CSCE643: Computer Vision Mean-Shift Object Tracking Jinxiang Chai Many slides from Yaron Ukrainitz & Bernard Sarel & Robert Collins.

Slides:



Advertisements
Similar presentations
Real-Time Template Tracking
Advertisements

CSCE 643 Computer Vision: Template Matching, Image Pyramids and Denoising Jinxiang Chai.
CSCE 643 Computer Vision: Lucas-Kanade Registration
Optimizing and Learning for Super-resolution
CSCE643: Computer Vision Bayesian Tracking & Particle Filtering Jinxiang Chai Some slides from Stephen Roth.
Image Repairing: Robust Image Synthesis by Adaptive ND Tensor Voting IEEE Computer Society Conference on Computer Vision and Pattern Recognition Jiaya.
Principal Component Analysis Based on L1-Norm Maximization Nojun Kwak IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008.
11/11/02 IDR Workshop Dealing With Location Uncertainty in Images Hasan F. Ates Princeton University 11/11/02.
Introduction To Tracking
Forward-Backward Correlation for Template-Based Tracking Xiao Wang ECE Dept. Clemson University.
Robust Object Tracking via Sparsity-based Collaborative Model
Instructor: Mircea Nicolescu Lecture 13 CS 485 / 685 Computer Vision.
Visual Recognition Tutorial
Lecture 5 Template matching
Modeling Pixel Process with Scale Invariant Local Patterns for Background Subtraction in Complex Scenes (CVPR’10) Shengcai Liao, Guoying Zhao, Vili Kellokumpu,
Mean Shift A Robust Approach to Feature Space Analysis Kalyan Sunkavalli 04/29/2008 ES251R.
Real-time Embedded Face Recognition for Smart Home Fei Zuo, Student Member, IEEE, Peter H. N. de With, Senior Member, IEEE.
Region Segmentation. Find sets of pixels, such that All pixels in region i satisfy some constraint of similarity.
Mean Shift Theory and Applications
Mean-Shift Algorithm and Its Application Bohyung Han
Vision Topics Seminar Mean Shift
Motion Analysis (contd.) Slides are from RPI Registration Class.
Announcements Quiz Thursday Quiz Review Tomorrow: AV Williams 4424, 4pm. Practice Quiz handout.
Segmentation Divide the image into segments. Each segment:
Optical flow and Tracking CISC 649/849 Spring 2009 University of Delaware.
Texture Reading: Chapter 9 (skip 9.4) Key issue: How do we represent texture? Topics: –Texture segmentation –Texture-based matching –Texture synthesis.
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.
Pattern Recognition. Introduction. Definitions.. Recognition process. Recognition process relates input signal to the stored concepts about the object.
Matching Compare region of image to region of image. –We talked about this for stereo. –Important for motion. Epipolar constraint unknown. But motion small.
Dorin Comaniciu Visvanathan Ramesh (Imaging & Visualization Dept., Siemens Corp. Res. Inc.) Peter Meer (Rutgers University) Real-Time Tracking of Non-Rigid.
CSCE 641 Computer Graphics: Image Registration Jinxiang Chai.
Scale-Invariant Feature Transform (SIFT) Jinxiang Chai.
Radial Basis Function Networks
Image Segmentation Image segmentation is the operation of partitioning an image into a collection of connected sets of pixels. 1. into regions, which usually.
Computer Vision Spring ,-685 Instructor: S. Narasimhan Wean Hall 5409 T-R 10:30am – 11:50am.
Computer Vision James Hays, Brown
Mean Shift : A Robust Approach Toward Feature Space Analysis - Bayesian Background Modeling
Feature and object tracking algorithms for video tracking Student: Oren Shevach Instructor: Arie nakhmani.
Prakash Chockalingam Clemson University Non-Rigid Multi-Modal Object Tracking Using Gaussian Mixture Models Committee Members Dr Stan Birchfield (chair)
Mean-shift and its application for object tracking
1 Interest Operators Harris Corner Detector: the first and most basic interest operator Kadir Entropy Detector and its use in object recognition SIFT interest.
1 Mean shift and feature selection ECE 738 course project Zhaozheng Yin Spring 2005 Note: Figures and ideas are copyrighted by original authors.
Mean Shift Theory and Applications Reporter: Zhongping Ji.
7.1. Mean Shift Segmentation Idea of mean shift:
ALIGNMENT OF 3D ARTICULATE SHAPES. Articulated registration Input: Two or more 3d point clouds (possibly with connectivity information) of an articulated.
CSE 185 Introduction to Computer Vision Pattern Recognition 2.
EECS 274 Computer Vision Segmentation by Clustering II.
CSCE 643 Computer Vision: Extractions of Image Features Jinxiang Chai.
Non-Euclidean Example: The Unit Sphere. Differential Geometry Formal mathematical theory Work with small ‘patches’ –the ‘patches’ look Euclidean Do calculus.
CS654: Digital Image Analysis Lecture 25: Hough Transform Slide credits: Guillermo Sapiro, Mubarak Shah, Derek Hoiem.
CS654: Digital Image Analysis Lecture 30: Clustering based Segmentation Slides are adapted from:
ECE 8443 – Pattern Recognition ECE 8527 – Introduction to Machine Learning and Pattern Recognition LECTURE 07: BAYESIAN ESTIMATION (Cont.) Objectives:
Boosted Particle Filter: Multitarget Detection and Tracking Fayin Li.
EECS 274 Computer Vision Tracking. Motivation: Obtain a compact representation from an image/motion sequence/set of tokens Should support application.
Real-Time Tracking with Mean Shift Presented by: Qiuhua Liu May 6, 2005.
Image Segmentation Shengnan Wang
Mean Shift ; Theory and Applications Presented by: Reza Hemati دی 89 December گروه بینایی ماشین و پردازش تصویر Machine Vision and Image Processing.
研 究 生:周暘庭 Q36994477 電腦與通信工程研究所 通訊與網路組 指導教授 :楊家輝 Mean-Shift-Based Color Tracking in Illuminance Change.
Lecture 30: Segmentation CS4670 / 5670: Computer Vision Noah Snavely From Sandlot ScienceSandlot Science.
Course Introduction to Medical Imaging Segmentation 1 – Mean Shift and Graph-Cuts Guy Gilboa.
1 C.A.L. Bailer-Jones. Machine Learning. Data exploration and dimensionality reduction Machine learning, pattern recognition and statistical data modelling.
CSSE463: Image Recognition Day 21
A segmentation and tracking algorithm
Image Segmentation Techniques
CSSE463: Image Recognition Day 23
PRAKASH CHOCKALINGAM, NALIN PRADEEP, AND STAN BIRCHFIELD
Announcements Questions on the project? New turn-in info online
CSSE463: Image Recognition Day 23
Mean Shift Theory and Applications
CSSE463: Image Recognition Day 23
Presentation transcript:

CSCE643: Computer Vision Mean-Shift Object Tracking Jinxiang Chai Many slides from Yaron Ukrainitz & Bernard Sarel & Robert Collins

Appearance-based Tracking Slide from Collins

Review: Lucas-Kanade Tracking/Registration Key Idea #1: Formulate the tracking/registration as a nonlinear least square minimization problem

Review: Lucas-Kanade Tracking/Registration Key Idea #2: Solve the problem with Gauss-Newton optimization techniques

Review: Gauss-Newton Optimization Rearrange

Review: Gauss-Newton Optimization

Rearrange Ab

Review: Gauss-Newton Optimization Rearrange A ATbATb b (A T A) -1

Lucas-Kanade Registration Initialize p=p 0 : Iterate: 1. Warp I with w(x;p) to compute I(w(x;p))

Lucas-Kanade Registration Initialize p=p 0 : Iterate: 1. Warp I with w(x;p) to compute I(w(x;p)) 2. Compute the error image

Lucas-Kanade Registration Initialize p=p 0 : Iterate: 1. Warp I with w(x;p) to compute I(w(x;p)) 2. Compute the error image 3. Warp the gradient with w(x;p)

Lucas-Kanade Registration Initialize p=p 0 : Iterate: 1. Warp I with w(x;p) to compute I(w(x;p)) 2. Compute the error image 3. Warp the gradient with w(x;p) 4. Evaluate the Jacobian at (x;p)

Lucas-Kanade Registration Initialize p=p 0 : Iterate: 1. Warp I with w(x;p) to compute I(w(x;p)) 2. Compute the error image 3. Warp the gradient with w(x;p) 4. Evaluate the Jacobian at (x;p) 5. Compute the using linear system solvers

Lucas-Kanade Registration Initialize p=p 0 : Iterate: 1. Warp I with w(x;p) to compute I(w(x;p)) 2. Compute the error image 3. Warp the gradient with w(x;p) 4. Evaluate the Jacobian at (x;p) 5. Compute the using linear system solvers 6. Update the parameters

Object Tracking Can we apply Lucas-Kanade techniques to non- rigid objects (e.g., a walking person)?

Motivation of Mean Shift Tracking To track non-rigid objects (e.g., a walking person), it is hard to specify an explicit 2D parametric motion model. Appearances of non-rigid objects can sometimes be modeled with color distributions

Mean-Shift Tracking The mean-shift algorithm is an efficient approach to tracking objects whose appearance is defined by histograms. - not limited to only color, however. - Could also use edge orientation, texture motion Slide from Robert Collins

Mean Shift Tracking: Demos

Mean Shift Mean Shift [Che98, FH75, Sil86] - An algorithm that iteratively shifts a data point to the average of data points in its neighborhood. - Similar to clustering. - Useful for clustering, mode seeking, probability density estimation, tracking, etc.

Mean Shift Reference Y. Cheng. Mean shift, mode seeking, and clustering. IEEE Trans. on Pattern Analysis and Machine Intelligence, 17(8):790–799, K. Fukunaga and L. D. Hostetler. The estimation of the gradient of a density function, with applications in pattern recognition. IEEE Trans. on Information Theory, 21:32– 40, B. W. Silverman. Density Estimation for Statistics and Data Analysis. Chapman and Hall, 1986.

Mean Shift Theory

Intuitive Description Distribution of identical billiard balls Region of interest Center of mass Mean Shift vector Objective : Find the densest region

Intuitive Description Distribution of identical billiard balls Region of interest Center of mass Mean Shift vector Objective : Find the densest region

Intuitive Description Distribution of identical billiard balls Region of interest Center of mass Mean Shift vector Objective : Find the densest region

Intuitive Description Distribution of identical billiard balls Region of interest Center of mass Mean Shift vector Objective : Find the densest region

Intuitive Description Distribution of identical billiard balls Region of interest Center of mass Mean Shift vector Objective : Find the densest region

Intuitive Description Distribution of identical billiard balls Region of interest Center of mass Mean Shift vector Objective : Find the densest region

Intuitive Description Distribution of identical billiard balls Region of interest Center of mass Objective : Find the densest region

What is Mean Shift ? Non-parametric Density Estimation Non-parametric Density GRADIENT Estimation (Mean Shift) Data Discrete PDF Representation PDF Analysis PDF in feature space Color space Scale space Actually any feature space you can conceive … A tool for: Finding modes in a set of data samples, manifesting an underlying probability density function (PDF) in R N

Non-Parametric Density Estimation Assumption : The data points are sampled from an underlying PDF Assumed Underlying PDFReal Data Samples Data point density implies PDF value !

Assumed Underlying PDFReal Data Samples Non-Parametric Density Estimation

Assumed Underlying PDFReal Data Samples ? Non-Parametric Density Estimation

Parametric Density Estimation Assumption : The data points are sampled from an underlying PDF Assumed Underlying PDF Estimate Real Data Samples

Kernel Density Estimation Parzen Windows - General Framework Kernel Properties: Normalized Symmetric Exponential weight decay ??? A function of some finite number of data points x 1 …x n Data

Kernel Density Estimation Parzen Windows - Function Forms A function of some finite number of data points x 1 …x n Data In practice one uses the forms: or Same function on each dimensionFunction of vector length only

Kernel Density Estimation Various Kernels A function of some finite number of data points x 1 …x n Examples: Epanechnikov Kernel Uniform Kernel Normal Kernel Data

Kernel Density Estimation Gradient Give up estimating the PDF ! Estimate ONLY the gradient Using the Kernel form: We get : Size of window

Kernel Density Estimation Gradient Computing The Mean Shift

Yet another Kernel density estimation ! Simple Mean Shift procedure: Compute mean shift vector Translate the Kernel window by m(x)

Mean Shift Mode Detection Updated Mean Shift Procedure: Find all modes using the Simple Mean Shift Procedure Prune modes by perturbing them (find saddle points and plateaus) Prune nearby – take highest mode in the window What happens if we reach a saddle point ? Perturb the mode position and check if we return back

Mean Shift Strengths & Weaknesses Strengths : Application independent tool Suitable for real data analysis Does not assume any prior shape (e.g. elliptical) on data clusters Can handle arbitrary feature spaces Only ONE parameter to choose h (window size) has a physical meaning, unlike K-Means Weaknesses : The window size (bandwidth selection) is not trivial Inappropriate window size can cause modes to be merged, or generate additional “shallow” modes  Use adaptive window size

Mean Shift Applications

D. Comaniciu, V. Ramesh, and P. Meer. Real-time tracking of non-rigid objects using mean shift. In IEEE Proc. on Computer Vision and Pattern Recognition, pages 673–678, (Best paper award) Journal version: Kernel-Based Object Tracking, PAMI, 2003.Kernel-Based Object Tracking Mean Shift Object Tracking

Non-Rigid Object Tracking … …

Real-Time SurveillanceDriver Assistance Object-Based Video Compression

Current frame …… Mean-Shift Object Tracking General Framework: Target Representation Choose a feature space Represent the model in the chosen feature space Choose a reference model in the current frame

Mean-Shift Object Tracking General Framework: Target Localization Search in the model’s neighborhood in next frame Start from the position of the model in the current frame Find best candidate by maximizing a similarity func. Repeat the same process in the next pair of frames Current frame …… ModelCandidate

Mean-Shift Object Tracking Target Representation Choose a reference target model Quantized Color Space Choose a feature space Represent the model by its PDF in the feature space Kernel Based Object Tracking, by Comaniniu, Ramesh, Meer

Mean-Shift Object Tracking PDF Representation Similarity Function: Target Model (centered at 0) Target Candidate (centered at y)

Mean-Shift Object Tracking Smoothness of Similarity Function Similarity Function: Problem: Target is represented by color info only Spatial info is lost Solution: Mask the target with an isotropic kernel in the spatial domain f(y) becomes smooth in y f is not smooth Gradient- based optimizations are not robust Large similarity variations for adjacent locations

Mean-Shift Object Tracking Finding the PDF of the target model Target pixel locations A differentiable, isotropic, convex, monotonically decreasing kernel Peripheral pixels are affected by occlusion and background interference The color bin index (1..m) of pixel x Normalization factor Pixel weight Probability of feature u in model Probability of feature u in candidate Normalization factor Pixel weight 0 model y candidate

Mean-Shift Object Tracking Similarity Function Target model: Target candidate: Similarity function: 1 1 The Bhattacharyya Coefficient

Mean-Shift Object Tracking Target Localization Algorithm Start from the position of the model in the current frame Search in the model’s neighborhood in next frame Find best candidate by maximizing a similarity func.

Mean-Shift Object Tracking Function Optimization Or

Mean-Shift Object Tracking Function Optimization Or This is similar to Lucas Kanade registration! - we can use gradient based optimization techniques to solve the problem.

Mean-Shift Object Tracking Function Optimization Or Mean Shift provides an efficient way to optimize the function!

Linear approx. (around y 0 ) Mean-Shift Object Tracking Approximating the Similarity Function Model location: Candidate location: Independent of y Density estimate! (as a function of y)

Mean-Shift Object Tracking Maximizing the Similarity Function The mode of = sought maximum Important Assumption: One mode in the searched neighborhood The target representation provides sufficient discrimination

Mean-Shift Object Tracking Applying Mean-Shift Original Mean-Shift: Find mode ofusing The mode of = sought maximum Extended Mean-Shift: Find mode of using

Mean-Shift Object Tracking About Kernels and Profiles A special class of radially symmetric kernels: The profile of kernel K Extended Mean-Shift: Find mode of using

Mean-Shift Object Tracking Choosing the Kernel Epanechnikov kernel: A special class of radially symmetric kernels: Extended Mean-Shift: Uniform kernel:

Mean-Shift Object Tracking Adaptive Scale Problem: The scale of the target changes in time The scale (h) of the kernel must be adapted Solution: Run localization 3 times with different h Choose h that achieves maximum similarity

Mean-Shift Object Tracking Results Feature space: 16  16  16 quantized RGB Target: manually selected on 1 st frame Average mean-shift iterations: 4

Mean-Shift Object Tracking Results Partial occlusion DistractionMotion blur

Mean-Shift Object Tracking Results

Mean-Shift Object Tracking Summary

Key idea #1: Formulate the tracking problem as nonlinear optimization by maximizing appearance/histogram consistency between target and template. Mean-Shift Object Tracking Summary

Key idea #2: Solving the optimization problem with mean-shift techniques Mean-Shift Object Tracking Summary

How to deal with scaling and rotation? Mean-Shift Object Tracking Discussion