Tutorial at DAGM 2010 on Computer Vision on GPUs |
21/09/2010, 14:00 - 18:00 Recent demand for high performance techniques has led to the use of GPUs as a fast processing platform for various computer vision algorithms. This development was driven by the ability of many computer vision algorithms to use standard computer graphics techniques to their benefit, the high performance gains of GPUs in recent years, and their increasing ability with to support general purpose computing. These trends gain wider acceptance and this course/tutorial aims to educate computer vision and image processing researchers about this exciting development of fast image analysis algorithms. In recent years, an increasing number of researchers have used GPUs for processing demonstrating the interest in the area. The tutorial will give an introduction to the programming of the current state of the art hardware to enable participants to employ the unique capabilities of GPUs. The following topics will be covered over the course in a half day:
|
Organizers: |
|
Curriculum Vitae: |
Jan-Michael Frahm is a Research Assistant Professor at University of North Carolina at Chapel Hill. He received his Ph.D in computer vision in 2005 from the Christian-Albrechts University of Kiel, Germany. His research interests include a variety of computer vision problems. He has worked on structure from motion for single/multi-camera systems for static and dynamic scenes to create 3D models of the scene; real-time multi-view stereo to create a dense scene geometry from camera images; use of camera-sensor systems for 3D scene reconstruction with fusion of multiple orthogonal sensors; improved robust and fast estimation methods from noisy data to compensate for highly noisy measurements in various stages of the reconstruction process; high performance feature tracking for salient image-point motion extraction; and the development of data-parallel algorithms for commodity graphics hardware for efficient 3D reconstruction. He received an Nvidia professor fellowship in 2007 and is currently a GPU computing champion for “Computer Vision” for GPUcomputing.net. |
P. J. Narayanan is a Professor at the International Institute of Information Technology (IIIT), Hyderabad and heads the Centre for Visual Information Technology there. He got his B.Tech from IIT, Kharagpur and his PhD from the University of Maryland, College Park. He was a research faculty member at the Robotics Institute, Carnegie Mellon University from 1992-1996 where he worked on the Virtualized Reality project. He headed the Computer Vision and Virtual Reality group at the Centre for Artificial Intelligence and Robotics (CAIR), a DRDO laboratory at Bangalore from 1996 to 2000. He joined IIIT, Hyderabad in 2000 and is currently the Dean of Research & Development there. Prof. Narayanan has been working on GPU algorithms for Computer Graphics and Computer Vision for the past 3-4 years and was declared as the first CUDA Fellow by Nvidia in November 2008. |
© 2009-2010 DAGM 2010 | TU Darmstadt, Interactive Graphics Systems Group |