|
Harpreet Singh Sawhney & Rakesh (Teddy) Kumar
Sarnoff Corporation
2D & 3D Manipulation of Motion Imagery
The confluence of Video and Vision research at Sarnoff is strongly
influenced by real world applications. Over the past decade or so,
advances in fundamental algorithms, and successes in creating customer
oriented technologies and products have produced a unique R&D
environment at Sarnoff. This talk will present a tour of algorithm and
application development as it has evolved at Sarnoff in the recent past.
Specifically, we will present a framework for video representation
within which progressively complex video alignment models reveal the
underlying 2D and 3D nature of scenes and objects behind moving video
pixels. The framework will be highlighted through applications ranging
from tele-presence, scene modeling, geo-registration and targeting,
video manipulation and enhanced visualization of video.
Video alignment is a key tool in the representation and manipulation of
the fundamental information content present in motion video sequences.
Global 2D parametric alignment models reveal the 2D nature of video
frames from close-by vantage points. These can be used for stabilization
of video sequences and construction of video panoramas. Layered
representations of motion video in terms of moving object and multiple
scene layers can be exploited for tracking, compression and indexing.
Alignment of video frames with generic optical flow and 3D models
reveals the rigid and non-rigid structure of objects and scenes, and can
be used for video enhancement, 3D recovery, modeling and image based
rendering. Alignment of videos to stored reference models enables
augmented reality, video insertion, and targeting. The talk will span
these and other related applications.
Biography:
HARPREET SAWHNEY (Member IEEE) received his Ph.D. in Computer Science in
1992 from the University of Massachusetts, Amherst, focusing on Computer
Vision. He is a Senior Member, Technical Staff in the Vision
Technologies Lab., at the Sarnoff Corp. where he has led R&D in 3D
modeling & manipulation from motion video, video enhancement & indexing,
and video mosaicing, under a number of commercial and government
programs since 1995. He led R&D in video annotation & indexing at the
IBM Almaden Research Center from 1992 to 1995. Dr. Sawhney has authored
50 technical publications, holds 5 patents and has a number of patent
applications pending.
RAKESH KUMAR (Member IEEE) is currently the head of the Media Vision
Group at Sarnoff Corporation, Princeton, New Jersey. He received his
Ph.D. in Computer Science from the University of Massachusetts at
Amherst in 1992, his MS from the State University of New York, Buffalo
and his B.Tech. from the Indian Institute of Technology, Kanpur. At
Sarnoff, he has been directing commercial and government research and
development projects in computer vision with a focus in the areas of
immersive tele-presence and 3D modeling from images, image registration,
video manipulation and exploitation. He is an Associate Editor for the
IEEE Transactions on Pattern Analysis and Machine Intelligence. He is an
author/ co-author of more than 30 technical publications and is a
co-inventor of 7 patents.
|
