Closing the Loop in Appearance-Guided Structure-from-Motion for Omnidirectional Cameras

In this paper, we present a method that allows us to recover a 400 meter trajectory purely from monocular omnidirectional images very accurately. The method uses a novel combination of appearance-guided structure from motion and loop closing. The appearance-guided monocular structure-from-motion scheme is used for initial motion estimation. Appearance information is used to correct the rotation estimates computed from feature points only. A place recognition scheme is employed for loop detection, which works with a visual word based approach. Loop closing is done by bundle adjustment minimizing the reprojection error of feature matches. The proposed method is successfully demonstrated on videos from an automotive platform. The experiments show that the use of appearance information leads to superior motion estimates compared to a purely feature based approach. And we demonstrate a working loop closing method which eliminates the residual drift errors of the motion estimation. Note that the recovered trajectory is one of the longest ones ever reported with a single omnidirectional camera.

[1]  M. Hebert,et al.  Omni-directional structure from motion , 2000, Proceedings IEEE Workshop on Omnidirectional Vision (Cat. No.PR00704).

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

[3]  Andrew W. Fitzgibbon,et al.  Bundle Adjustment - A Modern Synthesis , 1999, Workshop on Vision Algorithms.

[4]  Tomás Pajdla,et al.  Structure from motion with wide circular field of view cameras , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Maxime Lhuillier,et al.  Automatic Structure and Motion using a Catadioptric Camera , 2005 .

[6]  Frank Dellaert,et al.  Out-of-Core Bundle Adjustment for Large-Scale 3D Reconstruction , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[7]  Michael Bosse,et al.  Simultaneous Localization and Map Building in Large-Scale Cyclic Environments Using the Atlas Framework , 2004, Int. J. Robotics Res..

[8]  Bill Triggs,et al.  Autocalibration from Planar Scenes , 1998, ECCV.

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

[10]  Andrew Zisserman,et al.  Video Google: a text retrieval approach to object matching in videos , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[11]  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).

[12]  Frédéric Labrosse,et al.  The visual compass: Performance and limitations of an appearance‐based method , 2006, J. Field Robotics.

[13]  Roland Siegwart,et al.  Monocular Omnidirectional Visual Odometry for Outdoor Ground Vehicles , 2008, ICVS.

[14]  Paul Newman,et al.  Detecting Loop Closure with Scene Sequences , 2007, International Journal of Computer Vision.

[15]  David Nistér,et al.  Scalable Recognition with a Vocabulary Tree , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[16]  Roland Siegwart,et al.  Appearance-Guided Monocular Omnidirectional Visual Odometry for Outdoor Ground Vehicles , 2008, IEEE Transactions on Robotics.

[17]  Václav Hlaváč,et al.  MOTION ESTIMATION USING CENTRAL PANORAMIC CAMERAS , 1998 .

[18]  Michael Bosse,et al.  Vanishing points and 3D lines from omnidirectional video , 2002, Proceedings. International Conference on Image Processing.

[19]  Kostas Daniilidis,et al.  Structure and motion from uncalibrated catadioptric views , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[20]  Paul Newman,et al.  Probabilistic Appearance Based Navigation and Loop Closing , 2007, Proceedings 2007 IEEE International Conference on Robotics and Automation.

[21]  Tomás Pajdla,et al.  Autocalibration & 3D reconstruction with non-central catadioptric cameras , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[22]  Michael Bosse,et al.  ATLAS: a framework for large scale automated mapping and localization , 2004 .