Real-Time Tracking with Mean Shift Presented by: Qiuhua Liu May 6, 2005.

Slides:



Advertisements
Similar presentations
Clustering. How are we doing on the pass sequence? Pretty good! We can now automatically learn the features needed to track both people But, it sucks.
Advertisements

Clustering k-mean clustering Genome 559: Introduction to Statistical and Computational Genomics Elhanan Borenstein.
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.
Introduction To Tracking
Visual Tracking CMPUT 615 Nilanjan Ray. What is Visual Tracking Following objects through image sequences or videos Sometimes we need to track a single.
Robust Foreground Detection in Video Using Pixel Layers Kedar A. Patwardhan, Guillermoo Sapire, and Vassilios Morellas IEEE TRANSACTION ON PATTERN ANAYLSIS.
Foreground Modeling The Shape of Things that Came Nathan Jacobs Advisor: Robert Pless Computer Science Washington University in St. Louis.
A KLT-Based Approach for Occlusion Handling in Human Tracking Chenyuan Zhang, Jiu Xu, Axel Beaugendre and Satoshi Goto 2012 Picture Coding Symposium.
Nalin Pradeep Senthamil Masters Student, ECE Dept. Advisor, Dr Stan Birchfield Committee Members, Dr Adam Hoover, Dr Brian Dean.
A Robust Pedestrian Detection Approach Based on Shapelet Feature and Haar Detector Ensembles Wentao Yao, Zhidong Deng TSINGHUA SCIENCE AND TECHNOLOGY ISSNl.
Visual Recognition Tutorial
Lecture 6 Image Segmentation
Learning to Detect A Salient Object Reporter: 鄭綱 (3/2)
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
Tracking with Online Appearance Model Bohyung Han
Vision Topics Seminar Mean Shift
Announcements Project 2 more signup slots questions Picture taking at end of class.
Prénom Nom Document Analysis: Data Analysis and Clustering Prof. Rolf Ingold, University of Fribourg Master course, spring semester 2008.
Clustering Color/Intensity
1 Integration of Background Modeling and Object Tracking Yu-Ting Chen, Chu-Song Chen, Yi-Ping Hung IEEE ICME, 2006.
Multi-camera Video Surveillance: Detection, Occlusion Handling, Tracking and Event Recognition Oytun Akman.
Pattern Recognition. Introduction. Definitions.. Recognition process. Recognition process relates input signal to the stored concepts about the object.
Dorin Comaniciu Visvanathan Ramesh (Imaging & Visualization Dept., Siemens Corp. Res. Inc.) Peter Meer (Rutgers University) Real-Time Tracking of Non-Rigid.
Clustering with Bregman Divergences Arindam Banerjee, Srujana Merugu, Inderjit S. Dhillon, Joydeep Ghosh Presented by Rohit Gupta CSci 8980: Machine Learning.
~5,617,000 population in each state
Image Segmentation Image segmentation is the operation of partitioning an image into a collection of connected sets of pixels. 1. into regions, which usually.
Image Segmentation Rob Atlas Nick Bridle Evan Radkoff.
Methods in Medical Image Analysis Statistics of Pattern Recognition: Classification and Clustering Some content provided by Milos Hauskrecht, University.
Computer Vision James Hays, Brown
Mean Shift : A Robust Approach Toward Feature Space Analysis - Bayesian Background Modeling
Mean-shift and its application for object tracking
Introduction and Motivation Approaches for DE: Known model → parametric approach: p(x;θ) (Gaussian, Laplace,…) Unknown model → nonparametric approach Assumes.
Visual Tracking Decomposition Junseok Kwon* and Kyoung Mu lee Computer Vision Lab. Dept. of EECS Seoul National University, Korea Homepage:
Mean Shift Theory and Applications Reporter: Zhongping Ji.
A General Framework for Tracking Multiple People from a Moving Camera
Region Segmentation Readings: Chapter 10: 10.1 Additional Materials Provided K-means Clustering (text) EM Clustering (paper) Graph Partitioning (text)
CSE 185 Introduction to Computer Vision Pattern Recognition 2.
Remote Sensing Supervised Image Classification. Supervised Image Classification ► An image classification procedure that requires interaction with the.
EECS 274 Computer Vision Segmentation by Clustering II.
December 9, 2014Computer Vision Lecture 23: Motion Analysis 1 Now we will talk about… Motion Analysis.
A Region Based Stereo Matching Algorithm Using Cooperative Optimization Zeng-Fu Wang, Zhi-Gang Zheng University of Science and Technology of China Computer.
Non-Euclidean Example: The Unit Sphere. Differential Geometry Formal mathematical theory Work with small ‘patches’ –the ‘patches’ look Euclidean Do calculus.
MACHINE LEARNING 8. Clustering. Motivation Based on E ALPAYDIN 2004 Introduction to Machine Learning © The MIT Press (V1.1) 2  Classification problem:
CS654: Digital Image Analysis Lecture 30: Clustering based Segmentation Slides are adapted from:
Boosted Particle Filter: Multitarget Detection and Tracking Fayin Li.
CSSE463: Image Recognition Day 23 Midterm behind us… Midterm behind us… Foundations of Image Recognition completed! Foundations of Image Recognition completed!
Image Segmentation Shengnan Wang
Image Segmentation Superpixel methods Speaker: Hsuan-Yi Ko.
Mean Shift ; Theory and Applications Presented by: Reza Hemati دی 89 December گروه بینایی ماشین و پردازش تصویر Machine Vision and Image Processing.
Discriminative Training and Machine Learning Approaches Machine Learning Lab, Dept. of CSIE, NCKU Chih-Pin Liao.
ICCV 2007 National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Half Quadratic Analysis for Mean Shift: with Extension.
Local Stereo Matching Using Motion Cue and Modified Census in Video Disparity Estimation Zucheul Lee, Ramsin Khoshabeh, Jason Juang and Truong Q. Nguyen.
Course Introduction to Medical Imaging Segmentation 1 – Mean Shift and Graph-Cuts Guy Gilboa.
Student Gesture Recognition System in Classroom 2.0 Chiung-Yao Fang, Min-Han Kuo, Greg-C Lee, and Sei-Wang Chen Department of Computer Science and Information.
Edge Detection using Mean Shift Smoothing
CSSE463: Image Recognition Day 21
Particle Filtering for Geometric Active Contours
A segmentation and tracking algorithm
Probabilistic Models for Linear Regression
CSSE463: Image Recognition Day 23
KAIST CS LAB Oh Jong-Hoon
Seam Carving Project 1a due at midnight tonight.
Segmentation (continued)
Text Categorization Berlin Chen 2003 Reference:
CSSE463: Image Recognition Day 23
Mean Shift Theory and Applications
CSSE463: Image Recognition Day 23
Presentation transcript:

Real-Time Tracking with Mean Shift Presented by: Qiuhua Liu May 6, 2005

Outline Color model for the target Introduction to mean-shift Tracking algorithm with mean shift Compassion with Particle Filter algorithm with the similar color model

Color Model for the Target The target is represented by an ellipsoidal region in the image, normalized to a unit circle. Let be the normalized pixel locations in the region centered at 0. The probability of the feature(color) of the target was modeled by the its histogram with kernel : The kernel has a convex and monotonic decreasing kernel profile, assigning small weights to pixels farther away from the center.

The profile of kernel is defined as a function such that Let be the normalized pixel locations of the target candidates, centered at y in the current frame. The target candidate is modeled as: Target Candidate

Similarity Function The similarity function is defined as the metric distance between the candidate and the target model: Choose as the Bhattacharyya coefficients (it is a divergence type measure) Minimizing the distance is equivalent to maximizing.

Maximization with Mean Shift Assume the target candidate histogram does not change drastically, using Taylor expansion around the values at location : Only need to maximize the second term, which is the density estimate with kernel profile k(x) at y in the current frame, with the data being weighted by w i. where

Mean Shift First Introduced by Fukunaga and Hostetler in 1975 [1], Mean shift is a non-parametric, iterative procedure to find the mode of a density function represented by a set of samples and a Kernel K : d: dimension of data; h: band width. With the definition of the Profile of a kernel:

With mean shift method, the kernel is recursively moved from the current location to the new location until converge with: For a kernel with a convex and monotonic decreasing kernel profile, it is guaranteed to converge (to local maxima) where Mean Shift

The Epanechnikov kernel has a profile: Then where c d is the volume of the unit d -dimensional sphere. One Normally Used Kernel (*)

Tracking Algorithm with Mean Shift Very Simple: Given the target model and its location in the previous frame. 1. Initialize the location at the current frame with. 2. Compute the next location according to (*). 3. Iterate 1 and 2 until converge.

Tracked Result:

Mean Shift Maximization:

Summary and Comparison to Particle Filter Method Advantage: Good color histogram model and distance measure. Deterministic method: the mean shift usually converged at 2 to 3 iterations – Fast. Disadvantage: Sometimes get stuck at local minimum. Difficult to handle abrupt motion: Due to use of the kernels, the center of the target in the current frame has to be covered by the target model in the previous frame. Otherwise, the local maximum of the Bhattacharyya coefficient would not be a reliable indicator.

Connection to Particle Filter Tracking Adopting the same distance measure, Jaco Vermaak [4][5] proposed the following observation likelihood function for probabilistic tracking with particle filters and VB inference : The histogram does not necessarily need a kernel.

Comparison Top: Deterministic with Mean-shift Bottom: Probabilistic with particle filters

References [1] Fukunaga et al, “ The Estimation of the Gradient of a Density Function, with Applications in Pattern Recognition ”, IEEE Trans. on Information Theory, 1975 [2] Dorin Comaniciu et al, “ Real-time Tracking of Non-Rigid Objects Using Mean Shift ”, CVPR [3] Dorin Comaniciu et al, “ Kernel-Based Object Tracking ”, IEEE Trans. On Pattern Analysis and Machine Learning, May [4] Jaco Vermaak et al [5] Jaco Vermaak et al, “ Variational Inference for Visual Tracking ”, CVPR, 2003