Vision-Based Finger Detection and Its Applications 基於電腦視覺之手指偵測及其應用 Yi-Fan Chuang Advisor: Prof. Yi-Ping Hung Prof. Ming-Sui Lee.

Slides:



Advertisements
Similar presentations
PhishZoo: Detecting Phishing Websites By Looking at Them
Advertisements

A Natural Interactive Game By Zak Wilson. Background This project was my second year group project at University and I have chosen it to present as it.
PlayAnywhere: A Compact Interactive Tabletop Projection-Vision System Professor : Tsai, Lian-Jou Student : Tsai, Yu-Ming PPT Production rate : 100% Date.
Hand Gesture for Taking Self Portrait Shaowei Chu and Jiro Tanaka University of Tsukuba Japan 12th July 15 minutes talk.
The Escritoire: a personal projected display for interacting with documents Mark Ashdown Peter Robinson University of.
STANDARD AND DIRECT. At the end of this session students will: List the typical input devices Identify the types of input devices List their characteristics.
VisHap: Guangqi Ye, Jason J. Corso, Gregory D. Hager, Allison M. Okamura Presented By: Adelle C. Knight Augmented Reality Combining Haptics and Vision.
Su-ting, Chuang 2010/8/2. Outline Introduction Related Work System and Method Experiment Conclusion & Future Work 2.
Page 1 SIXTH SENSE TECHNOLOGY Presented by: KIRTI AGGARWAL 2K7-MRCE-CS-035.
KEVAL A JETHI NIKHIL PADHIYAR TY CE-A.  Seeing  Feeling  Smelling  Tasting  Hearing.
SIXTH SENSE TECHNOLOGY
A Robust Method of Detecting Hand Gestures Using Depth Sensors Yan Wen, Chuanyan Hu, Guanghui Yu, Changbo Wang Haptic Audio Visual Environments and Games.
Department of Electrical and Computer Engineering He Zhou Hui Zheng William Mai Xiang Guo Advisor: Professor Patrick Kelly ASLLENGE.
By shooting 2009/10/1. outline imTop overview imTop detection Finger Mobile Finger detection evaluation Mobile detection improvement.
Move With Me S.W Graduation Project An Najah National University Engineering Faculty Computer Engineering Department Supervisor : Dr. Raed Al-Qadi Ghada.
The Science of Digital Media Microsoft Surface 7May Metropolia University of Applied Sciences Display Technologies Seminar.
Efficient Moving Object Segmentation Algorithm Using Background Registration Technique Shao-Yi Chien, Shyh-Yih Ma, and Liang-Gee Chen, Fellow, IEEE Hsin-Hua.
Real-time Hand Pose Recognition Using Low- Resolution Depth Images
Computer Vision for Interactive Computer Graphics Mrudang Rawal.
Touchscreen Implementation for Multi-Touch
Interactive Sand Art Draw Using RGB-D Sensor Presenter : Senhua Chang.
Computer-Based Animation. ● To animate something – to bring it to life ● Animation covers all changes that have visual effects – Positon (motion dynamic)
Jason Li Jeremy Fowers Ground Target Following for Unmanned Aerial Vehicles.
MULTI-TOUCH TABLE Athena Frazier Chun Lau Adam Weissman March 25, 2008 Senior Projects II.
WUW - Wear Ur World - A Wearable Gestural Interface Joshua Latvatalo.
Knowledge Systems Lab JN 8/24/2015 A Method for Temporal Hand Gesture Recognition Joshua R. New Knowledge Systems Laboratory Jacksonville State University.
“S ixth Sense is a wearable gestural interface device that augments the physical world with digital information and lets people use natural hand gestures.
   Input Devices Main Memory Backing Storage PROCESSOR
A Fast and Robust Fingertips Tracking Algorithm for Vision-Based Multi-touch Interaction Qunqun Xie, Guoyuan Liang, Cheng Tang, and Xinyu Wu th.
Supporting Beyond-Surface Interaction for Tabletop Display Systems by Integrating IR Projections Hui-Shan Kao Advisor : Dr. Yi-Ping Hung.
3D Fingertip and Palm Tracking in Depth Image Sequences
Olga Zoidi, Anastasios Tefas, Member, IEEE Ioannis Pitas, Fellow, IEEE
Low-Cost Multi-Touch Sensing through Frustrated Total Internal Reflection Jefferson Y. Han, New York University Presented by: Cody Boisclair.
Presentation by: K.G.P.Srikanth. CONTENTS  Introduction  Components  Working  Applications.
Supporting Beyond-surface Interaction for Tabletop Systems by Integrating IR Projections Hui-Shan Kao.
3D SLAM for Omni-directional Camera
Submitted by:- Vinay kr. Gupta Computer Sci. & Engg. 4 th year.
Surface Computing Turning everyday surfaces into interactive intelligent interfaces Co-located input and output Mixed reality: tangible objects, natural.
Making Graphical Information Visible in Real Shadows on Interactive Tabletops Mariko Isogawa, Daisuke Iwai, and Kosuke Sato (Osaka Univ., Japan) IEEE TRANSACTIONS.
 Input Devices Input Devices  Examples of Input Devices Examples of Input Devices  Keyboard Keyboard  Pointing Devices Pointing Devices Mouse Joystick.
Projector Calibration of Interactive Multi-Resolution Display Systems 互動式多重解析度顯示系統之投影機校正 Presenter: 邱柏訊 Advisor: 洪一平 教授.
Interactive Sand Art Drawing Using RGB-D Sensor
Su-ting, Chuang 2010/8/2. Outline Introduction Related Work System and Method Experiment Conclusion & Future Work 2.
Su-ting, Chuang 2010/8/2. Outline Introduction Related Works System and Method Experiment Conclusion & Future Work 2.
Team Members Ming-Chun Chang Lungisa Matshoba Steven Preston Supervisors Dr James Gain Dr Patrick Marais.
Su-ting, Chuang 1. Outline Introduction Related work Hardware configuration Detection system Optimal parameter estimation framework Conclusion 2.
CONTENT FOCUS FOCUS INTRODUCTION INTRODUCTION COMPONENTS COMPONENTS TYPES OF GESTURES TYPES OF GESTURES ADVANTAGES ADVANTAGES CHALLENGES CHALLENGES REFERENCE.
It Starts with iGaze: Visual Attention Driven Networking with Smart Glasses It Starts with iGaze: Visual Attention Driven Networking with Smart Glasses.
Presented by : P L N GANESH CH DURGA PRASAD M RAVI TEJA 08551A A A0446.
IEEE International Conference on Multimedia and Expo.
By shooting. Optimal parameters estimation Sample collect Various finger size Hard press and soft press Exhaustive search.
Su-ting, Chuang 1. Outline Introduction Related work Hardware configuration Finger Detection system Optimal parameter estimation framework Conclusion.
Outline Introduction Related Work System Overview Methodology Experiment Conclusion and Future Work.
MULTI TOUCH. Introduction Multi-touch is a human-computer interaction technique. Consists of a touch screen as well as software that recognizes multiple.
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.
Contents Introduction Requirements Design Technology Working Interaction.
Over the recent years, computer vision has started to play a significant role in the Human Computer Interaction (HCI). With efficient object tracking.
TOUCHLESS TOUCHSCREEN USER INTERFACE
CIRP Annals - Manufacturing Technology 60 (2011) 1–4 Augmented assembly technologies based on 3D bare-hand interaction S.K. Ong (2)*, Z.B. Wang Mechanical.
TOUCHLESS TOUCH SCREEN USER INTERFACE
Hand Gestures Based Applications
Daniel A. Taylor Pitt- Bradford University
SIXTH SENSE TECHNOLOGY
TOUCH SCREEN TECHNOLOGY
SIXTH SENSE TECHNOLOGY
Chapter 5 - Input.
Jefferson Y. Han, New York University
眼動儀與互動介面設計 廖文宏 6/26/2009.
A visual surveillance using real-time curve evolution based on the level-set method and pan-tilt camera Good afternoon ~ sir. Today I want to talk about.
Presentation transcript:

Vision-Based Finger Detection and Its Applications 基於電腦視覺之手指偵測及其應用 Yi-Fan Chuang Advisor: Prof. Yi-Ping Hung Prof. Ming-Sui Lee

Outline  Introduction  Related Work  Fingertip Detection and Tracking  Applications i-m-Top Magic Crystal Ball (MaC Ball)  Conclusion & Future Work 2

Outline  Introduction  Related Work  Fingertip Detection and Tracking  Applications i-m-Top Magic Crystal Ball (MaC Ball)  Conclusion & Future Work 3

Introduction  Interactive system Bare-handed operations are more intuitive to manipulate digital objects directly Interactions Users: hover/touch gestures Objects: rotation, scaling, selection, special effects…. Use computer vision techniques Fingertip detection Fingertip tracking 4

Outline  Introduction  Related Work  Fingertip Detection and Tracking  Applications i-m-Top Magic Crystal Ball (MaC Ball)  Conclusion & Future Work 5

Related Work  Enhance Desk Fingertip finding Template matching Palm finding Morphological erosion H. KOIKE and Y. KOBAYASHI, “Integrating paper and digital information on enhanceddesk: a method for realtime finger tracking on an augmented desk system,“ ACM Transation Computer-Human Interaction, vol. 8, no. 4, pp , 2001.

Related Work  FTIR (Frustrated Total Internal Reflection) J. Y. Han, “Low-cost multi-touch sensing through frustrated total internal reflection," in Proceedings of the 18th annual ACM symposium on User interface software and technology (UIST '05). New York, NY, USA: ACM Press, 2005, pp

Related Work  Visual Touchpad Fingertip detection Curvature of contour Finger Orientation Touch detection Two warp images S. Malik and J. Laszlo, “Visual touchpad: a two-handed gestural input device," in Proceedings of the 6th international conference on Multimodal interfaces (ICMI '04). New York, NY, USA: ACM Press, 2004, pp

Related Work  PlayAnyWhere Touch and Hover Use appearance of shadows A. D. Wilson, “Playanywhere: a compact interactive tabletop projection-vision system," in Proceedings of the 18th annual ACM symposium on User interface software and technology (UIST '05). New York, NY, USA: ACM Press, 2005, pp

Related Work  Comparison 10 Enhance Desk (CHI 01’) FTIR (UIST 05’) Visual Touchpad (ICMI 04’) PlayAnyWhere (UIST 05’) Method Template matching Connected component analysis Curvature of contour Shadow DetectionTouch Touch/Hover (2 cameras) Touch/Hover (1 camera) Disadvantage One user Only touch Only touchOne user One finger for one palm Our Work: Touch/Hover (1 camera) Multi-user with multi-finger

Outline  Introduction  Related Work  Fingertip Detection and Tracking  Applications i-m-Top Magic Crystal Ball (MaC Ball)  Conclusion & Future Work 11

Overview  System setup An IR camera with IR illuminators to observe hands J. Rekimoto and N. Matsushita, “Perceptual surfaces: Towards a human and object sensitive interactive display," Workshop on Perceptural User Interfaces (PUI'97), Direct observation Clear shapes Indirect observation Unclear shapes

 System setup Direct observation Clear shapes Indirect observation Unclear shapes Overview Clear shapes (MaC Ball) Gesture Captured image

 System setup Direct observation Clear shapes Indirect observation Unclear shapes Overview 14 Unclear shapes (i-m-Top) Gesture Captured image

Overview  Fingertip detection  Fingertip tracking Detection results Kalman filtering Background subtraction Morphological opening Difference of previous two Principal component analysis Fingertip detection 15

Fingertip Detection  Background subtraction  Observation Contact area leaves strong reflection (Enhanced image) Background subtraction Morphological opening Difference of previous two PCA Fingertip detection 16

Fingertip Detection  Extract finger part Use a morphological opening operation The size of structuring element is larger than that of a normal finger and smaller than a palm. Original Morphological opening Finger (Enhanced image) Background subtraction Morphological opening Difference of previous two PCA Fingertip detection 17

Fingertip Detection  Difference and binarization  Principal component analysis Finger direction Possible fingertips’ positions (Enhanced image) Background subtraction Morphological opening Difference of previous two PCA Fingertip detection Background subtraction Morphological opening Difference of previous two PCA Fingertip detection 18

Fingertip Detection  Template matching (pattern matching) Template Remove false matchings Distance check Diagonal check Background subtraction Morphological opening Difference of previous two PCA Fingertip detection Finger patch

Detection Results on i-m-Top Fingertip detection Difference of previous two & PCA Morphological opening Background subtraction (Enhanced image) Separate finger touching and palm hovering

Detection Results on MaC Ball Fingertip detection Difference of previous two & PCA Morphological opening Background subtraction 21

Fingertip Tracking  Kalman filter Smooth the path Predict the new state and its uncertainty Correct the tracker with its new measurement Assume white noise and uniform velocity Original After Kalman filter 22

Performance Evaluation  Real-time system is possible 23

Outline  Introduction  Related Work  Fingertips Detection and Tracking  Applications i-m-Top Magic Crystal Ball (MaC Ball)  Conclusion & Future Work 24

Hardware Configuration  i-m-Top Interactive Multi-resolution Tabletop Cooperate with Yi-Wei Chia 25

Software Implementation  Fingertip detection and tracking  Palm detection and tracking  Association between fingertips and palms  Pen detection  Priority of pens and palms  Events definitions 26

Palm Detection and Tracking  Palm detection The average position is picked as palm position  Palm tracking Kalman filtering Palm detection Morphological opening (Palm part) Background subtraction (Enhanced Image)

Association between Fingertips and Palms  Allocate fingertips to palms Use the angle and the distance between fingers and palms (Enhanced Image) 28

Pen Detection and Priority  Pen Detection Use a higher threshold  Priority of pens and palms Higher priority for the pen tip If there is a palm around the pen tip, this palm and the fingertips associated to the palm will be ignored. 29

Events Definitions  Hover Palm position  Touch Palm position Finger position and its correspondent palm Pen position 30

Application I: Browsing and Editing  Operations Drag photo/document Zoom in and zoom out Stroke Move the foveal area 31

Application II: Video Retrieval System  Operations Query Browse Feedback 32 Video Top button Video plane Video wall Scroll bar

Outline  Introduction  Related Work  Fingertip Detection and Tracking  Applications i-m-Top Magic Crystal Ball (MaC Ball)  Conclusion & Future Work 33

Magic Crystal Ball (MaC Ball)  An interactive 3D display Slide fingers (like a wizard) on the ball surface to control the content 34

Hardware Configuration IR Camera IR Illuminator Pressure Sensors User Transparent Glass Ball Reflection Mirror Fresnel Lens LCD Display Module Detection Module

Software Implementation  Fingertip detection and tracking Detect fingertips’ positions Pointing gesture  Motion detection Optical flow algorithm Waving gesture  Contact Detection Pressure Sensor (Flexi Force) Detect whether users touch MaC Ball

Software Implementation  Contact detection – Pressure Sensors Observation p1 p2 p3 p1 p2 p1 p2 37

Events Definitions  Gesture switch Pointing Gesture Fingertips Detection Motion Detection Fingertips Detection Waving Gesture Pressure sensors Touch / Hover 38

Application: Virtual Exhibition  Operations Rotate Select Magnifier Change relics 39 Video

Outline  Introduction  Related Work  Fingertip Detection and Tracking  Applications i-m-Top Magic Crystal Ball (MaC Ball)  Conclusion & Future Work 40

Conclusion & Future Work  Multi-finger detection techniques Simple and real-time Cost-effective and flexible  Applications i-m-Top: interactive interface MaC Ball: interactive 3D display  Future work Use FTIR to enhance the accuracy of fingertip detection More gestures for interactive systems 41