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 無人機區域偵查及目標物件定位策略之技術研究
Technical Research on UAV Area Search and Object Geolocation Strategy
作者 劉益誠
Liu, Yi-Chen
貢獻者 劉吉軒
Liu, Jyi-Shane
劉益誠
Liu, Yi-Chen
關鍵詞 智慧無人機
區域偵查
平面視覺
距離預測
三角測量
地理座標投影
區域覆蓋路徑規劃
無人機定位策略
特徵比對
Smart UAV
Area Search
2D vision
Distance Estimation
Triangulation
Geographic Coordinate Projection
Coverage Path Planning
UAV Geolocation Strategy
Feature Matching
日期 2023
上傳時間 1-Sep-2023 15:24:38 (UTC+8)
摘要 無人機在現今產業發展快速，因其相較於需人員搭載的飛行器有更低的\n製造成本、更高的機動性而且減少了駕駛人員傷亡的風險而大量應用於過\n往需要人力的工作上。無人機發展初期主要應用於軍事用途上，但隨著技\n術逐漸商用化無人機逐漸在民生用途上取得大量的發展，包含在工業、農\n業、電影拍攝甚至是競技娛樂都出現了無人機的應用技術。除了無人機硬\n體本身的發展外，影像處理的技術發展使無人機能在更多應用場景發揮價\n值，尤其是平面視覺的影像處理技術使無人機能夠以平面視覺的相機進行\n更多的任務，特別是對於重量有限制而無法搭載大量感測器的微型無人機。\n對於微型無人機來說平面相機、GPS、指北針與高度計是常備的感測\n器，因此本研究對於偵查區域內目標物件定位任務以微型無人機常備的感\n測器發展三項定位策略來達成不同任務環境下的目標偵查與定位。其中，\n多點平均定位策略以單目視覺定位模組為主，搭配平面視覺影像及感測器\n數據來達成對地上目標物件的定位，並利用了無人機執行任務的連續性對\n感測器資料進行校正進而提升定位結果的可靠度。為了降低感測器的依賴\n程度，本研究以三角計算的方式發展三角測量定位策略，成功降低感測器\n的依賴度以及高度對於定位準確度的影響。影像比對定位策略則是以特徵\n比對技術為基礎來達成純影像的定位任務，使無人機在感測器失效的任務\n環境下仍能夠達成定位任務。
With the rapid development of unmanned aerial vehicle technology and it’s\nhigh mobility, low risk for drone pilot.Unmanned Aerial Vehicle have been used\nin a variety of applications.In early stage, UAV was mainly used for military\npurposes.But, with UAV technology became more and more prevalent, UAV widely\napplied on Manufacturing industry, agriculture and film industry.Beside the UAV\ntechnology, the development of image processing also improve development of\nUAV application.And 2D-vision-based image processing was important especially\nfor micro UAV because of it’s weight limit.\nFor micro UAV, the commonly equipped sensors are a camera, GPS, compass\nand altimeter. Therefore, this research develop three geolocation strategies using\nthe sensors commonly found on micro drones to achieve target detection and\npositioning in different mission environments. Among them, the multi-point\naveraging geolocation strategy focuses on the monocular visual positioning module,\nusing plane visual images and sensor data to locate ground target.This strategy\nalso calibrate the sensor data to improve the reliability of the positioning results.\nTo reduce sensor dependency, a triangulation geolocation strategy was developed\nusing trigonometric calculations, successfully reducing the reliance on sensors and\nmitigating the impact of altitude on positioning accuracy. The image matching\ngeolocation strategy is based on feature matching techniques to achieve pure imagebased\npositioning tasks, enabling drones to perform positioning tasks even in\nmission environments where sensors may fail.
參考文獻 [1] Robot operating system (ros) https://www.ros.org/.\n[2] Ros-mobile http://wiki.ros.org/ros-mobile.\n[3] Rodney Brooks. A robust layered control system for a mobile robot. IEEE Journal on\nRobotics and Automation, 2(1):14–23, 1986.\n[4] John Canny. A computational approach to edge detection. IEEE Transactions on Pattern\nAnalysis and Machine Intelligence, 8(6):679–698, 1986.\n[5] D. Comaniciu and P. Meer. Mean shift: a robust approach toward feature space analysis.\nIEEE Transactions on Pattern Analysis and Machine Intelligence, 24(5):603–619, 2002.\n[6] Daniel DeTone, Tomasz Malisiewicz, and Andrew Rabinovich. Superpoint: Self-\nsupervised interest point detection and description. Computer Vision and Pattern\nRecognition(CVPR), 2018.\n[7] Yoav Gabriely and Elon Rimon. Spanning-tree based coverage of continuous areas by a\nmobile robot. International Conference on Robotics and Automation, 2:1927–1933, 2001.\n[8] Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley,\nSherjil Ozair, Aaron Courville, and Yoshua Bengio. Generative adversarial networks.\nNeurIPS, 27, 2014.\n[9] Fatih Gökçe, Göktürk Üçoluk, Erol ̧Sahin, and Sinan Kalkan. Vision-based detection\nand distance estimation of micro unmanned aerial vehicles. Sensors, 15(9):23805–23846,\n2015.\n[10] Elder M. Hemerly. Automatic georeferencing of images acquired by uav’s. International\nJournal of Automation and Computing, 11(347–352), 2014.\n[11] Luc Van Gool Herbert Bay, Tinne Tuytelaars. Surf: Speeded up robust features. Computer\nVision\n–ECCV, 3951, 2006.\n[12] Phillip Isola, Jun-Yan Zhu, Tinghui Zhou, and Alexei A. Efros. Image-to-image translation\nwith conditional adversarial networks. International Journal of Computer Vision, 2018.\n[13] Charles F. F. Karney. Algorithms for geodesics. Journal of Geodesy, 87:43–55, 2013.\n[14] Ragab Khalil. The accuracy of gis tools for transforming assumed total station surveys to\nreal world coordinates. Geographic Information System, 5(486-491), 2013.\n[15] Arturo De la Escalera and Jose María Armingol. Automatic chessboard detection for\nintrinsic and extrinsic camera parameter calibration. Sensors, 10(3)(2027-2044), 2010.\n[16] Chaozhen Lan, Wanjie Lu, Junming Yu, and Qing Xu. Deep learning algorithm for feature\nmatching of cross modality remote sensing images. Acta Geodaetica et Cartographica\nSinica, 50(2):14–23, 2021.\n[17] Zuoyue Li, Jan Dirk Wegner, and Aurelien Lucchi. Topological map extraction from\noverhead images. International Conference on Computer Vision, 2019.\n[18] Xiao Ling, Yongjun Zhang, Jinxin Xiong, Xu Huang, and Zhipeng Chen. An image\nmatching algorithm integrating global srtm and image segmentation for multi-source\nsatellite imagery. Remote Sensing, 8, 2016.\n[19] D.G Lowe. Distinctive image features from scale-invariant keypoints. International\nJournal of Computer Vision, 60(91–110), 2004.\n[20] L. H. Nam, L. Huang, X. J. Li, and J. F. Xu. An approach for coverage path planning for\nuavs. IEEE 14th International Workshop on Advanced Motion Control, (411-416), 2016.\n[21] Donggeun Oh and Junghee Han. Smart search system of autonomous flight uavs for\ndisaster rescue. Sensors, 21(20), 2021.\n[22] Edwin Olson. Apriltag: A robust and flexible visual fiducial system. International\nConference on Robotics and Automation, 2011.\n[23] Parrot. Anafi https://www.parrot.com/en/drones/anafi.\n[24] Parrot. Bebop2 https://www.parrot.com/en/drones.\n[25] Shashikant Prasad. pix2pix gan for generating maps given satellite images using\npytorch, https:// medium.com/ @skpd/ pix2pix-gan-for-generating-map-given-satellite-\nimages-using-pytorch-6e50c318673a.\n[26] Wahyu Rahmaniar, Wen-June Wang, Wahyu Caesarendra, Adam Glowacz, Krzysztof\nOprz ̨edkiewicz, Maciej Sułowicz, and Muhammad Irfan. Distance measurement\nof unmanned aerial vehicles using vision-based systems in unknown environments.\nElectronics, 10(14), 2021.\n[27] Ethan Rublee, Vincent Rabaud, Kurt Konolige, and Gary Bradski. Orb: an efficient\nalternative to sift or surf. Proceedings of the IEEE International Conference on Computer\nVision, (2564-2571), 2011.\n[28] Sajid Saleem, Abdul Bais, and Robert Sablatnig. Towards feature points based image\nmatching between satellite imagery and aerial photographs of agriculture land. Computers\nand Electronics in Agriculture, 126:12–20, 2016.\n[29] Paul-Edouard Sarlin, Daniel DeTone, Tomasz Malisiewicz, and Andrew Rabinovich.\nSuperglue: Learning feature matching with graph neural networks. Computer Vision and\nPattern Recognition(CVPR), 2020.\n[30] Chris Simpson. Behavior trees for ai: How they work, https://www.gamedeveloper.com/\nprogramming/behavior-trees-for-ai-how-they-work.\n[31] Jiaming Sun, Zehong Shen, Yuang Wang, Hujun Bao, and Xiaowei Zhou. Loftr:\nDetector-free local feature matching with transformers. Computer Vision and Pattern\nRecognition(CVPR), 2021.\n[32] Dengqing Tang, Tianjiang Hu, Zhaowei Ma, Lincheng Shen, and Chongyu Pan. Apriltag\narray-aided extrinsic calibration of camera–laser multi-sensor system. Robotics and\nBiomimetics, 3(13), 2016.\n[33] Jinbiao Yuan, Zhenbao Liu, Yeda Lian, Lulu Chen, Qiang An, Lina Wang, and Bodi Ma.\nGlobal optimization of uav area coverage path planning based on good point set and genetic\nalgorithm. Aerospace, 9(2), 2022.\n[34] Xiaoyue Zhao, Fangling Pu, Zhihang Wang, Hongyu Chen, and Zhaozhuo Xu. Detection,\ntracking, and geolocation of moving vehicle from uav using monocular camera. IEEE\nAccess, 7:101160–101170, 2019.\n[35] 佐翼科技. Dx30-w1 https://www.droxotech.com/.\n[36] 內政部國土測繪中心. 國土測繪圖資服務雲 https://maps.nlsc.gov.tw.\n[37] 擎壤科技. Eg2 https://www.earthgen.com.tw/eg2.
描述 碩士
國立政治大學
資訊科學系
110753136
資料來源 http://thesis.lib.nccu.edu.tw/record/#G0110753136
資料類型 thesis
dc.contributor.advisor 劉吉軒zh_TW
dc.contributor.advisor Liu, Jyi-Shaneen_US
dc.contributor.author (Authors) 劉益誠zh_TW
dc.contributor.author (Authors) Liu, Yi-Chenen_US
dc.creator (作者) 劉益誠zh_TW
dc.creator (作者) Liu, Yi-Chenen_US
dc.date (日期) 2023en_US
dc.date.accessioned 1-Sep-2023 15:24:38 (UTC+8)-
dc.date.available 1-Sep-2023 15:24:38 (UTC+8)-
dc.date.issued (上傳時間) 1-Sep-2023 15:24:38 (UTC+8)-
dc.identifier (Other Identifiers) G0110753136en_US
dc.identifier.uri (URI) https://ah.lib.nccu.edu.tw/item?item_id=166507-
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) 110753136zh_TW
dc.description.abstract (摘要) 無人機在現今產業發展快速，因其相較於需人員搭載的飛行器有更低的\n製造成本、更高的機動性而且減少了駕駛人員傷亡的風險而大量應用於過\n往需要人力的工作上。無人機發展初期主要應用於軍事用途上，但隨著技\n術逐漸商用化無人機逐漸在民生用途上取得大量的發展，包含在工業、農\n業、電影拍攝甚至是競技娛樂都出現了無人機的應用技術。除了無人機硬\n體本身的發展外，影像處理的技術發展使無人機能在更多應用場景發揮價\n值，尤其是平面視覺的影像處理技術使無人機能夠以平面視覺的相機進行\n更多的任務，特別是對於重量有限制而無法搭載大量感測器的微型無人機。\n對於微型無人機來說平面相機、GPS、指北針與高度計是常備的感測\n器，因此本研究對於偵查區域內目標物件定位任務以微型無人機常備的感\n測器發展三項定位策略來達成不同任務環境下的目標偵查與定位。其中，\n多點平均定位策略以單目視覺定位模組為主，搭配平面視覺影像及感測器\n數據來達成對地上目標物件的定位，並利用了無人機執行任務的連續性對\n感測器資料進行校正進而提升定位結果的可靠度。為了降低感測器的依賴\n程度，本研究以三角計算的方式發展三角測量定位策略，成功降低感測器\n的依賴度以及高度對於定位準確度的影響。影像比對定位策略則是以特徵\n比對技術為基礎來達成純影像的定位任務，使無人機在感測器失效的任務\n環境下仍能夠達成定位任務。zh_TW
dc.description.abstract (摘要) With the rapid development of unmanned aerial vehicle technology and it’s\nhigh mobility, low risk for drone pilot.Unmanned Aerial Vehicle have been used\nin a variety of applications.In early stage, UAV was mainly used for military\npurposes.But, with UAV technology became more and more prevalent, UAV widely\napplied on Manufacturing industry, agriculture and film industry.Beside the UAV\ntechnology, the development of image processing also improve development of\nUAV application.And 2D-vision-based image processing was important especially\nfor micro UAV because of it’s weight limit.\nFor micro UAV, the commonly equipped sensors are a camera, GPS, compass\nand altimeter. Therefore, this research develop three geolocation strategies using\nthe sensors commonly found on micro drones to achieve target detection and\npositioning in different mission environments. Among them, the multi-point\naveraging geolocation strategy focuses on the monocular visual positioning module,\nusing plane visual images and sensor data to locate ground target.This strategy\nalso calibrate the sensor data to improve the reliability of the positioning results.\nTo reduce sensor dependency, a triangulation geolocation strategy was developed\nusing trigonometric calculations, successfully reducing the reliance on sensors and\nmitigating the impact of altitude on positioning accuracy. The image matching\ngeolocation strategy is based on feature matching techniques to achieve pure imagebased\npositioning tasks, enabling drones to perform positioning tasks even in\nmission environments where sensors may fail.en_US
dc.description.tableofcontents 第一章 緒論 1\n第一節 研究背景 1\n第二節 研究動機 2\n第三節 研究目的 4\n第二章 文獻探討 6\n第一節 無人機區域偵查與定位 6\n第二節 區域覆蓋路徑規劃 7\n第三節 距離估算 7\n第四節 地理對位 8\n第五節 影像特徵比對 10\n第三章 技術架構 12\n第一節 定位策略設計 12\n第二節 路徑規劃 14\n第三節 目標偵測 15\n第四節 多點平均定位策略 21\n一、單目視覺定位模組 21\n二、感測器資訊與影像之映射 24\n三、GPS 座標推算 25\n四、校正模組與結果計算 26\n第五節 三角測量定位策略 28\n第六節 影像比對定位策略 30\n一、衛星圖資 30\n二、特徵比對 31\n三、區域搜尋 31\n四、定位模組 36\n第七節 無人機控制 38\n一、ROS 節點設計 8\n二、行為樹設計 38\n三、無人機控制機制介面 40\n第四章 實驗及評估 42\n第一節 評估指標 42\n第二節 實驗設計 43\n第三節 實驗結果 46\n第五章 結論 53\n第一節 結果分析 53\n第二節 發展方向 54\n參考文獻 58zh_TW
dc.format.extent 15973369 bytes-
dc.format.mimetype application/pdf-
dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0110753136en_US
dc.subject (關鍵詞) 智慧無人機zh_TW
dc.subject (關鍵詞) 區域偵查zh_TW
dc.subject (關鍵詞) 平面視覺zh_TW
dc.subject (關鍵詞) 距離預測zh_TW
dc.subject (關鍵詞) 三角測量zh_TW
dc.subject (關鍵詞) 地理座標投影zh_TW
dc.subject (關鍵詞) 區域覆蓋路徑規劃zh_TW
dc.subject (關鍵詞) 無人機定位策略zh_TW
dc.subject (關鍵詞) 特徵比對zh_TW
dc.subject (關鍵詞) Smart UAVen_US
dc.subject (關鍵詞) Area Searchen_US
dc.subject (關鍵詞) 2D visionen_US
dc.subject (關鍵詞) Distance Estimationen_US
dc.subject (關鍵詞) Triangulationen_US
dc.subject (關鍵詞) Geographic Coordinate Projectionen_US
dc.subject (關鍵詞) Coverage Path Planningen_US
dc.subject (關鍵詞) UAV Geolocation Strategyen_US
dc.subject (關鍵詞) Feature Matchingen_US
dc.title (題名) 無人機區域偵查及目標物件定位策略之技術研究zh_TW
dc.title (題名) Technical Research on UAV Area Search and Object Geolocation Strategyen_US
dc.type (資料類型) thesisen_US
dc.relation.reference (參考文獻) [1] Robot operating system (ros) https://www.ros.org/.\n[2] Ros-mobile http://wiki.ros.org/ros-mobile.\n[3] Rodney Brooks. A robust layered control system for a mobile robot. IEEE Journal on\nRobotics and Automation, 2(1):14–23, 1986.\n[4] John Canny. A computational approach to edge detection. IEEE Transactions on Pattern\nAnalysis and Machine Intelligence, 8(6):679–698, 1986.\n[5] D. Comaniciu and P. Meer. Mean shift: a robust approach toward feature space analysis.\nIEEE Transactions on Pattern Analysis and Machine Intelligence, 24(5):603–619, 2002.\n[6] Daniel DeTone, Tomasz Malisiewicz, and Andrew Rabinovich. Superpoint: Self-\nsupervised interest point detection and description. Computer Vision and Pattern\nRecognition(CVPR), 2018.\n[7] Yoav Gabriely and Elon Rimon. Spanning-tree based coverage of continuous areas by a\nmobile robot. International Conference on Robotics and Automation, 2:1927–1933, 2001.\n[8] Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley,\nSherjil Ozair, Aaron Courville, and Yoshua Bengio. Generative adversarial networks.\nNeurIPS, 27, 2014.\n[9] Fatih Gökçe, Göktürk Üçoluk, Erol ̧Sahin, and Sinan Kalkan. Vision-based detection\nand distance estimation of micro unmanned aerial vehicles. Sensors, 15(9):23805–23846,\n2015.\n[10] Elder M. Hemerly. Automatic georeferencing of images acquired by uav’s. International\nJournal of Automation and Computing, 11(347–352), 2014.\n[11] Luc Van Gool Herbert Bay, Tinne Tuytelaars. Surf: Speeded up robust features. Computer\nVision\n–ECCV, 3951, 2006.\n[12] Phillip Isola, Jun-Yan Zhu, Tinghui Zhou, and Alexei A. Efros. Image-to-image translation\nwith conditional adversarial networks. International Journal of Computer Vision, 2018.\n[13] Charles F. F. Karney. Algorithms for geodesics. Journal of Geodesy, 87:43–55, 2013.\n[14] Ragab Khalil. The accuracy of gis tools for transforming assumed total station surveys to\nreal world coordinates. Geographic Information System, 5(486-491), 2013.\n[15] Arturo De la Escalera and Jose María Armingol. Automatic chessboard detection for\nintrinsic and extrinsic camera parameter calibration. Sensors, 10(3)(2027-2044), 2010.\n[16] Chaozhen Lan, Wanjie Lu, Junming Yu, and Qing Xu. Deep learning algorithm for feature\nmatching of cross modality remote sensing images. Acta Geodaetica et Cartographica\nSinica, 50(2):14–23, 2021.\n[17] Zuoyue Li, Jan Dirk Wegner, and Aurelien Lucchi. Topological map extraction from\noverhead images. International Conference on Computer Vision, 2019.\n[18] Xiao Ling, Yongjun Zhang, Jinxin Xiong, Xu Huang, and Zhipeng Chen. An image\nmatching algorithm integrating global srtm and image segmentation for multi-source\nsatellite imagery. Remote Sensing, 8, 2016.\n[19] D.G Lowe. Distinctive image features from scale-invariant keypoints. International\nJournal of Computer Vision, 60(91–110), 2004.\n[20] L. H. Nam, L. Huang, X. J. Li, and J. F. Xu. An approach for coverage path planning for\nuavs. IEEE 14th International Workshop on Advanced Motion Control, (411-416), 2016.\n[21] Donggeun Oh and Junghee Han. Smart search system of autonomous flight uavs for\ndisaster rescue. Sensors, 21(20), 2021.\n[22] Edwin Olson. Apriltag: A robust and flexible visual fiducial system. International\nConference on Robotics and Automation, 2011.\n[23] Parrot. Anafi https://www.parrot.com/en/drones/anafi.\n[24] Parrot. Bebop2 https://www.parrot.com/en/drones.\n[25] Shashikant Prasad. pix2pix gan for generating maps given satellite images using\npytorch, https:// medium.com/ @skpd/ pix2pix-gan-for-generating-map-given-satellite-\nimages-using-pytorch-6e50c318673a.\n[26] Wahyu Rahmaniar, Wen-June Wang, Wahyu Caesarendra, Adam Glowacz, Krzysztof\nOprz ̨edkiewicz, Maciej Sułowicz, and Muhammad Irfan. Distance measurement\nof unmanned aerial vehicles using vision-based systems in unknown environments.\nElectronics, 10(14), 2021.\n[27] Ethan Rublee, Vincent Rabaud, Kurt Konolige, and Gary Bradski. Orb: an efficient\nalternative to sift or surf. Proceedings of the IEEE International Conference on Computer\nVision, (2564-2571), 2011.\n[28] Sajid Saleem, Abdul Bais, and Robert Sablatnig. Towards feature points based image\nmatching between satellite imagery and aerial photographs of agriculture land. Computers\nand Electronics in Agriculture, 126:12–20, 2016.\n[29] Paul-Edouard Sarlin, Daniel DeTone, Tomasz Malisiewicz, and Andrew Rabinovich.\nSuperglue: Learning feature matching with graph neural networks. Computer Vision and\nPattern Recognition(CVPR), 2020.\n[30] Chris Simpson. Behavior trees for ai: How they work, https://www.gamedeveloper.com/\nprogramming/behavior-trees-for-ai-how-they-work.\n[31] Jiaming Sun, Zehong Shen, Yuang Wang, Hujun Bao, and Xiaowei Zhou. Loftr:\nDetector-free local feature matching with transformers. Computer Vision and Pattern\nRecognition(CVPR), 2021.\n[32] Dengqing Tang, Tianjiang Hu, Zhaowei Ma, Lincheng Shen, and Chongyu Pan. Apriltag\narray-aided extrinsic calibration of camera–laser multi-sensor system. Robotics and\nBiomimetics, 3(13), 2016.\n[33] Jinbiao Yuan, Zhenbao Liu, Yeda Lian, Lulu Chen, Qiang An, Lina Wang, and Bodi Ma.\nGlobal optimization of uav area coverage path planning based on good point set and genetic\nalgorithm. Aerospace, 9(2), 2022.\n[34] Xiaoyue Zhao, Fangling Pu, Zhihang Wang, Hongyu Chen, and Zhaozhuo Xu. Detection,\ntracking, and geolocation of moving vehicle from uav using monocular camera. IEEE\nAccess, 7:101160–101170, 2019.\n[35] 佐翼科技. Dx30-w1 https://www.droxotech.com/.\n[36] 內政部國土測繪中心. 國土測繪圖資服務雲 https://maps.nlsc.gov.tw.\n[37] 擎壤科技. Eg2 https://www.earthgen.com.tw/eg2.zh_TW