Robot navigation using panoramic tracking

A vision-based navigation system is presented for determining a mobile robot's position and orientation using panoramic imagery. Omni-directional sensors are useful in obtaining a 360? field of view, permitting various objects in the vicinity of a robot to be imaged simultaneously. Recognizing landmarks in a panoramic image from an a priori model of distinct features in an environment allows a robot's location information to be updated. A system is shown for tracking vertex and line features for omni-directional cameras constructed with catadioptric (containing both mirrors and lenses) optics. With the aid of the panoramic Hough transform, line features can be tracked without restricting the mirror geometry so that it satisfies the single viewpoint criteria. This allows the use of rectangular scene features to be used as landmarks. Two paradigms for localization are explored, with experiments conducted with synthetic and real images. A working implementation on a mobile robot is also shown.

[1]  J. Gaspar,et al.  Omni-directional vision for robot navigation , 2000, Proceedings IEEE Workshop on Omnidirectional Vision (Cat. No.PR00704).

[2]  Margrit Betke,et al.  Mobile robot localization using landmarks , 1997, IEEE Trans. Robotics Autom..

[3]  Shree K. Nayar,et al.  A theory of catadioptric image formation , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[4]  Gregory D. Hager,et al.  Image-based prediction of landmark features for mobile robot navigation , 1997, Proceedings of International Conference on Robotics and Automation.

[5]  Hans Burkhardt,et al.  Grouping edge points into line segments by sequential Hough transformation , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[6]  Yiannis Aloimonos,et al.  Structure from Motion: Beyond the Epipolar Constraint , 2000, International Journal of Computer Vision.

[7]  A. Leonardis,et al.  Robust localization using eigenspace of spinning-images , 2000, Proceedings IEEE Workshop on Omnidirectional Vision (Cat. No.PR00704).

[8]  Hong Zhang,et al.  Cylindrical panoramic image-based model for robot localization , 2001, Proceedings 2001 IEEE/RSJ International Conference on Intelligent Robots and Systems. Expanding the Societal Role of Robotics in the the Next Millennium (Cat. No.01CH37180).

[9]  Alfred M. Bruckstein,et al.  Omniview cameras with curved surface mirrors , 2000, Proceedings IEEE Workshop on Omnidirectional Vision (Cat. No.PR00704).

[10]  Enrico Magli,et al.  Determination of a segment endpoint by means of the Radon transform , 1999, ICECS'99. Proceedings of ICECS '99. 6th IEEE International Conference on Electronics, Circuits and Systems (Cat. No.99EX357).

[11]  Anup Basu,et al.  Hough transform for feature detection in panoramic images , 2002, Pattern Recognit. Lett..

[12]  John B. Moore,et al.  Resolution invariant surfaces for panoramic vision systems , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[13]  A. Ohya,et al.  A fast and accurate sonar-ring sensor for a mobile robot , 1999, Proceedings 1999 IEEE International Conference on Robotics and Automation (Cat. No.99CH36288C).

[14]  T. J. Majumdar,et al.  Extraction of shoreline and drainage patterns from aerial MSS thermal IR data over Cambay basin, India--an attempt to automatize the threshold selection , 1991, Pattern Recognit..

[15]  T. Yata,et al.  Fusion of omni-directional sonar and omni-directional vision for environment recognition of mobile robots , 2000, Proceedings 2000 ICRA. Millennium Conference. IEEE International Conference on Robotics and Automation. Symposia Proceedings (Cat. No.00CH37065).

[16]  Mi-Suen Lee,et al.  Segmentation, tracking and interpretation using panoramic video , 2000, Proceedings IEEE Workshop on Omnidirectional Vision (Cat. No.PR00704).

[17]  Rama Chellappa,et al.  Extraction of Straight Lines in Aerial Images , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[18]  Cyril Cauchois,et al.  Technique for calibrating an omnidirectional sensor , 1999, Proceedings 1999 IEEE/RSJ International Conference on Intelligent Robots and Systems. Human and Environment Friendly Robots with High Intelligence and Emotional Quotients (Cat. No.99CH36289).

[19]  G.D. Hager,et al.  Toward domain-independent navigation: dynamic vision and control , 1998, Proceedings of the 37th IEEE Conference on Decision and Control (Cat. No.98CH36171).

[20]  Illah R. Nourbakhsh,et al.  Appearance-based place recognition for topological localization , 2000, Proceedings 2000 ICRA. Millennium Conference. IEEE International Conference on Robotics and Automation. Symposia Proceedings (Cat. No.00CH37065).

[21]  Gregory D. Hager,et al.  Robot Navigation Using Image Sequences , 1996, AAAI/IAAI, Vol. 2.

[22]  M. Srinivasan,et al.  A complete panoramic vision system, incorporating imaging, ranging, and three dimensional navigation , 2000, Proceedings IEEE Workshop on Omnidirectional Vision (Cat. No.PR00704).

[23]  Enrico Magli,et al.  All-integer Hough transform: performance evaluation , 2001, Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205).

[24]  Hiroshi Ishiguro,et al.  Omni-directional stereo for making global map , 1990, [1990] Proceedings Third International Conference on Computer Vision.

[25]  Pedro U. Lima,et al.  Omni-directional catadioptric vision for soccer robots , 2001, Robotics Auton. Syst..

[26]  Kostas Daniilidis,et al.  A Unifying Theory for Central Panoramic Systems and Practical Applications , 2000, ECCV.

[27]  Enrico Magli,et al.  On high resolution positioning of straight patterns via multiscale matched filtering of the Hough transform , 2001, Pattern Recognit. Lett..

[28]  Ales Leonardis,et al.  Panoramic Eigenimages for Spatial Localisation , 1999, CAIP.

[29]  Bruce Randall Donald,et al.  Practical mobile robot self-localization , 2000, Proceedings 2000 ICRA. Millennium Conference. IEEE International Conference on Robotics and Automation. Symposia Proceedings (Cat. No.00CH37065).

[30]  Ulrich Nehmzow,et al.  Landmark-based navigation for a mobile robot , 1998 .

[31]  Kurt Konolige,et al.  Approximating a single viewpoint in panoramic imaging devices , 2000, Proceedings IEEE Workshop on Omnidirectional Vision (Cat. No.PR00704).

[32]  Shin'ichi Yuta,et al.  Using one bit wave memory for mobile robots' new sonar-ring sensors , 2000, Smc 2000 conference proceedings. 2000 ieee international conference on systems, man and cybernetics. 'cybernetics evolving to systems, humans, organizations, and their complex interactions' (cat. no.0.

[33]  D. Southwell,et al.  Omni-directional sensors for pipe inspection , 1995, 1995 IEEE International Conference on Systems, Man and Cybernetics. Intelligent Systems for the 21st Century.

[34]  Anup Basu,et al.  Line Segment Extraction in Panoramic Images , 2002, WSCG.

[35]  Hobart R. Everett,et al.  Mobile Robot Positioning - Sensors and Techniques , 1997 .

[36]  Pedro U. Lima,et al.  A Localization Method for a Soccer Robot Using a Vision-Based Omni-Directional Sensor , 2000, RoboCup.

[37]  Ruzena Bajcsy,et al.  Reflective surfaces as computational sensors , 2001, Image Vis. Comput..

[38]  Gregory D. Hager,et al.  A Color Interest Operator for Landmark-Based Navigation , 1997, AAAI/IAAI.

[39]  Ben J. A. Kröse,et al.  A probabilistic model for appearance-based robot localization , 2001, Image Vis. Comput..