A Hybrid Distributed Vision System for Robot Localization
Localization is one of the critical issues in the field of
robot navigation. With an accurate estimate of the robot pose, robots will be capable of navigating in the environment autonomously and efficiently. In this paper, a hybrid Distributed Vision System (DVS)
for robot localization is presented. The presented approach integrates
odometry data from robot and images captured from overhead cameras
installed in the environment to help reduce possibilities of fail
localization due to effects of illumination, encoder accumulated errors,
and low quality range data. An odometry-based motion model is applied to predict robot poses, and robot images captured by overhead
cameras are then used to update pose estimates with HSV histogram-based measurement model. Experiment results show the
presented approach could localize robots in a global world coordinate system with localization errors within 100mm.
[1] J. Borenstein, B. Everett, and L. Feng, 1996, "Navigating Mobile Robots:
Systems and Techniques," A. K. Peters, Ltd., Wellesley, MA.
[2] J. Gaspar, N. Winters, and J. Santos-Victor, 2000, "Vision-based navigation and environmental epresentations with an omnidirectional
camera," IEEE Transaction on Robotics and Automation, Vol. 16(6).
[3] J. Y. Bouget, "Camera calibration toolbox for Matlab,"
http://www.vision.caltech.edu/bougetj/calib_doc.
[4] H. Everett, D. Gage, G. Gilbreth, R. Laird, and R. Smurlo, 1994,
"Realworld issues in warehouse navigation," In Proceedings of the SPIE
Conference on Mobile Robots IX, Vol. 2352.
[5] D. Fox, W. Burgard, S. Thrun, and A. B. Cremers, 1998, "Position
estimation for mobile robots in dynamic environments," In Proceedings of
the AAAI Fifteenth National Conference on Artificial Intelligence.
[6] T. Wilhelm, H. J. B¨ohme, and H. M. Gross, August 2004, "A multi-modal system for tracking and analyzing faces on a mobile robot,"
Robotics and Autonomous Systems,Vol. 48, pp. 31-40.
[7] J. Wolf, W. Burgard, and H. Burkhardt, 2005, "Robust vision-based
localization by combining an image retrieval system with monte carlo
localization," IEEE Transactions on Robotics, 21(2), pp. 208-216.
[8] E. Menegatti, G. Gatto, E. Pagello, T. Minato, H. Ishiguro, "Distributed
Vision System for robot localization in indoor environments," Proc. of the
2nd European Conference on Mobile Robots ECMR'05 September 2005
Ancona - Italy, pp. 194-199.
[9] T. Sogo, H. Ishiguro and T. Ishida, 2001, ÔÇÿÔÇÿMobile robot navigation by a
distributed vision system,-- New Generation Computing,
Springer-Verlag.
[10] J. Bruce, M. Veloso, "Fast and accurate vision-based pattern detection
and identification", Dept. of Comput. Sci., Carnegie Mellon Univ.,
Pittsburgh, PA, USA.
[11] Y. Rui and Y. Chen, "Better proposal distributions: Object tracking using
unscented particle filter," in Proc. IEEE Conf. on Computer Vision and
Pattern Recognition, Kauai, Hawaii, volume II, 2001, pp. 786-793.
[12] J. Sangoh, "Histogram-Based Color Image Retrieval," Available:
http://scien.stanford.edu/class/psych221/projects/02/sojeong.
[1] J. Borenstein, B. Everett, and L. Feng, 1996, "Navigating Mobile Robots:
Systems and Techniques," A. K. Peters, Ltd., Wellesley, MA.
[2] J. Gaspar, N. Winters, and J. Santos-Victor, 2000, "Vision-based navigation and environmental epresentations with an omnidirectional
camera," IEEE Transaction on Robotics and Automation, Vol. 16(6).
[3] J. Y. Bouget, "Camera calibration toolbox for Matlab,"
http://www.vision.caltech.edu/bougetj/calib_doc.
[4] H. Everett, D. Gage, G. Gilbreth, R. Laird, and R. Smurlo, 1994,
"Realworld issues in warehouse navigation," In Proceedings of the SPIE
Conference on Mobile Robots IX, Vol. 2352.
[5] D. Fox, W. Burgard, S. Thrun, and A. B. Cremers, 1998, "Position
estimation for mobile robots in dynamic environments," In Proceedings of
the AAAI Fifteenth National Conference on Artificial Intelligence.
[6] T. Wilhelm, H. J. B¨ohme, and H. M. Gross, August 2004, "A multi-modal system for tracking and analyzing faces on a mobile robot,"
Robotics and Autonomous Systems,Vol. 48, pp. 31-40.
[7] J. Wolf, W. Burgard, and H. Burkhardt, 2005, "Robust vision-based
localization by combining an image retrieval system with monte carlo
localization," IEEE Transactions on Robotics, 21(2), pp. 208-216.
[8] E. Menegatti, G. Gatto, E. Pagello, T. Minato, H. Ishiguro, "Distributed
Vision System for robot localization in indoor environments," Proc. of the
2nd European Conference on Mobile Robots ECMR'05 September 2005
Ancona - Italy, pp. 194-199.
[9] T. Sogo, H. Ishiguro and T. Ishida, 2001, ÔÇÿÔÇÿMobile robot navigation by a
distributed vision system,-- New Generation Computing,
Springer-Verlag.
[10] J. Bruce, M. Veloso, "Fast and accurate vision-based pattern detection
and identification", Dept. of Comput. Sci., Carnegie Mellon Univ.,
Pittsburgh, PA, USA.
[11] Y. Rui and Y. Chen, "Better proposal distributions: Object tracking using
unscented particle filter," in Proc. IEEE Conf. on Computer Vision and
Pattern Recognition, Kauai, Hawaii, volume II, 2001, pp. 786-793.
[12] J. Sangoh, "Histogram-Based Color Image Retrieval," Available:
http://scien.stanford.edu/class/psych221/projects/02/sojeong.
@article{"International Journal of Information, Control and Computer Sciences:53593", author = "Hsiang-Wen Hsieh and Chin-Chia Wu and Hung-Hsiu Yu and Shu-Fan Liu", title = "A Hybrid Distributed Vision System for Robot Localization", abstract = "Localization is one of the critical issues in the field of
robot navigation. With an accurate estimate of the robot pose, robots will be capable of navigating in the environment autonomously and efficiently. In this paper, a hybrid Distributed Vision System (DVS)
for robot localization is presented. The presented approach integrates
odometry data from robot and images captured from overhead cameras
installed in the environment to help reduce possibilities of fail
localization due to effects of illumination, encoder accumulated errors,
and low quality range data. An odometry-based motion model is applied to predict robot poses, and robot images captured by overhead
cameras are then used to update pose estimates with HSV histogram-based measurement model. Experiment results show the
presented approach could localize robots in a global world coordinate system with localization errors within 100mm.", keywords = "Distributed Vision System, Localization, Measurement model, Motion model", volume = "2", number = "5", pages = "1463-7", }