Video Motion Capture视频运动捕获.pptVIP

Video Motion Capture Christoph Bregler Jitendra Malik UC Berkley 1997 Overview Challenges Review Method Results Conclusions Challenges High Accuracy Frequent Inter-part Occlusion Low Contrast Review Review Motion capture on synthetic images O’Rouke and Balder, 1980 1 DOF marker free tracking Hogg, 1983. Rohr, 1993 Higher DOF full body tracking Gravrila and Davis, 1995 Review About the previous work All in controlled environments with high contrast and clear edge bounries Most use skintight suits or markers Camera calibration needed Method Method Basic Assumptions From frame to frame, all intensity pixel intensity changes are local: u is motion model and is written as a matrix equation: Method Finding Gradients Gradient form of the first equation: Find a least squares solution to f Warp image I(t+1) based on f Find new gradients Repeat to minimize Method Motion as twists Standard pose matrix to move from object space to camera space (3D) Scaled orthographic projection moves to image space Requires knowing something about the 3D model of the image. Approximated as ellipsoids. Method Motion as twists Any motion can be represented as a rotation about an axis, and a translation about that axis For example, to make this motion: Method Motion as twists You make this motion: Method Motion as twists Twists can be represented as small vector or matrix Can be made to a pose by Encode the motion of a pixel between two frames Method Motion as twists Linear algebra manipulation allows using the twist vector to write a motion equation for each pixel Those equations are put in a vector and used to find a global f parameter for that object Method Kinematic chains Body parts represented as multiple connected objects Each object can be found by the top pose and an angle and twist for each object down the chain More linear algebra is used to find a f for each body part Method Multiple cameras Adds accuracy because change of fully occluded parts drop with each view Normal motion eq