整 64 4.1.6 模型訓練結果彙整 68 4.1.7 橋梁劣化分類性能與案例 72 4.1.8 灰階與原彩影像之辨識效能探討 75 4.1.9 結果分析與小結 77 4.2 前導實驗：系統可行性測試 79 4.2.1 驗證目的與測試條件 80 4.2.2 現地實驗紀錄 81 4.2.3 實驗觀察與問題分析 82 4.3 正式實驗：系統應用與資料取得 85 4.3.1 實驗設計與作業流程 86 4.3.2 系統運行結果 88 4.4 實驗資料後處理與結果展示：道南橋 93 4.4.1 稠密點雲重建成果 93 4.4.2 空間配準與劣化定位成果 94 4.4.3 橋梁劣化檢測報告書範例 99 4.4.4 三維劣化展示與互動 100 4.5 實驗結果與討論 101 4.5.1 實驗結果 101 4.5.2 問題與討論 102 第五章 結論與建議 104 5.1 結論 104 5.2 研究限制 105 5.3 未來研究建議 106 參考文獻 109 | - |
| dc.language.iso | zh_TW | - |
| dc.subject | 無人機 | zh_TW |
| dc.subject | 橋梁檢測 | zh_TW |
| dc.subject | 影像辨識 | zh_TW |
| dc.subject | 同步定位與地圖建構 | zh_TW |
| dc.subject | 邊緣運算 | zh_TW |
| dc.subject | 建築資訊模型 | zh_TW |
| dc.subject | Image Recognition | en |
| dc.subject | Unmanned Aerial Vehicle (UAV) | en |
| dc.subject | Bridge Inspection | en |
| dc.subject | Building Information Modeling (BIM) | en |
| dc.subject | Simultaneous Localization and Mapping (SLAM) | en |
| dc.subject | Edge Computing | en |
| dc.title | 整合影像辨識與 SLAM 技術建立 UAV 橋梁劣化即時檢測系統 | zh_TW |
| dc.title | Real-time Bridge Deterioration Detection System Using UAVs with Integrated Image Recognition and SLAM | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 113-2 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.oralexamcommittee | 林之謙;林偲妘;林祐正 | zh_TW |
| dc.contributor.oralexamcommittee | Jacob Je-Chian LIN;Szu-Yun LIN;Yu-Cheng Lin | en |
| dc.subject.keyword | 無人機,橋梁檢測,影像辨識,同步定位與地圖建構,邊緣運算,建築資訊模型, | zh_TW |
| dc.subject.keyword | Unmanned Aerial Vehicle (UAV),Bridge Inspection,Image Recognition,Simultaneous Localization and Mapping (SLAM),Edge Computing,Building Information Modeling (BIM), | en |
| dc.relation.page | 119 | - |
| dc.identifier.doi | 10.6342/NTU202502165 | - |
| dc.rights.note | 同意授權(全球公開) | - |
| dc.date.accepted | 2025-07-25 | - |
| dc.contributor.author-college | 工學院 | - |
| dc.contributor.author-dept | 土木工程學系 | - |
| dc.date.embargo-lift | 2025-07-31 | - |
| 顯示於系所單位： | 土木工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-113-2.pdf | 42.24 MB | Adobe PDF | 檢視/開啟 |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。