Loading Events

« All Events

  • This event has passed.

GRASP Seminar: Dr. Daniel Scharstein, Middlebury College, VT, “Benchmarking Stereo Vision and Optical Flow Algorithms”

September 17, 2007 @ 2:00 pm - 3:00 pm

Abstract: Stereo vision and optical flow methods attempt to measure scene depth and motion by tracking pixels over frames. To evaluate the performance of such methods, we need “ground truth” – the true depth or true object motion. In this talk I will describe different techniques for creating image datasets with ground truth, including structured lighting, laser and CT scanners, and hidden fluorescent texture. The Middlebury datasets are now well-established benchmarks in computer vision, and I will discuss both benefits and potential pitfalls of such benchmarks. I will also briefly touch on how data with ground truth can aid in developing new algorithms.


Daniel Scharstein currently is Associate Professor of Computer Science at Middlebury College in Vermont. He studied Computer Science at the Universitaet Karlsruhe, Germany, and then received his PhD from Cornell University in 1997. His research interests include computer vision, in particular stereo vision, as well as visual robot navigation.


September 17, 2007
2:00 pm - 3:00 pm
Event Category: