1. NCCU Academic Hub
  2. Publications
  3. College of Informatics
  4. Theses
  5. Item

Publications-Theses

Article View/Open

Publication Export

Google ScholarTM

NCCU Library

Citation Infomation

Related Publications in TAIR

題名 人機協作與視覺導航應用於無人機河川巡檢任務研究
The Study of Human-Robot Collaboration and Visual Navigation Applied to Unmanned Aerial Vehicle River Patrol Missions
作者 陳佳彣
Chen, Chia-Wen
貢獻者 劉吉軒
Liu, Jyi Shane
陳佳彣
Chen, Chia-Wen
關鍵詞 無人機
人機協作
河川巡檢
自主跟隨
任務控制
人機互動介面
UAV
Human-Robot Collaboration
River Patrol
Mission Control
Graphical User Interface
日期 2024
上傳時間 5-Aug-2024 12:45:05 (UTC+8)
摘要 近年來，隨著無人機技術的進步，其應用範圍從最初的軍事用途 逐漸擴展至民生服務和公共事業等領域，其中包括河川巡檢及人員搜 救等重要議題。無人機以其低部署成本和高機動性等特點，成為解決 方案中靈活且高效益的選擇。然而在控制方面，若僅依賴傳統搖桿操 作，會對操作人員帶來諸多不便，包括操作的複雜性、受限的自由度 以及無法同時觀看無人機影像等困難。此外，操作人員為了掌握無人 機控制，可能還需要接受專業培訓以習得執行任務所需的技能，這不 僅提高了操作門檻，也降低了系統應用的普及性。 為了建立直觀且易於操作的無人機控制系統，本研究提出了一種基 於視覺導航的人機協作方法，透過視覺化平台進行即時半自動化的飛 行調控，並將其應用於河川巡檢及人員搜救的任務場景中。 在任務執行過程中，無人機作為環境感知和執行任務的工具，以 河川作為跟隨目標，採用全球定位系統（GPS）作為大範圍定位的基 礎，並融合視覺導航和語意分割模組，以建立精準、穩定的河川跟隨 模型。同時，操作人員可以通過介面即時監控無人機的飛行數據和影 像，以便根據需求做出即時決策。本研究所提出的人機協作系統不僅 適用於河川巡檢任務，亦可應用於其他河川相關任務，如水位追蹤、 水污染檢測和垃圾檢測等情境。
In recent years, UAV technology has advanced, leading to its increased use in civilian applications such as river inspection and personnel rescue. UAVs are cost-effective and highly mobile, making them efficient solutions for various scenarios. However, traditional joystick operations for UAV control present challenges for operators, including complexity, limited freedom, and the inability to check UAV images simultaneously. Furthermore, operators need specialized training for mission execution, raising the operational threshold and reducing accessibility to the system. To address these issues, this study proposes a vision-based human-robot collaboration method for intuitive and easy UAV control. This method involves a visual platform for monitoring and real-time semi-automated flight control, specifically applied to river inspection and personnel rescue missions. During mission execution, UAV uses GPS for broad-range positioning and integrates visual navigation and semantic segmentation modules to accurately and stably follow the river as a target. Operators can monitor the UAV’s flight data and images in real time through the visual platform, allowing for timely decision-making based on mission needs. Importantly, the human-machine collaboration system proposed in this study is not limited to river inspection tasks but also extends to other river-related activities such as water level tracking, water pollution detection, and waste detection.
參考文獻 [1] Hazim Shakhatreh, Ahmad H. Sawalmeh, Ala Al-Fuqaha, Zuochao Dou, Eyad Almaita, Issa Khalil, Noor Shamsiah Othman, Abdallah Khreishah, and Mohsen Guizani. Unmanned aerial vehicles (uavs): A survey on civil applications and key research challenges. IEEE Access, 7:48572–48634, 2019. doi: 10.1109/ACCESS.2019.2909530. [2] Anupam Keshari Pankaj Singh Yadav R Faiyaz Ahmed, J. C. Mohanta. Recent advances in unmanned aerial vehicles: A review. Arabian Journal for Science and Engineering, 47:7963–7984, 2022. URL https://doi.org/10.1007/s13369-022-06738-0. [3] Wu Xiao Zhenqi Hu He Ren, Yanling Zhao. A review of uav monitoring in mining areas: current status and future perspectives. International Journal of Coal Science Technology, 2019. URL https://doi.org/10.1007/s40789-019-00264-5. [4] Bin Li, Zesong Fei, and Yan Zhang. Uav communications for 5g and beyond: Recent advances and future trends. IEEE Internet of Things Journal, 6(2):2241–2263, 2019. doi: 10.1109/JIOT.2018.2887086. [5] 中 華 民 國 內 政 部 消 防 署. 夏 日 玩 水 內 政 部 提 醒： 禁 制 溪 流 不 要 去. 2022. URL https://www.nfa.gov.tw/kid/index.phpcode=list&flag=detail&ids=1468&article_id=12201. [6] Zanchettin A.M. Ivaldi S. et al. Ajoudani, A. Progress and prospects of the human–robot collaboration. Autonomous Robots, page 957–975, 2018. URL https://doi.org/10.1007/s10514-017-9677-2. [7] Janis Arents, Valters Abolins, Janis Judvaitis, Oskars Vismanis, Aly Oraby, and Kaspars Ozols. Human–robot collaboration trends and safety aspects: A systematic review. Journal of Sensor and Actuator Networks, 10(3), 2021. ISSN 2224-2708. doi: 10.3390/jsan10030048. URL https://www.mdpi.com/2224-2708/10/3/48. [8] Lu Feng, Clemens Wiltsche, Laura Humphrey, and Ufuk Topcu. Controller synthesis for autonomous systems interacting with human operators. page 70–79, 2015. doi:10.1145/2735960.2735973. URL https://doi.org/10.1145/2735960.2735973. [9] Michael A. Goodrich, Joseph L. Cooper, Julie A. Adams, Curtis Humphrey, Ron Zeeman, and Brian G. Buss. Using a mini-uav to support wilderness search and rescue: Practices for human-robot teaming. pages 1–6, 2007. doi: 10.1109/SSRR.2007.4381284. [10] Julie A Adams. Critical considerations for human-robot interface development.pages 1–8, 2002. [11] UAS Europe. Skyview ground control system. 2013. URL https://www.uas-europe.se/documents/SkyView%20GCS.pdf. [12] Ardu Pilot. Introduction to pixhawk ground control station. 2010. URL https://diydrones.com/profiles/blogs/introduction-to-pixhawk-ground?xg_source=activity. [13] Nicolas Audebert, Bertrand Le Saux, and Sébastien Lefèvre. Segment-before-detect:Vehicle detection and classification through semantic segmentation of aerial images.Remote Sensing, 9(4), 2017. ISSN 2072-4292. doi: 10.3390/rs9040368. URL https://www.mdpi.com/2072-4292/9/4/368. [14] Jonathan Long, Evan Shelhamer, and Trevor Darrell. Fully convolutional networks for semantic segmentation. pages 3431–3440, 2015. doi: 10.1109/CVPR.2015.7298965. [15] Olaf Ronneberger, Philipp Fischer, and Thomas Brox. U-net: Convolutional networks for biomedical image segmentation. pages 234–241, 2015. [16] Vijay Badrinarayanan, Alex Kendall, and Roberto Cipolla. Segnet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(12):2481–2495, 2017. doi:10.1109/TPAMI.2016.2644615. [17] Changqian Yu, Changxin Gao, Jingbo Wang, Gang Yu, Chunhua Shen, and Nong Sang. Bisenet v2: Bilateral network with guided aggregation for real-time semantic segmentation. 2020. [18] Te-Wei Chen, Yen-Ting Huang, and Wen-Hung Liao. Far-sighted bisenet v2 for real-time semantic segmentation. pages 1–8, 2021. doi: 10.1109/AVSS52988.2021.9663738. [19] Keyan Chen, Chenyang Liu, Hao Chen, Haotian Zhang, Wenyuan Li, Zhengxia Zou, and Zhenwei Shi. Rsprompter: Learning to prompt for remote sensing instance segmentation based on visual foundation model. IEEE Transactions on Geoscience and Remote Sensing, 2024. [20] Zhengxia Zou, Keyan Chen, Zhenwei Shi, Yuhong Guo, and Jieping Ye. Object detection in 20 years: A survey. Proceedings of the IEEE, 111(3):257–276, 2023. doi: 10.1109/JPROC.2023.3238524. [21] Hui Zhang, Yu Du, Shurong Ning, Yonghua Zhang, Shuo Yang, and Chen Du. Pedestrian detection method based on faster r-cnn. pages 427–430, 2017. doi:10.1109/CIS.2017.00099. [22] A. P. P. Abdul Majeed L. L. Thai M. A. Mohd Razman J. C. Tang, A. F. B. Ab. Nasir and I. Mohd Khairuddin. Fine-tuned retinanet models for vision-based human presence detection. MEKATRONIKA, 4(2):16–23, November 2022. doi: 10.15282/mekatronika.v4i2.8850. URL https://journal.ump.edu.my/mekatronika/article/view/8850. [23] Wei-Yen Hsu and Wen-Yen Lin. Ratio-and-scale-aware yolo for pedestrian detection. IEEE Transactions on Image Processing, 30:934–947, 2021. doi: 10.1109/TIP.2020.3039574. [24] H.g Yu Y. Yang K. Duan G. Li W.g Zhang Q. Huang Q. Tian D. Du, Y. Qi. The unmanned aerial vehicle benchmark: Object detection and tracking. European Conference on Computer Vision (ECCV), 2018. [25] Pengfei Zhu, Longyin Wen, Dawei Du, Xiao Bian, Heng Fan, Qinghua Hu, and Haibin Ling. Detection and tracking meet drones challenge. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(11):7380–7399, 2021. [26] Jian Ding, Nan Xue, Gui-Song Xia, Xiang Bai, Wen Yang, Michael Yang, Serge Belongie, Jiebo Luo, Mihai Datcu, Marcello Pelillo, and Liangpei Zhang. Object detection in aerial images: A large-scale benchmark and challenges. IEEE Transactions on Pattern Analysis and Machine Intelligence, pages 1–1, 2021. doi:10.1109/TPAMI.2021.3117983. [27] Sasa Sambolek and Marina Ivasic-Kos. Automatic person detection in search and rescue operations using deep cnn detectors. IEEE Access, 9:37905–37922, 2021. doi: 10.1109/ACCESS.2021.3063681. [28] Igharoro O. Liu Y. et al. Hong, A. Investigating human-robot teams for learningbased semi-autonomous control in urban search and rescue environments. Journal of Intelligent Robotic Systems, page 669–686, 2019. URL https://doi.org/10.1007/s10846-018-0899-0. [29] Jeyan J. V. M. Ramesh, P. S. Comparative analysis of fixed-wing, rotary-wing and hybrid mini unmanned aircraft systems (uas) from the applications perspective. INCAS Bulletin, pages 137–151, 2022. URL https://doi.org/10.13111/2066-8201.2022.14.1.12. [30] Martin Molina, Pedro Frau, Dario Maraval, Jose Luis Sanchez Lopez, Hriday Bavle, and Pascual Campoy. Human-robot cooperation in surface inspection aerial missions. 2017. [31] Yenting Huang, Gongyi Lee, Rutai Soong, and Jyishane Liu. Real-time vision-based river detection and lateral shot following for autonomous uavs. pages 421–426, 2020. doi: 10.1109/RCAR49640.2020.9303263. [32] Norel Ya Qine Abderrahim, Saadane Abderrahim, and Azmi Rida. Road segmentation using u-net architecture. pages 1–4, 2020. doi: 10.1109/Morgeo49228.2020. 9121887. [33] Bipendra Basnyat, Nirmalya Roy, and Aryya Gangopadhyay. Flood detection using semantic segmentation and multimodal data fusion. pages 135–140, 2021. doi: 10.1109/PerComWorkshops51409.2021.9430985. [34] Kun Zhao, Li Liu, Yu Meng, and Qing Gu. Feature deep continuous aggregation for 3d vehicle detection. Applied Sciences, 9:5397, 12 2019. doi: 10.3390/app9245397. [35] Yuqi Chen, Xiangbin Zhu, Yonggang Li, Yuanwang Wei, and Lihua Ye. Enhanced semantic feature pyramid network for small object detection. Signal Processing: Image Communication, 113:116919, 2023. ISSN 0923-5965. doi: https://doi.org/10.1016/j.image.2023.116919. URL https://www.sciencedirect.com/science/article/pii/S0923596523000012. [36] Selim Seferbekov, Vladimir Iglovikov, Alexander Buslaev, and Alexey Shvets. Feature pyramid network for multi-class land segmentation. pages 272–275, 2018. [37] Michele Colledanchise and Petter Ögren. Behavior trees in robotics and ai: An introduction. 2018. [38] Hartmut Prautzsch, Wolfgang Boehm, and Marco Paluszny. Bézier and b-spline techniques. 6, 2002. [39] Jyi-Shane Liu and Gong-Yi Lee. A carrot in probabilistic grid approach for quadrotor line following on vertical surfaces. pages 1234–1241, 2019. doi: 10.1109/ICUAS.2019.8797792. [40] ultralytics. Yolov8. URL https://github.com/ultralytics/ultralytics?tab=readme-ov-file. [41] Lukas Weber and Daniela Schenk. Automatische zusammenführung zertrennter konstruktionspläne von wasserbauwerken. Bautechnik, 99(5):340, 2022. URL https://hdl.handle.net/20.500.11970/112696.
描述 碩士
國立政治大學
資訊科學系
111753119
資料來源 http://thesis.lib.nccu.edu.tw/record/#G0111753119
資料類型 thesis
dc.contributor.advisor 劉吉軒zh_TW
dc.contributor.advisor Liu, Jyi Shaneen_US
dc.contributor.author (Authors) 陳佳彣zh_TW
dc.contributor.author (Authors) Chen, Chia-Wenen_US
dc.creator (作者) 陳佳彣zh_TW
dc.creator (作者) Chen, Chia-Wenen_US
dc.date (日期) 2024en_US
dc.date.accessioned 5-Aug-2024 12:45:05 (UTC+8)-
dc.date.available 5-Aug-2024 12:45:05 (UTC+8)-
dc.date.issued (上傳時間) 5-Aug-2024 12:45:05 (UTC+8)-
dc.identifier (Other Identifiers) G0111753119en_US
dc.identifier.uri (URI) https://nccur.lib.nccu.edu.tw/handle/140.119/152568-
dc.description (描述) 碩士zh_TW
dc.description (描述) 國立政治大學zh_TW
dc.description (描述) 資訊科學系zh_TW
dc.description (描述) 111753119zh_TW
dc.description.abstract (摘要) 近年來，隨著無人機技術的進步，其應用範圍從最初的軍事用途 逐漸擴展至民生服務和公共事業等領域，其中包括河川巡檢及人員搜 救等重要議題。無人機以其低部署成本和高機動性等特點，成為解決 方案中靈活且高效益的選擇。然而在控制方面，若僅依賴傳統搖桿操 作，會對操作人員帶來諸多不便，包括操作的複雜性、受限的自由度 以及無法同時觀看無人機影像等困難。此外，操作人員為了掌握無人 機控制，可能還需要接受專業培訓以習得執行任務所需的技能，這不 僅提高了操作門檻，也降低了系統應用的普及性。 為了建立直觀且易於操作的無人機控制系統，本研究提出了一種基 於視覺導航的人機協作方法，透過視覺化平台進行即時半自動化的飛 行調控，並將其應用於河川巡檢及人員搜救的任務場景中。 在任務執行過程中，無人機作為環境感知和執行任務的工具，以 河川作為跟隨目標，採用全球定位系統（GPS）作為大範圍定位的基 礎，並融合視覺導航和語意分割模組，以建立精準、穩定的河川跟隨 模型。同時，操作人員可以通過介面即時監控無人機的飛行數據和影 像，以便根據需求做出即時決策。本研究所提出的人機協作系統不僅 適用於河川巡檢任務，亦可應用於其他河川相關任務，如水位追蹤、 水污染檢測和垃圾檢測等情境。zh_TW
dc.description.abstract (摘要) In recent years, UAV technology has advanced, leading to its increased use in civilian applications such as river inspection and personnel rescue. UAVs are cost-effective and highly mobile, making them efficient solutions for various scenarios. However, traditional joystick operations for UAV control present challenges for operators, including complexity, limited freedom, and the inability to check UAV images simultaneously. Furthermore, operators need specialized training for mission execution, raising the operational threshold and reducing accessibility to the system. To address these issues, this study proposes a vision-based human-robot collaboration method for intuitive and easy UAV control. This method involves a visual platform for monitoring and real-time semi-automated flight control, specifically applied to river inspection and personnel rescue missions. During mission execution, UAV uses GPS for broad-range positioning and integrates visual navigation and semantic segmentation modules to accurately and stably follow the river as a target. Operators can monitor the UAV’s flight data and images in real time through the visual platform, allowing for timely decision-making based on mission needs. Importantly, the human-machine collaboration system proposed in this study is not limited to river inspection tasks but also extends to other river-related activities such as water level tracking, water pollution detection, and waste detection.en_US
dc.description.tableofcontents 第一章 緒論 1 1.1 研究背景 1 1.2 研究動機與目的 2 1.3 研究架構 3 1.4 研究成果與貢獻 4 第二章 文獻探討 6 2.1 人機互動 6 2.1.1 人機協作 7 2.1.2 圖形化介面操控方式 7 2.2 視覺導航模組 8 2.2.1 影像分割技術 8 2.3 物件偵測 (Object Detection) 10 第三章 研究方法 11 3.1 系統架構 11 3.1.1 實驗設備與實施方法 12 3.1.2 無人機 12 3.1.3 操作人員 12 3.1.4 人機協作流程 13 3.2 河川自主跟隨 17 3.2.1 語意分割模型 18 3.3 行為樹 20 3.3.1 B-Spline 平滑遮罩 25 3.3.2 視覺導航 26 3.4 物件偵測 (Object Detection) 27 3.5 目標追蹤 29 第四章 實驗結果與分析 31 4.1 硬體設備 31 4.2 軟體設置 33 4.3 真實環境場域佈置 33 4.4 實驗設計 35 4.4.1 實驗一：自主巡檢與人員偵測 35 4.4.2 實驗二：河岸施工場地巡檢 37 4.5 人機互動介面 41 4.5.1 主選單 41 4.5.2 河川巡檢與人員偵測 41 4.5.3 河岸施工巡檢 43 4.5.4 任務回報畫面 44 4.5.5 異常情況飛行控制 45 4.6 實際場域驗證 46 4.6.1 實驗一：河川巡檢與人員偵測 46 4.6.2 實驗二：河岸施工場地巡檢 54 4.7 小結 57 第五章 結論與未來展望 59 5.1 研究結論 59 5.2 未來展望 60 參考文獻 62zh_TW
dc.format.extent 113408349 bytes-
dc.format.mimetype application/pdf-
dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0111753119en_US
dc.subject (關鍵詞) 無人機zh_TW
dc.subject (關鍵詞) 人機協作zh_TW
dc.subject (關鍵詞) 河川巡檢zh_TW
dc.subject (關鍵詞) 自主跟隨zh_TW
dc.subject (關鍵詞) 任務控制zh_TW
dc.subject (關鍵詞) 人機互動介面zh_TW
dc.subject (關鍵詞) UAVen_US
dc.subject (關鍵詞) Human-Robot Collaborationen_US
dc.subject (關鍵詞) River Patrolen_US
dc.subject (關鍵詞) Mission Controlen_US
dc.subject (關鍵詞) Graphical User Interfaceen_US
dc.title (題名) 人機協作與視覺導航應用於無人機河川巡檢任務研究zh_TW
dc.title (題名) The Study of Human-Robot Collaboration and Visual Navigation Applied to Unmanned Aerial Vehicle River Patrol Missionsen_US
dc.type (資料類型) thesisen_US
dc.relation.reference (參考文獻) [1] Hazim Shakhatreh, Ahmad H. Sawalmeh, Ala Al-Fuqaha, Zuochao Dou, Eyad Almaita, Issa Khalil, Noor Shamsiah Othman, Abdallah Khreishah, and Mohsen Guizani. Unmanned aerial vehicles (uavs): A survey on civil applications and key research challenges. IEEE Access, 7:48572–48634, 2019. doi: 10.1109/ACCESS.2019.2909530. [2] Anupam Keshari Pankaj Singh Yadav R Faiyaz Ahmed, J. C. Mohanta. Recent advances in unmanned aerial vehicles: A review. Arabian Journal for Science and Engineering, 47:7963–7984, 2022. URL https://doi.org/10.1007/s13369-022-06738-0. [3] Wu Xiao Zhenqi Hu He Ren, Yanling Zhao. A review of uav monitoring in mining areas: current status and future perspectives. International Journal of Coal Science Technology, 2019. URL https://doi.org/10.1007/s40789-019-00264-5. [4] Bin Li, Zesong Fei, and Yan Zhang. Uav communications for 5g and beyond: Recent advances and future trends. IEEE Internet of Things Journal, 6(2):2241–2263, 2019. doi: 10.1109/JIOT.2018.2887086. [5] 中 華 民 國 內 政 部 消 防 署. 夏 日 玩 水 內 政 部 提 醒： 禁 制 溪 流 不 要 去. 2022. URL https://www.nfa.gov.tw/kid/index.phpcode=list&flag=detail&ids=1468&article_id=12201. [6] Zanchettin A.M. Ivaldi S. et al. Ajoudani, A. Progress and prospects of the human–robot collaboration. Autonomous Robots, page 957–975, 2018. URL https://doi.org/10.1007/s10514-017-9677-2. [7] Janis Arents, Valters Abolins, Janis Judvaitis, Oskars Vismanis, Aly Oraby, and Kaspars Ozols. Human–robot collaboration trends and safety aspects: A systematic review. Journal of Sensor and Actuator Networks, 10(3), 2021. ISSN 2224-2708. doi: 10.3390/jsan10030048. URL https://www.mdpi.com/2224-2708/10/3/48. [8] Lu Feng, Clemens Wiltsche, Laura Humphrey, and Ufuk Topcu. Controller synthesis for autonomous systems interacting with human operators. page 70–79, 2015. doi:10.1145/2735960.2735973. URL https://doi.org/10.1145/2735960.2735973. [9] Michael A. Goodrich, Joseph L. Cooper, Julie A. Adams, Curtis Humphrey, Ron Zeeman, and Brian G. Buss. Using a mini-uav to support wilderness search and rescue: Practices for human-robot teaming. pages 1–6, 2007. doi: 10.1109/SSRR.2007.4381284. [10] Julie A Adams. Critical considerations for human-robot interface development.pages 1–8, 2002. [11] UAS Europe. Skyview ground control system. 2013. URL https://www.uas-europe.se/documents/SkyView%20GCS.pdf. [12] Ardu Pilot. Introduction to pixhawk ground control station. 2010. URL https://diydrones.com/profiles/blogs/introduction-to-pixhawk-ground?xg_source=activity. [13] Nicolas Audebert, Bertrand Le Saux, and Sébastien Lefèvre. Segment-before-detect:Vehicle detection and classification through semantic segmentation of aerial images.Remote Sensing, 9(4), 2017. ISSN 2072-4292. doi: 10.3390/rs9040368. URL https://www.mdpi.com/2072-4292/9/4/368. [14] Jonathan Long, Evan Shelhamer, and Trevor Darrell. Fully convolutional networks for semantic segmentation. pages 3431–3440, 2015. doi: 10.1109/CVPR.2015.7298965. [15] Olaf Ronneberger, Philipp Fischer, and Thomas Brox. U-net: Convolutional networks for biomedical image segmentation. pages 234–241, 2015. [16] Vijay Badrinarayanan, Alex Kendall, and Roberto Cipolla. Segnet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(12):2481–2495, 2017. doi:10.1109/TPAMI.2016.2644615. [17] Changqian Yu, Changxin Gao, Jingbo Wang, Gang Yu, Chunhua Shen, and Nong Sang. Bisenet v2: Bilateral network with guided aggregation for real-time semantic segmentation. 2020. [18] Te-Wei Chen, Yen-Ting Huang, and Wen-Hung Liao. Far-sighted bisenet v2 for real-time semantic segmentation. pages 1–8, 2021. doi: 10.1109/AVSS52988.2021.9663738. [19] Keyan Chen, Chenyang Liu, Hao Chen, Haotian Zhang, Wenyuan Li, Zhengxia Zou, and Zhenwei Shi. Rsprompter: Learning to prompt for remote sensing instance segmentation based on visual foundation model. IEEE Transactions on Geoscience and Remote Sensing, 2024. [20] Zhengxia Zou, Keyan Chen, Zhenwei Shi, Yuhong Guo, and Jieping Ye. Object detection in 20 years: A survey. Proceedings of the IEEE, 111(3):257–276, 2023. doi: 10.1109/JPROC.2023.3238524. [21] Hui Zhang, Yu Du, Shurong Ning, Yonghua Zhang, Shuo Yang, and Chen Du. Pedestrian detection method based on faster r-cnn. pages 427–430, 2017. doi:10.1109/CIS.2017.00099. [22] A. P. P. Abdul Majeed L. L. Thai M. A. Mohd Razman J. C. Tang, A. F. B. Ab. Nasir and I. Mohd Khairuddin. Fine-tuned retinanet models for vision-based human presence detection. MEKATRONIKA, 4(2):16–23, November 2022. doi: 10.15282/mekatronika.v4i2.8850. URL https://journal.ump.edu.my/mekatronika/article/view/8850. [23] Wei-Yen Hsu and Wen-Yen Lin. Ratio-and-scale-aware yolo for pedestrian detection. IEEE Transactions on Image Processing, 30:934–947, 2021. doi: 10.1109/TIP.2020.3039574. [24] H.g Yu Y. Yang K. Duan G. Li W.g Zhang Q. Huang Q. Tian D. Du, Y. Qi. The unmanned aerial vehicle benchmark: Object detection and tracking. European Conference on Computer Vision (ECCV), 2018. [25] Pengfei Zhu, Longyin Wen, Dawei Du, Xiao Bian, Heng Fan, Qinghua Hu, and Haibin Ling. Detection and tracking meet drones challenge. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(11):7380–7399, 2021. [26] Jian Ding, Nan Xue, Gui-Song Xia, Xiang Bai, Wen Yang, Michael Yang, Serge Belongie, Jiebo Luo, Mihai Datcu, Marcello Pelillo, and Liangpei Zhang. Object detection in aerial images: A large-scale benchmark and challenges. IEEE Transactions on Pattern Analysis and Machine Intelligence, pages 1–1, 2021. doi:10.1109/TPAMI.2021.3117983. [27] Sasa Sambolek and Marina Ivasic-Kos. Automatic person detection in search and rescue operations using deep cnn detectors. IEEE Access, 9:37905–37922, 2021. doi: 10.1109/ACCESS.2021.3063681. [28] Igharoro O. Liu Y. et al. Hong, A. Investigating human-robot teams for learningbased semi-autonomous control in urban search and rescue environments. Journal of Intelligent Robotic Systems, page 669–686, 2019. URL https://doi.org/10.1007/s10846-018-0899-0. [29] Jeyan J. V. M. Ramesh, P. S. Comparative analysis of fixed-wing, rotary-wing and hybrid mini unmanned aircraft systems (uas) from the applications perspective. INCAS Bulletin, pages 137–151, 2022. URL https://doi.org/10.13111/2066-8201.2022.14.1.12. [30] Martin Molina, Pedro Frau, Dario Maraval, Jose Luis Sanchez Lopez, Hriday Bavle, and Pascual Campoy. Human-robot cooperation in surface inspection aerial missions. 2017. [31] Yenting Huang, Gongyi Lee, Rutai Soong, and Jyishane Liu. Real-time vision-based river detection and lateral shot following for autonomous uavs. pages 421–426, 2020. doi: 10.1109/RCAR49640.2020.9303263. [32] Norel Ya Qine Abderrahim, Saadane Abderrahim, and Azmi Rida. Road segmentation using u-net architecture. pages 1–4, 2020. doi: 10.1109/Morgeo49228.2020. 9121887. [33] Bipendra Basnyat, Nirmalya Roy, and Aryya Gangopadhyay. Flood detection using semantic segmentation and multimodal data fusion. pages 135–140, 2021. doi: 10.1109/PerComWorkshops51409.2021.9430985. [34] Kun Zhao, Li Liu, Yu Meng, and Qing Gu. Feature deep continuous aggregation for 3d vehicle detection. Applied Sciences, 9:5397, 12 2019. doi: 10.3390/app9245397. [35] Yuqi Chen, Xiangbin Zhu, Yonggang Li, Yuanwang Wei, and Lihua Ye. Enhanced semantic feature pyramid network for small object detection. Signal Processing: Image Communication, 113:116919, 2023. ISSN 0923-5965. doi: https://doi.org/10.1016/j.image.2023.116919. URL https://www.sciencedirect.com/science/article/pii/S0923596523000012. [36] Selim Seferbekov, Vladimir Iglovikov, Alexander Buslaev, and Alexey Shvets. Feature pyramid network for multi-class land segmentation. pages 272–275, 2018. [37] Michele Colledanchise and Petter Ögren. Behavior trees in robotics and ai: An introduction. 2018. [38] Hartmut Prautzsch, Wolfgang Boehm, and Marco Paluszny. Bézier and b-spline techniques. 6, 2002. [39] Jyi-Shane Liu and Gong-Yi Lee. A carrot in probabilistic grid approach for quadrotor line following on vertical surfaces. pages 1234–1241, 2019. doi: 10.1109/ICUAS.2019.8797792. [40] ultralytics. Yolov8. URL https://github.com/ultralytics/ultralytics?tab=readme-ov-file. [41] Lukas Weber and Daniela Schenk. Automatische zusammenführung zertrennter konstruktionspläne von wasserbauwerken. Bautechnik, 99(5):340, 2022. URL https://hdl.handle.net/20.500.11970/112696.zh_TW