Dorin Comaniciu Visvanathan Ramesh (Imaging & Visualization Dept., Siemens Corp. Res. Inc.) Peter Meer (Rutgers University) Real-Time Tracking of Non-Rigid.

Slides:



Advertisements
Similar presentations
Pattern Recognition and Machine Learning
Advertisements

Pseudo-Relevance Feedback For Multimedia Retrieval By Rong Yan, Alexander G. and Rong Jin Mwangi S. Kariuki
Introduction to Non Parametric Statistics Kernel Density Estimation.
CSCE643: Computer Vision Mean-Shift Object Tracking Jinxiang Chai Many slides from Yaron Ukrainitz & Bernard Sarel & Robert Collins.
CSCE643: Computer Vision Bayesian Tracking & Particle Filtering Jinxiang Chai Some slides from Stephen Roth.
Principal Component Analysis Based on L1-Norm Maximization Nojun Kwak IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008.
Lecture Notes for E Alpaydın 2010 Introduction to Machine Learning 2e © The MIT Press (V1.0) ETHEM ALPAYDIN © The MIT Press, 2010
Dynamic Occlusion Analysis in Optical Flow Fields
Pattern Recognition and Machine Learning: Kernel Methods.
Maximum Likelihood And Expectation Maximization Lecture Notes for CMPUT 466/551 Nilanjan Ray.
1 Approximated tracking of multiple non-rigid objects using adaptive quantization and resampling techniques. J. M. Sotoca 1, F.J. Ferri 1, J. Gutierrez.
Introduction To Tracking
Robust Foreground Detection in Video Using Pixel Layers Kedar A. Patwardhan, Guillermoo Sapire, and Vassilios Morellas IEEE TRANSACTION ON PATTERN ANAYLSIS.
A Nonparametric Treatment for Location/Segmentation Based Visual Tracking Le Lu Integrated Data Systems Dept. Siemens Corporate Research, Inc. Greg Hager.
Robust Object Tracking via Sparsity-based Collaborative Model
Automatic Identification of Bacterial Types using Statistical Image Modeling Sigal Trattner, Dr. Hayit Greenspan, Prof. Shimon Abboud Department of Biomedical.
A KLT-Based Approach for Occlusion Handling in Human Tracking Chenyuan Zhang, Jiu Xu, Axel Beaugendre and Satoshi Goto 2012 Picture Coding Symposium.
Visual Recognition Tutorial
Modeling Pixel Process with Scale Invariant Local Patterns for Background Subtraction in Complex Scenes (CVPR’10) Shengcai Liao, Guoying Zhao, Vili Kellokumpu,
Boundary matting for view synthesis Samuel W. Hasinoff Sing Bing Kang Richard Szeliski Computer Vision and Image Understanding 103 (2006) 22–32.
Mean Shift A Robust Approach to Feature Space Analysis Kalyan Sunkavalli 04/29/2008 ES251R.
Mean Shift Theory and Applications
Mean-Shift Algorithm and Its Application Bohyung Han
Image processing. Image operations Operations on an image –Linear filtering –Non-linear filtering –Transformations –Noise removal –Segmentation.
Vision Topics Seminar Mean Shift
Adaptive Rao-Blackwellized Particle Filter and It’s Evaluation for Tracking in Surveillance Xinyu Xu and Baoxin Li, Senior Member, IEEE.
1 Integration of Background Modeling and Object Tracking Yu-Ting Chen, Chu-Song Chen, Yi-Ping Hung IEEE ICME, 2006.
Pattern Recognition. Introduction. Definitions.. Recognition process. Recognition process relates input signal to the stored concepts about the object.
Face Processing System Presented by: Harvest Jang Group meeting Fall 2002.
Jacinto C. Nascimento, Member, IEEE, and Jorge S. Marques
Lecture II-2: Probability Review
Image Segmentation Image segmentation is the operation of partitioning an image into a collection of connected sets of pixels. 1. into regions, which usually.
Binary Variables (1) Coin flipping: heads=1, tails=0 Bernoulli Distribution.
Image Segmentation Rob Atlas Nick Bridle Evan Radkoff.
Computer vision.
Computer Vision James Hays, Brown
Mean Shift : A Robust Approach Toward Feature Space Analysis - Bayesian Background Modeling
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 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.
Region Segmentation Readings: Chapter 10: 10.1 Additional Materials Provided K-means Clustering (text) EM Clustering (paper) Graph Partitioning (text)
7.1. Mean Shift Segmentation Idea of mean shift:
Tag Ranking Present by Jie Xiao Dept. of Computer Science Univ. of Texas at San Antonio.
CSE 185 Introduction to Computer Vision Pattern Recognition 2.
報告人 : 林福城 指導老師 : 陳定宏 1 From Res. Center of Intell. Transp. Syst., Beijing Univ. of Technol., Beijing, China By Zhe Liu ; Yangzhou Chen ; Zhenlong Li Appears.
ECE 8443 – Pattern Recognition LECTURE 07: MAXIMUM LIKELIHOOD AND BAYESIAN ESTIMATION Objectives: Class-Conditional Density The Multivariate Case General.
EECS 274 Computer Vision Segmentation by Clustering II.
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 30: Clustering based Segmentation Slides are adapted from:
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
 Present by 陳群元.  Introduction  Previous work  Predicting motion patterns  Spatio-temporal transition distribution  Discerning pedestrians  Experimental.
Mean Shift ; Theory and Applications Presented by: Reza Hemati دی 89 December گروه بینایی ماشین و پردازش تصویر Machine Vision and Image Processing.
ECE 8443 – Pattern Recognition ECE 8527 – Introduction to Machine Learning and Pattern Recognition LECTURE 12: Advanced Discriminant Analysis Objectives:
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.
1 Chapter 8: Model Inference and Averaging Presented by Hui Fang.
MOTION Model. Road Map Motion Model Non Parametric Motion Field : Algorithms 1.Optical flow field estimation. 2.Block based motion estimation. 3.Pel –recursive.
Zhaoxia Fu, Yan Han Measurement Volume 45, Issue 4, May 2012, Pages 650–655 Reporter: Jing-Siang, Chen.
Edge Detection using Mean Shift Smoothing
LECTURE 11: Advanced Discriminant Analysis
Linear Filters and Edges Chapters 7 and 8
Boosting and Additive Trees (2)
A segmentation and tracking algorithm
PRAKASH CHOCKALINGAM, NALIN PRADEEP, AND STAN BIRCHFIELD
Outline Texture modeling - continued Julesz ensemble.
LECTURE 09: BAYESIAN LEARNING
Mean Shift Theory and Applications
Presentation transcript:

Dorin Comaniciu Visvanathan Ramesh (Imaging & Visualization Dept., Siemens Corp. Res. Inc.) Peter Meer (Rutgers University) Real-Time Tracking of Non-Rigid Objects using Mean Shift

Outline Introduction Introduction Mean Shift Analysis Mean Shift Analysis Tracking Algorithm Tracking Algorithm Experiments Experiments Conclusion Conclusion 2

Outline Introduction Introduction Mean Shift Analysis Mean Shift Analysis Tracking Algorithm Tracking Algorithm Experiments Experiments Conclusion Conclusion 3

Introduction The proposed tracking is appropriate for a large variety of objects with different color/texture patterns. The proposed tracking is appropriate for a large variety of objects with different color/texture patterns. The mean shift iterations are employed to find the target candidate that is the most similar to a given target model, with the similarity being expressed by a metric based on the Bhattacharyya coefficient The mean shift iterations are employed to find the target candidate that is the most similar to a given target model, with the similarity being expressed by a metric based on the Bhattacharyya coefficient 4

Outline Introduction Introduction Mean Shift Analysis Mean Shift Analysis Tracking Algorithm Tracking Algorithm Experiments Experiments Conclusion Conclusion 5

Sample Mean Shift

Kernel Density Estimation Multivariate kernel density estimation Multivariate kernel density estimation Kernels Kernels –Gaussian –Epanechnikov

Kernel Density Estimation(2) In statistics, kernel density estimation (KDE) is a non-parametric way to estimate the probability density function (PDF)of a random variable In statistics, kernel density estimation (KDE) is a non-parametric way to estimate the probability density function (PDF)of a random variable Kernel: In non-parametric statistics, a kernel is a weighting function used in non-parametric estimation techniques. Kernels are used in kernel density estimation to estimate random variables' density functions Kernel: In non-parametric statistics, a kernel is a weighting function used in non-parametric estimation techniques. Kernels are used in kernel density estimation to estimate random variables' density functions 8

Nonparametric statistics Nonparametric statistics are statistics not based on parameterized families of probability distributions Nonparametric statistics are statistics not based on parameterized families of probability distributions 9

Non-parametric models(1) A histogram is a simple nonparametric estimate of a probability distribution. A histogram is a simple nonparametric estimate of a probability distribution. Kernel density estimation provides better estimates of the density than histograms. Kernel density estimation provides better estimates of the density than histograms.

Non-parametric models(2) Kernel density estimates are closely related to histograms, but can be endowed with properties such as smoothness or continuity by using a suitable kernel Kernel density estimates are closely related to histograms, but can be endowed with properties such as smoothness or continuity by using a suitable kernel

Histogram VS Kernel Density Estimators using these 6 data points: x1 = −2.1, x2 = −1.3, x3 = −0.4, x4 = 1.9, x5 = 5.1, x6 = bins each of width 2(left Histogram) normal kernel with variance 2.25 (indicated by the red dashed lines)(right KDE)

Kernel and Kernel Profile(1) The kernel density estimator The kernel density estimator A special class of radially symmetric kernels A special class of radially symmetric kernels where c k makes K(x) integrate to 1. where c k makes K(x) integrate to 1. k(·) is called profile k(·) is called profile

Kernel and Kernel Profile(2) We can use profile to describe the estimator We can use profile to describe the estimator

Derivative Kernel and Profile Define the derivative of the kernel profile Define the derivative of the kernel profile The kernel corresponding to g(x) is The kernel corresponding to g(x) is The kernel K(x) is called the shadow of G(x) The kernel K(x) is called the shadow of G(x)

Density Gradient Estimation Let’s compute the gradient of the kernel estimate Let’s compute the gradient of the kernel estimate

Mean-Shift Vector(1) Look at this Look at this which is the kernel density estimator using kernel g(·) So we have I In other words,

Mean-Shift Vector(2) We can treat ∇ pK (x)/pG (x) as a normalized density gradient estimate We can treat ∇ pK (x)/pG (x) as a normalized density gradient estimate Local mean − → large density change Local mean − → large density change Shift

Outline Introduction Introduction Mean Shift Analysis Mean Shift Analysis Tracking Algorithm Tracking Algorithm Experiments Experiments Conclusion Conclusion 19

Non-Rigid Object Tracking … …

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 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 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.

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) Bhattacharyya coefficient

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 Bhattacharyya Coefficient Maximization Algorithm

Outline Introduction Introduction Mean Shift Analysis Mean Shift Analysis Tracking Algorithm Tracking Algorithm Experiments Experiments Conclusion Conclusion 31

Mean-Shift Object Tracking Results Feature space: RGB space with 32  32  32 bins Target: manually selected on 1 st frame Average mean-shift iterations: frames of 352 X 240 pixels

Mean-Shift Object Tracking Results Partial occlusion(#105) Distraction(#140) Motion blur(#150)

Outline Introduction Introduction Mean Shift Analysis Mean Shift Analysis Tracking Algorithm Tracking Algorithm Experiments Experiments Conclusion Conclusion 34

Conclusion By exploiting the spatial gradient of the statistical measure (Bhattacharyya Coefficient) the new method achieves real-time tracking performance, while effectively rejecting background clutter and partial occlusions. By exploiting the spatial gradient of the statistical measure (Bhattacharyya Coefficient) the new method achieves real-time tracking performance, while effectively rejecting background clutter and partial occlusions. 35