Moving Horizon Estimation of Ego-Motion in Monocular Visual Systems
YANG Dong-Fang1,2,SUN Fu-Chun1,WANG Shi-Cheng2
1.State Key Laboratory of Intelligent Technology and Systems,Department of Computer Science and Technology,Tsinghua University,Beijing 100084 2.Department of Automatic Control,The Second Artillery Engineering University,Xi′an 710025
Abstract Estimating ego-motion in monocular visual systems from the input image sequence is a critical problem in computer vision. A moving horizon estimation (MHE) based algorithm is proposed to solve the pose estimation problem in most general application environment including buildings and trees. Firstly,different forms of epipolar constraints are analyzed. The time-space related constraints among the closed loop of image sequence are all involved in the global optimization model. In addition,the MHE is adopted to obtain the tradeoff between computation costs and estimation accuracy. Based on the general epipolar equations,the redundant epipolar constraints and the moving horizon constraints,the corresponding three referred pose estimation algorithms are performed comparatively,and the outdoor experimental results validate the effectiveness of the proposed method.
[1] Vijaykumar P,Kumar A,Bhatia S. Latest Trends,Applications and Innovations in Motion Estimation Research. International Journal of Scientific Engineering Research,2011,2(7): 1-6 [2] Pradalier C,Siegwart R,Hirzinger G. Estimating Ego-Motion in Panoramic Image Sequences with Inertial Measurements. Robotics Research,2011,70(3): 87-101 [3] Dhome M,Richetin M. Determination of the Attitude of 3D Objects from a Single Perspective View. IEEE Trans on Pattern Analysis and Machine Intelligence,1989,11(12): 1265-1278 [4] Horaud R,Conio B,Leboulleux O. An Analytic Solution for the Perspective 4-Point Problem. Computer Vision Graphics and Image Processing,1989,47(1): 33-44 [5] Faugeras O,Maybank S. Motion from Point Matches: Multiplicity of Solutions. The International Journal of Computer Vision,1990,4(3): 225-246 [6] de Menthon D,Davis S. A Exact and Approximate Solutions of the Perspective Three Point Problem. IEEE Trans on Pattern Analysis and Machine Intelligence,1992,14(11): 1100-1105 [7] Klein G,Murray D. Improving the Agility of Keyframe-Based SLAM // Proc of the 10th European Conference on Computer Vision. Marseille,Germany,2008: 802-815 [8] Mouragnon E,Lhuillier M,Dhome M. Generic and Real-Time Structure from Motion Using Local Bundle Adjustment. Image and Vision Computing,2009,27(8): 1178-1193 [9] Davison A,Molton N,Reid I. Mono SLAM: Real-Time Single Camera SLAM. IEEE Trans on Pattern Analysis and Machine Intelligence,2007,29(6): 1052-1067 [10] Eade E,Drummond T. Monocular SLAM as a Graph of Coalesced Observations // Proc of the IEEE International Conference on Computer Vision. Rio de Janeiro,Brazil,2007: 1-8 [11] Longuet H C,Higgins F R S. Multiple Interpretations of a Pair of Images of a Surface. Proc of the Royal Society of London Series A-Mathematical Physical and Engineering Sciences,1988,418(1854): 1-15 [12] Fraundorfer F,Scaramuzza D,Pollefeys M. A Constricted Bundle Adjustment Parame-Terization for Relative Scale Estimation in Visual Odometry // Proc of the IEEE International Conference on Robotics and Automation,Anchorage,USA,2010: 1899-1904 [13] Strelow D,Singh S. Motion Estimation from Image and Inertial Measurements. The International Journal of Robotics Research,2004,23(12): 1157-1195 [14] Taylor C,Veth M,Raquet J. Comparison of Two Image and Inertial Sensor Fusion Techniques for Navigation in Unmapped Environments. IEEE Trans on Aerospace and Electronic Systems,2011,47(2): 946-958 [15] Garcia R,Sotelo M,Parra I. 3D Visual Odometry for GPS Navigation Assistance//Proc of the IEEE Intelligent Vehicles Symposium. Istanbul,Turkey,2007: 444-449 [16] Lambert A,Furgale P,Barfoot T. Visual Odometry Aided by a Sun Sensor and Inclinometer // Proc of the IEEE Aerospace Conference,Big Sky,USA,2011: 1-14 [17] Soatto S,Frezza R,Perona P. Motion Estimation via Dynamic Vision. IEEE Trans on Automatic Control,1996,41(3): 393-413 [18] Civera J,Grasa O G,Davison A J,et al. 1-Point RANSAC for Extended Kalman Filtering: Application to Real-Time Structure from Motion and Visual Odometry. Journal of Field Robotics,2010,27(5): 609-631 [19] Joshi N,Kang S,Lawrence C. Image Deblurring Using Inertial Measurement Sensors. ACM Trans on Graphics,2010,29(4): 302-309 [20] Chroust S,Vincze M. Fusion of Vision and Inertial Data for Motion and Structure Estimation. Journal of Robotic Systems,2004,21(2): 73-83 [21] Wu A,Johnson E,Proctor A. Vision-Aided Inertial Navigation for Flight Control // Proc of the AIAA Guidance,Navigation,and Control Conference and Exhibit. San Francisco,USA,2005: 1-13 [22] Mondragon I,Olivares M,Campoy P. Unmanned Aerial Vehicles UAVs Attitude,Height,Motion Estimation and Control Using Visual Systems. Autonomous Robots,2010,29(1): 17-34 [23] Rao C,Rawlings J,Mayne D. Constrained State Estimation for Nonlinear Discrete-Time Systems: Stability and Moving Horizon Approximations. IEEE Trans on Automatic Control,2003,48(2): 246-258 [24] Hartley R,Zisserman A. Multiple View Geometry in Computer Vision. Cambridge,UK: Cambridge University Press,2000: 226-230 [25] Wu Fuchao. Mathematical Methods in Computer Vision. Beijing,China: Science Press,2008: 213-218(in Chinese) (吴福朝.计算机视觉中的数学方法.北京:科学出版社,2008: 213-218) [26] McInroy J,Qi Z. A Novel Pose Estimation Algorithm Based on Points to Regions Correspondence. International Journal of Math Imaging,2008,30(3): 195-207 [27] Ma Songde,Zhang Zhengyou. Computer Vision-Computing Theory and Algorithm Basis. Beijing,China: Science Press,1998: 152-156 (in Chinese) (马颂德,张正友.计算机视觉——计算理论与算法基础.北京:科学出版社,1998: 152-156) [28] Strasdat H,Montiel J,Davison A. Real-Time Monocular SLAM: Why Filter // Proc of the IEEE International Conference on Robotics and Automation. Anchorage,USA,2010: 2657-2664 [29] Scaramuzza D,Fraundorfer F,Siegwart R. Real-Time Monocular Visual Odometry for On-Road Vehicles with 1-Point RANSAC // Proc of the IEEE International Conference on Robotics and Automation. Kobe,Japan,2009: 488-494 [30] Pollefeys M,Koch R,van Gool L. Self-Calibration and Metric Reconstruction in Spite of Varying and Unknown Intrinsic Camera Parameters. International Journal of Computer Vision,1999,32(1),7-25 [31] Pollefeys M. Self Calibration and Metric 3D Reconstruction from Uncalibrated Image Sequences. Ph.D Dissertation. Katholieke,Le Royaume de Belgique : Katholieke University,1999
2013, Vol. 26 
