Belief Networks in Computer Vision Applications Alex Yakushev CMPS 290C final project Winter 2006.

Slides:



Advertisements
Similar presentations
Bayesian Belief Propagation
Advertisements

Mobile Robot Localization and Mapping using the Kalman Filter
State Estimation and Kalman Filtering CS B659 Spring 2013 Kris Hauser.
CSCE643: Computer Vision Bayesian Tracking & Particle Filtering Jinxiang Chai Some slides from Stephen Roth.
Dynamic Bayesian Networks (DBNs)
Hidden Markov Models Reading: Russell and Norvig, Chapter 15, Sections
Reducing Drift in Parametric Motion Tracking
Robot Localization Using Bayesian Methods
Chapter 15 Probabilistic Reasoning over Time. Chapter 15, Sections 1-5 Outline Time and uncertainty Inference: ltering, prediction, smoothing Hidden Markov.
Oklahoma State University Generative Graphical Models for Maneuvering Object Tracking and Dynamics Analysis Xin Fan and Guoliang Fan Visual Computing and.
Tracking Objects with Dynamics Computer Vision CS 543 / ECE 549 University of Illinois Derek Hoiem 04/21/15 some slides from Amin Sadeghi, Lana Lazebnik,
Motion Tracking. Image Processing and Computer Vision: 82 Introduction Finding how objects have moved in an image sequence Movement in space Movement.
CS 188: Artificial Intelligence Fall 2009 Lecture 20: Particle Filtering 11/5/2009 Dan Klein – UC Berkeley TexPoint fonts used in EMF. Read the TexPoint.
Autonomous Robot Navigation Panos Trahanias ΗΥ475 Fall 2007.
Stanford CS223B Computer Vision, Winter 2007 Lecture 12 Tracking Motion Professors Sebastian Thrun and Jana Košecká CAs: Vaibhav Vaish and David Stavens.
CS 547: Sensing and Planning in Robotics Gaurav S. Sukhatme Computer Science Robotic Embedded Systems Laboratory University of Southern California
Tracking using the Kalman Filter. Point Tracking Estimate the location of a given point along a sequence of images. (x 0,y 0 ) (x n,y n )
Stanford CS223B Computer Vision, Winter 2007 Lecture 12 Tracking Motion Professors Sebastian Thrun and Jana Košecká CAs: Vaibhav Vaish and David Stavens.
Stanford CS223B Computer Vision, Winter 2006 Lecture 11 Filters / Motion Tracking Professor Sebastian Thrun CAs: Dan Maynes-Aminzade, Mitul Saha, Greg.
Particle Filtering for Non- Linear/Non-Gaussian System Bohyung Han
© 2003 by Davi GeigerComputer Vision November 2003 L1.1 Tracking We are given a contour   with coordinates   ={x 1, x 2, …, x N } at the initial frame.
Computer vision: models, learning and inference Chapter 10 Graphical Models.
Tracking with Linear Dynamic Models. Introduction Tracking is the problem of generating an inference about the motion of an object given a sequence of.
Bayesian Filtering for Location Estimation D. Fox, J. Hightower, L. Liao, D. Schulz, and G. Borriello Presented by: Honggang Zhang.
Kalman Filtering Pieter Abbeel UC Berkeley EECS Many slides adapted from Thrun, Burgard and Fox, Probabilistic Robotics TexPoint fonts used in EMF. Read.
Non-invasive Techniques for Human Fatigue Monitoring Qiang Ji Dept. of Electrical, Computer, and Systems Engineering Rensselaer Polytechnic Institute
Non-invasive Techniques for Human Fatigue Monitoring Qiang Ji Dept. of Electrical, Computer, and Systems Engineering Rensselaer Polytechnic Institute
Computer Vision Linear Tracking Jan-Michael Frahm COMP 256 Some slides from Welch & Bishop.
Overview and Mathematics Bjoern Griesbach
ICBV Course Final Project Arik Krol Aviad Pinkovezky.
Computer vision: models, learning and inference Chapter 6 Learning and Inference in Vision.
Bayesian Filtering for Robot Localization
Kalman filter and SLAM problem
Markov Localization & Bayes Filtering
TP15 - Tracking Computer Vision, FCUP, 2013 Miguel Coimbra Slides by Prof. Kristen Grauman.
/09/dji-phantom-crashes-into- canadian-lake/
Computer vision: models, learning and inference Chapter 19 Temporal models.
From Bayesian Filtering to Particle Filters Dieter Fox University of Washington Joint work with W. Burgard, F. Dellaert, C. Kwok, S. Thrun.
Computer vision: models, learning and inference Chapter 19 Temporal models.
STUDY, MODEL & INTERFACE WITH MOTOR CORTEX Presented by - Waseem Khatri.
Recap: Reasoning Over Time  Stationary Markov models  Hidden Markov models X2X2 X1X1 X3X3 X4X4 rainsun X5X5 X2X2 E1E1 X1X1 X3X3 X4X4 E2E2 E3E3.
Computer Vision - A Modern Approach Set: Tracking Slides by D.A. Forsyth The three main issues in tracking.
1 Robot Environment Interaction Environment perception provides information about the environment’s state, and it tends to increase the robot’s knowledge.
Cognitive Computer Vision Kingsley Sage and Hilary Buxton Prepared under ECVision Specific Action 8-3
Young Ki Baik, Computer Vision Lab.
Computer Vision Group Prof. Daniel Cremers Autonomous Navigation for Flying Robots Lecture 6.1: Bayes Filter Jürgen Sturm Technische Universität München.
Mobile Robot Localization (ch. 7)
Processing Sequential Sensor Data The “John Krumm perspective” Thomas Plötz November 29 th, 2011.
Real-Time Simultaneous Localization and Mapping with a Single Camera (Mono SLAM) Young Ki Baik Computer Vision Lab. Seoul National University.
CHAPTER 8 DISCRIMINATIVE CLASSIFIERS HIDDEN MARKOV MODELS.
Michael Isard and Andrew Blake, IJCV 1998 Presented by Wen Li Department of Computer Science & Engineering Texas A&M University.
An Introduction to Kalman Filtering by Arthur Pece
NCAF Manchester July 2000 Graham Hesketh Information Engineering Group Rolls-Royce Strategic Research Centre.
Unscented Kalman Filter 1. 2 Linearization via Unscented Transform EKF UKF.
Boosted Particle Filter: Multitarget Detection and Tracking Fayin Li.
1 Chapter 15 Probabilistic Reasoning over Time. 2 Outline Time and UncertaintyTime and Uncertainty Inference: Filtering, Prediction, SmoothingInference:
Tracking with dynamics
CS 547: Sensing and Planning in Robotics Gaurav S. Sukhatme Computer Science Robotic Embedded Systems Laboratory University of Southern California
Visual Tracking by Cluster Analysis Arthur Pece Department of Computer Science University of Copenhagen
Autonomous Mobile Robots Autonomous Systems Lab Zürich Probabilistic Map Based Localization "Position" Global Map PerceptionMotion Control Cognition Real.
Zhaoxia Fu, Yan Han Measurement Volume 45, Issue 4, May 2012, Pages 650–655 Reporter: Jing-Siang, Chen.
Tracking We are given a contour G1 with coordinates G1={x1 , x2 , … , xN} at the initial frame t=1, were the image is It=1 . We are interested in tracking.
Today.
Tracking Objects with Dynamics
Particle Filtering for Geometric Active Contours
Probabilistic Reasoning Over Time
Introduction to particle filter
Introduction to particle filter
Probabilistic Map Based Localization
Chapter14-cont..
Presentation transcript:

Belief Networks in Computer Vision Applications Alex Yakushev CMPS 290C final project Winter 2006

Kalman Filters Predicted position = (Previous Position)* (Motion model ) + Noise True position = observed position + Noise Extrapolate object position by taking a weighted average of the two. Only depends on current observation and previous state

Kalman Filter as a Belief Network xkxk x k+1 zkzk z k+1 Motion model Prediction covariance Model Noise State model Observation noise

Kalman Filters Becomes a simple update rule

Something completely different ● Are old fashioned Bayesian networks of any use? ● What if the object we are trying to track does not have a constant velocity or acceleration? ● Sherrah and Gong have designed a BN to track hand and face movements.

Something completely different (Sherrah, Gong)

Results (Sherrah, Gong) ● For their setup they had 70% of frames classified correctly without any contextual knowledge ● This improved to 78% with a Kalman filter ● 87% with their method......but Assumptions are unreasonable: 1. the subject is oriented roughly towards the camera for most of the time 2. the subject is wearing long sleeves 3. reasonably good color segmentation of the head and hands is possible, and 4. the head and hands are the larges moving skin color clusters in the image

“Dynamic Bayesian Network” (Pavlovic, Rehg, Cham, Murphy) State variables s t belong to a set of S discrete symbols.

Dynamic Bayesian Network ● Two hidden variables (x t, s t ) ● If x 0 is Gaussian then x 1 is a mixture of S Gaussians, x 2 is a mixture of S 2 Gaussians... ● No “simple” update rule ● Exact inference is expensive (Pavlovic, Rehg, Cham, Murphy)

Conclusions ● As usual, increase in expressive power costs computation time ● People create custom networks, and either give a solution for the specific structure, or use approximate inference ● No silver bullet, good results possible with both simple and complex network structures ● Using a simpler structure (Markov Network) may work for many applications

References ● Jamie Sherrah, Shaogang Gong, Tracking Discontinuous Motion Using Bayesian Inference, Lecture Notes in Computer Science, Volume 1843, Jan 2000, Pages 150 – 166 ● V. Pavlović, J. M. Rehg, T. J. Cham, and K. P. Murphy, A dynamic Bayesian network approach to figure tracking using learned dynamic models, in International Conference on Computer Vision, Corfu, Greece, September ● Murphy, K., Dynamic Bayesian Networks: Representation, Inference and Learning. PhD thesis, UC Berkeley, Computer Science Division (2002) ● Hai Tao, Object Tracking and Kalman Filtering, CMPE264 Lecture notes,