Monocular visual odometry in urban environments using an omnidirectional camera

We present a system for monocular simultaneous localization and mapping (mono-SLAM) relying solely on video input. Our algorithm makes it possible to precisely estimate the camera trajectory without relying on any motion model. The estimation is completely incremental: at a given time frame, only the current location is estimated while the previous camera positions are never modified. In particular, we do not perform any simultaneous iterative optimization of the camera positions and estimated 3D structure (local bundle adjustment). The key aspect of the system is a fast and simple pose estimation algorithm that uses information not only from the estimated 3D map, but also from the epipolar constraint. We show that the latter leads to a much more stable estimation of the camera trajectory than the conventional approach. We perform high precision camera trajectory estimation in urban scenes with a large amount of clutter. Using an omnidirectional camera placed on a vehicle, we cover one of the longest distance ever reported, up to 2.5 kilometers.

[1]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[2]  Takeo Kanade,et al.  An Iterative Image Registration Technique with an Application to Stereo Vision , 1981, IJCAI.

[3]  Rama Chellappa,et al.  Estimation of Object Motion Parameters from Noisy Images , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Paul A. Beardsley,et al.  3D Model Acquisition from Extended Image Sequences , 1996, ECCV.

[5]  R. Hartley.  Triangulation, Computer Vision and Image Understanding , 1997 .

[6]  Anders Heyden,et al.  Euclidean reconstruction from image sequences with varying and unknown focal length and principal point , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[7]  Philip F. McLauchlan,et al.  A batch/recursive algorithm for 3D scene reconstruction , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[8]  Bernhard P. Wrobel,et al.  Multiple View Geometry in Computer Vision , 2001 .

[9]  David W. Murray,et al.  Simultaneous Localization and Map-Building Using Active Vision , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  Stefano Soatto,et al.  Structure from Motion Causally Integrated Over Time , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Gilman E. S. Toombes,et al.  Preemptive RANSAC for Live Structure and Motion Estimation , 2003 .

[12]  David Nistér,et al.  An efficient solution to the five-point relative pose problem , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[13]  Sebastian Thrun,et al.  Robotic mapping: a survey , 2003 .

[14]  David Nistér,et al.  An efficient solution to the five-point relative pose problem , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Peter I. Corke,et al.  Omnidirectional visual odometry for a planetary rover , 2004, 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE Cat. No.04CH37566).

[16]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[17]  Reinhard Koch,et al.  Visual Modeling with a Hand-Held Camera , 2004, International Journal of Computer Vision.

[18]  Seth J. Teller,et al.  Spectral Solution of Large-Scale Extrinsic Camera Calibration as a Graph Embedding Problem , 2004, ECCV.

[19]  Andrew W. Fitzgibbon,et al.  The Problem of Degeneracy in Structure and Motion Recovery from Uncalibrated Image Sequences , 1999, International Journal of Computer Vision.

[20]  Michael Bosse,et al.  Calibrated, Registered Images of an Extended Urban Area , 2003, International Journal of Computer Vision.

[21]  Richard Hartley,et al.  Visual localization and loopback detection with a high resolution omnidirectional camera , 2005 .

[22]  David Nistér,et al.  Preemptive RANSAC for live structure and motion estimation , 2005, Machine Vision and Applications.

[23]  Tim D. Barfoot,et al.  Online visual motion estimation using FastSLAM with SIFT features , 2005, 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[24]  Volker Graefe,et al.  Dynamic monocular machine vision , 1988, Machine Vision and Applications.

[25]  Tom Drummond,et al.  Fusing points and lines for high performance tracking , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[26]  Robert M. Haralick,et al.  Review and analysis of solutions of the three point perspective pose estimation problem , 1994, International Journal of Computer Vision.

[27]  Paolo Pirjanian,et al.  The vSLAM Algorithm for Robust Localization and Mapping , 2005, Proceedings of the 2005 IEEE International Conference on Robotics and Automation.

[28]  Ryan M. Eustice,et al.  Large-area visually augmented navigation for autonomous underwater vehicles , 2005 .

[29]  Michel Dhome,et al.  Monocular Vision for Mobile Robot Localization and Autonomous Navigation , 2007, International Journal of Computer Vision.

[30]  Robert C. Bolles,et al.  Outdoor Mapping and Navigation Using Stereo Vision , 2006, ISER.

[31]  Alexandru Tupan,et al.  Triangulation , 1997, Comput. Vis. Image Underst..

[32]  Udo Frese,et al.  A Discussion of Simultaneous Localization and Mapping , 2006, Auton. Robots.

[33]  David Nister,et al.  Recent developments on direct relative orientation , 2006 .

[34]  Hugh Durrant-Whyte,et al.  Simultaneous Localisation and Mapping ( SLAM ) : Part I The Essential Algorithms , 2006 .

[35]  James J. Little,et al.  /spl sigma/SLAM: stereo vision SLAM using the Rao-Blackwellised particle filter and a novel mixture proposal distribution , 2006, Proceedings 2006 IEEE International Conference on Robotics and Automation, 2006. ICRA 2006..

[36]  Frank Dellaert,et al.  Visual SLAM with a Multi-Camera Rig , 2006 .

[37]  James R. Bergen,et al.  Visual odometry for ground vehicle applications , 2006, J. Field Robotics.

[38]  Hugh Durrant-Whyte,et al.  Simultaneous localization and mapping (SLAM): part II , 2006 .

[39]  Tom Drummond,et al.  Scalable Monocular SLAM , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[40]  Olivier Stasse,et al.  MonoSLAM: Real-Time Single Camera SLAM , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[41]  Stergios I. Roumeliotis,et al.  Vision-Aided Inertial Navigation for Precise Planetary Landing: Analysis and Experiments , 2007, Robotics: Science and Systems.