Activity related recognition in AmI environments
|
|
- Sharleen Jodie Newton
- 5 years ago
- Views:
Transcription
1 Informatics & Telematics Institute Presentation Activity related recognition in AmI environments Mr. Anastasios Drosou (Dr. Tzovaras Group)
2 Outline Introduction Activity Detection Activity related recognition Human Tracking Reaching Part Grasping Part Classifiers Results Conclusions Presentation, Thessaloniki 16 March
3 Definition of Biometrics Biometrics measure the unique physical or behavioural characteristics of individuals as a means to recognize or authenticate their identity. Establish someone s identity based on who he/she is rather than on what he/she poseses (e.g. ID cards,) or what he/she remembers (e.g. password). Verification problem: Is the user Mr. X? 1:1 comparison. Identification: Who is the user? 1:many comparison. Presentation, Thessaloniki 16 March
4 Types of Biometrics Description Types Pros Cons Physiological Biometrics A physical attribute unique to a person Fingerprint, palm, iris, geometry, retina, facial characteristics, etc. High Accuracy. Obtrusive, Uncomfortable, Easy to spoof, Intolerant of changes over time. Behavioural Biometrics Traits that are learned or acquired from a person Facial Dynamics, Gait, Voice, Key-stroke Patterns, Activity related signals, etc. Unobtrusive, Difficult to spoof, Continuous & on-the-move authentication, Rare changes. Lower accuracy, yet... Presentation, Thessaloniki 16 March
5 Motivation We claim recognition potential because: 1. Personal behavioural patterns in everyday movements (i.e. gait, grimaces, standard movements, etc) 2. Physiology of the human body (height, arm length, finger lengths, etc.) 3. Bodymetric restrictions (i.e. impairments, etc.) 4. Minimum Jerk Model (Flash & Hogan) 5. Minimum Torque Change Model (Uno, Kawato & Suzuki) 6. End state comfort effect (Rosenbaum et al.) 7. Presentation, Thessaloniki 16 March
6 Case study: Prehension biometrics Response of the person to specific stimuli. Work related, everyday activities with no special protocol. Continuous authentication/recognition. Multi-activity concept for human authentication. 2 stages of a prehension movement: i. a fast initial movement (reaching) ii. a slow approach movement (grasping) Presentation, Thessaloniki 16 March
7 System-Level Criteria Characteristics of a biometric that must be present in order to use the system for authentication purposes Universality Universality: Every person should possess this characteristic In practice, this may not be the case Otherwise, population of non-universality must be small < 1% Uniqueness Uniqueness: No two individuals possess the same characteristic. Genotypical Genetically linked (e.g. identical twins will have same biometric) Phenotypical Non-genetically linked, different perhaps even on same individual Establishing uniqueness is difficult to prove analytically May be unique, but uniqueness must be distinguishable Permanence Permanence: The characteristic does not change in time, that is, it is time invariant At best this is an approximation Degree of permanence has a major impact on the system design and long term operation of biometrics. (e.g. enrollment, adaptive matching design, etc.) Long vs. short-term stability Collectability - Measurability Collectability: The characteristic can be quantitatively measured. In practice, the biometric collection must be: Non-intrusive Reliable and robust Cost effective for a given application Measurability: The trait can be measured with simple technical instruments Performance accuracy, speed, and robustness of technology used Circumvention The trait is easily measured with minimal discomfort.then it can potentially serve as a biometric for a given application. 7
8 Outline Introduction Activity Detection Activity related recognition Human Tracking Reaching Part Grasping Part Classifiers Results Conclusions Presentation, Thessaloniki 16 March
9 Motion Templates Motion Energy Image (MEI) Describes the motion energy for a given view of action. Binary image. E T ( x, y, t) = τ 1 i= 0 D( x, y, t i) Motion History Image (MHI) Intensity image. MHI T (, x y,) t τ if Dxyt (,, ) = 1 = max(0, MHIT ( x, y, t 1) 1) otherwise Presentation, Thessaloniki 16 March
10 Radon Transforms (I) 1. Face detection 2. Centre of Face 3. RIT Extraction Radial Integration Transform (RIT): RIT ( t θ) MHI ( r j u co ( t sθ), y j u sin t ()) θ J = J j= o for t = 1,..., T with T = 360 / θ Presentation, Thessaloniki 16 March
11 Radon Transforms (II) 1. Face detection 2. Centre of Face 3. CIT Extraction Circular Integration Transform (CIT): 1 CIT ( t ρ) MHI ( x k ρcos( t θ), y k ρsin( t θ)) T = T t= o for k = 1,..., K with T = 360 / θ Presentation, Thessaloniki 16 March
12 Similarity Metrics Euclidian Distance 2 n 2 E( xy, ) = ( x y) = ( ) i= 1 i i D x y Correlation Factor - Coefficients corr( x, y) cov( xy, ) = ρxy, = = σσ E(( x µ )( y µ )) x σσ x y x y y Presentation, Thessaloniki 16 March
13 Human Body Tracking Camera based tracking: Custom Tracker OpenNI Library Tracker Ascension Technology Corp. Magnetic Tracker (ground truth). Cyberglove finger tracking. Presentation, Thessaloniki 16 March 2011
14 Face Detection & Tracking Viola & Jones s real-time face detection method: T weak classifiers form a strong one, integral Image, haar like features (subtracting the pixel values in the dark from the bright rectangles), AdaBoost algorithm. Mean Shift algorithm: Bases on spatial and colour information between sequential frames. Bhattacharyya distance Presentation, Thessaloniki 16 March
15 Background Extraction Skin Colour Filtering Motion Detection Location of the face Disparity images (stereoscopic Camera) DI ( ) = SI ( ) BI ( ) No training required. Computational inexpensive. Simple approach - explicit rules. Skin cluster boundaries of RGB & HSV. M ( I) D ( I) D ( I) t 1 2 MHI ( x, y) t 2, if Mt ( Ixy (, )) = 1 = max(0, MHIt 1( x, y) 1), otherwise Presentation, Thessaloniki 16 March
16 Movement s Tracking Presentation, Thessaloniki 16 March
17 Body Tracker Evaluation Presentation, Thessaloniki 16 March 2011
18 Primesense TOF Sensor - OpenNI Open Source Library Real time & accurate. Human body form recognition and segmentation ecognizes the human Human body tracking by simultaneousl tracking of 48 essential points of the human body in the 3D space. Trained machine learning algorithm by millions of manually tagged images of people in different poses. OpenNI manages to adjust the most appropriate skeleton model to each human body in terms of size and pose. Presentation, Thessaloniki 16 March 2011
19 Cyberglove finger tracker 4 DoF for each finger 3 phalanxes for each finger 3 DoF for the orientation of the whole palm Time-stamped Data Presentation, Thessaloniki 16 March 2011
20 Outline Introduction Activity Detection Activity related recognition Human Tracking Reaching Part Grasping Part Classifiers Results Conclusions Presentation, Thessaloniki 16 March
21 Feature Extraction (I) x Head Right Hand Left Hand *The diameter of the dots is anti proportional to the depth of the tracked point. y Presentation, Thessaloniki 16 March
22 Phone Conversation Trajectories Subject 1 Subject 2 Subject Presentation, Thessaloniki 16 March
23 Office Panel Trajectories Subject 1 Subject 2 Subject Presentation, Thessaloniki 16 March
24 Warping the trajectory Enrollment Authentication Client: PD ( ') qpd ( ) q = = Impostor: P P Head Phone P P Head Phone Presentation, Thessaloniki 16 March
25 Feature Extraction (I) Exact location of the head/hand 3D position, at time t (timestamp tracking). v x, y, z = ds x, y, z dt Dynamic Spatial Cost a xyz,, = dv xyz,, dt S t S t x x p ( ) = p ( 1) + ( t ( t 1) ) + ( t ( t 1) ) + ( t ( t 1) ) y y z z Presentation, Thessaloniki 16 March
26 Feature Extraction (II) 26 Curvature - Derivative Torsion - Derivative abc c s b s a s s P i ) )( )( ( 4 ) ( ^ ^ ^ ^ * = κ g d b a P P P i i i s = ) ( ) ( 3 ) ( 1 * 1 * * κ κ κ ) ( 6 ) ( (6 2 1 ) ( * * * i i i P gmm H P def H P κ κ τ + = + g h d b a P P P r P P P i i s i i i i s = )) ( 6 ) / ( ) ( ( ) ( ) ( 4 ) ( * * * 1 * 1 * * κ κ τ τ τ τ Presentation, Thessaloniki 16 March 2011
27 Spatiotemporal Activity Surface 1. PCA on 3D Trajectories 2. 3-dimensional manifold trajectories using time as 3 rd dimension 3. Triangulation Presentation, Thessaloniki 16 March 2011 f ( θφ, ) = min { d( RP, s )} RP k = 1,, K i k i
28 Intra-similarity vs. Inter-variance of AS Presentation, Thessaloniki 16 March 2011
29 Static Anthropometric Attributed Graph Matching 7 Attributed Edges 8 Nodes G 7 = { V, E,{A},{B} i=1} Supports: Full-graph matching (n`=n) Sub-graph matching (n`>n) (AGM) problem: ( s ) q W j 1 j+ r B j PB = j min ' p B = PB' P ( +ε M ) T j 0 0 j j Presentation, Thessaloniki 16 March 2011
30 Confidence Factor Ergonomy 0.1 dtorso, object + 0.5, if dtorso, object < 5cm b = 1, if 5cm dtorso, object 35cm 0.02 dtorso, object + 1.7, if dtorso, object > 35cm f q = 1 N + N + N 3N misshead missrhand misslhand frames f q, final = bf q Presentation, Thessaloniki 16 March 2011
31 Outline Introduction Activity Detection Activity related recognition Human Tracking Reaching Part Grasping Part Classifiers Results Conclusions Presentation, Thessaloniki 16 March
32 F = { θ, θ,..., θ } a Feature Extraction Angle between the phalanxes of each finger, at time t (timestamp tracking). ω = dθ dt Dynamic Travel Cost θ a θ dω = = dt 2 d θ 2 dt * 2 ka j j [ Tj Tj ( aj)] Vj( aj( t), Tj) = ( )(1 + ) 2 r s T * ( a ( t)) = k ln( a + 1), k 0 The cost of moving joint j through an angle of size in the given time Presentation, Thessaloniki 16 March 2011 j j j j j Joint s optimal time 32
33 Dynamic Time Warping (DTW) Classifier Based on dynamic Programming No training required Simple Implementation Fast Area size The problem of finding the optimal warping path can be reduced to finding this sequence of nodes (x k ; y k ), which minimizes D(x k ; y k ) along the complete path. The main aim is to find the path for which the least cost is associated. Dx (, y) = Dx (, y ) + cx (, y) = cx (, y) k k ( k 1) ( k 1) k k m m m= 1 Presentation, Thessaloniki 16 March 2011 k S L L = V( p, q ) c i j i= 1 j= 1 D = S D ( LL, ) M c min Total dissimilarity
34 Hidden Markov Model (HMM) Classifier Fully connected, left-to-right, five-state (N=5) HMM. The triplet: λ = { π, α, b } j ij j π j is the probability of the j th trajectories, state being the first state among all the a ij is the probability of the j th state occurring immediately after the i th state, b j denotes the PDF of the j th state. The observational data from each state of the HMM are generated according to a PDF dependent on the instant of t th state,. b ( O ) Given HMMs for the L enrolled subjects and the new trajectory vectors, we assign user label m as the HMM that maximizes the likelihood (ML principle). S 5 j S 4 S 3 t S 1 S 2 Presentation, Thessaloniki 16 March
35 Spherical Harmonics 2l+ 1 ( l m)! Y P cos cos m isin m 4 π ( l+ m)! m ( θφ m l, ) = ( θ l )( ( φ ) + ( φ )) Spherical Harmonics series 2 l (, ) m (, ) π π (, ) m m = RPi l Ω= Ω 0 0 RPi l c f θφy θφd f θφy dθdφ Rotational Invariance: Z-Normalization: c z l c * l K l = c * l m= K µ σ Fusion among Reference Points: Presentation, Thessaloniki 16 March 2011 = y y l c m l N Spherical Harmonics coeffs. S = ws = ws + ws + + w S tot j j N N j= 1
36 Database ACTIBIO dataset (AmI indoor environment): 29 Subjects, 2 Time sessions - 8 repetitions in total, Annotated frame sequences, 5 cameras in total: 1 stereo camera (BumblebeeXB3 Point Grey Inc), 2 usb cameras (Lateral-Zenithal) Presentation, Thessaloniki 16 March
37 Outline Introduction Activity Detection Activity related recognition Human Tracking Reaching Part Grasping Part Classifiers Results Conclusions Presentation, Thessaloniki 16 March
38 Activity Detection Results Events Phone Panel Mic. Panel Drink Hands Up Phone 93.1% 0% 0% 6.9% 0% Panel 0% 89.7% 10.3% 0% 0% Mic. Panel 0% 3.44% 3.44% 93.1% 100% Drink 0% 10.3% 86.2% 3.44% 0% Presentation, Thessaloniki 16 March
39 Tracking Results Subject s No. Confidence Score Subject s No. Confidence Score Subject Subject Subject Subject Subject Subject Subject Subject Subject Presentation, Thessaloniki 16 March
40 Authentication HMM Results Phone Conv. (EER=15%) Office Panel (EER=9.8%) Presentation, Thessaloniki 16 March
41 Authentication Performance ACTIBIO Database (29 Subjects) Internal Database (15 Subjects ACTIBIO Database (29 Subjects) Score Level Fusion: S = 0.25* S * S total Phone Panel Presentation, Thessaloniki 16 March 2011
42 Recognition Performance (HMM) Presentation, Thessaloniki 16 March 2011 Score Level Fusion: S = 0.25* S * S total Phone Panel
43 Spherical Harmonics Results (EER=11.4%) (EER=15%) (EER=16.7%) Presentation, Thessaloniki 16 March 2011
44 Conclusions Recognition using just a common stereoscopic camera. Unobtrusive, on the move, continuous authentication. Significant recognition potential just by the spatial information of the trajectories. Higher authentication rates are expected, given the relative entropies. Rotational invariance from spherical harmonics analysis. Privacy enabled method, since no obtrusive information is stored. Activity-related biometric authentication provided very promising results and is expected to maximize the performance of a multimodal biometric system. Presentation, Thessaloniki 16 March
Biometrics: Introduction and Examples. Raymond Veldhuis
Biometrics: Introduction and Examples Raymond Veldhuis 1 Overview Biometric recognition Face recognition Challenges Transparent face recognition Large-scale identification Watch list Anonymous biometrics
More informationCITS 4402 Computer Vision
CITS 4402 Computer Vision A/Prof Ajmal Mian Adj/A/Prof Mehdi Ravanbakhsh Lecture 06 Object Recognition Objectives To understand the concept of image based object recognition To learn how to match images
More informationTemporal Modeling and Basic Speech Recognition
UNIVERSITY ILLINOIS @ URBANA-CHAMPAIGN OF CS 498PS Audio Computing Lab Temporal Modeling and Basic Speech Recognition Paris Smaragdis paris@illinois.edu paris.cs.illinois.edu Today s lecture Recognizing
More informationScore Normalization in Multimodal Biometric Systems
Score Normalization in Multimodal Biometric Systems Karthik Nandakumar and Anil K. Jain Michigan State University, East Lansing, MI Arun A. Ross West Virginia University, Morgantown, WV http://biometrics.cse.mse.edu
More informationDynamic Data Modeling, Recognition, and Synthesis. Rui Zhao Thesis Defense Advisor: Professor Qiang Ji
Dynamic Data Modeling, Recognition, and Synthesis Rui Zhao Thesis Defense Advisor: Professor Qiang Ji Contents Introduction Related Work Dynamic Data Modeling & Analysis Temporal localization Insufficient
More informationJoint Factor Analysis for Speaker Verification
Joint Factor Analysis for Speaker Verification Mengke HU ASPITRG Group, ECE Department Drexel University mengke.hu@gmail.com October 12, 2012 1/37 Outline 1 Speaker Verification Baseline System Session
More informationThis is an accepted version of a paper published in Elsevier Information Fusion. If you wish to cite this paper, please use the following reference:
This is an accepted version of a paper published in Elsevier Information Fusion. If you wish to cite this paper, please use the following reference: T. Murakami, T. Ohki, K. Takahashi, Optimal sequential
More informationHMM and IOHMM Modeling of EEG Rhythms for Asynchronous BCI Systems
HMM and IOHMM Modeling of EEG Rhythms for Asynchronous BCI Systems Silvia Chiappa and Samy Bengio {chiappa,bengio}@idiap.ch IDIAP, P.O. Box 592, CH-1920 Martigny, Switzerland Abstract. We compare the use
More informationRecognition Using Class Specific Linear Projection. Magali Segal Stolrasky Nadav Ben Jakov April, 2015
Recognition Using Class Specific Linear Projection Magali Segal Stolrasky Nadav Ben Jakov April, 2015 Articles Eigenfaces vs. Fisherfaces Recognition Using Class Specific Linear Projection, Peter N. Belhumeur,
More informationInformation geometry for bivariate distribution control
Information geometry for bivariate distribution control C.T.J.Dodson + Hong Wang Mathematics + Control Systems Centre, University of Manchester Institute of Science and Technology Optimal control of stochastic
More informationFace detection and recognition. Detection Recognition Sally
Face detection and recognition Detection Recognition Sally Face detection & recognition Viola & Jones detector Available in open CV Face recognition Eigenfaces for face recognition Metric learning identification
More informationFace Detection and Recognition
Face Detection and Recognition Face Recognition Problem Reading: Chapter 18.10 and, optionally, Face Recognition using Eigenfaces by M. Turk and A. Pentland Queryimage face query database Face Verification
More informationECE 661: Homework 10 Fall 2014
ECE 661: Homework 10 Fall 2014 This homework consists of the following two parts: (1) Face recognition with PCA and LDA for dimensionality reduction and the nearest-neighborhood rule for classification;
More informationRobust Speaker Identification
Robust Speaker Identification by Smarajit Bose Interdisciplinary Statistical Research Unit Indian Statistical Institute, Kolkata Joint work with Amita Pal and Ayanendranath Basu Overview } } } } } } }
More informationUnsupervised Anomaly Detection for High Dimensional Data
Unsupervised Anomaly Detection for High Dimensional Data Department of Mathematics, Rowan University. July 19th, 2013 International Workshop in Sequential Methodologies (IWSM-2013) Outline of Talk Motivation
More informationTime Series Classification
Distance Measures Classifiers DTW vs. ED Further Work Questions August 31, 2017 Distance Measures Classifiers DTW vs. ED Further Work Questions Outline 1 2 Distance Measures 3 Classifiers 4 DTW vs. ED
More informationOrientation Map Based Palmprint Recognition
Orientation Map Based Palmprint Recognition (BM) 45 Orientation Map Based Palmprint Recognition B. H. Shekar, N. Harivinod bhshekar@gmail.com, harivinodn@gmail.com India, Mangalore University, Department
More informationFingerprint Individuality
Fingerprint Individuality On the Individuality of Fingerprints, Sharat Pankanti, Anil Jain and Salil Prabhakar, IEEE Transactions on PAMI, 2002 US DOJ, Office of the Inspector General, A Review of the
More informationOutline: Ensemble Learning. Ensemble Learning. The Wisdom of Crowds. The Wisdom of Crowds - Really? Crowd wiser than any individual
Outline: Ensemble Learning We will describe and investigate algorithms to Ensemble Learning Lecture 10, DD2431 Machine Learning A. Maki, J. Sullivan October 2014 train weak classifiers/regressors and how
More informationModeling Complex Temporal Composition of Actionlets for Activity Prediction
Modeling Complex Temporal Composition of Actionlets for Activity Prediction ECCV 2012 Activity Recognition Reading Group Framework of activity prediction What is an Actionlet To segment a long sequence
More information2D Image Processing Face Detection and Recognition
2D Image Processing Face Detection and Recognition Prof. Didier Stricker Kaiserlautern University http://ags.cs.uni-kl.de/ DFKI Deutsches Forschungszentrum für Künstliche Intelligenz http://av.dfki.de
More informationHuman Mobility Pattern Prediction Algorithm using Mobile Device Location and Time Data
Human Mobility Pattern Prediction Algorithm using Mobile Device Location and Time Data 0. Notations Myungjun Choi, Yonghyun Ro, Han Lee N = number of states in the model T = length of observation sequence
More informationIf you wish to cite this paper, please use the following reference:
This is an accepted version of a paper published in Proceedings of the st IEEE International Workshop on Information Forensics and Security (WIFS 2009). If you wish to cite this paper, please use the following
More informationBoosting: Algorithms and Applications
Boosting: Algorithms and Applications Lecture 11, ENGN 4522/6520, Statistical Pattern Recognition and Its Applications in Computer Vision ANU 2 nd Semester, 2008 Chunhua Shen, NICTA/RSISE Boosting Definition
More informationFace recognition Computer Vision Spring 2018, Lecture 21
Face recognition http://www.cs.cmu.edu/~16385/ 16-385 Computer Vision Spring 2018, Lecture 21 Course announcements Homework 6 has been posted and is due on April 27 th. - Any questions about the homework?
More informationPalmprint based Verification System Robust to Occlusion using Low-order Zernike Moments of Sub-images
BADRINATH, NARESH, GUPTA: PALMPRINT BASED VERIFICATION SYSTEM 1 Palmprint based Verification System Robust to Occlusion using Low-order Zernike Moments of Sub-images Badrinath G. S. badri@cse.iitk.ac.in
More informationJun Zhang Department of Computer Science University of Kentucky
Application i of Wavelets in Privacy-preserving Data Mining Jun Zhang Department of Computer Science University of Kentucky Outline Privacy-preserving in Collaborative Data Analysis Advantages of Wavelets
More informationArtificial Intelligence & Neuro Cognitive Systems Fakultät für Informatik. Robot Dynamics. Dr.-Ing. John Nassour J.
Artificial Intelligence & Neuro Cognitive Systems Fakultät für Informatik Robot Dynamics Dr.-Ing. John Nassour 25.1.218 J.Nassour 1 Introduction Dynamics concerns the motion of bodies Includes Kinematics
More informationScore calibration for optimal biometric identification
Score calibration for optimal biometric identification (see also NIST IBPC 2010 online proceedings: http://biometrics.nist.gov/ibpc2010) AI/GI/CRV 2010, Ottawa Dmitry O. Gorodnichy Head of Video Surveillance
More informationLatent Variable Models and Expectation Maximization
Latent Variable Models and Expectation Maximization Oliver Schulte - CMPT 726 Bishop PRML Ch. 9 2 4 6 8 1 12 14 16 18 2 4 6 8 1 12 14 16 18 5 1 15 2 25 5 1 15 2 25 2 4 6 8 1 12 14 2 4 6 8 1 12 14 5 1 15
More informationForward algorithm vs. particle filtering
Particle Filtering ØSometimes X is too big to use exact inference X may be too big to even store B(X) E.g. X is continuous X 2 may be too big to do updates ØSolution: approximate inference Track samples
More informationAruna Bhat Research Scholar, Department of Electrical Engineering, IIT Delhi, India
International Journal of Scientific Research in Computer Science, Engineering and Information Technology 2017 IJSRCSEIT Volume 2 Issue 6 ISSN : 2456-3307 Robust Face Recognition System using Non Additive
More informationFINAL: CS 6375 (Machine Learning) Fall 2014
FINAL: CS 6375 (Machine Learning) Fall 2014 The exam is closed book. You are allowed a one-page cheat sheet. Answer the questions in the spaces provided on the question sheets. If you run out of room for
More informationVideo and Motion Analysis Computer Vision Carnegie Mellon University (Kris Kitani)
Video and Motion Analysis 16-385 Computer Vision Carnegie Mellon University (Kris Kitani) Optical flow used for feature tracking on a drone Interpolated optical flow used for super slow-mo optical flow
More informationEigenface-based facial recognition
Eigenface-based facial recognition Dimitri PISSARENKO December 1, 2002 1 General This document is based upon Turk and Pentland (1991b), Turk and Pentland (1991a) and Smith (2002). 2 How does it work? The
More informationE = K + U. p mv. p i = p f. F dt = p. J t 1. a r = v2. F c = m v2. s = rθ. a t = rα. r 2 dm i. m i r 2 i. I ring = MR 2.
v = v i + at x = x i + v i t + 1 2 at2 E = K + U p mv p i = p f L r p = Iω τ r F = rf sin θ v 2 = v 2 i + 2a x F = ma = dp dt = U v dx dt a dv dt = d2 x dt 2 A circle = πr 2 A sphere = 4πr 2 V sphere =
More informationAdvanced Machine Learning & Perception
Advanced Machine Learning & Perception Instructor: Tony Jebara Topic 1 Introduction, researchy course, latest papers Going beyond simple machine learning Perception, strange spaces, images, time, behavior
More informationChange Detection in Optical Aerial Images by a Multi-Layer Conditional Mixed Markov Model
Change Detection in Optical Aerial Images by a Multi-Layer Conditional Mixed Markov Model Csaba Benedek 12 Tamás Szirányi 1 1 Distributed Events Analysis Research Group Computer and Automation Research
More informationSTA 4273H: Statistical Machine Learning
STA 4273H: Statistical Machine Learning Russ Salakhutdinov Department of Statistics! rsalakhu@utstat.toronto.edu! http://www.utstat.utoronto.ca/~rsalakhu/ Sidney Smith Hall, Room 6002 Lecture 11 Project
More informationTennis player segmentation for semantic behavior analysis
Proposta di Tennis player segmentation for semantic behavior analysis Architettura Software per Robot Mobili Vito Renò, Nicola Mosca, Massimiliano Nitti, Tiziana D Orazio, Donato Campagnoli, Andrea Prati,
More informationShankar Shivappa University of California, San Diego April 26, CSE 254 Seminar in learning algorithms
Recognition of Visual Speech Elements Using Adaptively Boosted Hidden Markov Models. Say Wei Foo, Yong Lian, Liang Dong. IEEE Transactions on Circuits and Systems for Video Technology, May 2004. Shankar
More informationAdvanced Machine Learning & Perception
Advanced Machine Learning & Perception Instructor: Tony Jebara Topic 1 Introduction, researchy course, latest papers Going beyond simple machine learning Perception, strange spaces, images, time, behavior
More informationHMM part 1. Dr Philip Jackson
Centre for Vision Speech & Signal Processing University of Surrey, Guildford GU2 7XH. HMM part 1 Dr Philip Jackson Probability fundamentals Markov models State topology diagrams Hidden Markov models -
More informationPCA FACE RECOGNITION
PCA FACE RECOGNITION The slides are from several sources through James Hays (Brown); Srinivasa Narasimhan (CMU); Silvio Savarese (U. of Michigan); Shree Nayar (Columbia) including their own slides. Goal
More informationRecent Advances in Bayesian Inference Techniques
Recent Advances in Bayesian Inference Techniques Christopher M. Bishop Microsoft Research, Cambridge, U.K. research.microsoft.com/~cmbishop SIAM Conference on Data Mining, April 2004 Abstract Bayesian
More informationLearning to Disentangle Factors of Variation with Manifold Learning
Learning to Disentangle Factors of Variation with Manifold Learning Scott Reed Kihyuk Sohn Yuting Zhang Honglak Lee University of Michigan, Department of Electrical Engineering and Computer Science 08
More informationAround the Speaker De-Identification (Speaker diarization for de-identification ++) Itshak Lapidot Moez Ajili Jean-Francois Bonastre
Around the Speaker De-Identification (Speaker diarization for de-identification ++) Itshak Lapidot Moez Ajili Jean-Francois Bonastre The 2 Parts HDM based diarization System The homogeneity measure 2 Outline
More informationRobotics 2 AdaBoost for People and Place Detection
Robotics 2 AdaBoost for People and Place Detection Giorgio Grisetti, Cyrill Stachniss, Kai Arras, Wolfram Burgard v.1.0, Kai Arras, Oct 09, including material by Luciano Spinello and Oscar Martinez Mozos
More informationUniversität Potsdam Institut für Informatik Lehrstuhl Maschinelles Lernen. Decision Trees. Tobias Scheffer
Universität Potsdam Institut für Informatik Lehrstuhl Maschinelles Lernen Decision Trees Tobias Scheffer Decision Trees One of many applications: credit risk Employed longer than 3 months Positive credit
More informationMobile Robot Localization
Mobile Robot Localization 1 The Problem of Robot Localization Given a map of the environment, how can a robot determine its pose (planar coordinates + orientation)? Two sources of uncertainty: - observations
More informationI D I A P R E S E A R C H R E P O R T. Samy Bengio a. November submitted for publication
R E S E A R C H R E P O R T I D I A P Why Do Multi-Stream, Multi-Band and Multi-Modal Approaches Work on Biometric User Authentication Tasks? Norman Poh Hoon Thian a IDIAP RR 03-59 November 2003 Samy Bengio
More information10. Hidden Markov Models (HMM) for Speech Processing. (some slides taken from Glass and Zue course)
10. Hidden Markov Models (HMM) for Speech Processing (some slides taken from Glass and Zue course) Definition of an HMM The HMM are powerful statistical methods to characterize the observed samples of
More informationCOS 429: COMPUTER VISON Face Recognition
COS 429: COMPUTER VISON Face Recognition Intro to recognition PCA and Eigenfaces LDA and Fisherfaces Face detection: Viola & Jones (Optional) generic object models for faces: the Constellation Model Reading:
More informationMachine Learning - MT Clustering
Machine Learning - MT 2016 15. Clustering Varun Kanade University of Oxford November 28, 2016 Announcements No new practical this week All practicals must be signed off in sessions this week Firm Deadline:
More informationExpectation Maximization
Expectation Maximization Bishop PRML Ch. 9 Alireza Ghane c Ghane/Mori 4 6 8 4 6 8 4 6 8 4 6 8 5 5 5 5 5 5 4 6 8 4 4 6 8 4 5 5 5 5 5 5 µ, Σ) α f Learningscale is slightly Parameters is slightly larger larger
More informationTechnical Report. Results from 200 billion iris cross-comparisons. John Daugman. Number 635. June Computer Laboratory
Technical Report UCAM-CL-TR-635 ISSN 1476-2986 Number 635 Computer Laboratory Results from 200 billion iris cross-comparisons John Daugman June 2005 15 JJ Thomson Avenue Cambridge CB3 0FD United Kingdom
More informationIntroduction to Boosting and Joint Boosting
Introduction to Boosting and Learning Systems Group, Caltech 2005/04/26, Presentation in EE150 Boosting and Outline Introduction to Boosting 1 Introduction to Boosting Intuition of Boosting Adaptive Boosting
More informationUndirected Graphical Models
Outline Hong Chang Institute of Computing Technology, Chinese Academy of Sciences Machine Learning Methods (Fall 2012) Outline Outline I 1 Introduction 2 Properties Properties 3 Generative vs. Conditional
More informationLatent Variable Models and Expectation Maximization
Latent Variable Models and Expectation Maximization Oliver Schulte - CMPT 726 Bishop PRML Ch. 9 2 4 6 8 1 12 14 16 18 2 4 6 8 1 12 14 16 18 5 1 15 2 25 5 1 15 2 25 2 4 6 8 1 12 14 2 4 6 8 1 12 14 5 1 15
More informationSpectral Clustering with Eigenvector Selection
Spectral Clustering with Eigenvector Selection Tao Xiang and Shaogang Gong Department of Computer Science Queen Mary, University of London, London E 4NS, UK {txiang,sgg}@dcs.qmul.ac.uk Abstract The task
More informationCourse 495: Advanced Statistical Machine Learning/Pattern Recognition
Course 495: Advanced Statistical Machine Learning/Pattern Recognition Lecturer: Stefanos Zafeiriou Goal (Lectures): To present discrete and continuous valued probabilistic linear dynamical systems (HMMs
More informationHuman Pose Tracking I: Basics. David Fleet University of Toronto
Human Pose Tracking I: Basics David Fleet University of Toronto CIFAR Summer School, 2009 Looking at People Challenges: Complex pose / motion People have many degrees of freedom, comprising an articulated
More informationSpectral clustering with eigenvector selection
Pattern Recognition 41 (2008) 1012 1029 www.elsevier.com/locate/pr Spectral clustering with eigenvector selection Tao Xiang, Shaogang Gong Department of Computer Science, Queen Mary, University of London,
More informationActivity Mining in Sensor Networks
MITSUBISHI ELECTRIC RESEARCH LABORATORIES http://www.merl.com Activity Mining in Sensor Networks Christopher R. Wren, David C. Minnen TR2004-135 December 2004 Abstract We present results from the exploration
More informationExample: Face Detection
Announcements HW1 returned New attendance policy Face Recognition: Dimensionality Reduction On time: 1 point Five minutes or more late: 0.5 points Absent: 0 points Biometrics CSE 190 Lecture 14 CSE190,
More informationReconnaissance d objetsd et vision artificielle
Reconnaissance d objetsd et vision artificielle http://www.di.ens.fr/willow/teaching/recvis09 Lecture 6 Face recognition Face detection Neural nets Attention! Troisième exercice de programmation du le
More informationSpectral Clustering of Polarimetric SAR Data With Wishart-Derived Distance Measures
Spectral Clustering of Polarimetric SAR Data With Wishart-Derived Distance Measures STIAN NORMANN ANFINSEN ROBERT JENSSEN TORBJØRN ELTOFT COMPUTATIONAL EARTH OBSERVATION AND MACHINE LEARNING LABORATORY
More informationCSCI-567: Machine Learning (Spring 2019)
CSCI-567: Machine Learning (Spring 2019) Prof. Victor Adamchik U of Southern California Mar. 19, 2019 March 19, 2019 1 / 43 Administration March 19, 2019 2 / 43 Administration TA3 is due this week March
More informationFINAL EXAM: FALL 2013 CS 6375 INSTRUCTOR: VIBHAV GOGATE
FINAL EXAM: FALL 2013 CS 6375 INSTRUCTOR: VIBHAV GOGATE You are allowed a two-page cheat sheet. You are also allowed to use a calculator. Answer the questions in the spaces provided on the question sheets.
More informationMachine Learning for OR & FE
Machine Learning for OR & FE Hidden Markov Models Martin Haugh Department of Industrial Engineering and Operations Research Columbia University Email: martin.b.haugh@gmail.com Additional References: David
More informationEECS490: Digital Image Processing. Lecture #26
Lecture #26 Moments; invariant moments Eigenvector, principal component analysis Boundary coding Image primitives Image representation: trees, graphs Object recognition and classes Minimum distance classifiers
More informationUser Requirements, Modelling e Identification. Lezione 1 prj Mesa (Prof. Ing N. Muto)
User Requirements, Modelling e Identification. Lezione 1 prj Mesa (Prof. Ing N. Muto) 1.1 Introduction: A customer has requested the establishment of a system for the automatic orientation of a string
More informationDeriving Principal Component Analysis (PCA)
-0 Mathematical Foundations for Machine Learning Machine Learning Department School of Computer Science Carnegie Mellon University Deriving Principal Component Analysis (PCA) Matt Gormley Lecture 11 Oct.
More informationAdvanced Machine Learning & Perception
Advanced Machine Learning & Perception Instructor: Tony Jebara Topic 6 Standard Kernels Unusual Input Spaces for Kernels String Kernels Probabilistic Kernels Fisher Kernels Probability Product Kernels
More informationA brief introduction to Conditional Random Fields
A brief introduction to Conditional Random Fields Mark Johnson Macquarie University April, 2005, updated October 2010 1 Talk outline Graphical models Maximum likelihood and maximum conditional likelihood
More informationFinal Examination CS540-2: Introduction to Artificial Intelligence
Final Examination CS540-2: Introduction to Artificial Intelligence May 9, 2018 LAST NAME: SOLUTIONS FIRST NAME: Directions 1. This exam contains 33 questions worth a total of 100 points 2. Fill in your
More informationClassification for High Dimensional Problems Using Bayesian Neural Networks and Dirichlet Diffusion Trees
Classification for High Dimensional Problems Using Bayesian Neural Networks and Dirichlet Diffusion Trees Rafdord M. Neal and Jianguo Zhang Presented by Jiwen Li Feb 2, 2006 Outline Bayesian view of feature
More informationPredictive analysis on Multivariate, Time Series datasets using Shapelets
1 Predictive analysis on Multivariate, Time Series datasets using Shapelets Hemal Thakkar Department of Computer Science, Stanford University hemal@stanford.edu hemal.tt@gmail.com Abstract Multivariate,
More informationShape of Gaussians as Feature Descriptors
Shape of Gaussians as Feature Descriptors Liyu Gong, Tianjiang Wang and Fang Liu Intelligent and Distributed Computing Lab, School of Computer Science and Technology Huazhong University of Science and
More informationHidden Markov Models Part 1: Introduction
Hidden Markov Models Part 1: Introduction CSE 6363 Machine Learning Vassilis Athitsos Computer Science and Engineering Department University of Texas at Arlington 1 Modeling Sequential Data Suppose that
More informationSymmetries 2 - Rotations in Space
Symmetries 2 - Rotations in Space This symmetry is about the isotropy of space, i.e. space is the same in all orientations. Thus, if we continuously rotated an entire system in space, we expect the system
More informationMachine Learning Basics
Security and Fairness of Deep Learning Machine Learning Basics Anupam Datta CMU Spring 2019 Image Classification Image Classification Image classification pipeline Input: A training set of N images, each
More informationRelational Event Modeling: Basic Framework and Applications. Aaron Schecter & Noshir Contractor Northwestern University
Relational Event Modeling: Basic Framework and Applications Aaron Schecter & Noshir Contractor Northwestern University Why Use Relational Events? Social network analysis has two main frames of reference;
More informationINTEGRATING RECOGNITION AND REASONING IN SMART ENVIRONMENTS
INTEGRATING RECOGNITION AND REASONING IN SMART ENVIRONMENTS Vivek Menon, Bharat Jayaraman, Venu Govindaraju Amrita University, Coimbatore 641 105, India vivek menon@ettimadai.amrita.edu University at Buffalo,
More informationQualifier: CS 6375 Machine Learning Spring 2015
Qualifier: CS 6375 Machine Learning Spring 2015 The exam is closed book. You are allowed to use two double-sided cheat sheets and a calculator. If you run out of room for an answer, use an additional sheet
More informationIndependent Component Analysis and Unsupervised Learning. Jen-Tzung Chien
Independent Component Analysis and Unsupervised Learning Jen-Tzung Chien TABLE OF CONTENTS 1. Independent Component Analysis 2. Case Study I: Speech Recognition Independent voices Nonparametric likelihood
More informationIndependent Component Analysis and Unsupervised Learning
Independent Component Analysis and Unsupervised Learning Jen-Tzung Chien National Cheng Kung University TABLE OF CONTENTS 1. Independent Component Analysis 2. Case Study I: Speech Recognition Independent
More informationRecurrent Autoregressive Networks for Online Multi-Object Tracking. Presented By: Ishan Gupta
Recurrent Autoregressive Networks for Online Multi-Object Tracking Presented By: Ishan Gupta Outline Multi Object Tracking Recurrent Autoregressive Networks (RANs) RANs for Online Tracking Other State
More informationSpeaker Representation and Verification Part II. by Vasileios Vasilakakis
Speaker Representation and Verification Part II by Vasileios Vasilakakis Outline -Approaches of Neural Networks in Speaker/Speech Recognition -Feed-Forward Neural Networks -Training with Back-propagation
More informationGraphical Object Models for Detection and Tracking
Graphical Object Models for Detection and Tracking (ls@cs.brown.edu) Department of Computer Science Brown University Joined work with: -Ying Zhu, Siemens Corporate Research, Princeton, NJ -DorinComaniciu,
More informationRotation. Rotational Variables
Rotation Rigid Bodies Rotation variables Constant angular acceleration Rotational KE Rotational Inertia Rotational Variables Rotation of a rigid body About a fixed rotation axis. Rigid Body an object that
More informationSTA 414/2104: Machine Learning
STA 414/2104: Machine Learning Russ Salakhutdinov Department of Computer Science! Department of Statistics! rsalakhu@cs.toronto.edu! http://www.cs.toronto.edu/~rsalakhu/ Lecture 9 Sequential Data So far
More informationStatistical and Learning Techniques in Computer Vision Lecture 2: Maximum Likelihood and Bayesian Estimation Jens Rittscher and Chuck Stewart
Statistical and Learning Techniques in Computer Vision Lecture 2: Maximum Likelihood and Bayesian Estimation Jens Rittscher and Chuck Stewart 1 Motivation and Problem In Lecture 1 we briefly saw how histograms
More informationECE 521. Lecture 11 (not on midterm material) 13 February K-means clustering, Dimensionality reduction
ECE 521 Lecture 11 (not on midterm material) 13 February 2017 K-means clustering, Dimensionality reduction With thanks to Ruslan Salakhutdinov for an earlier version of the slides Overview K-means clustering
More informationOptimal Control Problems in Eye Movement. Bijoy K. Ghosh Department of Mathematics and Statistics Texas Tech University, Lubbock, TX
Optimal Control Problems in Eye Movement Bijoy K. Ghosh Department of Mathematics and Statistics Texas Tech University, Lubbock, TX We study the human oculomotor system as a simple mechanical control
More informationMaster of Intelligent Systems - French-Czech Double Diploma. Hough transform
Hough transform I- Introduction The Hough transform is used to isolate features of a particular shape within an image. Because it requires that the desired features be specified in some parametric form,
More informationRole of Assembling Invariant Moments and SVM in Fingerprint Recognition
56 Role of Assembling Invariant Moments SVM in Fingerprint Recognition 1 Supriya Wable, 2 Chaitali Laulkar 1, 2 Department of Computer Engineering, University of Pune Sinhgad College of Engineering, Pune-411
More informationMissing Data and Dynamical Systems
U NIVERSITY OF ILLINOIS AT URBANA-CHAMPAIGN CS598PS Machine Learning for Signal Processing Missing Data and Dynamical Systems 12 October 2017 Today s lecture Dealing with missing data Tracking and linear
More informationClustering and Gaussian Mixtures
Clustering and Gaussian Mixtures Oliver Schulte - CMPT 883 2 4 6 8 1 12 14 16 18 2 4 6 8 1 12 14 16 18 5 1 15 2 25 5 1 15 2 25 2 4 6 8 1 12 14 2 4 6 8 1 12 14 5 1 15 2 25 5 1 15 2 25 detected tures detected
More information