Lucas-Kanade Image Alignment Iain Matthews. Paper Reading Simon Baker and Iain Matthews, Lucas-Kanade 20 years on: A Unifying Framework, Part 1

Slides:



Advertisements
Similar presentations
Real-Time Template Tracking
Advertisements

Active Appearance Models
DTAM: Dense Tracking and Mapping in Real-Time
CSCE 643 Computer Vision: Lucas-Kanade Registration
Optimizing and Learning for Super-resolution
Sami Romdhani Volker Blanz Thomas Vetter University of Freiburg
Face Alignment with Part-Based Modeling
Intensity-based deformable registration of 2D fluoroscopic X- ray images to a 3D CT model Aviv Hurvitz Advisor: Prof. Leo Joskowicz.
Wangfei Ningbo University A Brief Introduction to Active Appearance Models.
AAM based Face Tracking with Temporal Matching and Face Segmentation Dalong Du.
Computer Vision Optical Flow
CSCE 641: Forward kinematics and inverse kinematics Jinxiang Chai.
Face alignment using Boosted Appearance Model (BAM)
Medical Imaging Mohammad Dawood Department of Computer Science University of Münster Germany.
Medical Imaging Mohammad Dawood Department of Computer Science University of Münster Germany.
Iterative Image Registration: Lucas & Kanade Revisited Kentaro Toyama Vision Technology Group Microsoft Research.
Motion Analysis (contd.) Slides are from RPI Registration Class.
CSci 6971: Image Registration Lecture 4: First Examples January 23, 2004 Prof. Chuck Stewart, RPI Dr. Luis Ibanez, Kitware Prof. Chuck Stewart, RPI Dr.
Announcements Quiz Thursday Quiz Review Tomorrow: AV Williams 4424, 4pm. Practice Quiz handout.
Direct Methods for Visual Scene Reconstruction Paper by Richard Szeliski & Sing Bing Kang Presented by Kristin Branson November 7, 2002.
CSCE 641 Computer Graphics: Image Registration Jinxiang Chai.
Detecting and Tracking Moving Objects for Video Surveillance Isaac Cohen and Gerard Medioni University of Southern California.
CSCE 641: Forward kinematics and inverse kinematics Jinxiang Chai.
Real-time Combined 2D+3D Active Appearance Models Jing Xiao, Simon Baker,Iain Matthew, and Takeo Kanade CVPR 2004 Presented by Pat Chan 23/11/2004.
Announcements Project1 artifact reminder counts towards your grade Demos this Thursday, 12-2:30 sign up! Extra office hours this week David (T 12-1, W/F.
Announcements Project 1 test the turn-in procedure this week (make sure your folder’s there) grading session next Thursday 2:30-5pm –10 minute slot to.
Optical flow and Tracking CISC 649/849 Spring 2009 University of Delaware.
Lecture 19: Optical flow CS6670: Computer Vision Noah Snavely
Motion Estimation Today’s Readings Trucco & Verri, 8.3 – 8.4 (skip 8.3.3, read only top half of p. 199) Numerical Recipes (Newton-Raphson), 9.4 (first.
Matching Compare region of image to region of image. –We talked about this for stereo. –Important for motion. Epipolar constraint unknown. But motion small.
Computational Photography: Image Registration Jinxiang Chai.
CSCE 641 Computer Graphics: Image Registration Jinxiang Chai.
Learning the Appearance of Faces: A Unifying Approach for the Analysis and Synthesis of Images. Thomas Vetter Germany University of Freiburg
A plane-plus-parallax algorithm Basic Model: When FOV is not very large and the camera motion has a small rotation, the 2D displacement (u,v) of an image.
CSC 589 Lecture 22 Image Alignment and least square methods Bei Xiao American University April 13.
Generating panorama using translational movement model.
Digital Camera and Computer Vision Laboratory Department of Computer Science and Information Engineering National Taiwan University, Taipei, Taiwan, R.O.C.
1 Numerical Shape Optimisation in Blow Moulding Hans Groot.
Biointelligence Laboratory, Seoul National University
Optical Flow Donald Tanguay June 12, Outline Description of optical flow General techniques Specific methods –Horn and Schunck (regularization)
Last Lecture (optical center) origin principal point P (X,Y,Z) p (x,y) x y.
1 ECE 738 Paper presentation Paper: Active Appearance Models Author: T.F.Cootes, G.J. Edwards and C.J.Taylor Student: Zhaozheng Yin Instructor: Dr. Yuhen.
Motion estimation Digital Visual Effects Yung-Yu Chuang with slides by Michael Black and P. Anandan.
EECS 274 Computer Vision Motion Estimation.
Ch. 3: Geometric Camera Calibration
Motion Estimation Today’s Readings Trucco & Verri, 8.3 – 8.4 (skip 8.3.3, read only top half of p. 199) Newton's method Wikpedia page
Motion Estimation Today’s Readings Trucco & Verri, 8.3 – 8.4 (skip 8.3.3, read only top half of p. 199) Newton's method Wikpedia page
Representing Moving Images with Layers J. Y. Wang and E. H. Adelson MIT Media Lab.
Motion estimation Digital Visual Effects, Spring 2006 Yung-Yu Chuang 2005/4/12 with slides by Michael Black and P. Anandan.
Optical flow and keypoint tracking Many slides adapted from S. Seitz, R. Szeliski, M. Pollefeys.
Motion estimation Parametric motion (image alignment) Tracking Optical flow.
Motion estimation Digital Visual Effects, Spring 2005 Yung-Yu Chuang 2005/3/23 with slides by Michael Black and P. Anandan.
Lecture 10: Image alignment CS4670/5760: Computer Vision Noah Snavely
Inverse Compositional Spatial Transformer Networks
CPSC 641: Image Registration
Estimating Parametric and Layered Motion
Motion and Optical Flow
Digital Visual Effects Yung-Yu Chuang
Unsupervised Face Alignment by Robust Nonrigid Mapping
Representing Moving Images with Layers
Multiway Cut for Stereo and Motion with Slanted Surfaces
Non-linear Least-Squares
Representing Moving Images with Layers
Structure from Motion with Non-linear Least Squares
Announcements more panorama slots available now
Announcements Questions on the project? New turn-in info online
Lecture 8: Image alignment
Announcements more panorama slots available now
Optical flow Computer Vision Spring 2019, Lecture 21
Structure from Motion with Non-linear Least Squares
Presentation transcript:

Lucas-Kanade Image Alignment Iain Matthews

Paper Reading Simon Baker and Iain Matthews, Lucas-Kanade 20 years on: A Unifying Framework, Part 1 And Project 3 Description

Some operations preserve the range but change the domain of f : What kinds of operations can this perform? Still other operations operate on both the domain and the range of f. Recall - Image Processing Lecture

Face Morphing

Applications of Image Alignment Ubiquitous computer vision technique Mosaicing Tracking Parametric and layered motion estimation Image registration and alignment Face coding / parameterization Super-resolution

Generative Model for an Image Parameterized model ParametersImage shape appearance

Fitting a Model to an Image What are the best model parameters to match an image? ParametersImage shape appearance Nonlinear optimization problem

Region of interest Appearance Shape Active Appearance Model Landmarks Cootes, Edwards, Taylor, 1998 Warp to reference

Image Alignment Image, I(x) Warp, W(x;p) Template, T(x) Image coordinates x = (x, y) T Warp parameters, p = (p 1, p 2, …, p n ) T Warp, W(x;p+  p)

Want to: Minimize the Error Warp image to get compute Template, T(x) Warped, I(W(x;p)) T(x) - I(W(x;p))

How to: Minimize the Error Minimise SSD with respect to p, Solution: solve for increments to current estimate, - = Generally a nonlinear optimisation problem 

Taylor series expansion, linearize function f about x 0 : Linearize For image alignment:

Gradient Descent Solution Least squares problem, solve for  p Solution, Gradient Error Image Jacobian Hessian

Gradient Images Compute image gradient IxIx IyIy W(x;p)W(x;p)W(x;p)W(x;p) I(W(x;p))

Jacobian Compute Jacobian Mesh parameterization Warp, W(x;p) Template, T(x)Image, I(x) Image coordinates x = (x, y) T Warp parameters, p = (p 1, p 2, …, p n ) T = (dx 1, dy 1, …, dx n, dy n ) T =

Lucas-Kanade Algorithm 1.Warp I with W(x;p)  I(W(x;p)) 2.Compute error image T(x) - I(W(x;p)) 3.Warp gradient of I to compute  I 4.Evaluate Jacobian 5.Compute Hessian 6.Compute  p 7.Update parameters p  p   p -= 

Fast Gradient Descent? To reduce Hessian computation: 1.Make Jacobian simple (or constant) 2.Avoid computing gradients on I

Shum-Szeliski Image Aligment Additive Image Alignment – Lucas, Kanade I(x)I(x) W(x;p)W(x;p) T(x)T(x) W(x;p+  p) I(x)I(x) T(x)T(x) W(x;p)W(x;p) I(W(x;p)) W(x;p) o W(x;  p) Compositional Alignment – Shum, Szeliski W(x;p)W(x;p) W(x;0 +  p) = W(x;  p)

I(x)I(x) W(x;p)W(x;p) T(x)T(x) W(x;p)W(x;p) I(W(x;p)) W(x;p) o W(x;  p) Compositional Image Alignment Minimise, Jacobian is constant, evaluated at (x, 0)  “simple”.

Compositional Algorithm 1.Warp I with W(x;p)  I(W(x;p)) 2.Compute error image T(x) - I(W(x;p)) 3.Warp gradient of I to compute  I 4.Evaluate Jacobian 5.Compute Hessian 6.Compute  p 7.Update W(x;p)  W(x;p) o W(x;  p) -= 

Inverse Compositional Why compute updates on I? Can we reverse the roles of the images? Yes! [Baker, Matthews CMU-RI-TR-01-03] Proof that algorithms take the same steps (to first order)

I(x)I(x) W(x;p)W(x;p) T(x)T(x) W(x;p)W(x;p) I(W(x;p)) W(x;p) o W(x;  p) Inverse Compositional Forwards compositional I(x)I(x) W(x;p)W(x;p) T(x)T(x) W(x;p)W(x;p) I(W(x;p)) W(x;p) o W(x;  p) -1 Inverse compositional

Inverse Compositional Minimise, Solution Update 

Inverse Compositional Jacobian is constant - evaluated at (x, 0) Gradient of template is constant Hessian is constant Can pre-compute everything but error image!

Inverse Compositional Algorithm 1.Warp I with W(x;p)  I(W(x;p)) 2.Compute error image T(x) - I(W(x;p)) 3.Warp gradient of I to compute  I 4.Evaluate Jacobian 5.Compute Hessian 6.Compute  p 7.Update W(x;p)  W(x;p) o W(x;  p) -1 -= 

Framework Baker and Matthews 2003 Formulated framework, proved equivalence AlgorithmCan be applied toEfficient?Authors Forwards Additive AnyNoLucas, Kanade Forwards Compositional Any semi-groupNoShum, Szeliski Inverse Compositional Any groupYesBaker, Matthews Inverse AdditiveSimple linear 2D+Yes Hager, Belhumeur

Example