Multi-Person Multi-Camera Tracking for EasyLiving John Krumm Steve Harris Brian Meyers Barry Brumitt Michael Hale Steve Shafer Vision Technology Research.

Slides:



Advertisements
Similar presentations
CSE 424 Final Presentation Team Members: Edward Andert Shang Wang Michael Vetrano Thomas Barry Roger Dolan Eric Barber Sponsor: Aviral Shrivastava.
Advertisements

RGB-D object recognition and localization with clutter and occlusions Federico Tombari, Samuele Salti, Luigi Di Stefano Computer Vision Lab – University.
Inpainting Assigment – Tips and Hints Outline how to design a good test plan selection of dimensions to test along selection of values for each dimension.
Multimedia Specification Design and Production 2012 / Semester 1 / week 6 Lecturer: Dr. Nikos Gazepidis
Inexpensive, Easy-To-Use, and Feature-Rich Worm Tracking
Nathan Johnson1 Background Subtraction Various Methods for Different Inputs.
Parallel Tracking and Mapping for Small AR Workspaces Vision Seminar
Real-time Tracking of Multiple People Using Stereo David BeymerBob Bolles Kurt Konolige Chris Eveland Artificial Intelligence Center SRI International.
Tracking Multiple Occluding People by Localizing on Multiple Scene Planes Professor :王聖智 教授 Student :周節.
Object Inter-Camera Tracking with non- overlapping views: A new dynamic approach Trevor Montcalm Bubaker Boufama.
Overview: The system contains 3 main components: the tag, the video capturing and processing unit (VCPU), and the software. The tag consists of an IRED.
A KLT-Based Approach for Occlusion Handling in Human Tracking Chenyuan Zhang, Jiu Xu, Axel Beaugendre and Satoshi Goto 2012 Picture Coding Symposium.
Robust Multi-Pedestrian Tracking in Thermal-Visible Surveillance Videos Alex Leykin and Riad Hammoud.
Formation et Analyse d’Images Session 8
Boundary matting for view synthesis Samuel W. Hasinoff Sing Bing Kang Richard Szeliski Computer Vision and Image Understanding 103 (2006) 22–32.
Slide 1 Tiled Display Walls - Relation to the Access Grid and Other Systems Mike Walterman, Manager of Graphics Programming, Scientific Computing and Visualization.
Facial Tracking and Animation Todd Belote Bryan Harris David Brown Brad Busse.
Ensemble Tracking Shai Avidan IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE February 2007.
Game Development with Kinect
Vigilant Real-time storage and intelligent retrieval of visual surveillance data Dr Graeme A. Jones.
Fast Illumination-invariant Background Subtraction using Two Views: Error Analysis, Sensor Placement and Applications Ser-Nam Lim, Anurag Mittal, Larry.
Domenico Bloisi, Luca Iocchi, Dorothy Monekosso, Paolo Remagnino
Location Systems for Ubiquitous Computing Jeffrey Hightower and Gaetano Borriello.
Student: Hsu-Yung Cheng Advisor: Jenq-Neng Hwang, Professor
Real-Time Face Detection and Tracking Using Multiple Cameras RIT Computer Engineering Senior Design Project John RuppertJustin HnatowJared Holsopple This.
AKSHAY UTTAMANI( ) DIVYAM JAISWAL( ) SAURABH KHANDELWAL( )
1 Video Surveillance systems for Traffic Monitoring Simeon Indupalli.
College of Engineering and Science Clemson University
1 Activity and Motion Detection in Videos Longin Jan Latecki and Roland Miezianko, Temple University Dragoljub Pokrajac, Delaware State University Dover,
Digital Video An Introduction to the Digital Signal File Formats Acquisition IEEE 1394.
1 Formation et Analyse d’Images Session 7 Daniela Hall 7 November 2005.
Intelligent Ground Vehicle Competition Navigation Michael Lebson - James McLane - Image Processing Hamad Al Salem.
Smart Environments for Occupancy Sensing and Services Paper by Pirttikangas, Tobe, and Thepvilojanapong Presented by Alan Kelly December 7, 2011.
Two Examples Of Indoor And Outdoor Surveillance Systems: Motivation, Design, And Testing Ioannis Pavlidis Vassilios Morellas Honeywell Laboratories.
BraMBLe: The Bayesian Multiple-BLob Tracker By Michael Isard and John MacCormick Presented by Kristin Branson CSE 252C, Fall 2003.
Tracking by Sampling Trackers Junseok Kwon* and Kyoung Mu lee Computer Vision Lab. Dept. of EECS Seoul National University, Korea Homepage:
Real-time object tracking using Kalman filter Siddharth Verma P.hD. Candidate Mechanical Engineering.
A General Framework for Tracking Multiple People from a Moving Camera
Portable Vision-Based HCI A Real-Time Hand Mouse System on Portable Devices 連矩鋒 (Burt C.F. Lien) Department of Computer Science and Information Engineering.
Object Stereo- Joint Stereo Matching and Object Segmentation Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on Michael Bleyer Vienna.
UCSB Talk - March 6 th, 2009 Andy Wilson & Hrvoje Benko Microsoft Research.
1 Virtual Rear Projection: Technology & Evaluation Jay Summet
Towards real-time camera based logos detection Mathieu Delalandre Laboratory of Computer Science, RFAI group, Tours city, France Osaka Prefecture Partnership.
1 Research Question  Can a vision-based mobile robot  with limited computation and memory,  and rapidly varying camera positions,  operate autonomously.
Computer Systems Week 14: Memory Management Amanda Oddie.
IP VIDEOSURVEILLANCE SOLUTION IP VIDEOSURVEILLANCE SOLUTION First network videosurveillance server, CamTrace has an innovative architecture.
Expectation-Maximization (EM) Case Studies
Chapter 5 Multi-Cue 3D Model- Based Object Tracking Geoffrey Taylor Lindsay Kleeman Intelligent Robotics Research Centre (IRRC) Department of Electrical.
EEC 490 GROUP PRESENTATION: KINECT TASK VALIDATION Scott Kruger Nate Dick Pete Hogrefe James Kulon.
Machine Vision Introduction to Using Cognex DVT Intellect.
By Naveen kumar Badam. Contents INTRODUCTION ARCHITECTURE OF THE PROPOSED MODEL MODULES INVOLVED IN THE MODEL FUTURE WORKS CONCLUSION.
Laser beam diagnostics : BEAMDIAG program. Stéphan Del Burgo CERN PS/LP 30 January 1998 DBS 01/
Using Adaptive Tracking To Classify And Monitor Activities In A Site W.E.L. Grimson, C. Stauffer, R. Romano, L. Lee.
Final Year Project. Project Title Kalman Tracking For Image Processing Applications.
IEEE International Conference on Multimedia and Expo.
CSSE463: Image Recognition Day 29 This week This week Today: Surveillance and finding motion vectors Today: Surveillance and finding motion vectors Tomorrow:
Suggested Machine Learning Class: – learning-supervised-learning--ud675
Pervasive Computing MIT SMA 5508 Spring 2006 Larry Rudolph 1 Tracking Indoors.
What you need: In order to use these programs you need a program that sends out OSC messages in TUIO format. There are a few options in programs that.
Vision Based hand tracking for Interaction The 7th International Conference on Applications and Principles of Information Science (APIS2008) Dept. of Visual.
OPERATING SYSTEM REVIEW. System Software The programs that control and maintain the operation of the computer and its devices The two parts of system.
Design and Calibration of a Multi-View TOF Sensor Fusion System Young Min Kim, Derek Chan, Christian Theobalt, Sebastian Thrun Stanford University.
Problem Ubicomp environment (i.e., instrumented room) usually public
Learning Patterns of Activity
Week 2 - Friday CS361.
Jun Shimamura, Naokazu Yokoya, Haruo Takemura and Kazumasa Yamazawa
A Forest of Sensors: Using adaptive tracking to classify and monitor activities in a site Eric Grimson AI Lab, Massachusetts Institute of Technology
Vehicle Segmentation and Tracking in the Presence of Occlusions
Fusion, Face, HD Face Matthew Simari | Program Manager, Kinect Team
Eric Grimson, Chris Stauffer,
Presentation transcript:

Multi-Person Multi-Camera Tracking for EasyLiving John Krumm Steve Harris Brian Meyers Barry Brumitt Michael Hale Steve Shafer Vision Technology Research Group Microsoft Research Redmond, WA USA

What Is EasyLiving? EasyLiving is a prototype architecture and technologies for building intelligent environments that facilitate the unencumbered interaction of people with other people, with computers, and with devices.

Example Behaviors Adjust lights as you move around a space Route video to best display Move your Windows session as you move Deliver e-messages to where you are Monitor a young child or old person

EasyLiving Demo (7 min.)

Self-Aware Space EasyLiving must know about people, computers, software, devices, and geometry to work right.

Who’s Where?

Person- Tracking System 5 Triclops stereo cameras 5 PCs running “Stereo Module” (and Microsoft Windows 2000) 1 PC running “Person Tracker” (only U.S. $319) (includes Internet Explorer) (as part of the OS) (for a limited time only?)

Triclops Cameras Now superceded by “Digiclops” digital IEEE-1394 version

Typical Images Color image from TriclopsDisparity image from Triclops

Requirements To work in a real-life intelligent environment, our tracking system must … 1.Maintain location & identity of people 2.Run at reasonable speeds (we get 3.5 Hz) 3.Work with multiple people (we handle up to three) 4.Create and delete people instances 5.Work with multiple cameras (we’re up to five) 6.Use cameras in the room 7.Work for extended periods 8.Tolerate partial occlusions and variable postures

Other Systems Non-Vision Olivetti Research (’92) & Xerox PARC (’93) – IR badges AT&T Laboratories (Cambridge) (’97) – Ultrasonic badges PinPoint, Ascension, Polhemus – commercial RF badges Vision (for multiple people) Haritaoglu & Davis (’98-’99) Darrell et al. (’98) Orwell et al. (’99) Collins et al. (’99) Rosales & Sclaroff (’99) Kettnaker & Zabih (’99) Intille et al. (’95, ’97) Rehg et al. (’97) Boult et al. (‘99) Stiefelhagen et al. (’99) MacCormick & Blake (’99) Cai & Aggarwal (’98) Halevi & Weinshall (’97) Gavrila & Davis (’96) “I see by the current issue of ‘Lab News,’ Ridgeway, that you’ve been working for the last twenty years on the same problem I’ve been working on for the last twenty years.”

Why Use Vision? Alternative sensors: Active badges Pressure-sensitive floors Motion sensors Localized sensors, e.g. on door, chair But … Cameras are getting cheap Cameras are easy to install Cameras give location and identity Cameras can find other objects, e.g. video screens Cameras can be use to model room geometry (active badge)

Person Detection Steps 1.Background subtraction 2.Blob clustering 3.Histogram identification Camera calibration Background modeling

Camera Calibration All tracking done in ground plane Record path of single person walking around room Compute (  x,  y,  ) that best aligns paths Requires robust alignment to deal with outliers Paths before calibrationPaths after calibration

Background Modeling View of space Combined color & disparity background image

Background Subtraction Foreground if: valid depth over invalid depth - OR - depth difference > T d - OR - any (R,G,B) difference > T c Color takes over when person sinks into couch cushions Potential problem when person walks in front of moving video (thus turn on moving video when acquiring background)

Person Detection Region-growing on foreground pixels gives fragmented blobs Group blobs into people-shaped clusters

Blob Clustering Minimum spanning tree Break really long links Find five remaining longest links Break all combinations of these five:  Covariance matrices of 3D coordinates of linked blobs Eigenvalues of covariance matrices Compare eigenvalues to person model

Color Histograms Identify people with RGB color histograms, 16x16x16 Each camera PC maintains its own histograms Space-variant histograms built as person moves around room Person tracker uses histogram to resolve ambiguities window Bluish tint Regular color

So Far calibration, background background subtraction (color & depth) blob clustering histogram maintenance

Person Tracking Takes reports from stereo modules Transforms to common coordinate frame (common coordinate frame)

Person Tracking – Steady State One “track” for each person Predicted location Resolve with color histograms Feed back results to stereo modules for histogram updating

Person Tracking – Bad Data Measurement Noise: Computed position based on predicted position from many reports Occlusions: Multiple cameras Long timeout on unsupported tracks

Person Creation Zone Tracks begin and end here Initial tracks are provisional Makes remainder of room more robust

Summary Live demos, 20 minutes long Person tracker runs at 3.5 Hz Up to three people in room People can: enter leave walk around stop moving sit collide

Recent Efforts Stop breaking the vision system! Moved chairs & changing lights  bad background model Special behavior, e.g. slow through person creation zone Lots of people, e.g. around conference table Find other objects to enable interesting behaviors, e.g. “Where’s that book?” Easier method to model room geometry

Workshop on Multi-Object Tracking