簡易檢索 / 詳目顯示

研究生: 何佳瑋
Raphalen, Léon
論文名稱: 服務型機器人對於人的辨認,追蹤及導引功能的開發與實做
Human Detection and Tracking with Visual Odometry and Automatic Vehicle Control
指導教授: 譚俊豪
Tarn, Jiun-Haur
學位類別: 碩士
Master
系所名稱: 工學院 - 航空太空工程學系
Department of Aeronautics & Astronautics
論文出版年: 2018
畢業學年度: 106
語文別: 英文
論文頁數: 56
外文關鍵詞: Computer Vision, Control Theory, Human Detection, Human Tracking, Loop Closure, Mechatronics, MPC, ROS, SIFT, SURF, SLAM, Track Following, Visual Odometry
相關次數: 點閱:134下載:3
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
  • This Master's Thesis presents a robot designed for guiding and tracking people from one point to another using only a Kinect as sensor.

    Using Speeded-Up Robust Features feature extraction, keypoints are retrieved from the images and stored using the Bag-of-Word model.
    A simultaneous localization and mapping program then performs loop closure to create maps in which the vehicle can localize itself.

    Based on a reference path and the vehicle dynamic model, a Model Predictive Control algorithm is used to produce steering angle and velocity inputs designed to optimize a track following trajectory.
    The cost function takes into consideration input variation to provide a smoother trajectory for the user to follow.

    Finally, depth clustering and bin summing performed on the point clouds to extract regions of interest ready for upper-body detection.
    The person detections are then transmitted to a multi-hypothesis tracker that determines overlap-free people tracks over time.
    The vehicle control inputs are then transmitted to the vehicle controller based on the detection and tracking of the user to be guided.

    This Master's Thesis thus provides a real-time operating framework able to automatically guide its user along a smooth track while monitoring his presence.

    Declaration of Authorship iii Abstract iv Acknowledgements v 1 Introduction 1 1.1 Project Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 1.2 Case Scenario . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2 1.3 Related Work . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2 2 Hardware Presentation 4 2.1 Vehicle Structure . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4 2.2 Electronics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5 3 Software Architecture 8 3.1 ROS . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8 3.1.1 Robotics Middleware . . . . . . . . . . . . . . . . . . . . . . . . . 8 3.1.2 Intracommunication System . . . . . . . . . . . . . . . . . . . . 8 3.2 Softwares Overview . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9 3.2.1 OpenNI - Sensor Interface . . . . . . . . . . . . . . . . . . . . . . 10 3.2.2 RTAB-Map - Visual Odometry and On-Line Loop Closure . . . 10 3.2.3 MPC - Automatic Vehicle Control and Track Following . . . . . 10 3.2.4 Spencer - Human Detection and Tracking . . . . . . . . . . . . . 10 3.2.5 Loco - Actuator Interface . . . . . . . . . . . . 11 4 RTAB-Map: Visual Odometry and On-line Mapping 12 4.1 Feature Representation . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12 4.1.1 Scale-Space Extrema Detection . . . . . . . . . . . . . . . . . . . 12 4.1.2 Keypoint Localization . . . . . . . . . . . . . . . . . . . . . . . . 14 4.1.3 Orientation Assignment . . . . . . . . . . . . . . . . . . . . . . . 15 4.1.4 Local Image Description . . . . . . . . . . . . . . . . . . . . . . . 16 4.2 Bag-of-Word Model Map Initialization . . . . . . . . . . . . . . . . . . . 17 4.2.1 Codebook Generation . . . . . . . . . . . . . . . . . . . . . . . . 18 4.2.2 Keypoint Matching . . . . . . . . . . . . . . . . . . . . . . . . . . 18 4.2.3 Camera Calibration . . . . . . . . . . . . . . . . . . . . . . . . . . 20 4.2.4 Map Initialization . . . . . . . . . . . . . . . . . . . . . . . . . . . 20 4.3 Appearance-Based Loop Closure . . . . . . . . . . . . . . . . . . . . . . 20 4.3.1 Memory Management . . . . . . . . . . . . . . . . . . . . . . . . 21 4.3.2 Location Creation . . . . . . . . . . . . . . . . . . . . . . . . . . . 23 4.3.3 Weight Update . . . . . . . . . . . . . . . . . . . . . . . . . . . . 24 4.3.4 Bayesian Filter Update . . . . . . . . . . . . . . . . . . . . . . . . 24 4.3.5 Loop Closure Hypothesis Selection . . . . . . . . . . . . . . . . 25 4.3.6 Retrieval Process . . . . . . . . . . . . . . . . . . . . . . . . . . . 25 4.3.7 Transfer Process . . . . . . . . . . . . . . . . . . . . . . . . . . . . 26 4.3.8 Map Output . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 27 4.4 Project Integration . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 28 4.4.1 Image Retrieval . . . . . . . . . . . . . . . . . . . . . . . . . . . . 28 4.4.2 Frames Publication . . . . . . . . . . . . . . . . . . . . . . . . . . 28 5 MPC: Automatic Track Following 30 5.1 Optimization Problem Formulation . . . . . . . . . . . . . . . . . . . . . 30 5.1.1 Control Algorithm Principle . . . . . . . . . . . . . . . . . . . . 30 5.1.2 Optimization Problem Formulation . . . . . . . . . . . . . . . . 31 5.1.3 Parameters and constraints definition . . . . . . . . . . . . . . . 32 5.2 Simulation Representation . . . . . . . . . . . . . . . . . . . . . . . . . . 33
 5.2.1 Track representation . . . . . . . . . . . . . . . . . . . . . . . . . 33
 5.2.2 Vehicle Model . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 34
 5.2.3 Software Support . . . . . . . . . . . . . . . . . . . . . . . . . . . 35 5.3 Track Following . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 36 
 5.3.1 Initial Cost Function . . . . . . . . . . . . . . . . . . . . . . . . . 36 5.3.2 Variation-Limiting Tuning . . . . . . . . . . . . . . . . . . . . . . 37
 5.3.3 Track Following Simulation . . . . . . . . . . . . . . . . . . . . . 38 5.4 Project Integration . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 39 
 5.4.1 Odometry Retrieval . . . . . . . . . . . . . . . . . . . . . . . . . 39 5.4.2 Control Inputs Publication . . . . . . . . . . . . . . . . . . . . . 40 
 6 Spencer: Human Detection and Tracking 42 6.1 Point Clustering . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 42 
 6.1.1 Ground Plane Estimation . . . . . . . . . . . . . . . . . . . . . . 42 
 6.1.2 Structure Labeling . . . . . . . . . . . . . . . . . . . . . . . . . . 43 6.1.3 Regions of Interest Extraction . . . . . . . . . . . . . . . . . . . . 43 
 6.1.4 Quick Shift Segmentation . . . . . . . . . . . . . . . . . . . . . . 45 6.2 Upper-Body Detection . . . . . . . . . . . . . . . . . . . . . . . . . . . . 47 
 6.2.1 RoI Cleaning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 47 6.2.2 Local Contour Maxima . . . . . . . . . . . . . . . . . . . . . . . . 48 
 6.2.3 Template Sliding . . . . . . . . . . . . . . . . . . . . . . . . . . . 49
 6.2.4 Detection Refining . . . . . . . . . . . . . . . . . . . . . . . . . . 49 6.3 Multi-Hypothesis Tracking . . . . . . . . . . . . . . . . . . . . . . . . . . 51
 6.3.1 Hypothesis Detection . . . . . . . . . . . . . . . . . . . . . . . . 51 6.3.2 Bi-Directional Trajectory Estimation . . . . . . . . . . . . . . . . 52 6.3.3 Hypothesis Selection . . . . . . . . . . . . . . . . . . . . . . . . . 53 6.4 Project Integration . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 54 6.4.1 Image, Mapand Navigation Retrieval . . . . . . . . . . . . . . . 54 6.4.2 Navigation Forwarding . . . . . . . . . . . . . . . . . . . . . . . 55 7 Conclusion 56 Bibliography 57

    A. Angeli et al. “Fast and Incremental Method for Loop Closure Detection using Bags of Visual Words”. In: IEEE Transactions on Robotics 24.5 (2008).
    M. Bansal et al. “A Real-Time Pedestrian Detection System Based on Structure and Appearance Classification”. In: IEEE International Conference on Robotics and Automation. Anchorage, USA, 2010.
    H. Bay, T. Tuytelaars, and L. Van Gool. “SURF: Speeded-Up Robust Features”. In: Computer Vision and Image Understanding 110.3 (2006).
    J. S. Beis and Davig G. Lowe. “Shape Indexing using Approximate Nearest-Neighbor Search in High-Dimensional Spaces”. In: Conference on Computer Vision and Pattern Recognition. San Juan, PRI, 1997.
    G. Bradski. “The OpenCV Library”. In: Dr. Dobb’s Journal of Software Tools (2000).
    A. Ess et al. “Improved Multi-Person Tracking with Active Occlusion Handling”. In: IEEE ICRA Workshop on People Detection and Tracking. Kobe, JPN, 2009.
    M. A. Fischler and R. C. Bolles. “Random Sample Consensus: a Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography”. In: Communications of the ACM 24.6 (1981).
    E. P. Fotiadis, M. Garzon, and A. Barrientos. “Human Detection from a Mobile Robot Using Fusion of Laser and Vision Information”. In: Sensors (Basel) 13.9 (2013).
    C. Harris and M. Stephens. “A Combined Corner and Edge Detection”. In: Fourth Alley Vision Conference. Manchester, GBR, 1988.
    G. T. He. “Optimization-Based Path Planning, Trajectory Tracking and Obstacle Avoidance of 1:10 Scale Race Car”. MA thesis. Tainan, TWN: National Cheng Kung University, 2018.
    C. K. Ho. “Autonomous Trajectory Tracking and Obstacle Avoidance via Pure Pursuit and Optimization”. MA thesis. Tainan, TWN: National Cheng Kung University, 2017.
    Y. D. Hsieh. “Autonomous Drift Modeling, Planning and Control”. MA thesis. Tainan, TWN: National Cheng Kung University, 2018.
    O. H. Jafari, D. Mitzel, and B. Leibe. “Real-Time RGB-D Based People Detection and Tracking for Mobile Robots and Head-Worn Cameras”. In: IEEE International Conference on Robotics and Automation. Hong Kong, HKG, 2014.
    H. Kim, W. Chung, and Y. Yoo. “Detection and Tracking of Human Legs for a Mobile Service Robot”. In: IEEE International Conference on Advanced Intelligent Mechatronics. Montreal, CAN, 2014.
    M. Labbé and F. Michaud. “Appearance-Based Loop Closure Detection for Online Large-Scale and Long-Term Operation”. In: IEEE Transactions on Robotics 29.3 (2013).
    M. Labbé and F. Michaud. “Online Global Loop Closure Detection for Large-Scale Multi-Session Graph-Based SLAM”. In: IEEE/RSJ International Conference on Intelligent Robots and Systems. Chicago, USA, 2014.
    B. Leibe et al. “Coupled Object Detection and Tracking from Static Cameras and Moving Vehicles”. In: IEEE Transactions on Pattern Analysis and Machine Intelligence 20.10 (2008).
    J. J. J. Lien. “Scale Invariant Feature Transform”. NCKU Computer Science and Information Engineering Course. 2018.
    Team LoCo. Evasive Maneuvers and Drifting for Autonomous Vehicles. Tech. rep. CMU, 2017.
    D. G. Lowe. “Distinctive Image Features from Scale-Invariant Keypoints”. In: International Journal of Computer Vision 60.2 (2004).
    D. G. Lowe and M. Brown. “Invariant Features from Interest Point Groups (Cardiff, Wales)”. In: British Machine Vision Conference. Cardiff, GBR, 2002.
    D. Mistry. “Comparison of Feature Detection and Matching Approaches: SIFT and SURF”. In: Global Research and Development Journal for Engineering 2.4 (2017).
    D. Mitzel and B. Leibe. “Close-Range Human Detection for Head-Mounted Cameras”. In: British Machine Vision Conference. 2012.
    M. Muja and D. G. Lowe. “Fast Approximate Nearest Neighbors with Automatic Algorithm Configuration”. In: International Conference on Computer Vision Theory and Application. Lisboa, PRT, 2009.
    P. M. Panchal, S. R. Panchal, and S. K. Shah. “A Comparison of SIFT and SURF”. In: International Journal of Innovative Research in Computer and Communication Engineering 1.2 (2013).
    J. Sivic and A. Zisserman. “Video Google: A Text Retrieval Approach to Object Matching in Videos”. In: 9th International Conference on Computer Vision. Nice, FRA, 2003.
    Consortium Spencer. People Detection and Tracking from Depth and Vision Data. Tech. rep. RWTH, 2014.
    P. Spengler and C. Gammeter. “Modeling of 1:43 Scale Race Cars”. MA thesis. Zurich, CHE: ETHZ, 2010.
    A. Vedaldi and S. Soatto. “Quick Shift and Kernel Methods for Mode Seeking”. In: European Conference on Computer Vision. Vol. 4. Marseille, FRA, 2008.
    A. Wächter and L. T. Biegler. “On the Implementation of a Primal-Dual Interior Point Filter Line Search Algorithm for Large-Scale Nonlinear Programming”. PhD thesis. Pittsburgh, USA: CMU, 2006.
    L. Wunderli. “MPC-Based Trajectory Tracking for 1:43 Scale Race Cars”. MA thesis. Zurich, CHE: ETHZ, 2011.

    下載圖示 校內:立即公開
    校外:立即公開
    QR CODE