1Background Subtraction15-463: Rendering and Image ProcessingAlexei EfrosImage StackAs can look at video data as a spatio-temporal volume• If camera is stationary, each line through time corresponds to a single ray in space• We can look at how each ray behaves • What are interesting things to ask?t0255time2ExampleGetting the right pixelsAverage imageMedian Image3Input VideoAverage ImageWhat is happening?4Average ImageWhat can we do with this?Background Subtraction--==5Crowd Synthesis (with Pooja Nath)1. Do background subtraction in each frame2. Find and record “blobs”3. For synthesis, randomly sample the blobs, taking care not to overlap themBackground Subtraction for mattingA very hard problem.But sometimes it works:6Removing Shadows (Weiss, 2001)How does one detect (subtract away) shadows?Averaging Derivatives7Recovering ShadowsCompositing with Shadows8Figure-centric RepresentationContext-based Image CorrectionInput sequence3 closestframesmedian images9Midterm Stats# of people: 11Total points possible: 120Mean: 77.1Median: 76Max: 98Min: 56Std. Div: 13.2Skewness: -0.04Kurtosis: 1.9The scores: [56 61 68 70 71 76 82 88 89 89 98]Fun with Focal Length (Jim
View Full Document