Measuring time-to-contact using active camera control
In this paper we use a simple, active-camera model to estimate the time-to-contact (TTC) of a moving object. We estimate TTC by enforcing a “uniform scale” constraint on the moving object. By actively adjusting the focal length of the pinhole model, the projected object maintains a fixed image scale regardless of its motion. These adjustments on the ideal pinhole focal length are translated into changes of the actual zoom and focus settings of a real camera system. We obtain improvements over a fixed-camera approach because the scale adjustment (zoom) improves image divergence measurements. We show experimental results indicating that our active method can reduce errors over a larger distance range than fixed-camera methods of estimating time-to-contact.
Unable to display preview. Download preview PDF.
- 1.Yiannis Aloimonos, Isaac Weiss, and Amut Bandyopadhyay. Active vision. In Proc. 1st Int. Conf. on Computer Vision, pages 35–54, 1987.Google Scholar
- 2.Ruzena Bajcsy. Active perception vs. passive perception. In Proc. IEEE Workshop on Computer Vision, pages 55–59, 1985.Google Scholar
- 3.R. Cipolla and A. Blake. The dynamic analysis of apparent contours. Proc. 3rd Int. Conf. Computer Vision, pages 616–623, 1990.Google Scholar
- 4.R. Cipolla and A. Blake. Surface orientation and time to contact from image divergence and deformation. In Proceedings of ECCV, pages 187–202, 1992.Google Scholar
- 5.David Coombs and Christopher Brown. Real-time smooth pursuit tracking for a moving binocular robot. In Proc. Computer Vision and Pattern Recognition, pages 23–28, 1992.Google Scholar
- 6.R. Curwen, A. Blake, and A. Zisserman. Real-time visual tracking for surveillance and path planning. In Proc. 2nd European Conf. on Computer Vision, pages 879–883, 1992.Google Scholar
- 7.M. Dose E. R. Shulze, S. Bohrer and S. Fuhrmann. An active vision system for task specific information processing. UustererUennung 90 DAGU Symposium, pages 67–74, 1990.Google Scholar
- 8.O. D. Faugeras. Three-Dimensional Computer Vision: A Geometric Approach. MIT Press, 1993.Google Scholar
- 9.M. Kass, A. Witkin, and D. Terzopoulos. Snakes: active contour models. Int. J. Computer Vision, pages 321–331, 1988.Google Scholar
- 10.Kourosh Pahlavan and Jan-Olof Eklundh. A head-eye system — analysis and design. CVGIP: Image Understanding, 56(1):41–56, 1992, Special Issue on Purposive, Qualitative, Active Vision.Google Scholar
- 11.W. B. Seales. Measuring time-to-contact using active camera control. Technical report, University of Kentucky, Lexington, KY, 1995.Google Scholar
- 12.Massimo Tistarelli and Giulio Sandini. Dynamic aspects of active vision. CVGIP: Image Understanding, 56:108–129, 1992.Google Scholar
- 13.Donna Williams and Mubarak Shah. A fast algorithm for active contours and curvature estimation. CVGIP: Image Understanding, 55:14–26, 1992.Google Scholar