Lecture-9 - 1 Lecture-9 Model-Based Image Coding 2...

Info iconThis preview shows pages 1–11. Sign up to view the full content.

View Full Document Right Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: 1 Lecture-9 Model-Based Image Coding 2 Model-Based Image Coding Model-Based Image Coding The transmitter and receiver both posses the same 3D face model and texture images. During the session, at the transmitter the facial motion parameters: global and local, are extracted. At the receiver the image is synthesized using estimated motion parameters. The difference between synthesized and actual image can be transmitted as residuals. 3 Candide Model Face Model Candide model has 108 nodes, 184 polygons. Candide is a generic head and shoulder model. It needs to be conformed to a particular persons face. Cyberware scan gives head model consisting of 460,000 polygons. 4 Wireframe Model Fitting Fit orthographic projection of wireframe to the frontal view of speaker using Affine transformation. Locate three to four features in the image and the projection of a model. Find parameters of Affine transformation using least squares fit. Apply Affine to all vertices, and scale depth. 2 ) ( 2 2 4 2 1 a a + 5 6 Synthesis Collapse initial wire frame onto the image to obtain a collection of triangles. Map observed texture in the first frame into respective triangles. Rotate and translate the initial wire frame according to global and local motion, and collapse onto the next frame. Map texture within each triangle from first frame to the next frame by interpolation. Texture Mapping 7 Video Phones Motion Estimation Perspective Projection (optical flow) 2 1 2 3 3 1 2 2 2 1 3 3 2 1 ) ( ) ( y f xy f y Z V x Z V f v x f xy f y x Z V Z V f u - +- + - = + - -- + = 8 Optical Flow Constraint Eq = + + t y x f v f u f ) ) ( ( ) ) ( ( 2 1 2 3 3 1 2 2 2 1 3 3 2 1 = + - +- + - + + - -- + t y x f y f xy f y Z V x Z V f f x f xy f y x Z V Z V f f t y x y x x y y x y x y x f x f y f f xy f f x f f f f f f y f f xy f V y f x f Z f V Z f f V Z f f- = + + + + + - +- +- + + 3 2 2 1 2 3 2 1 ) ( ) ( ) ( ) ( ( ) ( ) ( 9 t y x y x x y y x y x y x f x f y f f xy f f x f f f f f f y f f xy f V y f x f Z f V Z f f V Z f f- = + + + + + - +- +- + + 3 2 2 1 2 3 2 1 ) ( ) ( ) ( ) ( ( ) ( ) ( b Ax = ) , , , , , ( 3 2 1 3 2 1 = V V V x Solve by Least Squares = + + +- +-- M M M M t y x y x x y y x y x y x f V V V x f y f f xy f f x f f f f f f y f f xy f y f x f Z f Z f f Z f f 3 2 1 3 2 1 2 2 ) ( ) ( ) ( ) ( ( ) ( ) ( b Ax = 10 Comments This is a simpler (linear) problem than sfm because depth is assumed to be known....
View Full Document

This note was uploaded on 06/12/2011 for the course CAP 6411 taught by Professor Shah during the Spring '09 term at University of Central Florida.

Page1 / 27

Lecture-9 - 1 Lecture-9 Model-Based Image Coding 2...

This preview shows document pages 1 - 11. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online