User Attention Tracking in Large Display Face Tracking and Pose Estimation Yuxiao Hu Media Computing Group Microsoft Research, Asia.

Slides:



Advertisements
Similar presentations
Active Appearance Models
Advertisements

Statistical Learning of Multi-View Face Detection
Pattern Analysis Prof. Bennett Math Model of Learning and Discovery 2/14/05 Based on Chapter 1 of Shawe-Taylor and Cristianini.
DESCRIBING INPUT DEVICES
Doorjamb: Unobtrusive Room-level Tracking of People in Homes using Doorway Sensors Timothy W. Hnat, Erin Griffiths, Ray Dawson, Kamin Whitehouse U of Virginia.
David Wild Supervisor: James Connan Rhodes University Computer Science Department Gaze Tracking Using A Webcamera.
Robust 3D Head Pose Classification using Wavelets by Mukesh C. Motwani Dr. Frederick C. Harris, Jr., Thesis Advisor December 5 th, 2002 A thesis submitted.
Database-Based Hand Pose Estimation CSE 6367 – Computer Vision Vassilis Athitsos University of Texas at Arlington.
Face Alignment by Explicit Shape Regression
Essential Introduction to Computers
Face detection Many slides adapted from P. Viola.
A KLT-Based Approach for Occlusion Handling in Human Tracking Chenyuan Zhang, Jiu Xu, Axel Beaugendre and Satoshi Goto 2012 Picture Coding Symposium.
Face Recognition & Biometric Systems, 2005/2006 Face recognition process.
UNIVERSITY OF MURCIA (SPAIN) ARTIFICIAL PERCEPTION AND PATTERN RECOGNITION GROUP A PERCEPTUAL INTERFACE USING INTEGRAL PROJECTIONS Ginés García Mateos.
The Science of Digital Media Microsoft Surface 7May Metropolia University of Applied Sciences Display Technologies Seminar.
Real-time Embedded Face Recognition for Smart Home Fei Zuo, Student Member, IEEE, Peter H. N. de With, Senior Member, IEEE.
UPM, Faculty of Computer Science & IT, A robust automated attendance system using face recognition techniques PhD proposal; May 2009 Gawed Nagi.
UNIVERSITY OF MURCIA (SPAIN) ARTIFICIAL PERCEPTION AND PATTERN RECOGNITION GROUP Estimating 3D Facial Pose in Video with Just Three Points Ginés García.
4EyesFace-Realtime face detection, tracking, alignment and recognition Changbo Hu, Rogerio Feris and Matthew Turk.
Robust Real-Time Object Detection Paul Viola & Michael Jones.
UNIVERSITY OF MURCIA (SPAIN) ARTIFICIAL PERCEPTION AND PATTERN RECOGNITION GROUP REFINING FACE TRACKING WITH INTEGRAL PROJECTIONS Ginés García Mateos Dept.
Smart Traveller with Visual Translator for OCR and Face Recognition LYU0203 FYP.
California Car License Plate Recognition System ZhengHui Hu Advisor: Dr. Kang.
Non-invasive Techniques for Human Fatigue Monitoring Qiang Ji Dept. of Electrical, Computer, and Systems Engineering Rensselaer Polytechnic Institute
Non-invasive Techniques for Human Fatigue Monitoring Qiang Ji Dept. of Electrical, Computer, and Systems Engineering Rensselaer Polytechnic Institute
Real-Time Face Detection and Tracking Using Multiple Cameras RIT Computer Engineering Senior Design Project John RuppertJustin HnatowJared Holsopple This.
Autonomous Control of Scalextric Slot Car on User-Defined Track Siddharth Kamath Souma Mondal Dhaval Patel School of Electrical and Computer Engineering.
Face Alignment Using Cascaded Boosted Regression Active Shape Models
HiTrack Introduction Shanghai Zhuo-Shi Software Technology Co., Ltd Shanghai Zhuo-Shi Software Technology Co., Ltd
Visual Tracking Decomposition Junseok Kwon* and Kyoung Mu lee Computer Vision Lab. Dept. of EECS Seoul National University, Korea Homepage:
Navi Rutgers University 2012 Design Presentation
Digital Face Replacement in Photographs CSC2530F Project Presentation By: Shahzad Malik January 28, 2003.
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.
V part C.  Different programs have different ways of displaying objects in real-time while the scenes are being created within the workspace. Some.
Windows 7 Logo Requirements Screen Coverage Screen Coverage HID (Human Interface Device) Class HID (Human Interface Device) Class Battery Operation Battery.
Windows Movie Maker Getting Started. What is Windows Movie Maker? Windows Movie Maker allows a user to capture (from a video camera) or import audio,
CHRONOS-CONTROL COMPUTER CONTROL USING TI CHRONOS Cihat Keser Yeditepe University
DIEGO AGUIRRE COMPUTER VISION INTRODUCTION 1. QUESTION What is Computer Vision? 2.
Enabling User Interactions with Video Contents Khalad Hasan, Yang Wang, Wing Kwong and Pourang Irani.
ECE738 Advanced Image Processing Face Detection IEEE Trans. PAMI, July 1997.
A Two-level Pose Estimation Framework Using Majority Voting of Gabor Wavelets and Bunch Graph Analysis J. Wu, J. M. Pedersen, D. Putthividhya, D. Norgaard,
REAL TIME FACE DETECTION
 Input Devices Input Devices  Examples of Input Devices Examples of Input Devices  Keyboard Keyboard  Pointing Devices Pointing Devices Mouse Joystick.
Tracking CSE 6367 – Computer Vision Vassilis Athitsos University of Texas at Arlington.
Computer Basics & Keyboarding. What Is A Computer? An electronic device operating under the control of instructions stored in its own memory unit An electronic.
Pyramidal Implementation of Lucas Kanade Feature Tracker Jia Huang Xiaoyan Liu Han Xin Yizhen Tan.
Face Detection Ying Wu Electrical and Computer Engineering Northwestern University, Evanston, IL
Industrial Vision Industrial Vision: components.
The Viola/Jones Face Detector A “paradigmatic” method for real-time object detection Training is slow, but detection is very fast Key ideas Integral images.
ROBOGRAPHERS FACIAL EXPRESSION RECOGNITION USING SWARMS SPONSORED BY: DR. KATIA SYCARA TEAM :GAURI GANDHI SIDA WANG TIFFANY MAY JIMIT GANDHI ROHIT DASHRATHI.
Looking at people and Image-based Localisation Roberto Cipolla Department of Engineering Research team
Counting How Many Words You Read
AAM based Face Tracking with Temporal Matching and Face Segmentation Mingcai Zhou 1 、 Lin Liang 2 、 Jian Sun 2 、 Yangsheng Wang 1 1 Institute of Automation.
Team Members Ming-Chun Chang Lungisa Matshoba Steven Preston Supervisors Dr James Gain Dr Patrick Marais.
Basic Parts of a Computer B. Keyboard C. Monitor A. CPU D. Mouse.
Visual Odometry David Nister, CVPR 2004
Turning a Mobile Device into a Mouse in the Air
Face Detection and Head Tracking Ying Wu Electrical Engineering & Computer Science Northwestern University, Evanston, IL
3D head pose estimation from multiple distant views X. Zabulis, T. Sarmis, A. A. Argyros Institute of Computer Science, Foundation for Research and Technology.
1 VeTrack: Real Time Vehicle Tracking in Uninstrumented Indoor Environments Mingmin Zhao 1, Tao Ye 1, Ruipeng Gao 1, Fan Ye 2, Yizhou Wang 1, Guojie Luo.
Presented By Bhargav (08BQ1A0435).  Images play an important role in todays information because A single image represents a thousand words.  Google's.
FINGERTEC FACE ID FACE RECOGNITION Technology Overview.
Signal and Image Processing Lab
Lecture 26 Hand Pose Estimation Using a Database of Hand Images
Play game, pause video, move cursor… with your eyes
Efficient Deformable Template Matching for Face Tracking
What is blue eyes ? aims on creating computational machines that have perceptual and sensory ability like those of human beings. interactive computer.
Automated Detection of Human Emotion
PRELIMINARY DESIGN REVIEW
Automatic operation IR rework system Automatic Component placement 2 x K-type thermocouples IR-pyro sensor RPC-camera.
Presentation transcript:

User Attention Tracking in Large Display Face Tracking and Pose Estimation Yuxiao Hu Media Computing Group Microsoft Research, Asia

Scenario  When using a large scale display or multiple monitors, a user often “lost” the mouse cursor / input cursor;  When working with multiple windows, a user often need to move the mouse cursor for long distance to click a window and activate it.

Our Solution  Track the user’s face with real-time face detector and tracker;  Estimate the user’s head pose according to the face and facial components detection results;  Switch the mouse/keyboard cursor among multiple monitors/windows according to the user’s attention direction

System Framework

Key Issues  Robust: detect and track the user’s face with arbitrary pose, expression under unconstrained illumination  Accurate: estimate the 3D pose of the user’s head precisely;  Fast: detect, track the user’s face and estimate its pose in real-time  Convenient: easy initialization and no special operations  Light: use typical CPU, web camera, and low system resource cost

Preliminary Test Results  Pose Coverage: yaw ±60°, roll: ±30°  Precision in yaw pose: error < ±10 ° (can support up to 5 monitors)  Speed: 15 frame/sec  Typical USB Web Camera: 320*240 resolution  CPU Usage: 20% average and 80% max

Performance Comparison MethodFeatureAccuracySpeed Ellipsoidal model, edge density feature point Wide-Range, person and Illumination- Insensitive 19 º for different person, about 10 º if initialization for person 200ms~30 0ms on PII 450M Hz PCA + SVRKernel-based learning 10 º for different person N/A KPCA+ SVCKernel-based learning, multi-class classification 99% classification accuracy, within 20 º,97% within 10 º N/A Confidence of Feature Point + Regression (our method) Fast, accurate, small change 6.54 º in yaw angle and 5.35 º in tilt angle if initialization for person <100 ms on P4 1.4GH z

For More Details  Related Publication: Y.X. Hu, L.B. Chen, Y. Zhou, H.J. Zhang, "Estimating Face Pose by Facial Asymmetry and Geometry",FGR2004  Website:  Contacts: Yuxiao Hu,

Let track it for you ! Cannot find your mouse cursor ? User Attention Area Tracking in Large Display