Computer Vision Object and People Tracking

Size: px
Start display at page:

Download "Computer Vision Object and People Tracking"

Transcription

1 Computer Vision Object and People Prof. Didier Stricker Doz. Dr. Gabriele Bleser Kaiserlautern University DFKI Deutsches Forschungszentrum für Künstliche Intelligenz

2 AG Augmented Vision Uni-KL und DFKI Research Computer vision: 3D reconstruction and object recognition/tracking Sensor fusion: (body) motion tracking and activity recognition Visualization and rendering: realistic rendering, visualization and interaction Application domains Virtual Engineering Ambient Assisted Living Safety and Security

3 Computer Vision: Object and People Lecture: Monday 08:00 09:30 Room: SWS: 2V+1Ü Credit point: 4 LP Language: English

4 Object and People : lecture Topics Introduction Basics on image processing Edge, corner and blob detection Feature descriptors and matching Background modelling and subtraction Feature tracking and optical flow Recursive estimation Bayesian tracking (Extended) Kalman filter Particle filter Advanced tracking and applications

5 Object and People : exercises 4 exercise sheets and tutorial sessions planned throughout semester dates and material will be published on the website Theoretical questions + implementation tasks (Matlab) Answers to questions and implementations MUST be handed in (submission after approx. 1 week) Groups of up to 4 students are allowed Tutorial sessions shortly after submission deadline: discussion of questions, solution of implementation tasks

6 Contact Prof. Didier Stricker Dr. Gabriele Bleser: -> Teaching

7 Other courses taught by AV SS 2014: Seminar 3D Computer Vision & Augmented Reality, 4 CP Project 3D Computer Vision & Augmented Reality, 8 CP WS 2014/15 Lecture 3D Computer Vision, 4 CP, 2+1 Seminar Computer Vision: Object and People, 4 CP Project Computer Vision: Object and People, 8 CP Build upon OPT We also offer student jobs in various areas (CV, sensor fusion, HCI, ). Check the website, or just ask us! 3DCV topics: complementary to OPT Camera model and camera calibration Fitting and parameter estimation (deterministic) Two and multiple view reconstruction Structure from motion Dense reconstruction

8 What is Visual? Video tracking is the process of locating a moving object (or multiple objects) over time using a camera. The objective of video tracking is to associate target objects in consecutive video frames. -- Models of the objects are supposed to be available in advance, from which the relevant image features can be automatically selected.

9 What is tracking? detection recognition tracking Blair Bush Chirac

10 What is tracking? Definition: using image measurements and a predictive dynamic model to consistently estimate the state(s) Xt of one or more object(s) over the discrete time steps corresponding to video frames. X t-1 X t X t+1 t-1 t t+1 10

11 What is tracking? Why not just do detection? Estimate the state X at each time step - inefficient - data association problem

12 What is tracking? It s better to do tracking Maintain an estimate of X over time, predict the future location + efficient, restricts search space + smoothes noisy measurements - requires knowledge about object behavior 12

13 assumptions Smooth camera No instant transitions between viewpoints Any camera pose/parameter changes are gradual Object motion can be modeled Linear models Non-linear models Likelihood of object presence at a location in the image can be modeled Typically uses local image information 13

14 Approaches to tracking Sequential (recursive, online) + Inexpensive real-time - no future information - cannot revisit past errors Batch Processing (offline) - Expensive not real-time + considers all information + can correct past errors t=1,,t t-1 t t+1

15 Approaches to tracking Parallel trackers several single-object trackers computationally less expensive how to handle interaction, cross-overs? Joint state single multi-object representation computationally expensive principled interaction models x t x t x t x t x t x t x t x t x t x t x t 15

16 Approaches to tracking Non-probabilistic + quick convergence + efficient - stuck in local minima - does not model multiple objects Probabilistic + flexible, principled + multi-modal - slower - interpretation 16

17 applications 17

18 Abstraction: the 3 main aspects of object tracking Models Object Vision From: Giorgio Panin Book: Model-based Visual

19 Prior Models

20 Object model Object model Models Object Giorgio Panin, TUM-Informatik VI

21 Object model ground shape Shape Object model Models 2D model Object 3D (polyhedral) 3D mesh (approximate round surfaces)

22 Object model appearance Shape Object model Appearance Models Reference images Object Surface colors Texture map

23 Object model degrees of freedom Shape Object model Appearance Degrees of freedom Models 2D transformation Object 3D (rigid) 3D (deformable)

24 Object model temporal dynamics Shape Appearance Degrees of freedom Object model Models t0 t1 t3 t2 Random motion Temporal dynamics Object t0 tk ti Smooth trajectory (free) t0 t1 t2 Smooth motion (constrained)

25 Sensor models Sensors Models Object

26 Sensor models Sensors External (camera positions) Internal (projection model) Models Object

27 Context information Context Models Object Background Environment constraints Light sources Target interactions

28 Model adaptation from a prototype If we know the class that the model belongs to, we may adapt a prototype of this class to the specific object to be tracked. Example 1: head shape adapts the prototype using feature lines Example 2: pin-hole camera model Estimate focal length and resolution ry f rx

29 Visual data processing

30 Example: Model features for tracking Shape blobs Intensity gradients Contour lines Color statistics Texture template Motion (optical flow) Local keypoints

31 Visual modalities and features Natural features Color Motion Edges Keypoints Texture Modalities Object Vision

32 Data association Associate data to target/background Multi-target: solve ambiguities Missing detection x x x x Vision Object x x x False alarms Predicted pose and covariances x Measurements Data association

33 Multi-modal data fusion Object Vision Combine multiple information sources, at different levels Multi-modal data fusion Improve robustness, adaptivity

34 Multi-sensor data fusion + Object Vision Combine multi-camera information Multi-sensor data fusion Improve robustness, adaptivity

35 Likelihood models Pixel-level measurement Predicted shadow Object Segmented image Vision Measurement likelihood = how good is our prediction Error image

36 Likelihood models Pixel level Feature level Predicted features Object Vision Likelihood Matched data

37 Likelihood models Pixel level Feature level Object level Object Predicted state Estimated state Likelihood Vision

38 The tracking pipeline

39 Image acquisition Object Image acquisition

40 Initial target detection Object Time 0: Detection

41 State prediction Object Last estimates New pose? Time t: Prediction

42 Data processing (measurement) Object Measurement

43 Data association and fusion Object Data association

44 State update Object Correction

45 The tracking pipeline 1. Acquire New image 2. Predict object position 3. Measure Feature points Last estimates New pose? RESULT: Estimated pose 5. Correct the prediction 4. Match model features

46 The tracking pipeline 2. Prediction 3. Measurement 1. Image acquisition 4. Model matching 5. Correction

47 A general tracking system Main components of a tracking system Detection and loss detection: (re-)initialize the system : measurement processing and state update Models: all useful prior information about objects, sensors, and environment t It Visual Processing Measurement Prediction Output Update It Object Detection Initial estimate Loss Detection Shape Appearance Degrees of freedom Models Dynamics Sensors Context

48 Detection vs. tracking Detection = find the object without any prior prediction, only with the model Only static data association and measurement fusion can be done The search is global (over the full state-space) coarse and slow Features must be invariant to viewpoint change = update the object state(s) using the previous state and the dynamical model Dynamic data association/fusion can be done Search is local (around the predicted features/states) fast and accurate Features do not have to be invariant (the viewpoint is not much different)

49 Resume: tracking on a slide Object Sensors Context Models Image acquisition Modalities Object Detection / Prediction Likelihood Vision Measurement Data association Data fusion State update

50 What is the state of the art? Major sources of difficulties

51 What is the state of the art? Despite being classic computer vision problem, tracking is largely unsolved Some limited successes No general-purpose tracker No standard data corpus for comparison No standard evaluation methodology Challenging problems remain

52 Obstacles to tracking appearance change occlusion distraction illumination change difficult motion multiple objects scale change Ruei-Sung Lin, David Ross, Jongwoo Lim, Ming-Hsuan Yang, Adaptive discriminative generative model and its Applications Neural Information Processing Systems Conference (NIPS), 2004 Slide: Kevin Smith

53 Obstacles to tracking appearance change occlusion distraction illumination change difficult motion multiple objects scale change Amit Adam, Ehud Rivlin and Ilan Shimshoni, Robust Fragments-based using the Integral Histogram (pdf). IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2006

54 Obstacles to tracking appearance change occlusion distraction illumination change difficult motion multiple objects scale change Michael Isard and Andrew Blake CONDENSATION -- conditional density propagation for visual tracking International Journal of Computer Vision (IJCV), 29, 1, 5--28, (1998)

55 Obstacles to tracking appearance change occlusion distraction illumination change difficult motion multiple objects scale change Ruei-Sung Lin, David Ross, Jongwoo Lim, Ming-Hsuan Yang, Adaptive discriminative generative model and its 55 Applications Neural Information Processing Systems Conference (NIPS), 2004

56 Obstacles to tracking appearance change occlusion distraction illumination change difficult motion multiple objects scale change Michael Isard and Andrew Blake CONDENSATION -- conditional density propagation for visual tracking International Journal of Computer Vision (IJCV), 29, 1, 5--28, (1998)

57 Obstacles to tracking appearance change occlusion distraction illumination change difficult motion multiple objects scale change Saad Ali and Mubarak Shah, Floor Fields for in High Density Crowd Scenes, European Conference on Computer Vision (ECCV), 2008.

58 Obstacles to tracking appearance change occlusion distraction illumination change difficult motion multiple objects scale change Shawn Lankton, James Malcolm, Arie Nakhmani, and Allen Tannenbaum. Through Changes in Scale Proceedings of International Conference on Image Processing (ICIP), 2008.

59 Application examples

60 applications is an essential step in many computer vision based applications Detection + Feature Extraction Activity Recognition + Event Recognition Behavior Analysis + Social Models Prithwijit Guha, Amitabha Mukerjee and K. S. Venkatesh, Spatio-temporal Discovery: Appearance + Behavior = Agent, Computer Vision, Graphics and Image Processing , 2007

61 applications Surveillance 61 K. Smith, P. Quelhas, and D. Gatica-Perez, Detecting Abandoned Luggage Items in a Public Space, Performance Evaluation of and Surveillance (PETS) Workshop at CVPR, New York, NY, June

62 applications Biological Research Goal: develop a method to trap Salmonella bacteria P. Horvath, Q. Buhkari, 3D of point-like objects in 2D image sequences, LMC, ETHZ

63 Thank You!

31/01/2012. Outline. Tracking. What is tracking?

31/01/2012. Outline. Tracking. What is tracking? INF 5300 Advanced Topic: Video Content Analysis Tracking 2 Outline Introduction to the tracking problem What is tracking? Approaches & assumptions Tracking applications State of the art & challenges Asbjørn

More information

Model-based Visual Tracking:

Model-based Visual Tracking: Technische Universität München Model-based Visual Tracking: the OpenTL framework Giorgio Panin Technische Universität München Institut für Informatik Lehrstuhl für Echtzeitsysteme und Robotik (Prof. Alois

More information

3D Computer Vision. Structured Light II. Prof. Didier Stricker. Kaiserlautern University.

3D Computer Vision. Structured Light II. Prof. Didier Stricker. Kaiserlautern University. 3D Computer Vision Structured Light II Prof. Didier Stricker Kaiserlautern University http://ags.cs.uni-kl.de/ DFKI Deutsches Forschungszentrum für Künstliche Intelligenz http://av.dfki.de 1 Introduction

More information

Feature Tracking and Optical Flow

Feature Tracking and Optical Flow Feature Tracking and Optical Flow Prof. D. Stricker Doz. G. Bleser Many slides adapted from James Hays, Derek Hoeim, Lana Lazebnik, Silvio Saverse, who 1 in turn adapted slides from Steve Seitz, Rick Szeliski,

More information

3D Computer Vision. Structure from Motion. Prof. Didier Stricker

3D Computer Vision. Structure from Motion. Prof. Didier Stricker 3D Computer Vision Structure from Motion Prof. Didier Stricker Kaiserlautern University http://ags.cs.uni-kl.de/ DFKI Deutsches Forschungszentrum für Künstliche Intelligenz http://av.dfki.de 1 Structure

More information

2D Image Processing Feature Descriptors

2D Image Processing Feature Descriptors 2D Image Processing Feature Descriptors Prof. Didier Stricker Kaiserlautern University http://ags.cs.uni-kl.de/ DFKI Deutsches Forschungszentrum für Künstliche Intelligenz http://av.dfki.de 1 Overview

More information

Particle Filtering. CS6240 Multimedia Analysis. Leow Wee Kheng. Department of Computer Science School of Computing National University of Singapore

Particle Filtering. CS6240 Multimedia Analysis. Leow Wee Kheng. Department of Computer Science School of Computing National University of Singapore Particle Filtering CS6240 Multimedia Analysis Leow Wee Kheng Department of Computer Science School of Computing National University of Singapore (CS6240) Particle Filtering 1 / 28 Introduction Introduction

More information

Human Upper Body Pose Estimation in Static Images

Human Upper Body Pose Estimation in Static Images 1. Research Team Human Upper Body Pose Estimation in Static Images Project Leader: Graduate Students: Prof. Isaac Cohen, Computer Science Mun Wai Lee 2. Statement of Project Goals This goal of this project

More information

Simultaneous Appearance Modeling and Segmentation for Matching People under Occlusion

Simultaneous Appearance Modeling and Segmentation for Matching People under Occlusion Simultaneous Appearance Modeling and Segmentation for Matching People under Occlusion Zhe Lin, Larry S. Davis, David Doermann, and Daniel DeMenthon Institute for Advanced Computer Studies University of

More information

Augmented Reality, Advanced SLAM, Applications

Augmented Reality, Advanced SLAM, Applications Augmented Reality, Advanced SLAM, Applications Prof. Didier Stricker & Dr. Alain Pagani alain.pagani@dfki.de Lecture 3D Computer Vision AR, SLAM, Applications 1 Introduction Previous lectures: Basics (camera,

More information

Multiclass SVM and HoG based object recognition of AGMM detected and KF tracked moving objects from single camera input video

Multiclass SVM and HoG based object recognition of AGMM detected and KF tracked moving objects from single camera input video IOSR Journal of VLSI and Signal Processing (IOSR-JVSP) Volume 6, Issue 5, Ver. I (Sep. - Oct. 2016), PP 10-16 e-issn: 2319 4200, p-issn No. : 2319 4197 www.iosrjournals.org Multiclass SVM and HoG based

More information

Tracking Algorithms. Lecture16: Visual Tracking I. Probabilistic Tracking. Joint Probability and Graphical Model. Deterministic methods

Tracking Algorithms. Lecture16: Visual Tracking I. Probabilistic Tracking. Joint Probability and Graphical Model. Deterministic methods Tracking Algorithms CSED441:Introduction to Computer Vision (2017F) Lecture16: Visual Tracking I Bohyung Han CSE, POSTECH bhhan@postech.ac.kr Deterministic methods Given input video and current state,

More information

Augmented Reality VU. Computer Vision 3D Registration (2) Prof. Vincent Lepetit

Augmented Reality VU. Computer Vision 3D Registration (2) Prof. Vincent Lepetit Augmented Reality VU Computer Vision 3D Registration (2) Prof. Vincent Lepetit Feature Point-Based 3D Tracking Feature Points for 3D Tracking Much less ambiguous than edges; Point-to-point reprojection

More information

3D Computer Vision. Dense 3D Reconstruction II. Prof. Didier Stricker. Christiano Gava

3D Computer Vision. Dense 3D Reconstruction II. Prof. Didier Stricker. Christiano Gava 3D Computer Vision Dense 3D Reconstruction II Prof. Didier Stricker Christiano Gava Kaiserlautern University http://ags.cs.uni-kl.de/ DFKI Deutsches Forschungszentrum für Künstliche Intelligenz http://av.dfki.de

More information

Definition, Detection, and Evaluation of Meeting Events in Airport Surveillance Videos

Definition, Detection, and Evaluation of Meeting Events in Airport Surveillance Videos Definition, Detection, and Evaluation of Meeting Events in Airport Surveillance Videos Sung Chun Lee, Chang Huang, and Ram Nevatia University of Southern California, Los Angeles, CA 90089, USA sungchun@usc.edu,

More information

Feature Tracking and Optical Flow

Feature Tracking and Optical Flow Feature Tracking and Optical Flow Prof. D. Stricker Doz. G. Bleser Many slides adapted from James Hays, Derek Hoeim, Lana Lazebnik, Silvio Saverse, who in turn adapted slides from Steve Seitz, Rick Szeliski,

More information

Chapter 9 Object Tracking an Overview

Chapter 9 Object Tracking an Overview Chapter 9 Object Tracking an Overview The output of the background subtraction algorithm, described in the previous chapter, is a classification (segmentation) of pixels into foreground pixels (those belonging

More information

NIH Public Access Author Manuscript Proc Int Conf Image Proc. Author manuscript; available in PMC 2013 May 03.

NIH Public Access Author Manuscript Proc Int Conf Image Proc. Author manuscript; available in PMC 2013 May 03. NIH Public Access Author Manuscript Published in final edited form as: Proc Int Conf Image Proc. 2008 ; : 241 244. doi:10.1109/icip.2008.4711736. TRACKING THROUGH CHANGES IN SCALE Shawn Lankton 1, James

More information

3D Computer Vision. Depth Cameras. Prof. Didier Stricker. Oliver Wasenmüller

3D Computer Vision. Depth Cameras. Prof. Didier Stricker. Oliver Wasenmüller 3D Computer Vision Depth Cameras Prof. Didier Stricker Oliver Wasenmüller Kaiserlautern University http://ags.cs.uni-kl.de/ DFKI Deutsches Forschungszentrum für Künstliche Intelligenz http://av.dfki.de

More information

Augmenting Reality, Naturally:

Augmenting Reality, Naturally: Augmenting Reality, Naturally: Scene Modelling, Recognition and Tracking with Invariant Image Features by Iryna Gordon in collaboration with David G. Lowe Laboratory for Computational Intelligence Department

More information

Dynamic Shape Tracking via Region Matching

Dynamic Shape Tracking via Region Matching Dynamic Shape Tracking via Region Matching Ganesh Sundaramoorthi Asst. Professor of EE and AMCS KAUST (Joint work with Yanchao Yang) The Problem: Shape Tracking Given: exact object segmentation in frame1

More information

Evaluation of Moving Object Tracking Techniques for Video Surveillance Applications

Evaluation of Moving Object Tracking Techniques for Video Surveillance Applications International Journal of Current Engineering and Technology E-ISSN 2277 4106, P-ISSN 2347 5161 2015INPRESSCO, All Rights Reserved Available at http://inpressco.com/category/ijcet Research Article Evaluation

More information

Automatic Tracking of Moving Objects in Video for Surveillance Applications

Automatic Tracking of Moving Objects in Video for Surveillance Applications Automatic Tracking of Moving Objects in Video for Surveillance Applications Manjunath Narayana Committee: Dr. Donna Haverkamp (Chair) Dr. Arvin Agah Dr. James Miller Department of Electrical Engineering

More information

Tracking. Hao Guan( 管皓 ) School of Computer Science Fudan University

Tracking. Hao Guan( 管皓 ) School of Computer Science Fudan University Tracking Hao Guan( 管皓 ) School of Computer Science Fudan University 2014-09-29 Multimedia Video Audio Use your eyes Video Tracking Use your ears Audio Tracking Tracking Video Tracking Definition Given

More information

On-line and Off-line 3D Reconstruction for Crisis Management Applications

On-line and Off-line 3D Reconstruction for Crisis Management Applications On-line and Off-line 3D Reconstruction for Crisis Management Applications Geert De Cubber Royal Military Academy, Department of Mechanical Engineering (MSTA) Av. de la Renaissance 30, 1000 Brussels geert.de.cubber@rma.ac.be

More information

Face detection in a video sequence - a temporal approach

Face detection in a video sequence - a temporal approach Face detection in a video sequence - a temporal approach K. Mikolajczyk R. Choudhury C. Schmid INRIA Rhône-Alpes GRAVIR-CNRS, 655 av. de l Europe, 38330 Montbonnot, France {Krystian.Mikolajczyk,Ragini.Choudhury,Cordelia.Schmid}@inrialpes.fr

More information

Multi-View Face Tracking with Factorial and Switching HMM

Multi-View Face Tracking with Factorial and Switching HMM Multi-View Face Tracking with Factorial and Switching HMM Peng Wang, Qiang Ji Department of Electrical, Computer and System Engineering Rensselaer Polytechnic Institute Troy, NY 12180 Abstract Dynamic

More information

Part I: HumanEva-I dataset and evaluation metrics

Part I: HumanEva-I dataset and evaluation metrics Part I: HumanEva-I dataset and evaluation metrics Leonid Sigal Michael J. Black Department of Computer Science Brown University http://www.cs.brown.edu/people/ls/ http://vision.cs.brown.edu/humaneva/ Motivation

More information

A Novel Multi-Planar Homography Constraint Algorithm for Robust Multi-People Location with Severe Occlusion

A Novel Multi-Planar Homography Constraint Algorithm for Robust Multi-People Location with Severe Occlusion A Novel Multi-Planar Homography Constraint Algorithm for Robust Multi-People Location with Severe Occlusion Paper ID:086 Abstract Multi-view approach has been proposed to solve occlusion and lack of visibility

More information

Moving Object Tracking in Video Using MATLAB

Moving Object Tracking in Video Using MATLAB Moving Object Tracking in Video Using MATLAB Bhavana C. Bendale, Prof. Anil R. Karwankar Abstract In this paper a method is described for tracking moving objects from a sequence of video frame. This method

More information

ENGN D Photography / Spring 2018 / SYLLABUS

ENGN D Photography / Spring 2018 / SYLLABUS ENGN 2502 3D Photography / Spring 2018 / SYLLABUS Description of the proposed course Over the last decade digital photography has entered the mainstream with inexpensive, miniaturized cameras routinely

More information

3D Computer Vision. Structured Light I. Prof. Didier Stricker. Kaiserlautern University.

3D Computer Vision. Structured Light I. Prof. Didier Stricker. Kaiserlautern University. 3D Computer Vision Structured Light I Prof. Didier Stricker Kaiserlautern University http://ags.cs.uni-kl.de/ DFKI Deutsches Forschungszentrum für Künstliche Intelligenz http://av.dfki.de 1 Introduction

More information

Designing Applications that See Lecture 7: Object Recognition

Designing Applications that See Lecture 7: Object Recognition stanford hci group / cs377s Designing Applications that See Lecture 7: Object Recognition Dan Maynes-Aminzade 29 January 2008 Designing Applications that See http://cs377s.stanford.edu Reminders Pick up

More information

Visuelle Perzeption für Mensch- Maschine Schnittstellen

Visuelle Perzeption für Mensch- Maschine Schnittstellen Visuelle Perzeption für Mensch- Maschine Schnittstellen Vorlesung, WS 2009 Prof. Dr. Rainer Stiefelhagen Dr. Edgar Seemann Institut für Anthropomatik Universität Karlsruhe (TH) http://cvhci.ira.uka.de

More information

Nonrigid Surface Modelling. and Fast Recovery. Department of Computer Science and Engineering. Committee: Prof. Leo J. Jia and Prof. K. H.

Nonrigid Surface Modelling. and Fast Recovery. Department of Computer Science and Engineering. Committee: Prof. Leo J. Jia and Prof. K. H. Nonrigid Surface Modelling and Fast Recovery Zhu Jianke Supervisor: Prof. Michael R. Lyu Committee: Prof. Leo J. Jia and Prof. K. H. Wong Department of Computer Science and Engineering May 11, 2007 1 2

More information

CS4670: Computer Vision

CS4670: Computer Vision CS4670: Computer Vision Noah Snavely Lecture 6: Feature matching and alignment Szeliski: Chapter 6.1 Reading Last time: Corners and blobs Scale-space blob detector: Example Feature descriptors We know

More information

Scale-invariant visual tracking by particle filtering

Scale-invariant visual tracking by particle filtering Scale-invariant visual tracing by particle filtering Arie Nahmani* a, Allen Tannenbaum a,b a Dept. of Electrical Engineering, Technion - Israel Institute of Technology, Haifa 32000, Israel b Schools of

More information

Announcements. Computer Vision I. Motion Field Equation. Revisiting the small motion assumption. Visual Tracking. CSE252A Lecture 19.

Announcements. Computer Vision I. Motion Field Equation. Revisiting the small motion assumption. Visual Tracking. CSE252A Lecture 19. Visual Tracking CSE252A Lecture 19 Hw 4 assigned Announcements No class on Thursday 12/6 Extra class on Tuesday 12/4 at 6:30PM in WLH Room 2112 Motion Field Equation Measurements I x = I x, T: Components

More information

Probabilistic Tracking and Reconstruction of 3D Human Motion in Monocular Video Sequences

Probabilistic Tracking and Reconstruction of 3D Human Motion in Monocular Video Sequences Probabilistic Tracking and Reconstruction of 3D Human Motion in Monocular Video Sequences Presentation of the thesis work of: Hedvig Sidenbladh, KTH Thesis opponent: Prof. Bill Freeman, MIT Thesis supervisors

More information

Vision and Image Processing Lab., CRV Tutorial day- May 30, 2010 Ottawa, Canada

Vision and Image Processing Lab., CRV Tutorial day- May 30, 2010 Ottawa, Canada Spatio-Temporal Salient Features Amir H. Shabani Vision and Image Processing Lab., University of Waterloo, ON CRV Tutorial day- May 30, 2010 Ottawa, Canada 1 Applications Automated surveillance for scene

More information

Computer Vision Lecture 17

Computer Vision Lecture 17 Computer Vision Lecture 17 Epipolar Geometry & Stereo Basics 13.01.2015 Bastian Leibe RWTH Aachen http://www.vision.rwth-aachen.de leibe@vision.rwth-aachen.de Announcements Seminar in the summer semester

More information

Visual Motion Analysis and Tracking Part II

Visual Motion Analysis and Tracking Part II Visual Motion Analysis and Tracking Part II David J Fleet and Allan D Jepson CIAR NCAP Summer School July 12-16, 16, 2005 Outline Optical Flow and Tracking: Optical flow estimation (robust, iterative refinement,

More information

Computer Vision Lecture 17

Computer Vision Lecture 17 Announcements Computer Vision Lecture 17 Epipolar Geometry & Stereo Basics Seminar in the summer semester Current Topics in Computer Vision and Machine Learning Block seminar, presentations in 1 st week

More information

Image processing and features

Image processing and features Image processing and features Gabriele Bleser gabriele.bleser@dfki.de Thanks to Harald Wuest, Folker Wientapper and Marc Pollefeys Introduction Previous lectures: geometry Pose estimation Epipolar geometry

More information

EECS150 - Digital Design Lecture 14 FIFO 2 and SIFT. Recap and Outline

EECS150 - Digital Design Lecture 14 FIFO 2 and SIFT. Recap and Outline EECS150 - Digital Design Lecture 14 FIFO 2 and SIFT Oct. 15, 2013 Prof. Ronald Fearing Electrical Engineering and Computer Sciences University of California, Berkeley (slides courtesy of Prof. John Wawrzynek)

More information

Low Cost Motion Capture

Low Cost Motion Capture Low Cost Motion Capture R. Budiman M. Bennamoun D.Q. Huynh School of Computer Science and Software Engineering The University of Western Australia Crawley WA 6009 AUSTRALIA Email: budimr01@tartarus.uwa.edu.au,

More information

Mixed-Reality for Intuitive Photo-Realistic 3D-Model Generation

Mixed-Reality for Intuitive Photo-Realistic 3D-Model Generation Mixed-Reality for Intuitive Photo-Realistic 3D-Model Generation Wolfgang Sepp, Tim Bodenmueller, Michael Suppa, and Gerd Hirzinger DLR, Institut für Robotik und Mechatronik @ GI-Workshop VR/AR 2009 Folie

More information

Automatic visual recognition for metro surveillance

Automatic visual recognition for metro surveillance Automatic visual recognition for metro surveillance F. Cupillard, M. Thonnat, F. Brémond Orion Research Group, INRIA, Sophia Antipolis, France Abstract We propose in this paper an approach for recognizing

More information

Computer Vision Course Lecture 04. Template Matching Image Pyramids. Ceyhun Burak Akgül, PhD cba-research.com. Spring 2015 Last updated 11/03/2015

Computer Vision Course Lecture 04. Template Matching Image Pyramids. Ceyhun Burak Akgül, PhD cba-research.com. Spring 2015 Last updated 11/03/2015 Computer Vision Course Lecture 04 Template Matching Image Pyramids Ceyhun Burak Akgül, PhD cba-research.com Spring 2015 Last updated 11/03/2015 Photo credit: Olivier Teboul vision.mas.ecp.fr/personnel/teboul

More information

Computer Vision 2 Lecture 8

Computer Vision 2 Lecture 8 Computer Vision 2 Lecture 8 Multi-Object Tracking (30.05.2016) leibe@vision.rwth-aachen.de, stueckler@vision.rwth-aachen.de RWTH Aachen University, Computer Vision Group http://www.vision.rwth-aachen.de

More information

Face Detection and Alignment. Prof. Xin Yang HUST

Face Detection and Alignment. Prof. Xin Yang HUST Face Detection and Alignment Prof. Xin Yang HUST Many slides adapted from P. Viola Face detection Face detection Basic idea: slide a window across image and evaluate a face model at every location Challenges

More information

CAP 5415 Computer Vision Fall 2012

CAP 5415 Computer Vision Fall 2012 CAP 5415 Computer Vision Fall 01 Dr. Mubarak Shah Univ. of Central Florida Office 47-F HEC Lecture-5 SIFT: David Lowe, UBC SIFT - Key Point Extraction Stands for scale invariant feature transform Patented

More information

Observing people with multiple cameras

Observing people with multiple cameras First Short Spring School on Surveillance (S 4 ) May 17-19, 2011 Modena,Italy Course Material Observing people with multiple cameras Andrea Cavallaro Queen Mary University, London (UK) Observing people

More information

Part-Based Models for Object Class Recognition Part 2

Part-Based Models for Object Class Recognition Part 2 High Level Computer Vision Part-Based Models for Object Class Recognition Part 2 Bernt Schiele - schiele@mpi-inf.mpg.de Mario Fritz - mfritz@mpi-inf.mpg.de https://www.mpi-inf.mpg.de/hlcv Class of Object

More information

Part-Based Models for Object Class Recognition Part 2

Part-Based Models for Object Class Recognition Part 2 High Level Computer Vision Part-Based Models for Object Class Recognition Part 2 Bernt Schiele - schiele@mpi-inf.mpg.de Mario Fritz - mfritz@mpi-inf.mpg.de https://www.mpi-inf.mpg.de/hlcv Class of Object

More information

Visual Tracking. Antonino Furnari. Image Processing Lab Dipartimento di Matematica e Informatica Università degli Studi di Catania

Visual Tracking. Antonino Furnari. Image Processing Lab Dipartimento di Matematica e Informatica Università degli Studi di Catania Visual Tracking Antonino Furnari Image Processing Lab Dipartimento di Matematica e Informatica Università degli Studi di Catania furnari@dmi.unict.it 11 giugno 2015 What is visual tracking? estimation

More information

Class 3: Advanced Moving Object Detection and Alert Detection Feb. 18, 2008

Class 3: Advanced Moving Object Detection and Alert Detection Feb. 18, 2008 Class 3: Advanced Moving Object Detection and Alert Detection Feb. 18, 2008 Instructor: YingLi Tian Video Surveillance E6998-007 Senior/Feris/Tian 1 Outlines Moving Object Detection with Distraction Motions

More information

Object Tracking using HOG and SVM

Object Tracking using HOG and SVM Object Tracking using HOG and SVM Siji Joseph #1, Arun Pradeep #2 Electronics and Communication Engineering Axis College of Engineering and Technology, Ambanoly, Thrissur, India Abstract Object detection

More information

Face Tracking. Synonyms. Definition. Main Body Text. Amit K. Roy-Chowdhury and Yilei Xu. Facial Motion Estimation

Face Tracking. Synonyms. Definition. Main Body Text. Amit K. Roy-Chowdhury and Yilei Xu. Facial Motion Estimation Face Tracking Amit K. Roy-Chowdhury and Yilei Xu Department of Electrical Engineering, University of California, Riverside, CA 92521, USA {amitrc,yxu}@ee.ucr.edu Synonyms Facial Motion Estimation Definition

More information

Switching Hypothesized Measurements: A Dynamic Model with Applications to Occlusion Adaptive Joint Tracking

Switching Hypothesized Measurements: A Dynamic Model with Applications to Occlusion Adaptive Joint Tracking Switching Hypothesized Measurements: A Dynamic Model with Applications to Occlusion Adaptive Joint Tracking Yang Wang Tele Tan Institute for Infocomm Research, Singapore {ywang, telctan}@i2r.a-star.edu.sg

More information

Multi-Camera Occlusion and Sudden-Appearance-Change Detection Using Hidden Markovian Chains

Multi-Camera Occlusion and Sudden-Appearance-Change Detection Using Hidden Markovian Chains 1 Multi-Camera Occlusion and Sudden-Appearance-Change Detection Using Hidden Markovian Chains Xudong Ma Pattern Technology Lab LLC, U.S.A. Email: xma@ieee.org arxiv:1610.09520v1 [cs.cv] 29 Oct 2016 Abstract

More information

Motion and Tracking. Andrea Torsello DAIS Università Ca Foscari via Torino 155, Mestre (VE)

Motion and Tracking. Andrea Torsello DAIS Università Ca Foscari via Torino 155, Mestre (VE) Motion and Tracking Andrea Torsello DAIS Università Ca Foscari via Torino 155, 30172 Mestre (VE) Motion Segmentation Segment the video into multiple coherently moving objects Motion and Perceptual Organization

More information

Visuelle Perzeption für Mensch- Maschine Schnittstellen

Visuelle Perzeption für Mensch- Maschine Schnittstellen Visuelle Perzeption für Mensch- Maschine Schnittstellen Vorlesung, WS 2009 Prof. Dr. Rainer Stiefelhagen Dr. Edgar Seemann Institut für Anthropomatik Universität Karlsruhe (TH) http://cvhci.ira.uka.de

More information

Computer Vision 2 Lecture 1

Computer Vision 2 Lecture 1 Computer Vision 2 Lecture 1 Introduction (14.04.2016) leibe@vision.rwth-aachen.de, stueckler@vision.rwth-aachen.de RWTH Aachen University, Computer Vision Group http://www.vision.rwth-aachen.de Organization

More information

Visual Tracking. Image Processing Laboratory Dipartimento di Matematica e Informatica Università degli studi di Catania.

Visual Tracking. Image Processing Laboratory Dipartimento di Matematica e Informatica Università degli studi di Catania. Image Processing Laboratory Dipartimento di Matematica e Informatica Università degli studi di Catania 1 What is visual tracking? estimation of the target location over time 2 applications Six main areas:

More information

Dense 3D Reconstruction. Christiano Gava

Dense 3D Reconstruction. Christiano Gava Dense 3D Reconstruction Christiano Gava christiano.gava@dfki.de Outline Previous lecture: structure and motion II Structure and motion loop Triangulation Wide baseline matching (SIFT) Today: dense 3D reconstruction

More information

Volume 3, Issue 11, November 2013 International Journal of Advanced Research in Computer Science and Software Engineering

Volume 3, Issue 11, November 2013 International Journal of Advanced Research in Computer Science and Software Engineering Volume 3, Issue 11, November 2013 ISSN: 2277 128X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: www.ijarcsse.com Comparison

More information

KinectFusion: Real-Time Dense Surface Mapping and Tracking

KinectFusion: Real-Time Dense Surface Mapping and Tracking KinectFusion: Real-Time Dense Surface Mapping and Tracking Gabriele Bleser Thanks to Richard Newcombe for providing the ISMAR slides Overview General: scientific papers (structure, category) KinectFusion:

More information

Lecture 20: Tracking. Tuesday, Nov 27

Lecture 20: Tracking. Tuesday, Nov 27 Lecture 20: Tracking Tuesday, Nov 27 Paper reviews Thorough summary in your own words Main contribution Strengths? Weaknesses? How convincing are the experiments? Suggestions to improve them? Extensions?

More information

ROBUST OBJECT TRACKING BY SIMULTANEOUS GENERATION OF AN OBJECT MODEL

ROBUST OBJECT TRACKING BY SIMULTANEOUS GENERATION OF AN OBJECT MODEL ROBUST OBJECT TRACKING BY SIMULTANEOUS GENERATION OF AN OBJECT MODEL Maria Sagrebin, Daniel Caparròs Lorca, Daniel Stroh, Josef Pauli Fakultät für Ingenieurwissenschaften Abteilung für Informatik und Angewandte

More information

Feature descriptors and matching

Feature descriptors and matching Feature descriptors and matching Detections at multiple scales Invariance of MOPS Intensity Scale Rotation Color and Lighting Out-of-plane rotation Out-of-plane rotation Better representation than color:

More information

1/1 1. Challenging vision tasks meeting depth sensing: an in-depth look. Austrian Institute of Technology

1/1 1. Challenging vision tasks meeting depth sensing: an in-depth look. Austrian Institute of Technology Short intro who are we in 20 seconds Austrian Institute of Technology Challenging vision tasks meeting depth sensing: an in-depth look Csaba Beleznai Csaba Beleznai Senior Scientist Video- and Safety Technology

More information

AUTOMATIC 3D HUMAN ACTION RECOGNITION Ajmal Mian Associate Professor Computer Science & Software Engineering

AUTOMATIC 3D HUMAN ACTION RECOGNITION Ajmal Mian Associate Professor Computer Science & Software Engineering AUTOMATIC 3D HUMAN ACTION RECOGNITION Ajmal Mian Associate Professor Computer Science & Software Engineering www.csse.uwa.edu.au/~ajmal/ Overview Aim of automatic human action recognition Applications

More information

Tracking Using a Hierarchical Structural Representation

Tracking Using a Hierarchical Structural Representation Tracking Using a Hierarchical Structural Representation Anonymous OAGM submission Abstract Acquiring a highly specific target representation is a major challenge in the task of visual object tracking.

More information

A Sparsity-Driven Approach to Multi-camera Tracking in Visual Sensor Networks

A Sparsity-Driven Approach to Multi-camera Tracking in Visual Sensor Networks A Sparsity-Driven Approach to Multi-camera Tracking in Visual Sensor Networks Serhan Coşar a,b a INRIA Sophia Antipolis, STARS team 2004 R. des Lucioles, 06902 S. Antipolis, France serhan.cosar@inria.fr

More information

Motion in 2D image sequences

Motion in 2D image sequences Motion in 2D image sequences Definitely used in human vision Object detection and tracking Navigation and obstacle avoidance Analysis of actions or activities Segmentation and understanding of video sequences

More information

Structured Light II. Thanks to Ronen Gvili, Szymon Rusinkiewicz and Maks Ovsjanikov

Structured Light II. Thanks to Ronen Gvili, Szymon Rusinkiewicz and Maks Ovsjanikov Structured Light II Johannes Köhler Johannes.koehler@dfki.de Thanks to Ronen Gvili, Szymon Rusinkiewicz and Maks Ovsjanikov Introduction Previous lecture: Structured Light I Active Scanning Camera/emitter

More information

3D Model Acquisition by Tracking 2D Wireframes

3D Model Acquisition by Tracking 2D Wireframes 3D Model Acquisition by Tracking 2D Wireframes M. Brown, T. Drummond and R. Cipolla {96mab twd20 cipolla}@eng.cam.ac.uk Department of Engineering University of Cambridge Cambridge CB2 1PZ, UK Abstract

More information

Topics to be Covered in the Rest of the Semester. CSci 4968 and 6270 Computational Vision Lecture 15 Overview of Remainder of the Semester

Topics to be Covered in the Rest of the Semester. CSci 4968 and 6270 Computational Vision Lecture 15 Overview of Remainder of the Semester Topics to be Covered in the Rest of the Semester CSci 4968 and 6270 Computational Vision Lecture 15 Overview of Remainder of the Semester Charles Stewart Department of Computer Science Rensselaer Polytechnic

More information

IN computer vision develop mathematical techniques in

IN computer vision develop mathematical techniques in International Journal of Scientific & Engineering Research Volume 4, Issue3, March-2013 1 Object Tracking Based On Tracking-Learning-Detection Rupali S. Chavan, Mr. S.M.Patil Abstract -In this paper; we

More information

2D Image Processing INFORMATIK. Kaiserlautern University. DFKI Deutsches Forschungszentrum für Künstliche Intelligenz

2D Image Processing INFORMATIK. Kaiserlautern University.   DFKI Deutsches Forschungszentrum für Künstliche Intelligenz 2D Image Processing - Filtering Prof. Didier Stricker Kaiserlautern University http://ags.cs.uni-kl.de/ DFKI Deutsches Forschungszentrum für Künstliche Intelligenz http://av.dfki.de 1 What is image filtering?

More information

The Hilbert Problems of Computer Vision. Jitendra Malik UC Berkeley & Google, Inc.

The Hilbert Problems of Computer Vision. Jitendra Malik UC Berkeley & Google, Inc. The Hilbert Problems of Computer Vision Jitendra Malik UC Berkeley & Google, Inc. This talk The computational power of the human brain Research is the art of the soluble Hilbert problems, circa 2004 Hilbert

More information

Video Surveillance System for Object Detection and Tracking Methods R.Aarthi, K.Kiruthikadevi

Video Surveillance System for Object Detection and Tracking Methods R.Aarthi, K.Kiruthikadevi IJISET - International Journal of Innovative Science, Engineering & Technology, Vol. 2 Issue 11, November 2015. Video Surveillance System for Object Detection and Tracking Methods R.Aarthi, K.Kiruthikadevi

More information

Feature descriptors. Alain Pagani Prof. Didier Stricker. Computer Vision: Object and People Tracking

Feature descriptors. Alain Pagani Prof. Didier Stricker. Computer Vision: Object and People Tracking Feature descriptors Alain Pagani Prof. Didier Stricker Computer Vision: Object and People Tracking 1 Overview Previous lectures: Feature extraction Today: Gradiant/edge Points (Kanade-Tomasi + Harris)

More information

Optical Flow-Based Motion Estimation. Thanks to Steve Seitz, Simon Baker, Takeo Kanade, and anyone else who helped develop these slides.

Optical Flow-Based Motion Estimation. Thanks to Steve Seitz, Simon Baker, Takeo Kanade, and anyone else who helped develop these slides. Optical Flow-Based Motion Estimation Thanks to Steve Seitz, Simon Baker, Takeo Kanade, and anyone else who helped develop these slides. 1 Why estimate motion? We live in a 4-D world Wide applications Object

More information

Notes 9: Optical Flow

Notes 9: Optical Flow Course 049064: Variational Methods in Image Processing Notes 9: Optical Flow Guy Gilboa 1 Basic Model 1.1 Background Optical flow is a fundamental problem in computer vision. The general goal is to find

More information

Occlusion Robust Multi-Camera Face Tracking

Occlusion Robust Multi-Camera Face Tracking Occlusion Robust Multi-Camera Face Tracking Josh Harguess, Changbo Hu, J. K. Aggarwal Computer & Vision Research Center / Department of ECE The University of Texas at Austin harguess@utexas.edu, changbo.hu@gmail.com,

More information

Using temporal seeding to constrain the disparity search range in stereo matching

Using temporal seeding to constrain the disparity search range in stereo matching Using temporal seeding to constrain the disparity search range in stereo matching Thulani Ndhlovu Mobile Intelligent Autonomous Systems CSIR South Africa Email: tndhlovu@csir.co.za Fred Nicolls Department

More information

Other Reconstruction Techniques

Other Reconstruction Techniques Other Reconstruction Techniques Ruigang Yang CS 684 CS 684 Spring 2004 1 Taxonomy of Range Sensing From Brain Curless, SIGGRAPH 00 Lecture notes CS 684 Spring 2004 2 Taxonomy of Range Scanning (cont.)

More information

A Fast Moving Object Detection Technique In Video Surveillance System

A Fast Moving Object Detection Technique In Video Surveillance System A Fast Moving Object Detection Technique In Video Surveillance System Paresh M. Tank, Darshak G. Thakore, Computer Engineering Department, BVM Engineering College, VV Nagar-388120, India. Abstract Nowadays

More information

Introduction to behavior-recognition and object tracking

Introduction to behavior-recognition and object tracking Introduction to behavior-recognition and object tracking Xuan Mo ipal Group Meeting April 22, 2011 Outline Motivation of Behavior-recognition Four general groups of behaviors Core technologies Future direction

More information

Real-Time Tracking of Multiple People through Stereo Vision

Real-Time Tracking of Multiple People through Stereo Vision Proc. of IEE International Workshop on Intelligent Environments, 2005 Real-Time Tracking of Multiple People through Stereo Vision S. Bahadori, G. Grisetti, L. Iocchi, G.R. Leone, D. Nardi Dipartimento

More information

Large-Scale Traffic Sign Recognition based on Local Features and Color Segmentation

Large-Scale Traffic Sign Recognition based on Local Features and Color Segmentation Large-Scale Traffic Sign Recognition based on Local Features and Color Segmentation M. Blauth, E. Kraft, F. Hirschenberger, M. Böhm Fraunhofer Institute for Industrial Mathematics, Fraunhofer-Platz 1,

More information

Part based models for recognition. Kristen Grauman

Part based models for recognition. Kristen Grauman Part based models for recognition Kristen Grauman UT Austin Limitations of window-based models Not all objects are box-shaped Assuming specific 2d view of object Local components themselves do not necessarily

More information

Learning Articulated Skeletons From Motion

Learning Articulated Skeletons From Motion Learning Articulated Skeletons From Motion Danny Tarlow University of Toronto, Machine Learning with David Ross and Richard Zemel (and Brendan Frey) August 6, 2007 Point Light Displays It's easy for humans

More information

Combining Multiple Tracking Modalities for Vehicle Tracking in Traffic Intersections

Combining Multiple Tracking Modalities for Vehicle Tracking in Traffic Intersections Combining Multiple Tracking Modalities for Vehicle Tracking in Traffic Intersections Harini Veeraraghavan Nikolaos Papanikolopoulos Artificial Intelligence, Vision and Robotics Lab Department of Computer

More information

Visual Tracking of Human Body with Deforming Motion and Shape Average

Visual Tracking of Human Body with Deforming Motion and Shape Average Visual Tracking of Human Body with Deforming Motion and Shape Average Alessandro Bissacco UCLA Computer Science Los Angeles, CA 90095 bissacco@cs.ucla.edu UCLA CSD-TR # 020046 Abstract In this work we

More information

HUMAN COMPUTER INTERFACE BASED ON HAND TRACKING

HUMAN COMPUTER INTERFACE BASED ON HAND TRACKING Proceedings of MUSME 2011, the International Symposium on Multibody Systems and Mechatronics Valencia, Spain, 25-28 October 2011 HUMAN COMPUTER INTERFACE BASED ON HAND TRACKING Pedro Achanccaray, Cristian

More information

Computer Vision and Virtual Reality. Introduction

Computer Vision and Virtual Reality. Introduction Computer Vision and Virtual Reality Introduction Tomáš Svoboda, svoboda@cmp.felk.cvut.cz Czech Technical University in Prague, Center for Machine Perception http://cmp.felk.cvut.cz Last update: October

More information

Multi-Person Tracking-by-Detection based on Calibrated Multi-Camera Systems

Multi-Person Tracking-by-Detection based on Calibrated Multi-Camera Systems Multi-Person Tracking-by-Detection based on Calibrated Multi-Camera Systems Xiaoyan Jiang, Erik Rodner, and Joachim Denzler Computer Vision Group Jena Friedrich Schiller University of Jena {xiaoyan.jiang,erik.rodner,joachim.denzler}@uni-jena.de

More information