Vanishing points and three-dimensional lines from omni-directional video

This paper describes a system for structure from motion using vanishing points and three-dimensional lines extracted from omni-directional video sequences. To track lines, we use a novel dynamic programming approach to improve ambiguity resolution, and we use delayed states to aid in the initialization of landmarks. By reobserving vanishing points we get direct measurements of the robot’s three-dimensional attitude that are independent of its position. Using vanishing points simplifies the representation since parallel lines share the same direction states. We show the performance of the system in various indoor and outdoor environments and include comparisons with independent two-dimensional reference maps for each experiment.

[1]  Hugh F. Durrant-Whyte,et al.  An Experimental and Theoretical Investigation into Simultaneous Localisation and Map Building , 1999, ISER.

[2]  J. M. M. Montiel,et al.  The SPmap: a probabilistic framework for simultaneous localization and map building , 1999, IEEE Trans. Robotics Autom..

[3]  R. K. Shyamasundar,et al.  Introduction to algorithms , 1996 .

[4]  Peter Cheeseman,et al.  A stochastic map for uncertain spatial relationships , 1988 .

[5]  Camillo J. Taylor,et al.  VideoPlus: A Method for Capturing the Structure and Appearance of Immersive Environments , 2000, IEEE Trans. Vis. Comput. Graph..

[6]  Matthew E. Antone.  Robust camera pose recovery using stochastic geometry , 2001 .

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

[8]  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).

[9]  Stefano Soatto,et al.  MFM": 3-D motion from 2-D motion causally integrated over time , 2000, ECCV 2000.

[10]  S. M. Steve.  SUSAN - a new approach to low level image processing , 1997 .

[11]  Michael Bosse,et al.  An Atlas framework for scalable mapping , 2003, 2003 IEEE International Conference on Robotics and Automation (Cat. No.03CH37422).

[12]  Michael Bosse,et al.  Mapping Partially Observable Features from Multiple Uncertain Vantage Points , 2002, Int. J. Robotics Res..

[13]  Andrew J. Davison,et al.  Mobile Robot Navigation Using Active Vision , 1998 .

[14]  Raja Chatila,et al.  Stochastic multisensory data fusion for mobile robot location and environment modeling , 1989 .

[15]  Michael Bosse,et al.  Calibrated, Registered Images of an Extended Urban Area , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[16]  Eduardo Mario Nebot,et al.  Optimization of the simultaneous localization and map-building algorithm for real-time implementation , 2001, IEEE Trans. Robotics Autom..

[17]  David J. Kriegman,et al.  Structure and Motion from Line Segments in Multiple Images , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[18]  Sebastian Thrun,et al.  An Online Mapping Algorithm for Teams of Mobile Robots , 2000 .

[19]  Seth J. Teller,et al.  Automatic recovery of relative camera rotations for urban scenes , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[20]  Raja Chatila,et al.  An Experimental System for Incremental Environment Modelling by an Autonomous Mobile Robot , 1989, ISER.

[21]  O. Faugeras,et al.  The Geometry of Multiple Images , 1999 .

[22]  Y. Bar-Shalom.  Tracking and data association , 1988 .