學術產出-Theses

Article View/Open

Publication Export

Google ScholarTM

政大圖書館

Citation Infomation

題名 微型無人機基於視覺自動區域偵查與物件偵測定位
Miniature UAV based on visual automatic area search with object detection and geolocalization
作者 李德暐
Li, De-Wei
貢獻者 劉吉軒
Liu, Jyi-Shane
李德暐
Li,De-Wei
關鍵詞 無人機
區域偵察
行為樹
物件偵測
物件追蹤
電子地圖
地理對位
Drone
Area reconnaissance
Behavior tree
Object detection
Object tracking
Digital map
Georeferencing
日期 2020
上傳時間 1-Feb-2021 14:11:04 (UTC+8)
摘要 隨著無人機的技術越來越成熟,從一開始發展目的為戰爭武器,到現在民眾能使用娛樂用途的空拍機,無人機慢慢地融入了我們的生活之中。無人機擁有獨特空間運動能力,因此出現越來越多的應用。像是美國Airware公司推出無人機屋頂檢查系統,無人機能夠自動收集房屋範圍內的影像資訊等。無人機展現出強大的資訊蒐集能力。雖然目前無人機用於偵察的例子很多,但大都是以高階的機種為主,原因是需要更多的感測器去幫助執行偵察任務,像是熱像儀、鐳射掃描儀等等感測器。然而目前政府機構、民間機構所擁有比較多的機種都是較為便宜的低階微型無人機。有鑑於此,本研究希望能在低成本微型無人機上能使用。基於視覺使用電腦視覺輔助偵測物件並定位,搭配行為樹使其自動控制化減少人力上控制的需求。
As the technology of drones has become more and more mature, from the beginning of the development of weapons of war, to now that people can use aerial cameras for entertainment purposes, drones have slowly integrated into our lives. UAVs have unique space movement capabilities, so more and more applications appear. For example, the United States Airware company launched a drone roof inspection system, which can automatically collect image information within the house. Unmanned aerial vehicles demonstrate powerful information gathering capabilities. Although there are many examples of drones used for
investigation, most of them are based on high-end drones. The reason is that more sensors are needed to help perform investigation tasks, such as thermal imaging cameras, laser scanners, etc. However, at present, government agencies and private organizations have a relatively large number of aircraft types that are relatively inexpensive low-end micro drones. In view of this, this research hopes to be used on low-cost micro drones. Based on vision, computer vision is used to assist in detecting and positioning objects, and the behavior tree is used to make it automatically controlled to reduce the need for human control.
參考文獻 [1] R. Austin, Unmanned Aircraft Systems: UAVS Design Development and Deployment, Chichester, U.K.:Wiley, Apr. 2010.
[2] C. Sandbrook, "The social implications of using drones for biodiversity conservation", Ambio, vol. 44, no. Suppl 4, (S4), pp. 636-647, 2015.
[3] Parrot Drones SAS (n.d.). Retrieved November 15,2020,from https://support.parrot.com/global/support/products
[4] C. Bolkcom and E. Bone, "Unmanned aerial vehicles: Background and issues for congress report for congress congressional research service", Proc. Libr. Congr., pp. 13, 2003.
[5] K. Daniel, S. Rohde, and C. Wietfeld, “Leveraging public wireless communication infrastructures for UAV-based sensor networks,” in Proc. IEEE Int. Conf. Technol. Homeland Secur., Nov. 2010, pp. 179–184.
[6] S. Nebikera, A. Annena, M. Scherrerb and D. Oeschc, "A lightweight multispectral sensor for micro U A V -Opportunities for very high resolution airborne remote sensing", Int. Archiv. Photogram. Remote Sens. Spatial Inform. Sci, vol. 37, no. B1, pp. 1193-2000, 2008.
[7] C. Korpela, T. Danko, and P. Oh, "MM-UAV: Mobile manipulating unmanned aerial vehicle," Journal of Intelligent and Robotics Systems, vol. 65, no. 1, pp. 93-101, 2012.
[8] D. Erdos, A. Erdos and S. E. Watkins, "An experimental UAV system for search and rescue challenge", IEEE Aerospace and Electronic Systems Magazine, vol. 28, no. 5, pp. 32-37, May 2013.
[9] UAV CHALLENGE Retrieved November 15,2020, from https://uavchallenge.org/about/
[10] N. Michael, D. Mellinger, Q. Lindsey, and V Kumar, "The grasp multiple micro uav testbed," IEEE Robotics and Automation Magazine, Sept. 2010.
[11] T. Shima and S. Rasmussen, UAV Cooperative Decision and Control: Challenges and Practical Approaches, SIAM, 2009.
[12] M. Colledanchise and P. Ögren,"Behavior trees in robotics and AI: An introduction",CoRR,2017,[online]Available:http://arxiv.org/abs/1709.00084.
[13] P. Rudol and P. Doherty, "Human body detection and geolocalization for UAV search and rescue missions using color and thermal imagery", Proc. IEEE Aerosp. Conf., pp. 1-8, Mar. 2008.
[14] I. Martinez-Alpiste, G. Golcarenarenji, Q. Wang, and J. Calero, " Altitude-Adaptive and Cost-Effective Object Recognition in an Integrated Smartphone and UAV System." In 2020 European Conference on Networks and Communications (EuCNC) (pp. 316-320). IEEE.
[15] P. Ogren, "Increasing Modularity of UAV Control Systems using Computer Game Behavior Trees", AIAA Guidance Navigation and Control Conference, 2012.
[16] K. Y. W. Scheper, S. Tijmons, C. C. de Visser and G. C. H. E. de Croon, "Behaviour trees for evolutionary robotics", Artificial Life, vol. 22, no. 1, pp. 23-48, 2016.
[17] A. Klöckner, "Behavior trees for uav mission management", INFORMATIK 2013: Informatik angepasst an Mensch Organisation und Umwelt, pp. 57-68, 2013.
[18] M. Colledanchise and P. Ögren, "How behavior trees modularize robustness and safety in hybrid systems", Proc. IEEE/RSJ Int. Conf. Intell. Robots Syst., pp. 1482-1488, Jun. 2014.
[19] H. H. Helgesen, F. S. Leira, T. A. Johansen and T. I. Fossen, Detection and Tracking of Floating Objects Using a UAV with Thermal Camera, Cham:Springer International Publishing, pp. 289-316, 2017.
[20] S. Drake, "Converting GPS coordinates [phi Lambda h] to navigation coordinates (ENU)", 2002.
[21] E. M. Hemerly, “Automatic georeferencing of images acquired by
uav’s,” International Journal of Automation and Computing, vol. 11,
no. 4, pp. 347–352, Aug 2014.
[22] H. Xiang and L. Tian, "Method for automatic georeferencing aerial remote sensing (RS) images from an unmanned aerial vehicle (UAV) platform", Biosystems Engineering, vol. 108, pp. 104-113, 2011.
[23] L . Deng and D. Yu, "Deep learning: Methods and applications", Foundations and Trends in Signal Processing, vol. 7, no. 3–4, pp. 197-387, 2014.
[24] Z. Zhao, P. Zheng, S. Xu and X. Wu, "Object detection with deep learning: a review", IEEE Trans. on Neural Net. and Learning Systems, pp. 1-21, January 2019.
[25] X. Liu, Z. Deng and Y. Yang, "Recent progress in semantic image segmentation", Artificial Intelligence Review, pp. 1-18, 2018.
[26] R. Girshick, J. Donahue, T. Darrell and J. Malik, "Rich feature hierarchies for accurate object detection and semantic segmentation", Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp. 580-587, 2014.
[27] R. Girshick, "Fast R-CNN", Proc. IEEE Int. Conf. Comput. Vis., pp. 1440-1448, 2015.
[28] W. Liu, D. Anguelov, D. Erhan, C. Szegedy and S. Reed, "SSD: Single shot multibox detector", 2015.
[29] J. Redmon, S. Divvala, R. Girshick and A. Farhadi, "You only look once: Unified real-time object detection", Proc. IEEE Int. Conf. Computer Vision and Pattern Recognition (CVPR), pp. 779-788, 2016.
[30] J. Redmon and A. Farhadi, "YOLO9000: Better faster stronger", Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp. 6517-6525, 2017.
[31] J. Redmon and A. Farhadi, "YOLOv3: An incremental improvement" in arXiv:1804.02767, 2018, [online] Available: http://arxiv.org/abs/1804.02767.
[32] A. Bochkovskiy, C.-Y. Wang and H.-Y. M. Liao, YOLOv4: Optimal Speed and Accuracy of Object Detection, 2020, [online] Available: http://arxiv.org/abs/2004.10934.
[33] Y. Wu, J. Lim and M. H. Yang, "Online object tracking: A benchmark", Proc. Comput. Vis. Pattern Recognit., pp. 2411-2418, 2013.
[34] D. Comaniciu, V. Ramesh and P. Meer, "Kernel-based object tracking", IEEE Trans. Pattern Anal. Mach. Intell., vol. 25, no. 5, pp. 564-577, May. 2003.
[35] A. Yilmaz, X. Li and M. Shah, "Object contour tracking using level sets", Proc. Asian Conf. Computer Vision, 2004.
[36] X. Farhodov, O. Kwon, K. W. Kang, S. Lee and K. Kwon, "Faster RCNN detection based OpenCV CSRT tracker using drone data", International Conference on Information Science and Communications Technologies (ICISCT), pp. 1-3, 2019.
[37] L. Tan, X. Dong, Y. Ma and C. Yu, "A multiple object tracking algorithm based on YOLO detection", Int. Congress Image Signal Processing BioMedical Engineering Informatics, pp. 1-5, 2018.
[38] T. Vincenty, "Direct and inverse solutions of geodesics on the ellipsoid with application of nested equations", Survey Review, vol. 22, no. 176, pp. 88-93, 1975.
[39] Bebop_autonomy.(n.d.). Retrieved November 15,2020, from https://bebopautonomy.readthedocs.io/en/latest/
[40] E. Olson, "April`Tag: A robust and flexible visual fiducial system", 2011 IEEE International Conference on Robotics and Automation, May 2011.
[41] 內政部國土測繪中心Retrieved November 15,2020, from https://maps.nlsc.gov.tw/
描述 碩士
國立政治大學
資訊科學系
107753039
資料來源 http://thesis.lib.nccu.edu.tw/record/#G0107753039
資料類型 thesis
dc.contributor.advisor 劉吉軒zh_TW
dc.contributor.advisor Liu, Jyi-Shaneen_US
dc.contributor.author (Authors) 李德暐zh_TW
dc.contributor.author (Authors) Li,De-Weien_US
dc.creator (作者) 李德暐zh_TW
dc.creator (作者) Li, De-Weien_US
dc.date (日期) 2020en_US
dc.date.accessioned 1-Feb-2021 14:11:04 (UTC+8)-
dc.date.available 1-Feb-2021 14:11:04 (UTC+8)-
dc.date.issued (上傳時間) 1-Feb-2021 14:11:04 (UTC+8)-
dc.identifier (Other Identifiers) G0107753039en_US
dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/133896-
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) 107753039zh_TW
dc.description.abstract (摘要) 隨著無人機的技術越來越成熟,從一開始發展目的為戰爭武器,到現在民眾能使用娛樂用途的空拍機,無人機慢慢地融入了我們的生活之中。無人機擁有獨特空間運動能力,因此出現越來越多的應用。像是美國Airware公司推出無人機屋頂檢查系統,無人機能夠自動收集房屋範圍內的影像資訊等。無人機展現出強大的資訊蒐集能力。雖然目前無人機用於偵察的例子很多,但大都是以高階的機種為主,原因是需要更多的感測器去幫助執行偵察任務,像是熱像儀、鐳射掃描儀等等感測器。然而目前政府機構、民間機構所擁有比較多的機種都是較為便宜的低階微型無人機。有鑑於此,本研究希望能在低成本微型無人機上能使用。基於視覺使用電腦視覺輔助偵測物件並定位,搭配行為樹使其自動控制化減少人力上控制的需求。zh_TW
dc.description.abstract (摘要) As the technology of drones has become more and more mature, from the beginning of the development of weapons of war, to now that people can use aerial cameras for entertainment purposes, drones have slowly integrated into our lives. UAVs have unique space movement capabilities, so more and more applications appear. For example, the United States Airware company launched a drone roof inspection system, which can automatically collect image information within the house. Unmanned aerial vehicles demonstrate powerful information gathering capabilities. Although there are many examples of drones used for
investigation, most of them are based on high-end drones. The reason is that more sensors are needed to help perform investigation tasks, such as thermal imaging cameras, laser scanners, etc. However, at present, government agencies and private organizations have a relatively large number of aircraft types that are relatively inexpensive low-end micro drones. In view of this, this research hopes to be used on low-cost micro drones. Based on vision, computer vision is used to assist in detecting and positioning objects, and the behavior tree is used to make it automatically controlled to reduce the need for human control.
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 3
1.3 論文架構 5
1.4 研究成果與貢獻 6
第二章 文獻探討 7
2.1 行為樹 7
2.2 自動地理對位 10
2.3 物件偵測 12
2.4 物件追蹤 13
第三章 自動區域搜索與物件偵測定位模型 15
3.1 基於行為樹設計的行為控制流程 16
3.1.1 航向目的地與確認任務子行為樹 16
3.1.2 執行偵察紀錄任務子行為樹 18
3.1.3 返航起飛點任務子行為樹 19
3.2 影像處理模組 21
3.2.1 物件偵測模型 22
3.2.2 物件追蹤模型 25
3.2.3 自動地理對位模型 32
3.3 電子地圖資料集模型 34
第四章 實驗設計與結果分析 37
4.1 實驗設計 37
4.2 實驗評估指標計算 42
4.2.1 計算預估目標物個數之誤差率與準確率 42
4.2.2 計算預估目標物位置之誤差範圍 44
4.3 實驗結果與分析 46
4.3.1 模型預估目標物個數之誤差率與準確率指標實驗結果 46
4.3.2 模型預估目標物位置之誤差範圍指標實驗結果 54
4.4 多種目標物偵測追蹤之探討 56
4.5 小結 59
第五章 結論與未來展望 60
5.1 研究結論 60
5.2 未來展望 62
參考文獻 63
附錄 69
zh_TW
dc.format.extent 3824977 bytes-
dc.format.mimetype application/pdf-
dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0107753039en_US
dc.subject (關鍵詞) 無人機zh_TW
dc.subject (關鍵詞) 區域偵察zh_TW
dc.subject (關鍵詞) 行為樹zh_TW
dc.subject (關鍵詞) 物件偵測zh_TW
dc.subject (關鍵詞) 物件追蹤zh_TW
dc.subject (關鍵詞) 電子地圖zh_TW
dc.subject (關鍵詞) 地理對位zh_TW
dc.subject (關鍵詞) Droneen_US
dc.subject (關鍵詞) Area reconnaissanceen_US
dc.subject (關鍵詞) Behavior treeen_US
dc.subject (關鍵詞) Object detectionen_US
dc.subject (關鍵詞) Object trackingen_US
dc.subject (關鍵詞) Digital mapen_US
dc.subject (關鍵詞) Georeferencingen_US
dc.title (題名) 微型無人機基於視覺自動區域偵查與物件偵測定位zh_TW
dc.title (題名) Miniature UAV based on visual automatic area search with object detection and geolocalizationen_US
dc.type (資料類型) thesisen_US
dc.relation.reference (參考文獻) [1] R. Austin, Unmanned Aircraft Systems: UAVS Design Development and Deployment, Chichester, U.K.:Wiley, Apr. 2010.
[2] C. Sandbrook, "The social implications of using drones for biodiversity conservation", Ambio, vol. 44, no. Suppl 4, (S4), pp. 636-647, 2015.
[3] Parrot Drones SAS (n.d.). Retrieved November 15,2020,from https://support.parrot.com/global/support/products
[4] C. Bolkcom and E. Bone, "Unmanned aerial vehicles: Background and issues for congress report for congress congressional research service", Proc. Libr. Congr., pp. 13, 2003.
[5] K. Daniel, S. Rohde, and C. Wietfeld, “Leveraging public wireless communication infrastructures for UAV-based sensor networks,” in Proc. IEEE Int. Conf. Technol. Homeland Secur., Nov. 2010, pp. 179–184.
[6] S. Nebikera, A. Annena, M. Scherrerb and D. Oeschc, "A lightweight multispectral sensor for micro U A V -Opportunities for very high resolution airborne remote sensing", Int. Archiv. Photogram. Remote Sens. Spatial Inform. Sci, vol. 37, no. B1, pp. 1193-2000, 2008.
[7] C. Korpela, T. Danko, and P. Oh, "MM-UAV: Mobile manipulating unmanned aerial vehicle," Journal of Intelligent and Robotics Systems, vol. 65, no. 1, pp. 93-101, 2012.
[8] D. Erdos, A. Erdos and S. E. Watkins, "An experimental UAV system for search and rescue challenge", IEEE Aerospace and Electronic Systems Magazine, vol. 28, no. 5, pp. 32-37, May 2013.
[9] UAV CHALLENGE Retrieved November 15,2020, from https://uavchallenge.org/about/
[10] N. Michael, D. Mellinger, Q. Lindsey, and V Kumar, "The grasp multiple micro uav testbed," IEEE Robotics and Automation Magazine, Sept. 2010.
[11] T. Shima and S. Rasmussen, UAV Cooperative Decision and Control: Challenges and Practical Approaches, SIAM, 2009.
[12] M. Colledanchise and P. Ögren,"Behavior trees in robotics and AI: An introduction",CoRR,2017,[online]Available:http://arxiv.org/abs/1709.00084.
[13] P. Rudol and P. Doherty, "Human body detection and geolocalization for UAV search and rescue missions using color and thermal imagery", Proc. IEEE Aerosp. Conf., pp. 1-8, Mar. 2008.
[14] I. Martinez-Alpiste, G. Golcarenarenji, Q. Wang, and J. Calero, " Altitude-Adaptive and Cost-Effective Object Recognition in an Integrated Smartphone and UAV System." In 2020 European Conference on Networks and Communications (EuCNC) (pp. 316-320). IEEE.
[15] P. Ogren, "Increasing Modularity of UAV Control Systems using Computer Game Behavior Trees", AIAA Guidance Navigation and Control Conference, 2012.
[16] K. Y. W. Scheper, S. Tijmons, C. C. de Visser and G. C. H. E. de Croon, "Behaviour trees for evolutionary robotics", Artificial Life, vol. 22, no. 1, pp. 23-48, 2016.
[17] A. Klöckner, "Behavior trees for uav mission management", INFORMATIK 2013: Informatik angepasst an Mensch Organisation und Umwelt, pp. 57-68, 2013.
[18] M. Colledanchise and P. Ögren, "How behavior trees modularize robustness and safety in hybrid systems", Proc. IEEE/RSJ Int. Conf. Intell. Robots Syst., pp. 1482-1488, Jun. 2014.
[19] H. H. Helgesen, F. S. Leira, T. A. Johansen and T. I. Fossen, Detection and Tracking of Floating Objects Using a UAV with Thermal Camera, Cham:Springer International Publishing, pp. 289-316, 2017.
[20] S. Drake, "Converting GPS coordinates [phi Lambda h] to navigation coordinates (ENU)", 2002.
[21] E. M. Hemerly, “Automatic georeferencing of images acquired by
uav’s,” International Journal of Automation and Computing, vol. 11,
no. 4, pp. 347–352, Aug 2014.
[22] H. Xiang and L. Tian, "Method for automatic georeferencing aerial remote sensing (RS) images from an unmanned aerial vehicle (UAV) platform", Biosystems Engineering, vol. 108, pp. 104-113, 2011.
[23] L . Deng and D. Yu, "Deep learning: Methods and applications", Foundations and Trends in Signal Processing, vol. 7, no. 3–4, pp. 197-387, 2014.
[24] Z. Zhao, P. Zheng, S. Xu and X. Wu, "Object detection with deep learning: a review", IEEE Trans. on Neural Net. and Learning Systems, pp. 1-21, January 2019.
[25] X. Liu, Z. Deng and Y. Yang, "Recent progress in semantic image segmentation", Artificial Intelligence Review, pp. 1-18, 2018.
[26] R. Girshick, J. Donahue, T. Darrell and J. Malik, "Rich feature hierarchies for accurate object detection and semantic segmentation", Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp. 580-587, 2014.
[27] R. Girshick, "Fast R-CNN", Proc. IEEE Int. Conf. Comput. Vis., pp. 1440-1448, 2015.
[28] W. Liu, D. Anguelov, D. Erhan, C. Szegedy and S. Reed, "SSD: Single shot multibox detector", 2015.
[29] J. Redmon, S. Divvala, R. Girshick and A. Farhadi, "You only look once: Unified real-time object detection", Proc. IEEE Int. Conf. Computer Vision and Pattern Recognition (CVPR), pp. 779-788, 2016.
[30] J. Redmon and A. Farhadi, "YOLO9000: Better faster stronger", Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp. 6517-6525, 2017.
[31] J. Redmon and A. Farhadi, "YOLOv3: An incremental improvement" in arXiv:1804.02767, 2018, [online] Available: http://arxiv.org/abs/1804.02767.
[32] A. Bochkovskiy, C.-Y. Wang and H.-Y. M. Liao, YOLOv4: Optimal Speed and Accuracy of Object Detection, 2020, [online] Available: http://arxiv.org/abs/2004.10934.
[33] Y. Wu, J. Lim and M. H. Yang, "Online object tracking: A benchmark", Proc. Comput. Vis. Pattern Recognit., pp. 2411-2418, 2013.
[34] D. Comaniciu, V. Ramesh and P. Meer, "Kernel-based object tracking", IEEE Trans. Pattern Anal. Mach. Intell., vol. 25, no. 5, pp. 564-577, May. 2003.
[35] A. Yilmaz, X. Li and M. Shah, "Object contour tracking using level sets", Proc. Asian Conf. Computer Vision, 2004.
[36] X. Farhodov, O. Kwon, K. W. Kang, S. Lee and K. Kwon, "Faster RCNN detection based OpenCV CSRT tracker using drone data", International Conference on Information Science and Communications Technologies (ICISCT), pp. 1-3, 2019.
[37] L. Tan, X. Dong, Y. Ma and C. Yu, "A multiple object tracking algorithm based on YOLO detection", Int. Congress Image Signal Processing BioMedical Engineering Informatics, pp. 1-5, 2018.
[38] T. Vincenty, "Direct and inverse solutions of geodesics on the ellipsoid with application of nested equations", Survey Review, vol. 22, no. 176, pp. 88-93, 1975.
[39] Bebop_autonomy.(n.d.). Retrieved November 15,2020, from https://bebopautonomy.readthedocs.io/en/latest/
[40] E. Olson, "April`Tag: A robust and flexible visual fiducial system", 2011 IEEE International Conference on Robotics and Automation, May 2011.
[41] 內政部國土測繪中心Retrieved November 15,2020, from https://maps.nlsc.gov.tw/
zh_TW
dc.identifier.doi (DOI) 10.6814/NCCU202100035en_US