A Probabilistic Framework for Video Representation Arnaldo Mayer, Hayit Greenspan Dept. of Biomedical Engineering Faculty of Engineering Tel-Aviv University,

Slides:



Advertisements
Similar presentations
A probabilistic model for retrospective news event detection
Advertisements

Pseudo-Relevance Feedback For Multimedia Retrieval By Rong Yan, Alexander G. and Rong Jin Mwangi S. Kariuki
Unsupervised Learning
Víctor Ponce Miguel Reyes Xavier Baró Mario Gorga Sergio Escalera Two-level GMM Clustering of Human Poses for Automatic Human Behavior Analysis Departament.
Presented By: Vennela Sunnam
Patch to the Future: Unsupervised Visual Prediction
Segmentation and Fitting Using Probabilistic Methods
Foreground Modeling The Shape of Things that Came Nathan Jacobs Advisor: Robert Pless Computer Science Washington University in St. Louis.
Automatic Identification of Bacterial Types using Statistical Image Modeling Sigal Trattner, Dr. Hayit Greenspan, Prof. Shimon Abboud Department of Biomedical.
Texture Segmentation Based on Voting of Blocks, Bayesian Flooding and Region Merging C. Panagiotakis (1), I. Grinias (2) and G. Tziritas (3)
On Constrained Optimization Approach To Object Segmentation Chia Han, Xun Wang, Feng Gao, Zhigang Peng, Xiaokun Li, Lei He, William Wee Artificial Intelligence.
ICIP 2000, Vancouver, Canada IVML, ECE, NTUA Face Detection: Is it only for Face Recognition?  A few years earlier  Face Detection Face Recognition 
Lecture 6 Image Segmentation
Unsupervised Image Clustering using Probabilistic Continuous Models and Information Theoretic Principles Shiri Gordon Electrical Engineering – System,
HMM-BASED PATTERN DETECTION. Outline  Markov Process  Hidden Markov Models Elements Basic Problems Evaluation Optimization Training Implementation 2-D.
A Bayesian Formulation For 3d Articulated Upper Body Segmentation And Tracking From Dense Disparity Maps Navin Goel Dr Ara V Nefian Dr George Bebis.
Multimedia Search and Retrieval Presented by: Reza Aghaee For Multimedia Course(CMPT820) Simon Fraser University March.2005 Shih-Fu Chang, Qian Huang,
Prénom Nom Document Analysis: Data Analysis and Clustering Prof. Rolf Ingold, University of Fribourg Master course, spring semester 2008.
Incremental Learning of Temporally-Coherent Gaussian Mixture Models Ognjen Arandjelović, Roberto Cipolla Engineering Department, University of Cambridge.
Multiple Human Objects Tracking in Crowded Scenes Yao-Te Tsai, Huang-Chia Shih, and Chung-Lin Huang Dept. of EE, NTHU International Conference on Pattern.
Visual Querying By Color Perceptive Regions Alberto del Bimbo, M. Mugnaini, P. Pala, and F. Turco University of Florence, Italy Pattern Recognition, 1998.
Using spatio-temporal probabilistic framework for object tracking By: Guy Koren-Blumstein Supervisor: Dr. Hayit Greenspan Emphasis on Face Detection &
1 Integration of Background Modeling and Object Tracking Yu-Ting Chen, Chu-Song Chen, Yi-Ping Hung IEEE ICME, 2006.
Presented by Zeehasham Rasheed
A Probabilistic Framework For Segmentation And Tracking Of Multiple Non Rigid Objects For Video Surveillance Aleksandar Ivanovic, Tomas S. Huang ICIP 2004.
ICME 2004 Tzvetanka I. Ianeva Arjen P. de Vries Thijs Westerveld A Dynamic Probabilistic Multimedia Retrieval Model.
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.
Object Tracking for Retrieval Application in MPEG-2 Lorenzo Favalli, Alessandro Mecocci, Fulvio Moschetti IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR.
Jacinto C. Nascimento, Member, IEEE, and Jorge S. Marques
1 Activity and Motion Detection in Videos Longin Jan Latecki and Roland Miezianko, Temple University Dragoljub Pokrajac, Delaware State University Dover,
Isolated-Word Speech Recognition Using Hidden Markov Models
1 TEMPLATE MATCHING  The Goal: Given a set of reference patterns known as TEMPLATES, find to which one an unknown pattern matches best. That is, each.
Characterizing activity in video shots based on salient points Nicolas Moënne-Loccoz Viper group Computer vision & multimedia laboratory University of.
Automatic Image Annotation by Using Concept-Sensitive Salient Objects for Image Content Representation Jianping Fan, Yuli Gao, Hangzai Luo, Guangyou Xu.
Presented by Anuradha Venkataraman.  Introduction  Existing Approaches  Video Representation  Volume Based Video Representation  Events and Actions.
MACHINE LEARNING 8. Clustering. Motivation Based on E ALPAYDIN 2004 Introduction to Machine Learning © The MIT Press (V1.1) 2  Classification problem:
Advances in digital image compression techniques Guojun Lu, Computer Communications, Vol. 16, No. 4, Apr, 1993, pp
A DISTRIBUTION BASED VIDEO REPRESENTATION FOR HUMAN ACTION RECOGNITION Yan Song, Sheng Tang, Yan-Tao Zheng, Tat-Seng Chua, Yongdong Zhang, Shouxun Lin.
CVPR2013 Poster Detecting and Naming Actors in Movies using Generative Appearance Models.
Probabilistic Latent Query Analysis for Combining Multiple Retrieval Sources Rong Yan Alexander G. Hauptmann School of Computer Science Carnegie Mellon.
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.
Using Cross-Media Correlation for Scene Detection in Travel Videos.
Dynamic Data Analysis Projects in the Image Analysis and Motion Capture Labs Figure: functional brain MRI of a monetary reward task; left: 16 cocaine subjects,
Visual Tracking by Cluster Analysis Arthur Pece Department of Computer Science University of Copenhagen
1 Review and Summary We have covered a LOT of material, spending more time and more detail on 2D image segmentation and analysis, but hopefully giving.
May 2003 SUT Color image segmentation – an innovative approach Amin Fazel May 2003 Sharif University of Technology Course Presentation base on a paper.
Digital Image Processing CCS331 Relationships of Pixel 1.
ENTERFACE 08 Project 9 “ Tracking-dependent and interactive video projection ” Mid-term presentation August 19th, 2008.
Detection, Tracking and Recognition in Video Sequences Supervised By: Dr. Ofer Hadar Mr. Uri Perets Project By: Sonia KanOra Gendler Ben-Gurion University.
Gaussian Mixture Model classification of Multi-Color Fluorescence In Situ Hybridization (M-FISH) Images Amin Fazel 2006 Department of Computer Science.
Unsupervised Learning Part 2. Topics How to determine the K in K-means? Hierarchical clustering Soft clustering with Gaussian mixture models Expectation-Maximization.
Automatic Video Shot Detection from MPEG Bit Stream
IMAGE PROCESSING RECOGNITION AND CLASSIFICATION
Traffic Sign Recognition Using Discriminative Local Features Andrzej Ruta, Yongmin Li, Xiaohui Liu School of Information Systems, Computing and Mathematics.
A Forest of Sensors: Using adaptive tracking to classify and monitor activities in a site Eric Grimson AI Lab, Massachusetts Institute of Technology
Introduction Computer vision is the analysis of digital images
Saliency, Scale and Image Description (by T. Kadir and M
V. Mezaris, I. Kompatsiaris, N. V. Boulgouris, and M. G. Strintzis
Image Segmentation Techniques
Introduction Computer vision is the analysis of digital images
PRAKASH CHOCKALINGAM, NALIN PRADEEP, AND STAN BIRCHFIELD
Unsupervised Learning II: Soft Clustering with Gaussian Mixture Models
Region and Shape Extraction
INTRODUCTION TO Machine Learning
Introduction Computer vision is the analysis of digital images
A Novel Smoke Detection Method Using Support Vector Machine
EM Algorithm and its Applications
Presentation transcript:

A Probabilistic Framework for Video Representation Arnaldo Mayer, Hayit Greenspan Dept. of Biomedical Engineering Faculty of Engineering Tel-Aviv University, Israel Jacob Goldberger, CUTe Systems, Ltd.

Introduction In this work we describe a novel statistical video representation and modeling scheme. Video representation schemes are needed to enable segmenting a video stream into meaningful video- objects, useful for event detection, indexing and retrieval applications.

PACS: Picture Archiving & Communication Systems Storage Query/Retrieve InternetDatabaseManagement Query/Retrieve VisualInformation Tele-Medicine

Spatio-Temporal Segmentation of Multiple Sclerosis Lesions in MRI What are interesting events in medical data? Spatio-Temporal Tracking of Tracer in Digital Angiography

Analysis of a video as a single entity Vs analysis of video as a sequence of frames Inherent Spatio-temporal tracking Gaussian Mixture Modeling in color & space- time domain t x y Introduction

Learning a Probabilistic Model in Space-Time Feature Vectors [L,a,b,x,y,t] (6 - dimensional space) Expectation Maximization (EM) t y Gaussian Mixture Model x

Video Representation via Gaussian Mixture Modeling Each Component of the GMM Represents a Cluster in the Feature Space (=Blob) and a Spatio-temporal region in the video PdF For the GMM : With the Parameter set

Given a set of feature vectors and parameter values, the Likelihood expresses how well the model fits the data. The EM algorithm: iterative method to obtain the parameter values that maximize the Likelihood …

Expectation step: estimate the Gaussian clusters to which the points in feature space belong Maximization step: maximum likelihood parameter estimates using this data The EM Algorithm

Initialization & Model selection Initialization of the EM algorithm via K-means: –Unsupervised clustering method –Non-parametric Model selection via MDL (Minimum Description Length) –Choose k to maximize: –l k = #free parameters for a model with k mixture components

Static space-time blobDynamic space-time blob The GMM for a given video sequence can be visualized as a set of hyper-ellipsoids (2 sigma contour) within the 6 dimensional color-space-time domain. Video Model Visualization

Detection & Recognition of Events in Video C L a b x y t C xt C tt C tt - Duration of space-time blob Static/Dynamic blobs - thresholds on R xt (Hor. motion) & R yt (Ver. motion) Direction of motion - sign of R xt, R yt Correlation coefficient : C yt

Detection & Recognition of Events in Video C L a b x y t C xt C tt Blob motion (pixels per frame) via linear regression models in space & time : C yt Horizontal velocity of blob motion in image plane is extracted as the ratio of cov. parameters. Similar formalism allows for the modeling of any other motion in the image plane.

Probabilistic Image Segmentation A direct correspondence can be made between the mixture representation and the image plane. Each pixel of the original image is now affiliated with the most probable Gaussian cluster. Pixel labeling: Probability of pixel x to be labeled:

OriginalModel Segmentation

OriginalModel SegmentationDynamic Event Tracking

Limitations of the Global Model How can we represent non-convex spatio-temporal regions? All the data must be available simultaneously - Inappropriate for live video - Model fitting time increases directly with sequence length

Piecewise Gaussian Mixture Modeling Modeling the Video sequence as a succession of overlapping blocks of frames. Obtain a succession of GMMs instead of a single global model. Important issues: initialization; matching between adjacent segments for region tracking. (“gluing”)

Piecewise GMM : “Gluing” / Matching at Junctions Frame J 5 blobs via GMM 5 Frame J 5 blobs via GMM 6 Frame J 5 Ex: Blob matching

Original SequenceDynamic Event Tracking Model Sequence

Horizontal Velocity in function of Block of Frame Index Pix / frame BoF #

Vertical Velocity in function of Block of Frame Index Pix / frame BoF #

Original Sequence Segmentation Map Sequence BOF # Pix / frame Horizontal Velocity BOF # Pix / frame Vertical Velocity Sweater Trousers

Spatio-Temporal Segmentation of Multiple Sclerosis Lesions in MRI Sequences

Methodology Time K >= 4 1) CSF 2) White Matter 3) Gray Matter 4) Sclerotic Lesions Segmentation Maps Blobs in [L x y t] Feature Space Frame by frame Segmentation 3D (x,y,t) Connected Components GMM for Luminance

Original Sequence Dynamic Event Tracking Segmentation Maps Sequence

Area (in Pixels) Time point Time Evolution

Conclusions The modeling and the segmentation are combined to enable the extraction of video-regions that represent coherent regions across the video sequence, otherwise termed video-objects or sub-objects. Extracting video regions provides for a compact video content description, that may be useful for later indexing and retrieval applications. Medical applications: lesion modeling & tracking Acknowledgment Part of the work was supported by the Israeli Ministry of Science, Grant number