簡易檢索 / 詳目顯示

回結果列表
研究生： 李承家
Cheng-Chia Lee
論文名稱： 高速影像伺服應用於無人機追蹤控制
High Speed Visual Servoing for UAV Tracking Control
指導教授： 金台齡
Tai-Lin Chin
口試委員: 蔡明忠
Ming-Jong Tsai
鄧惟中
Wei-Chung Teng
花凱龍
Kai-Lung Hua
學位類別： 碩士
Master
系所名稱： 電資學院 - 資訊工程系
Department of Computer Science and Information Engineering
論文出版年： 2016
畢業學年度： 104
語文別： 英文
論文頁數： 80
中文關鍵詞： 視覺物件追蹤 、無人機 、影像伺服控制 、即時
外文關鍵詞： Visual object tracking, UAV, Visual servoing, real-time
相關次數： 點閱：217  下載：2 
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

    • 在機器視覺的研究領域裡，視覺物件追蹤是一個很重要的研究課題且有許多相關應用，在機器人的感知方面也是一項重要的任務。本研究的目的是要建立一套基於影像伺服的無人機即時控制系統，可以延伸應用於自動化監控或是人類跟隨拍攝等。儘管現在的電腦已經發展快速，攜帶式裝置仍然不能負荷現有視覺物件追蹤方法的計算量。
    在本論文中提出一個基於特徵點的視覺物件追蹤方法為FAVT，可追蹤任意未知的物件，此演算法流程是受到Nebebay的方法CMT所啟發。對於FAVT，為了減少計算量，特徵點的追蹤是採用光流法而非整張影像的特徵點匹配，當光流法追蹤產生失敗時，本研究提出了一個新方法去匹配特定的候選特徵點，能夠提高配對成功率並減少配對計算量。此外，本篇論文描述了一個基於視覺的追蹤控制應用於四旋翼無人機跟隨移動的物件。
    在實驗結果的部分，本研究利用七十七部包含各式物件影片的數據集去評估FAVT演算法，結果顯示FAVT方法的準確度優於現行的四種視覺物件追蹤演算法，且計算速度是CMT的五倍。最後，透過模擬器驗證四旋翼無人機的影像伺服控制系統，並且實際測試飛行於戶外。

    Visual object tracking is one of the significant studies in many applications of computer vision, and also an important task for robotic perception. Our objective is to build an image-based visual servo control system for UAV which can be applied to automated surveillance, people following and filming etc. In spite of the evolving of computer, portable devices still cannot afford the computation of existing approach.
    In this thesis we propose a keypoint-based method for unknown object tracking called FAVT which is inspired by Nebehay’s approach. For FAVT, we use only optical flow to track the keypoints instead of matching whole candidate points in order to reduce the computation, when the keypoint being failed to track, the novel fashion is proposed to match the specific candidate point. Moreover, we describe a vision-based method to control the quadrotor to track a moving object.
    We demonstrate the evaluation result experimentally on a diverse dataset of 77 sequences for FAVT. The result shows that FAVT outperforms the state-of-the-art and the computing speed is faster than CMT by five times. The visual servo control system for quadrotor is validated by simulation and implemented in practical experiments.

    Abstract in Chinese I Abstract II Acknowledgment III Contents IV List of Figures VII List of Tables IX 1.Introduction 1 1.1Motivation 1 1.2Research purposes 1 2.Related work 2 2.1Visual tracking 2 2.2UAV control 4 3.Method 5 3.1Problem definition 5 3.2FAVT 5 3.2.1Initialization 6 3.2.2Tracking 10 3.2.3Detecting and matching 15 3.2.4Estimating scale and rotation 17 3.2.5Voting 19 3.2.6Inverse detecting and matching 22 3.3Control system 24 3.3.1Dynamics 24 3.3.2Vision-based system 27 3.3.3Image-based visual servoing 28 4.Experiment and results 30 4.1Experiment for FAVT 30 4.1.1Setup 30 4.1.2Parameter settings 31 4.1.3Evaluation methodology 31 4.1.4Benchmark 34 4.1.5Overall performance 35 4.1.6Comparing with CMT 36 4.1.7Attribute-based performance 38 4.1.8Speed performance 43 4.2UAV tracking control system 46 4.2.1Hardware description 46 4.2.2Software description 48 4.2.1Simulation 49 4.2.2Practical experiments 56 5.Conclusion 57 Reference 58 Appendix 1:The sequences of tracking dataset 64 Appendix 2:The distribution histogram of linear errors with fitting curve (target with constant speed) 65 Appendix 3:The distribution histogram of angular errors with fitting curve (target with constant speed) 66 Appendix 4:The distribution histogram of linear errors with fitting curve (target with random speed) 67 Appendix 5:The distribution histogram of angular errors with fitting curve (target with random speed) 68

    [1]E. Maggio and A. Cavallaro, "What is video tracking?," in Video Tracking, ed: John Wiley & Sons, Ltd, 2010, pp. 1-14.
    [2]A. Yilmaz, O. Javed, and M. Shah, "Object tracking: A survey," ACM Comput. Surv., vol. 38, p. 13, 2006.
    [3]G. Nebehay and R. Pflugfelder, "Clustering of static-adaptive correspondences for deformable object tracking," in 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 2784-2791.
    [4]D. G. Lowe, "Distinctive Image Features from Scale-Invariant Keypoints," International Journal of Computer Vision, vol. 60, pp. 91-110, 2004// 2004.
    [5]H. Bay, A. Ess, T. Tuytelaars, and L. Van Gool, "Speeded-Up Robust Features (SURF)," Computer Vision and Image Understanding, vol. 110, pp. 346-359, 6// 2008.
    [6]E. Rosten, R. Porter, and T. Drummond, "Faster and Better: A Machine Learning Approach to Corner Detection," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 32, pp. 105-119, 2010.
    [7]M. Calonder, V. Lepetit, C. Strecha, and P. Fua, "BRIEF: Binary Robust Independent Elementary Features," in Computer Vision – ECCV 2010: 11th European Conference on Computer Vision, Heraklion, Crete, Greece, September 5-11, 2010, Proceedings, Part IV, K. Daniilidis, P. Maragos, and N. Paragios, Eds., ed Berlin, Heidelberg: Springer Berlin Heidelberg, 2010, pp. 778-792.
    [8]S. Leutenegger, M. Chli, and R. Y. Siegwart, "BRISK: Binary Robust invariant scalable keypoints," in 2011 International Conference on Computer Vision, 2011, pp. 2548-2555.
    [9]A. Alahi, R. Ortiz, and P. Vandergheynst, "FREAK: Fast Retina Keypoint," in Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on, 2012, pp. 510-517.
    [10]M. Kashif, T. M. Deserno, D. Haak, and S. Jonas, "Feature description with SIFT, SURF, BRIEF, BRISK, or FREAK? A general question answered for bone age assessment," Computers in Biology and Medicine, vol. 68, pp. 67-75, 1/1/ 2016.
    [11]M. A. Fischler and R. C. Bolles, "Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography," Commun. ACM, vol. 24, pp. 381-395, 1981.
    [12]P. V. C. Hough, "METHOD AND MEANS FOR RECOGNIZING COMPLEX PATTERNS," US 3069654 United StatesFri Dec 11 15:05:56 EST 2009DTIE; NSA-17-008572English, 1962.
    [13]S. Bouabdallah, P. Murrieri, and R. Siegwart, "Design and control of an indoor micro quadrotor," in Robotics and Automation, 2004. Proceedings. ICRA '04. 2004 IEEE International Conference on, 2004, pp. 4393-4398 Vol.5.
    [14]P. Pounds, R. Mahony, P. Hynes, and J. Roberts, Design of a Four-Rotor Aerial Robot, 2002.
    [15]B. Erginer and E. Altug, "Modeling and PD Control of a Quadrotor VTOL Vehicle," in 2007 IEEE Intelligent Vehicles Symposium, 2007, pp. 894-899.
    [16]S. Bouabdallah, A. Noth, and R. Siegwart, "PID vs LQ control techniques applied to an indoor micro quadrotor," in Intelligent Robots and Systems, 2004. (IROS 2004). Proceedings. 2004 IEEE/RSJ International Conference on, 2004, pp. 2451-2456 vol.3.
    [17]H. Gabriel, H. Haomiao, W. Steven, and T. Claire, "Quadrotor Helicopter Flight Dynamics and Control: Theory and Experiment," in AIAA Guidance, Navigation and Control Conference and Exhibit, ed: American Institute of Aeronautics and Astronautics, 2007.
    [18]F. Chaumette and S. Hutchinson, "Visual servo control. I. Basic approaches," IEEE Robotics & Automation Magazine, vol. 13, pp. 82-90, 2006.
    [19]B. Espiau, F. Chaumette, and P. Rives, "A new approach to visual servoing in robotics," IEEE Transactions on Robotics and Automation, vol. 8, pp. 313-326, 1992.
    [20]S. Hutchinson, G. D. Hager, and P. I. Corke, "A tutorial on visual servo control," IEEE Transactions on Robotics and Automation, vol. 12, pp. 651-670, 1996.
    [21]D. Lee, T. Ryan, and H. J. Kim, "Autonomous landing of a VTOL UAV on a moving platform using image-based visual servoing," in Robotics and Automation (ICRA), 2012 IEEE International Conference on, 2012, pp. 971-976.
    [22]E. Rosten and T. Drummond, "Fusing points and lines for high performance tracking," in Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1, 2005, pp. 1508-1515 Vol. 2.
    [23]E. Rosten, G. Reitmayr, and T. Drummond, "Real-Time Video Annotations for Augmented Reality," in Advances in Visual Computing: First International Symposium, ISVC 2005, Lake Tahoe, NV, USA, December 5-7, 2005. Proceedings, G. Bebis, R. Boyle, D. Koracin, and B. Parvin, Eds., ed Berlin, Heidelberg: Springer Berlin Heidelberg, 2005, pp. 294-302.
    [24]E. Tola, V. Lepetit, and P. Fua, "DAISY: An Efficient Dense Descriptor Applied to Wide-Baseline Stereo," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 32, pp. 815-830, 2010.
    [25]B. D. Lucas and T. Kanade, "An iterative image registration technique with an application to stereo vision," presented at the Proceedings of the 7th international joint conference on Artificial intelligence - Volume 2, Vancouver, BC, Canada, 1981.
    [26]Z. Kalal, K. Mikolajczyk, and J. Matas, "Forward-Backward Error: Automatic Detection of Tracking Failures," in Pattern Recognition (ICPR), 2010 20th International Conference on, 2010, pp. 2756-2759.
    [27]J. Y. Bouguet, "Pyramidal implementation of the affine lucas kanade feature tracker description of the algorithm," Intel Corporation 5, 2001.
    [28]D. W. Eggert, A. Lorusso, and R. B. Fisher, "Estimating 3-D rigid body transformations: a comparison of four major algorithms," Machine Vision and Applications, vol. 9, pp. 272-290, 1997.
    [29]S. C. Johnson, "Hierarchical clustering schemes," Psychometrika, vol. 32, pp. 241-254, 1967.
    [30]X. Rui and D. Wunsch, "Survey of clustering algorithms," IEEE Transactions on Neural Networks, vol. 16, pp. 645-678, 2005.
    [31]Open Computer Vision. Available: http://opencv.org/
    [32]Y. Wu, J. Lim, and M. H. Yang, "Online Object Tracking: A Benchmark," in Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on, 2013, pp. 2411-2418.
    [33]T. Vojir. Trakcing dataset. Available: http://cmp.felk.cvut.cz/~vojirtom/dataset/
    [34]G. Nebehay and R. Pflugfelder, "Consensus-based matching and tracking of keypoints for object tracking," in IEEE Winter Conference on Applications of Computer Vision, 2014, pp. 862-869.
    [35]G. Nebehay, B. Micusik, C. Picus, and R. Pflugfelder, "Evaluation of an online learning approach for robust object tracking," AIT Austrian Institute of Technologymar 2011.
    [36]S. Hare, A. Saffari, and P. H. S. Torr, "Struck: Structured output tracking with kernels," in 2011 International Conference on Computer Vision, 2011, pp. 263-270.
    [37]Z. Kalal, K. Mikolajczyk, and J. Matas, "Tracking-Learning-Detection," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 34, pp. 1409-1422, 2012.
    [38]K. Zhang, L. Zhang, and M.-H. Yang, "Real-time compressive tracking," presented at the Proceedings of the 12th European conference on Computer Vision - Volume Part III, Florence, Italy, 2012.
    [39]Github. Available: https://github.com/
    [40]3D Robotics. Available: https://3dr.com/
    [41]Robot Operating System. Available: http://www.ros.org/
    [42]GAZEBO. Available: http://gazebosim.org/

    QR CODE