home · mobile · calendar · colloquia · 2003-2004 · 

Colloquium - Sawhney

Representations of Video and 3D Data for Manipulation and Recognition
Harpreet Sawhney
Vision Technologies Laboratory, Sarnoff Corp.
8/1/2003
11:00am-12:00pm

Video cameras are no longer being used only in their traditional role of providing "viewable pixels", but are rapidly becoming sources of intelligent information about the world. More recently 3D sensors are being developed to directly provide 3D measurements of objects and scenes. My work in the past few years has concentrated on creating representations and algorithms that enable manipulation and recognition of objects and scenes from the raw sensor data.

Appearance and geometry of objects and scenes, and the temporal dynamics of objects are the key information bearing sources for visual information in videos. This work will highlight the representation of dynamic scenes in terms of 2D and 3D layered representations. Applications ranging from mosaicing, and tracking to scene modeling, and enhanced video visualization for tele-presence will be used to illustrate the work.

I will also present highlights of recent work on classification and recognition of 3D objects from view-based 3D sensor data. I will describe a structural coarse-to-fine indexing and matching approach for scalable 3D object recognition.

This has been joint work with collaborators/colleagues at IBM Almaden, Sarnoff, CMU and UC Berkeley.

Dr. Harpreet S. Sawhney - Technical Manager, leads the Vision Technologies group at the Sarnoff Corporation in Princeton, NJ. Dr. Sawhney obtained his PhD in Computer Science in February 1992 from the University of Massachusetts, Amherst, focusing on Computer Vision. His research interests are in the areas of Immersive Tele-presence, Vision & Graphics Synthesis, 3D Modeling, Data Mining, Object Recognition, Image & Video Indexing, and Optimization Techniques. Since 1995, at Sarnoff Dr. Sawhney has led government and commercial programs in Immersive Telepresence, Image based 3D Modeling, Video Indexing, Video Mosaicing, Geo-registration and 2D and 3D Video Manipulation. He was a key technical leader for two of Sarnoff's startups, VideoBrush and Lifeclips. From 1997-2002, Dr. Sawhney was awarded the Sarnoff Technical Achievement Awards five times for his contributions in Video Mosaicing, Video Enhancement and 3D Vision. Between 1992 and 1995 he led algorithm video annotation and indexing research at the IBM Almaden Research Center in San Jose, CA. Dr. Sawhney has served on the Program Committees of numerous Computer Vision and Pattern Recognition conferences. Dr. Sawhney has published over 50 papers, and holds 11 patents.

Department of Computer Science
University of Colorado Boulder
Boulder, CO 80309-0430 USA
webmaster@cs.colorado.edu
www.cs.colorado.edu
May 5, 2012 (14:13)
XHTML 1.0/CSS2
©2012