Tracking using CONDENSATION: Conditional Density Propagation

Similar documents
Training an RBM: Contrastive Divergence. Sargur N. Srihari

An Improved Particle Filter with Applications in Ballistic Target Tracking

Bayes Decision Rule and Naïve Bayes Classifier

Intelligent Systems: Reasoning and Recognition. Artificial Neural Networks

Multi-Scale/Multi-Resolution: Wavelet Transform

International Journal of Scientific & Engineering Research, Volume 4, Issue 9, September ISSN

Combining Classifiers

Ştefan ŞTEFĂNESCU * is the minimum global value for the function h (x)

Machine Learning Basics: Estimators, Bias and Variance

Pattern Recognition and Machine Learning. Artificial Neural networks

Using EM To Estimate A Probablity Density With A Mixture Of Gaussians

Identical Maximum Likelihood State Estimation Based on Incremental Finite Mixture Model in PHD Filter

Quantum algorithms (CO 781, Winter 2008) Prof. Andrew Childs, University of Waterloo LECTURE 15: Unstructured search and spatial search

Pseudo-marginal Metropolis-Hastings: a simple explanation and (partial) review of theory

SPECTRUM sensing is a core concept of cognitive radio

Intelligent Systems: Reasoning and Recognition. Perceptrons and Support Vector Machines

Inspection; structural health monitoring; reliability; Bayesian analysis; updating; decision analysis; value of information

Pattern Recognition and Machine Learning. Learning and Evaluation for Pattern Recognition

Data-Driven Imaging in Anisotropic Media

Course Notes for EE227C (Spring 2018): Convex Optimization and Approximation

Effective joint probabilistic data association using maximum a posteriori estimates of target states

Course Notes for EE227C (Spring 2018): Convex Optimization and Approximation

Bayesian inference for stochastic differential mixed effects models - initial steps

W-BASED VS LATENT VARIABLES SPATIAL AUTOREGRESSIVE MODELS: EVIDENCE FROM MONTE CARLO SIMULATIONS

Ufuk Demirci* and Feza Kerestecioglu**

Principal Components Analysis

SEISMIC FRAGILITY ANALYSIS

Pattern Recognition and Machine Learning. Artificial Neural networks

Department of Physics, Sri Venkateswara University, Tirupati Range Operations, Satish Dhawan Space Centre SHAR, ISRO, Sriharikota

P032 3D Seismic Diffraction Modeling in Multilayered Media in Terms of Surface Integrals

Bayesian Approach for Fatigue Life Prediction from Field Inspection

A remark on a success rate model for DPA and CPA

Figure 1: Equivalent electric (RC) circuit of a neurons membrane

1 Proof of learning bounds

Using a De-Convolution Window for Operating Modal Analysis

Boosting with log-loss

The Simplex Method is Strongly Polynomial for the Markov Decision Problem with a Fixed Discount Rate

Non-Parametric Non-Line-of-Sight Identification 1

Kalman filtering and friends: Inference in time series models. Herke van Hoof slides mostly by Michael Rubinstein

Probability Distributions

Condition Monitoring and Fault Detection of Railway Vehicle Suspension using Multiple-Model Approach

Kernel Methods and Support Vector Machines

Ensemble Based on Data Envelopment Analysis

A Smoothed Boosting Algorithm Using Probabilistic Output Codes

Sharp Time Data Tradeoffs for Linear Inverse Problems

SHORT TIME FOURIER TRANSFORM PROBABILITY DISTRIBUTION FOR TIME-FREQUENCY SEGMENTATION

Uncertainty Propagation and Nonlinear Filtering for Space Navigation using Differential Algebra

Ch 12: Variations on Backpropagation

e-companion ONLY AVAILABLE IN ELECTRONIC FORM

Pattern Recognition and Machine Learning. Artificial Neural networks

Handwriting Detection Model Based on Four-Dimensional Vector Space Model

Chapter 4: Hypothesis of Diffusion-Limited Growth

ESTIMATING AND FORMING CONFIDENCE INTERVALS FOR EXTREMA OF RANDOM POLYNOMIALS. A Thesis. Presented to. The Faculty of the Department of Mathematics

Bayesian Learning. Chapter 6: Bayesian Learning. Bayes Theorem. Roles for Bayesian Methods. CS 536: Machine Learning Littman (Wu, TA)

Reduction of Uncertainty in Post-Event Seismic Loss Estimates Using Observation Data and Bayesian Updating

ACTIVE VIBRATION CONTROL FOR STRUCTURE HAVING NON- LINEAR BEHAVIOR UNDER EARTHQUAKE EXCITATION

OBJECTIVES INTRODUCTION

Interactive Markov Models of Evolutionary Algorithms

Smoothing Framework for Automatic Track Initiation in Clutter

Topic 5a Introduction to Curve Fitting & Linear Regression

Symbolic Analysis as Universal Tool for Deriving Properties of Non-linear Algorithms Case study of EM Algorithm

arxiv: v1 [cs.lg] 8 Jan 2019

Forecasting Financial Indices: The Baltic Dry Indices

N-Point. DFTs of Two Length-N Real Sequences

2D Image Processing (Extended) Kalman and particle filter

Support recovery in compressed sensing: An estimation theoretic approach

An Adaptive UKF Algorithm for the State and Parameter Estimations of a Mobile Robot

Image Reconstruction by means of Kalman Filtering in Passive Millimetre- Wave Imaging

Stochastic Subgradient Methods

Bayes Theorem & Diagnostic Tests Screening Tests

A Nonlinear Sparsity Promoting Formulation and Algorithm for Full Waveform Inversion

Teaching Old Sensors New Tricks: Archetypes of Intelligence

Recovering Data from Underdetermined Quadratic Measurements (CS 229a Project: Final Writeup)

Randomized Recovery for Boolean Compressed Sensing

Human Pose Tracking I: Basics. David Fleet University of Toronto

A MESHSIZE BOOSTING ALGORITHM IN KERNEL DENSITY ESTIMATION

Removal of Intensity Bias in Magnitude Spin-Echo MRI Images by Nonlinear Diffusion Filtering

1 Generalization bounds based on Rademacher complexity

Linear Dynamical Systems

Extension of CSRSM for the Parametric Study of the Face Stability of Pressurized Tunnels

PAC-Bayes Analysis Of Maximum Entropy Learning

CONDENSATION Conditional Density Propagation for Visual Tracking

are equal to zero, where, q = p 1. For each gene j, the pairwise null and alternative hypotheses are,

Generalized Queries on Probabilistic Context-Free Grammars

What is Probability? (again)

International Scientific and Technological Conference EXTREME ROBOTICS October 8-9, 2015, Saint-Petersburg, Russia

Lower Bounds for Quantized Matrix Completion

Detection and Estimation Theory

HIGH RESOLUTION NEAR-FIELD MULTIPLE TARGET DETECTION AND LOCALIZATION USING SUPPORT VECTOR MACHINES

Block designs and statistics

Some Proofs: This section provides proofs of some theoretical results in section 3.

Real-time Super-resolution Sound Source Localization for Robots

STA 4273H: Statistical Machine Learning

A Decision-Based Model and Algorithm for Maneuvering Target Tracking

Multiscale Entropy Analysis: A New Method to Detect Determinism in a Time. Series. A. Sarkar and P. Barat. Variable Energy Cyclotron Centre

NUMERICAL MODELLING OF THE TYRE/ROAD CONTACT

A Simple Regression Problem

CS Lecture 13. More Maximum Likelihood

The Kalman Filter ImPr Talk

Feature Extraction Techniques

Transcription:

Tracking using CONDENSATION: Conditional Density Propagation Goal Model-based visual tracking in dense clutter at near video frae rates M. Isard and A. Blake, CONDENSATION Conditional density propagation for visual tracking, Int. J. Coputer Vision 29(1), 1998, pp. 4-28. Exaple of CONDENSATION Algorith Approach Probabilistic fraework for tracking objects such as curves in clutter using an iterative sapling algorith Model otion and shape of target Top-down approach Siulation instead of analytic solution 1

Probabilistic Fraework Object dynaics for a teporal Markov chain p Observations, z t, are independent (utually and w.r.t process) Use Bayes rule ( x Χ ) p( x x ) t t 1 t t 1 t 1 (, x X ) p( x X ) p( z x ) p Z t 1 t t 1 t t 1 i 1 i i X Z p(x) p(z) Notation State vector, e.g., curve s position and orientation Measureent vector, e.g., iage edge locations Prior probability of state vector; suarizes prior doain knowledge, e.g., by independent easureents Probability of easuring Z; fixed for any given iage p(z X) Probability of easuring Z given that the state is X; copares iage to expectation based on state p(x Z) Probability of X given that easureent Z has occurred; called state posterior Tracking as Estiation Copute state posterior, p(x Z), and select next state to be the one that axiizes this (Maxiu a Posteriori (MAP) estiate) Measureents are coplex and noisy, so posterior cannot be evaluated in closed for Particle filter (iterative sapling) idea: Stochastically approxiate the state posterior with a set of N weighted particles, (s, π), where s is a saple state and π is its weight Use Bayes rule to copute p(x Z) Factored Sapling Generate a set of saples that approxiates the posterior p(x Z) ( 1) ( N) Saple set s { s,..., s } generated fro p(x); each saple has a weight ( probability ) π i N p j 1 z p ( s z ( i ) ( s p z ( x) p( z x) ) ( j ) ) 2

Factored Sapling Estiating Target State N15 X CONDENSATION for one iage p ( X Z) Bayes Rule This is what you can evaluate This is what you want. Knowing p(x Z) will tell us what is the ost likely state X. This is what you ay know a priori, or what you can predict p( Z X) p( X) p( Z) This is a constant for a given iage CONDENSATION Algorith 1. Select: Randoly select N particles fro {s t-1 } based on weights π t-1 ; sae particle ay be picked ultiple ties (factored sapling) 2. Predict: Move particles according to deterinistic dynaics (drift), then perturb individually (diffuse) 3. Measure: Get a likelihood for each new saple by coparing it with the iage s local appearance, i.e., based on p(z t x t ); then update weight accordingly to obtain {(s t, π t )} 3

Posterior at tie k-1 Predicted state at tie k Posterior at tie k observation density s s k k s 1, π k, π k 1 k drift diffuse easure Notes on Updating Enforcing plausibility: Particles that represent ipossible configurations are discarded Diffusion odeled with a Gaussian Likelihood function: Convert goodness of prediction score to pseudo-probability More arkings closer to predicted arkings higher likelihood State Posterior State Posterior Aniation 4

Object Motion Model For video tracking we need a way to propagate probability densities, so we need a otion odel such as X t+1 A X t + B W t where W is a noise ter and A and B are state transition atrices that can be learned fro training sequences The state, X, of an object, e.g., a B-spline curve, can be represented as a point in a 6D state space of possible 2D affine transforations of the object φ Evaluating p(z X) x ρ z 2 if x p( z x) qp( z clutter) + p( z x, φ ) p( φ ) 1 where φ {true easureent is z } for 1,,M, and q 1 - Σ p(φ ) is the probability that the target is not visible M z otherwise < δ Dancing Exaple Hand Exaple 5

Pointing Hand Exaple Glasses Exaple 6D state space of affine transforations of a spline curve Edge detector applied along norals to the spline Autoregressive otion odel 3D Model-based Exaple 3D state space: iage position + angle Polyhedral odel of object Minerva Museu tour guide robot that used CONDENSATION to track its position in the useu Desired Location Exhibit 6

Advantages of Particle Filtering Nonlinear dynaics, easureent odel easily incorporated Copes with lots of false positives Multi-odal posterior okay (unlike Kalan filter) Multiple saples provides ultiple hypotheses Fast and siple to ipleent 7