COLLOQUIUM

Department of Computer Science and Engineering

University of South Carolina

Monocular Vision Modules

for Mobile Robotics Applications

Stan Birchfield

Department of Electrical and Computer Engineering

Clemson University

Date: October 27, 2011

Time: 1515-1615 (3:15pm-4-15pm)

Place: Swearingen 1C02 (Amoco Hall)

Abstract

The U.S. government has recently announced a major multi-year initiative to invest in the next generation of robots. These robots will work alongside people as co-workers, co-protectors, and co-inhabitants. One of the key challenges that will need to be overcome in order to achieve this goal is sensing. Robots need to be able to sense not only their static environment, but also the important objects in the environment and the humans moving about them, both in order to interact with the world and to safely avoid collision. In this talk I will describe some of the work we have been doing in our lab to develop important technologies to facilitate mobile robotic sensing. We developed vision modules that use monocular vision as the input and enable the robot to follow a path, detect and follow a person, detect doors, segment floors, avoid obstacles, and navigate corridors. These modules will serve as important components in an overall robust system for domestic or other unconstrained environments.

Stan Birchfield is an Associate Professor in the Electrical and Computer Engineering Department of Clemson University, where he has been since 2003. He received a Ph.D. from Stanford University in 1999, an M.S. from Stanford in 1996, and a B.S. from Clemson in 1993, all in Electrical Engineering. While at Stanford, his research was supported by a National Science Foundation Graduate Research Fellowship, and he was part of the team that won first place at the AAAI Mobile Robotics Competition of 1994. After graduating from Stanford, he was a research engineer with Quindi Corporation, a startup company in Palo Alto, California, where he developed algorithms for intelligent audio and video and was the lead engineer and principal architect of the Meeting Companion product. Over the years he has worked with or consulted for various companies, including Sun Microsystems, SRI International, Canon, Microsoft, and Autodesk. More recently, he has been instrumental in co-founding TrafficVision (http://www.trafficvision.com/), a South Carolina company that uses computer vision to collect aggregate traffic parameters automatically from live video feeds. Dr. Birchfield has authored or co-authored more than 50 publications in the areas of computer vision, stereo correspondence, visual tracking, spatial acoustics, and mobile robotics; and his open-source Kanade-Lucas-Tomasi (KLT) feature tracker has been used by thousands of researchers around the world.