Abstract
In this paper we show that the rate of change of the area that a moving object projects on the image plane and the temporal behaviour of the time-to-crash between the object and the camera are deeply connected. In the case of pure translational motion, these changes turn out being expansions or contractions of the area, according to the motion versus. We have realized a visual sensor which is able to detect these types of changes of the area shape, without any explicit computation of the optical flow field. This sensor realizes the input module of an opto- motor reflex, working in real-time (12.5 Hz), which is able to keep constant in time the distance between the camera and a frontal obstacle. The whole methodology has been extensively tested by using a mobile platform. The performances of the reflex on real image sequences will be shown.
Acknowledgements: this paper describes research done at the Robotic & Automation Laboratory of Tecnopolis CSATA. Partial support is provided by the Progetto Finalizzato Trasporti (PROMETHEUS), Progetto Finalizzato Robotica and by Progetto Finalizzato Calcolo Parallelo of the C.N.R.
Preview
Unable to display preview. Download preview PDF.
References
E.C. Hildreth. Recovering heading for visually-guided navigation. Technical Report A.I. Memo No. 1297, Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, May-1991.
R.C. Nelson and J. Aloimonos. Using flow field divergence for obstacle avoidance: Towards qualitative vision. In Second International Conference on Computer Vision, pages 188–196, Tampa-Florida-U.S.A., December 5 1988.
N. Ancona and T. Poggio. Optical flow from 1d correlation: a simple ttc detector. Technical Report 9112-01, Tecnopolis CSATA Novus Ortus-Valenzano-Bari, 1991.
A. Verri and M. Campani. An algebraic procedure for the computation of optical flow from first order derivatives of the image brightness. In IEEE Work. on Robust Comp. Vision, Seattle, 1990.
G. Sandini and M. Tistarelli. Robust obstacle detection using optical flow. In IEEE Workshop on Robust Computer Vision, Seattle-USA, 1–3 October 1990.
W. Enkelmann. Obstacle detection by evaluation of optical flow fields from image sequences. In First European Conference on Computer Vision, Antibes-France, April 1990.
T. Poggio, A. Verri, and V. Torre. Green theorems and qualitative properties of the optical flow. Technical Report A.I. Memo No. 1289, Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, 1991.
N. Ancona. A fast obstacle detection method based on optical flow. In Second European Conference on Computer Vision '92, S. Margherita Ligure — Italy, May 18–23 1992.
E. D. Dickmanns and V. Graefe. Applications of dynamic monocular machine vision. Machine Vision and Applications, 1(4):241–261, 1988.
E. D. Dickmanns and V. Graefe. Dynamic monocular machine vision. Machine Vision and Applications, 1(4):223–240, 1988.
R. Cipolla and A. Blake. Surface orientation and time to contact from image divergence and deformation. In Second European Conference on Computer Vision, pages 187–202, Santa Margherita Ligure — Italy, 1992.
M. Romano and N. Ancona. Un sensore per espansione di aree: esempio di un riflesso opto-motorio. Technical Report 9205-01, Tecnopolis CSATA Novus Ortus-Valenzano-Bari, 1992.
M. Kass, A. Witkin, and D. Terzopoulos. Snakes: Active contour models. In First International Conference on Computer Vision, pages 259–268, London-England, June 8 1987.
A.A. Amini, S. Tehrani, and T.E. Weymouth. Using dynamic programming for minimizing the energy of active contours in presence of hard constraints. In Second International Conference on Computer Vision, pages 95–99, Tampa-Florida-U.S.A., December 5 1988.
D.J. Williams and M. Shah. A fast algorithm for active contours. In Third International Conference on Computer Vision, pages 592–595, Osaka-Japan, December 4 1990.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1993 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Romano, M., Ancona, N. (1993). A time-to-crash detector based on area expansions: Example of an opto-motor reflex. In: Roberto, V. (eds) Intelligent Perceptual Systems. Lecture Notes in Computer Science, vol 745. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-57379-8_22
Download citation
DOI: https://doi.org/10.1007/3-540-57379-8_22
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-57379-1
Online ISBN: 978-3-540-48103-4
eBook Packages: Springer Book Archive