Daniel P. Huttenlocher

Daniel P. Huttenlocher
Associate Professor
PhD MIT, 1988

My research area is computer vision, and my work focuses on the problems of model-based recognition, geometric shape comparison, and the computation of visual correspondence. My approach to these problems involves a combination of theoretical analysis, algorithm design, implementation, and experimentation. The overall goal of my work is to produce systems that work well in practice and have a firm underlying theoretical and algorithmic foundation. Recently we have begun to look at tasks in which two-dimensional shape matching methods can be used to solve problems that are three-dimensional in nature. The main question that we are investigating is whether purely two-dimensional representations are sufficient for solving certain tasks, such as motion tracking or visual navigation. We have developed a system that uses visual information to guide a mobile robot using only two-dimensional representations. In addition to robotic applications, we have been developing model-based video compression schemes using the same underlying two-dimensional shape matching methods.

University Activities

Chair, Computer Science Department Computing Facilities Committee
Department of Electrical Engineering Recruiting Committee
Faculty Advisory Board on Information Technology

Professional Activities

Associate Editor, IEEE Transactions on Pattern Analysis and Machine Intelligence
Program Committee, Fifth International Conference on Computer Vision
Program Committee, Workshop on Context Based Vision

Awards

National Science Foundation Presidential Young Investigator Award (1990-95)
Outstanding Educator Award, Merrill Presidential Scholar Program, Cornell University, 1995

Lectures

Using two-dimensional image matching to interpret the three-dimensional world. University of California Berkeley AI Seminar, Berkeley CA, January 1995.
___. Sandia National Labs Robotics Seminar, Albuquerque NM, December 1994.
___. Carnegie Mellon University Robotics Institute, Pittsburgh PA, November 1994.
Geometric algorithms for computer vision. University of British Columbia Computer Science Dept., Vancouver BC, August 1994.
___. Microsoft Corp., Redmond WA, June 1994.

Publications

A study of affine matching with bounded sensor error. International Journal of Computer Vision 13, 1 (1994), 7-32 (with W.E.L. Grimson and D.W. Jacobs).
Computing visual correspondence: incorporating the probability of a false match. Proceedings of the Fifth International Conference on Computer Vision, (1995) (with E.W. Jaquith).
Visually guided navigation by comparing two-dimensional edge images. Proceedings of the IEEE Computer Vision and Pattern Recognition Conference, (1994), 842-847 (with M.E. Leventon and W.J. Rucklidge).
Comparing images using the Hausdorff distance. IEEE Transactions on Pattern Analysis and Machine Intelligence 15, 9 (1993), 850-863 (with G.A. Klanderman and W.J. Rucklidge).

Return to:

1994-1995 Annual Report Home Page
Departmental Home Page If you have questions or comments please contact: www@cs.cornell.edu. Last modified: 24 November 1995 by Denise Moore (denise@cs.cornell.edu).