Tuesday, June 02, 2015, 02:00pm
Deloitte Foundation Distinguished Lectures in CS
Professor, EECS Department, Massachusetts Institute of Technology
"A Big World of Tiny Motions"
Abstract: We have developed a "motion microscope" to visualize small motions by synthesizing a video with the desired motions amplified. The project began as an algorithm to amplify small color changes in videos, allowing color changes from blood flow to be visualized. Modifications to this algorithm allow small motions to be amplified ina video. I'll describe the algorithms, and show color-magnifiedvideos of adults and babies, and motion-magnified videos of throats,pipes, cars, smoke, and pregnant bellies. These algorithms are beingused in biological, civil, and mechanical engineering applications. Having this tool led us to explore other vision problems involving tiny motions. I'll describe recent work in analyzing fluid flow and depth by exploiting small motions in video or stereo video sequences caused by refraction of turbulent air flow (joint work with the authors below and Tianfan Xue, Anat Levin, and Hossein Mobahi). We have also developed a "visual microphone" to record sounds by watching objects, like a bag of chips, vibrate (joint with the authors belowand Abe Davis and Gautam Mysore).
Bio: Prof. William T. Freeman is Professor of Electrical Engineering and Computer Science at MIT, and a member of the Computer Science and ArtificialIntelligence Laboratory (CSAIL) there. He is currently on leave, startinga computer vision group at Google in Cambridge, MA.His current research interests include machine learning applied tocomputer vision, Bayesian models of visual perception, andcomputational photography. He received outstanding paper awards atcomputer vision or machine learning conferences in 1997, 2006, 2009and 2012, and test-of-time awards for papers from 1990 and 1995.Previous research topics include steerable filters and pyramids,orientation histograms, the generic viewpoint assumption, colorconstancy, computer vision for computer games, and belief propagationin networks with loops.He is active in the program or organizing committees of computervision, graphics, and machine learning conferences. He was theprogram co-chair for ICCV 2005, and for CVPR 2013.
Hosted by: EECS Prof. Oliver (Ollie) Cossairt. One of a series of talks sponsored by the Deloitte Foundation.
Accelerating education to meet the pace of business The Deloitte Foundation, a non-profit organization, has been a strong supporter of higher education for more than 86 years. The Foundation supports education through a variety of initiatives that help develop the talent of the future and their influencers and promote excellence in teaching, research and curriculum innovation. Northwestern University is grateful for the Foundation’s sponsorship of this three-part lecture series.