Foreground Modeling The Shape of Things that Came Nathan Jacobs Advisor: Robert Pless Computer Science Washington University in St. Louis.

Slides:



Advertisements
Similar presentations
Bayesian Belief Propagation
Advertisements

Change Detection C. Stauffer and W.E.L. Grimson, “Learning patterns of activity using real time tracking,” IEEE Trans. On PAMI, 22(8): , Aug 2000.
Computer vision: models, learning and inference Chapter 13 Image preprocessing and feature extraction.
電腦視覺 Computer and Robot Vision I Chapter2: Binary Machine Vision: Thresholding and Segmentation Instructor: Shih-Shinh Huang 1.
Proportion Priors for Image Sequence Segmentation Claudia Nieuwenhuis, etc. ICCV 2013 Oral.
Foreground Background detection from video Foreground Background detection from video מאת : אבישג אנגרמן.
MPEG-4 Objective Standardize algorithms for audiovisual coding in multimedia applications allowing for Interactivity High compression Scalability of audio.
Forward-Backward Correlation for Template-Based Tracking Xiao Wang ECE Dept. Clemson University.
Adviser : Ming-Yuan Shieh Student ID : M Student : Chung-Chieh Lien VIDEO OBJECT SEGMENTATION AND ITS SALIENT MOTION DETECTION USING ADAPTIVE BACKGROUND.
São Paulo Advanced School of Computing (SP-ASC’10). São Paulo, Brazil, July 12-17, 2010 Looking at People Using Partial Least Squares William Robson Schwartz.
Robust Moving Object Detection & Categorization using self- improving classifiers Omar Javed, Saad Ali & Mubarak Shah.
Learning to Detect A Salient Object Reporter: 鄭綱 (3/2)
Modeling Pixel Process with Scale Invariant Local Patterns for Background Subtraction in Complex Scenes (CVPR’10) Shengcai Liao, Guoying Zhao, Vili Kellokumpu,
Motion Tracking. Image Processing and Computer Vision: 82 Introduction Finding how objects have moved in an image sequence Movement in space Movement.
Motion Detection And Analysis Michael Knowles Tuesday 13 th January 2004.
3-D Depth Reconstruction from a Single Still Image 何開暘
Segmentation and Tracking of Multiple Humans in Crowded Environments Tao Zhao, Ram Nevatia, Bo Wu IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,
A Bayesian algorithm for tracking multiple moving objects in outdoor surveillance video Department of Electrical Engineering and Computer Science The University.
Ensemble Tracking Shai Avidan IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE February 2007.
Project 4 out today –help session today –photo session today Project 2 winners Announcements.
Segmentation by Clustering Reading: Chapter 14 (skip 14.5) Data reduction - obtain a compact representation for interesting image data in terms of a set.
Object Detection and Tracking Mike Knowles 11 th January 2005
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 )
CS 223B Assignment 1 Help Session Dan Maynes-Aminzade.
1 Integration of Background Modeling and Object Tracking Yu-Ting Chen, Chu-Song Chen, Yi-Ping Hung IEEE ICME, 2006.
A Self-Organizing Approach to Background Subtraction for Visual Surveillance Applications Lucia Maddalena and Alfredo Petrosino, Senior Member, IEEE.
Effective Gaussian mixture learning for video background subtraction Dar-Shyang Lee, Member, IEEE.
MULTIPLE MOVING OBJECTS TRACKING FOR VIDEO SURVEILLANCE SYSTEMS.
Multi-camera Video Surveillance: Detection, Occlusion Handling, Tracking and Event Recognition Oytun Akman.
Computer Vision I Instructor: Prof. Ko Nishino. Today How do we recognize objects in images?
Shadow Detection In Video Submitted by: Hisham Abu saleh.
Jacinto C. Nascimento, Member, IEEE, and Jorge S. Marques
Video Trails: Representing and Visualizing Structure in Video Sequences Vikrant Kobla David Doermann Christos Faloutsos.
Computer Vision - A Modern Approach Set: Segmentation Slides by D.A. Forsyth Segmentation and Grouping Motivation: not information is evidence Obtain a.
1 Activity and Motion Detection in Videos Longin Jan Latecki and Roland Miezianko, Temple University Dragoljub Pokrajac, Delaware State University Dover,
Multimodal Interaction Dr. Mike Spann
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
BraMBLe: The Bayesian Multiple-BLob Tracker By Michael Isard and John MacCormick Presented by Kristin Branson CSE 252C, Fall 2003.
Shape-Based Human Detection and Segmentation via Hierarchical Part- Template Matching Zhe Lin, Member, IEEE Larry S. Davis, Fellow, IEEE IEEE TRANSACTIONS.
1. Introduction Motion Segmentation The Affine Motion Model Contour Extraction & Shape Estimation Recursive Shape Estimation & Motion Estimation Occlusion.
#MOTION ESTIMATION AND OCCLUSION DETECTION #BLURRED VIDEO WITH LAYERS
December 9, 2014Computer Vision Lecture 23: Motion Analysis 1 Now we will talk about… Motion Analysis.
Vehicle Segmentation and Tracking From a Low-Angle Off-Axis Camera Neeraj K. Kanhere Committee members Dr. Stanley Birchfield Dr. Robert Schalkoff Dr.
Limitations of Cotemporary Classification Algorithms Major limitations of classification algorithms like Adaboost, SVMs, or Naïve Bayes include, Requirement.
Expectation-Maximization (EM) Case Studies
Determining the location and orientation of webcams using natural scene variations Nathan Jacobs.
Boosted Particle Filter: Multitarget Detection and Tracking Fayin Li.
Segmentation of Vehicles in Traffic Video Tun-Yu Chiang Wilson Lau.
 Present by 陳群元.  Introduction  Previous work  Predicting motion patterns  Spatio-temporal transition distribution  Discerning pedestrians  Experimental.
Presented by: Idan Aharoni
Visual Tracking by Cluster Analysis Arthur Pece Department of Computer Science University of Copenhagen
Occlusion Tracking Using Logical Models Summary. A Variational Partial Differential Equations based model is used for tracking objects under occlusions.
Learning Image Statistics for Bayesian Tracking Hedvig Sidenbladh KTH, Sweden Michael Black Brown University, RI, USA
Using Clouds Shadows to Infer Scene Structure and Camera Calibration
Contents Team introduction Project Introduction Applicability
A Forest of Sensors: Using adaptive tracking to classify and monitor activities in a site Eric Grimson AI Lab, Massachusetts Institute of Technology
Motion Detection And Analysis
Dynamical Statistical Shape Priors for Level Set Based Tracking
Vehicle Segmentation and Tracking in the Presence of Occlusions
Image Segmentation Techniques
PRAKASH CHOCKALINGAM, NALIN PRADEEP, AND STAN BIRCHFIELD
Image and Video Processing
Announcements Project 2 artifacts Project 3 due Thursday night
Announcements Project 4 out today Project 2 winners help session today
Where are we? We have covered: Project 1b was due today
Announcements Artifact due Thursday
EM Algorithm and its Applications
Announcements Artifact due Thursday
The “Margaret Thatcher Illusion”, by Peter Thompson
Presentation transcript:

Foreground Modeling The Shape of Things that Came Nathan Jacobs Advisor: Robert Pless Computer Science Washington University in St. Louis

Nathan Jacobs2 Visual Surveillance Observe people and vehicles –Where are they? –Where have they been? –Where are they going? Answering these questions requires object tracking.

Nathan Jacobs3 Probabilistic Tracking Tracking is commonly cast in a Bayesian framework to estimate object shape and location –Initial estimate = combination of image data likelihood and initialization prior –Updated estimate = combination of image data likelihood and state prediction prior Likelihood functions are the focus of most tracking work –Color histograms, templates Our focus is on the prior terms

Nathan Jacobs4 Quotes from yesterday “Initialization of tracking is important but not addressed here.” “Our object model assumes a well calibrated camera and a flat-ground plane.” “The prior term is a tricky thing to design.”

Nathan Jacobs5 Passive Vision : The Big Picture Learn strong scene-specific priors by watching the same scene for a long time –Made easier because the cameras are static –Should be learned online Priors can be used to improve anomaly detection and tracking algorithms

Nathan Jacobs6 Scene-specific Motion Priors

Nathan Jacobs7 Unusual Traffic Motion Video segment with anomalous motion (an ambulance using the median to pass stopped cars). False color sequence highlighting anomalous motions.

Nathan Jacobs8 Online Prior Learning for Tracking Online learning and use of motion priors: reduces the number of particles needed increases the number of objects that can be tracked. Frames Objects

Nathan Jacobs9 What else can we model? Watching for a long time allows us to build models of –Pixel intensity –Image derivatives –Image motion patterns We now transition to features based on the shape of foreground objects

Nathan Jacobs10 An Example Video

Nathan Jacobs11 Generating Examples Shapes Current Frame Foreground Mask Shape Descriptor Background Image For a long time: 1.Detect foreground objects 2.Generate a shape descriptor for each object 3.Add shape descriptor to training set

Nathan Jacobs12 Shape Descriptor Currently using a simple shape model –A 20-dimensional feature vector –Each dimension is the distance from center to edge of object Other shape models are possible

Nathan Jacobs13 Two Shape Model Types Both models are PCA subspaces Global model –Subspace is location independent –Distribution estimate is location dependent Local model –Subspace and distribution are both location dependent

Nathan Jacobs14 A location-independent Shape Basis Training Set Generate shape subspace using PCA on all shapes in training set. First Principle Component (~size) Second Principle Component (~orientation)

Nathan Jacobs15 Location-dependent Coefficients First Principle Component (~size) Second Principle Component (~orientation)

Nathan Jacobs16 Location-specific Shape Subspaces Generate a shape subspace using shapes found in a small region of the image. Location-specific mean shapes

Nathan Jacobs17 Location-specific Shape Subspaces Shape subspaces are location dependent. Much smaller variations in some regions. First PC VariationsSecond PC Variations

Nathan Jacobs18 Shapes in (Shape) Space

Nathan Jacobs19 An Example from PETS First Principle Component (~size) Second Principle Component (~aspect)

Nathan Jacobs20 Location-dependent Mean Shapes Mean Shapes

Nathan Jacobs21 Location-dependent Subspaces First PC VariationsSecond PC Variations

Nathan Jacobs22 Object Initialization for Tracking Object initialization is a crucial step of any tracking algorithm Use shape priors to determine object boundaries –Combines image information and shape prior –Penalize unlikely shapes –More accurate than image information alone Major point: strong priors make simple methods work

Nathan Jacobs23 Object Boundary Detection Goal is to determine object boundaries to improve tracking initialization Algorithm –Find candidates using background subtraction –Initialize each candidate with a location- specific mean shape –Optimize shape by gradient descent in PCA shape subspace (penalize object overlap) Image data term: sum of per-pixel foreground probability inside shape Shape prior term: sum of absolute value of PCA coefficients

Nathan Jacobs24 Segmentation Results Subspace onlySubspace and Prior Global shape model Local shape model

Nathan Jacobs25 Summary 1.Static cameras give strong priors. 2.Unsupervised training of a localized shape prior is possible. 3.Localized shape priors can be used to improve object initialization for tracking.

Background

Nathan Jacobs27 Efficient Segmentation Use gradient descent in low-dimensional shape subspace Gradient estimation –For each underlying shape parameter Sum along two edges of polygon –For PC components and object location Weighted combination of polygon edge scores

Nathan Jacobs28 Choice of Support Region

Nathan Jacobs29 Choosing Constants for Updating Prior Models Threshold The best learning rate depends on scene, application, time-of-day, weather, image location. Slow updateFast update Current Frame VSSN 2006

Nathan Jacobs30 Segmentation Energy Function Minimize Penalty on size Per-pixel foreground likelihood Shape penalty based on prior (sum of PCA coefficients)