Zoom tracking

In this paper we present a new active vision technique called zoom tracking. Zoom tracking is the continuous adjustment of a camera's focal length, to keep a constant-sized image of an object moving along the camera's optical axis. Two methods for performing zoom tracking are presented: a closed-loop visual feedback algorithm based on optical flow, and use of depth information obtained from an autofocus camera's range sensor. We show that the image stability provided by zoom tracking improves the performance of algorithms that are scale variant, such as correlation-based trackers. While zoom tracking cannot totally compensate an object's motion, due to the effect of perspective distortion, an analysis of this distortion provides a quantitative estimate of the performance of zoom tracking.

[1]  Minoru Asada,et al.  Visual servoing utilizing zoom mechanism , 1995, Proceedings of 1995 IEEE International Conference on Robotics and Automation.

[2]  Ruzena Bajcsy,et al.  Adaptive Correlation Tracking of Targets With Changing Scale , 1996 .

[3]  Ian D. Reid,et al.  Saccade and pursuit on an active head/eye platform , 1994, Image Vis. Comput..

[4]  Ian D. Reid,et al.  Saccade and pursuit on an active head/eye platform , 1994, Image Vis. Comput..

[5]  Berthold K. P. Horn,et al.  Determining Optical Flow , 1981, Other Conferences.

[6]  Michel Dhome,et al.  Dense Reconstruction by Zooming , 1996, ECCV.

[7]  Jun Ma,et al.  Depth from zooming , 1990 .

[8]  Dana H. Ballard,et al.  Animate Vision , 1991, Artif. Intell..

[9]  John K. Tsotsos,et al.  Directing attention to onset and offset of image events for eye-head movement control , 1994, Proceedings of 12th International Conference on Pattern Recognition.

[10]  Yiannis Aloimonos,et al.  Active vision , 2004, International Journal of Computer Vision.

[11]  Y. J. Tejwani,et al.  Robot vision , 1989, IEEE International Symposium on Circuits and Systems,.

[12]  Hans-Peter Seidel,et al.  An Image-Based Model for Realistic Lens Systems in Interactive Computer Graphics , 1997, Graphics Interface.

[13]  Murali Subbarao.  Parallel Depth Recovery By Changing Camera Parameters , 1988, [1988 Proceedings] Second International Conference on Computer Vision.

[14]  Christopher M. Brown,et al.  Real-time smooth pursuit tracking for a moving binocular robot , 1992, Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[15]  Alan Watt,et al.  Fundamentals of three-dimensional computer graphics , 1989 .

[16]  Takeo Kanade,et al.  Fast template matching based on the normalized correlation by using multiresolution eigenimages , 1994, Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS'94).

[17]  Michel Dhome,et al.  Three-dimensional reconstruction by zooming , 1993, IEEE Trans. Robotics Autom..

[18]  Bijan G. Mobasseri.  Focal length and compression of space , 1993, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[19]  Sven J. Dickinson,et al.  A quantitative analysis of view degeneracy and its use for active focal length control , 1995, Proceedings of IEEE International Conference on Computer Vision.