Abstract
In this paper a method to compute a reliable optical flow from image sequences and detect static and moving obstacles during ego-motion is presented. The method consists of two phases: an off-line calibration phase during which a reference optical flow relative to the ground plane and a given camera velocity is computed; a fast on-line procedure to compute the amplitude of the optical flow during the motion of the camera, which is compared with the reference map obtained from the calibration phase.
For the calibration phase, the optical flow is computed using a closed form solution of an over-determined system of equations involving both first and second order partial derivatives, in space and time, of the image intensities. The detection of static obstacles implies the computation of first order partial dervatives only. The on-line procedure can be very fast and is suitable for hardware of firmware implementation in a real-time, robust vision system for navigation purposes. Experiments on real image sequences are presented.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Reference
N. Ayache and O.D.Faugeras, Maintaining representations of the environment of a mobile robot. IEEE Trans, on Robotics and Automat., RA-5, No 6, pages 804–819, December 1989.
J. Aloimonos, Purposive and qualitative active vision. In Intl. Workshop on Active Control in Visual Perception, Antibes, France, April 27 1990.
J. Aloimonos and D. Tsakiris, Tracking in a complex visual environment. In Proc. of first European Conference on Computer Vision, Antibes, France, Apr. 23–26, 1990. Springer Verlag.
R. Sharma and J. Aloimonos, Robust Detection of Independent Motion: and Active and Purposive Solution. Technical report CAR-TR-534, Computer Vision Laboratory, Center for Automation Research, University of Maryland, (MD) USA.
J. Aloimonos, I. Weiss, and A. Bandyopadhyay, Active vision. Intl. Journal of Computer Vision, 1 (4) pages 333–356, 1988.
D. H.Ballard, R. C.Nelson, and B. Yamauchi, “Animate vision”. Optics News, 15 (5): 17–25, 1989.
S. Carlsson and J.O. Eklundh, Object detection using model based prediction and motion parallax. In Proc. of first European Conference on Computer Vision, Antibes, France, Apr. 23–26, 1990. Springer Verlag.
J. L. Crawley, Dynamic modeling of free-space for a mobile robot. In Proc. of Intl. Workshop on Intelligent Robots and Systems, Tsukuba, Japan, September 4–6, 1989. IEEE/RJS.
E. DeMicheli, G. Sandini, M. Tistarelli, and V. Torre, Estimation of visual motion and 3d motion parameters from singular points. In Proc. of Intl. Workshop on Intelligent Robots and Systems, Tokyo, Japan, Oct. 31–Nov. 2, 1988. IEEE Computer Society.
W. Enkelmann, Obstacle detection by evaluation of optical flow fields from image sequences. In Proc. of first European Conference on Computer Vision, Antibes, France, Apr. 23–26, 1990. Springer Verlag.
F. Ferrari, E. Grosso, M. Magrassi, and G. Sandini, “A stereo vision system for real time obstacle avoidance in unknown environment”. In Proc. of Intl. Workshop on Intelligent Robots and Systems, Tokyo, Japan, July 1990. IEEE Computer Society.
B. K. P. Horn and B. G. Schunck, “Determining optical flow”. Artificial Intelligence, 17 No. 1–3: 185–204, 1981.
D. J. Kriegman, E. Triendl, and T. O.Binford, Stereo vision and navigation in buildings for mobile robots. IEEE Trans, on Robotics and Automat., RA-5, No 6 pages 792–803, December 1989.
R. Manmatha, R. Dutta, E. M. Riseman, and M. A. Snyder, Issues in extracting motion parameters and depth from approximate translational motion. In Proc. of Intl. Workshop on Visual Motion, Irvine, CA, March 20–22 1989. IEEE Computer Society.
Y. Nakamura and Y. Xu, Controller for multi-sensor robotic systems. In Proc. of the Intl. Symposium and Exposition on Robots, Sidney, Australia, November 6–10, 1988.
R. C. Nelson and J. Aloimonos, “Using flow field divergence for obstacle avoidance in visual navigation”. IEEE Trans, on PAMI, PAMI-11, No. 10, October 1989.
J. W. Roach and J. K. Aggarwal, Computer tracking of moving objects in space. IEEE Trans, on PAMI, PAMI-1, No. 2, 1979.
G. Sandini, F. Bosero, F. Bottino, and A. Ceccherini, The use of an anthropomorphic visual sensor for motion estimation and object tracking. In Proc. of the OSA Topical Meeting on Image Understanding and Machine Vision, June 12–14 1989.
G. Sandini and M. Tistarelli, Active tracking strategy for monocular depth inference over multiple frames. IEEE Trans, on PAMI, PAMI-12, No. 1, January 1990.
G. Sandini and M. Tistarelli, “Understanding optical flow anomalies”. Technical report, DIST University of Genoa - LIRA lab., Genoa, Italy, May 1990.
G. Sandini and M. Tistarelli, Robust obstacle detection using optical flow. In Proc. of IEEE Intl. Workshop on Robust Computer Vision, pages 396–411, Seattle, (WA), Oct. 1–3, 1990. IEEE Computer Society.
RJ. Schalkoff and E. S. McVey, A model and tracking algorithm for a class of video target. IEEE Trans, on PAMI, PAMI-4, No. 1, 1982.
G. Succi, E. Grosso, G. Sandini and M. Tistarelli, 3d feature extraction from sequences of range data. In Proc. 5th Int. Symposium on Robotics Research, Tokyo, Japan, 1989. MIT-Press.
M. B. Thompson and T. C. Pong, Detecting moving objects. Intl. Journal of Computer Vision, 4 (1) pages 39–58, 1990.
M. Tistarelli and G. Sandini, Dynamic Aspects in Active Vision. CVGIP: Image Understanding, Vol. 56, No. 1 pages 108–129, July 1992.
M. Tistarelli, G. Sandini, and P. Baraldi, “Spatio-temporal filtering for gradient-based motion estimation”. In Proc. of 2nd Prometheus Workshop, Stockolm, Sweden, Oct. 30–31, 1989.
S. Uras, F. Girosi, A. Verri, and V. Torre, “Computational approach to motion perception”. Biological Cybernetics, 60: 69–87, 1988.
A. Verri, F. Girosi, and V. Torre, Mathematical properties of the 2d motion field: from singular points to motion parameters. In Proc. of Intl. Workshop on Visual Motion, Irvine, CA, March 20–22 1989. IEEE Computer Society.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1995 ECSC-EC-EAEC, Brussels-Luxembourg
About this chapter
Cite this chapter
Tistarelli, M., Sandini, G. (1995). Obstacle Detection from a Moving Vehicle. In: Pfleger, S., Gonçalves, J., Varghese, K. (eds) Advances in Human-Computer Interaction. Research Reports Esprit, vol 1. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-85220-6_10
Download citation
DOI: https://doi.org/10.1007/978-3-642-85220-6_10
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-60145-6
Online ISBN: 978-3-642-85220-6
eBook Packages: Springer Book Archive