Retinex 를 이용한 안정적인 Motion Tracking Interaction 콘텐츠 개발 DongSeo University Department of Visual Contents Ki-Young Sung

Slides:



Advertisements
Similar presentations
Hand Gesture for Taking Self Portrait Shaowei Chu and Jiro Tanaka University of Tsukuba Japan 12th July 15 minutes talk.
Advertisements

LING 111 Teaching Demo By Tenghui Zhu Introduction to Edge Detection Image Segmentation.
4th European Micro-UAV Meeting Sept , 2004
계층적 particle 필터를 이용한 다관절 상체 추적과 SVM을 이용한 포즈 인식
Surveillance Application Ankit Mathur Mayank Agarwal Subhajit Sanyal Lavanya Sharan Vipul Kansal.
Adviser : Ming-Yuan Shieh Student ID : M Student : Chung-Chieh Lien VIDEO OBJECT SEGMENTATION AND ITS SALIENT MOTION DETECTION USING ADAPTIVE BACKGROUND.
A KLT-Based Approach for Occlusion Handling in Human Tracking Chenyuan Zhang, Jiu Xu, Axel Beaugendre and Satoshi Goto 2012 Picture Coding Symposium.
Broadcast Court-Net Sports Video Analysis Using Fast 3-D Camera Modeling Jungong Han Dirk Farin Peter H. N. IEEE CSVT 2008.
Retinex Image Enhancement Techniques --- Algorithm, Application and Advantages Prepared by: Zhixi Bian and Yan Zhang.
Mean-Shift Algorithm and Its Application Bohyung Han
Recent Developments in Human Motion Analysis
Motion based Correspondence for Distributed 3D tracking of multiple dim objects Ashok Veeraraghavan.
Region-Level Motion- Based Background Modeling and Subtraction Using MRFs Shih-Shinh Huang Li-Chen Fu Pei-Yung Hsiao 2007 IEEE.
Fast Illumination-invariant Background Subtraction using Two Views: Error Analysis, Sensor Placement and Applications Ser-Nam Lim, Anurag Mittal, Larry.
Deriving Intrinsic Images from Image Sequences Mohit Gupta Yair Weiss.
Background Subtraction for Urban Traffic Monitoring using Webcams Master Graduation Project Final Presentation Supervisor: Rein van den Boomgaard Mark.
Large Lump Detection by SVM Sharmin Nilufar Nilanjan Ray.
Introduction to Object Tracking Presented by Youyou Wang CS643 Texas A&M University.
Dorin Comaniciu Visvanathan Ramesh (Imaging & Visualization Dept., Siemens Corp. Res. Inc.) Peter Meer (Rutgers University) Real-Time Tracking of Non-Rigid.
Jacinto C. Nascimento, Member, IEEE, and Jorge S. Marques
Human Computer Interface based on Hand Tracking P. Achanccaray, C. Muñoz, L. Rojas and R. Rodríguez 4 th International Symposium on Mutlibody Systems and.
Computer graphics & visualization Introduction. computer graphics & visualization Simulation and Animation – SS 07 Jens Krüger – Computer Graphics and.
I mage and M edia U nderstanding L aboratory for Performance Evaluation of Vision-based Real-time Motion Capture Naoto Date, Hiromasa Yoshimoto, Daisaku.
Jason Li Jeremy Fowers Ground Target Following for Unmanned Aerial Vehicles.
Professor : Yih-Ran Sheu Student’s name : Nguyen Van Binh Student ID: MA02B203 Kinect camera 1 Southern Taiwan University Department of Electrical Engineering.
Proposal for SK C&C ㈜ 타오네트웍스 Goal  Wireless  Multimedia.
Fingertip Tracking Based Active Contour for General HCI Application Proceedings of the First International Conference on Advanced Data and Information.
HANBAT Univ. Copyright ⓒ Embedded Team. All Rights Reserved Embedded System Software EMPOS II 를 이용한 PMP 기능 구현.
Gesture-Based Interactive Beam- Bending By Justin Gigliotti Mentored by Professor Tarek El Dokor And Dr. David Lanning Arizona/NASA Space Grant Symposium.
A Method for Hand Gesture Recognition Jaya Shukla Department of Computer Science Shiv Nadar University Gautam Budh Nagar, India Ashutosh Dwivedi.
Many-SC 아키텍처 기반 OpenCL 프레임워크상에서의 응용프로그램 구현 및 최적화
報告人 : 林福城 指導老師 : 陳定宏 1 From Res. Center of Intell. Transp. Syst., Beijing Univ. of Technol., Beijing, China By Zhe Liu ; Yangzhou Chen ; Zhenlong Li Appears.
Multitouch Game Table Senior Design Fall 2006 What we did right and what we did wrong… Aditya Mittal James Wallace Albert You Paul Ferrara.
出處: Signal Processing and Communications Applications, 2006 IEEE 作者: Asanterabi Malima, Erol Ozgur, and Miijdat Cetin 2015/10/251 指導教授:張財榮 學生:陳建宏 學號: M97G0209.
Video Segmentation Prepared By M. Alburbar Supervised By: Mr. Nael Abu Ras University of Palestine Interactive Multimedia Application Development.
Online Kinect Handwritten Digit Recognition Based on Dynamic Time Warping and Support Vector Machine Journal of Information & Computational Science, 2015.
Edward Land’86 There exists a discrepancy between the human vision system and the recorded color images. Dynamic range difference results in the loss.
Bo QIN, Zongshun MA, Zhenghua FANG, Shengke WANG Computer-Aided Design and Computer Graphics, th IEEE International Conference on, p Presenter.
Motion Analysis using Optical flow CIS750 Presentation Student: Wan Wang Prof: Longin Jan Latecki Spring 2003 CIS Dept of Temple.
Interactive Sand Art Drawing Using RGB-D Sensor
Moshe Gutman Michael Mills Nathaniel Troutman. The Idea  Present the participant with a “Glass Box”, a portal to an interactive world where they can.
Fingertip Detection with Morphology and Geometric Calculation Dung Duc Nguyen ; Thien Cong Pham ; Jae Wook Jeon Intelligent Robots and Systems, IEEE/RSJ.
Kernel Programming Task Management ( 월 ) 이 병 희
PROJECT#3(b) Astrocyte Analysis
Looking at people and Image-based Localisation Roberto Cipolla Department of Engineering Research team
Jessie. Kim Intelligent Systems Group Feb. 2014
Project Multi-Touch Albert You Aditya Mittal Paul Ferrara Jim Wallace.
IEEE International Conference on Multimedia and Expo.
상대적인 SATD cost에 기반한 화면내 부호화 모드 고속 결정 방법
Visual Tracking by Cluster Analysis Arthur Pece Department of Computer Science University of Copenhagen
Virtual Pointing Device Using Stereo Camera The 6th International Conference on Applications and Principles of Information Science Jan , 2007, Kuala.
Target Tracking In a Scene By Saurabh Mahajan Supervisor Dr. R. Srivastava B.E. Project.
연료레일에서의 맥동저감을 위한 유체-구조 상호작용 해석
CGIV Hand tracking interaction Yeong-Mi Jeon Real time hand-tracking and finger tracking for interaction Yeong-Mi Jeon
Vision Based hand tracking for Interaction The 7th International Conference on Applications and Principles of Information Science (APIS2008) Dept. of Visual.
Color Clustering and Learning for Image Segmentation Based on Neural Networks Guo Dong, Member, IEEE, and Ming Xie, Member, IEEE 최지혜.
Portable Camera-Based Assistive Text and Product Label Reading From Hand-Held Objects for Blind Persons.
Zhaoxia Fu, Yan Han Measurement Volume 45, Issue 4, May 2012, Pages 650–655 Reporter: Jing-Siang, Chen.
ENTERFACE 08 Project 9 “ Tracking-dependent and interactive video projection ” Mid-term presentation August 19th, 2008.
Motion Estimation of Moving Foreground Objects Pierre Ponce ee392j Winter March 10, 2004.
LOGO “ Add your company slogan ” Final Project Group: T2H2 Mai Thi Thu Nguyen Van Thanh Do Van Huu Pham Ngoc Huy Supervisor: DungHA TrungNT T2H2 Group:
Department of Biomedical Engineering O 2 MONITORING SYSTEM AMC 의료용 O2 Monitor 의 개발 김기태, 조성범, 추교진, 신상영, 이성대, 김서확, 신동익, 허수진 서울중앙병원 의공학과, 울산의대 의공학교실.
Tracking Under Low-light Conditions Using Background Subtraction Matthew Bennink Clemson University Clemson, SC.
SPACE MOUSE. INTRODUCTION  It is a human computer interaction technology  Helps in movement of manipulator in 6 degree of freedom * 3 translation degree.
Video object segmentation and its salient motion detection using adaptive background generation Kim, T.K.; Im, J.H.; Paik, J.K.;  Electronics Letters 
A New Approach to Track Multiple Vehicles With the Combination of Robust Detection and Two Classifiers Weidong Min , Mengdan Fan, Xiaoguang Guo, and Qing.
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.
LEAP MOTION: GESTURAL BASED 3D INTERACTIONS
Youngmin Jung Open SSO 설치 Youngmin Jung
Automated Detection of Human Emotion
Presentation transcript:

Retinex 를 이용한 안정적인 Motion Tracking Interaction 콘텐츠 개발 DongSeo University Department of Visual Contents Ki-Young Sung

CONTENTS 서론 관련연구 시스템 구성 Motion Tracking Analysis Physics 결론 Reference

서 론

1. 서론 1.1. 연구배경 ※출처 : 2008 국내외 문화콘텐츠 산업 전망 ( 한국문화콘텐츠진흥원 )

1. 서론 1.2. 개요

1. 서론 1.2. 개요 KMMS, 28~29 May.2010, Cheong-ju Univ., “Interactive Contents development Using Motion Tracking and Physics”

관련 연구

2. 관련연구 2.1. 인터렉티브 콘텐츠 연구 KMMS, 28~29 May.2010, Cheong-ju Univ., “Interactive Contents development Using Motion Tracking and Physics”

2. 관련연구 KMMS, 28~29 May.2010, Cheong-ju Univ., “Interactive Contents development Using Motion Tracking and Physics” 2.2. 기존 인터렉티브 콘텐츠 연구

2. 관련연구 KMMS, 28~29 May.2010, Cheong-ju Univ., “Interactive Contents development Using Motion Tracking and Physics” 2.2. 기존 인터렉티브 콘텐츠 연구

관련 연구

3. 시스템 구성 3.1. 하드웨어 구성 HVR2300CA Beam ProjectorComputer KMMS, 28~29 May.2010, Cheong-ju Univ., “Interactive Contents development Using Motion Tracking and Physics” Viewrun DFK WebCam

3. 시스템 구성 HVR2300CA Computer Beam Projector Screen 3.2. 하드웨어 설치 구성도 KMMS, 28~29 May.2010, Cheong-ju Univ., “Interactive Contents development Using Motion Tracking and Physics”

3.3. 시스템 단계 3. 시스템 구성 · Background Setting · Background Subtraction · Blurring · Labeling · Morphology · Contour Tracking Camera Setting Frame Grab Image Processing · Object OpenGL Display Physics KMMS, 28~29 May.2010, Cheong-ju Univ., “Interactive Contents development Using Motion Tracking and Physics”

3.4. 소프트웨어 구성도 3. 시스템 구성 KMMS, 28~29 May.2010, Cheong-ju Univ., “Interactive Contents development Using Motion Tracking and Physics”

3. 시스템 구성 KMMS, 28~29 May.2010, Cheong-ju Univ., “Interactive Contents development Using Motion Tracking and Physics” 3.4. 소프트웨어 구성도

3. 시스템 구성 3.5. 시스템 설치 구상도 KMMS, 28~29 May.2010, Cheong-ju Univ., “Interactive Contents development Using Motion Tracking and Physics”

Motion Tracking Analysis

4. Motion Tracking Analysis 4.1. 백그라운드 캡쳐 KMMS, 28~29 May.2010, Cheong-ju Univ., “Interactive Contents development Using Motion Tracking and Physics”

4. Motion Tracking Analysis 4.2. Retinex Algorithm KMMS, 28~29 May.2010, Cheong-ju Univ., “Interactive Contents development Using Motion Tracking and Physics”

4. Motion Tracking Analysis 4.2. Retinex Algorithm KMMS, 28~29 May.2010, Cheong-ju Univ., “Interactive Contents development Using Motion Tracking and Physics”

4. Motion Tracking Analysis 4.2. Retinex Algorithm KMMS, 28~29 May.2010, Cheong-ju Univ., “Interactive Contents development Using Motion Tracking and Physics” 사전적인 의미 : Retinex( 망막 ) + Cortex( 피질 )

4. Motion Tracking Analysis 4.2. Retinex Algorithm KMMS, 28~29 May.2010, Cheong-ju Univ., “Interactive Contents development Using Motion Tracking and Physics”

4. Motion Tracking Analysis 4.2. Retinex Algorithm KMMS, 28~29 May.2010, Cheong-ju Univ., “Interactive Contents development Using Motion Tracking and Physics” SSR (single-scale retinex) MSR (Multi-scale retinex)

4. Motion Tracking Analysis 4.2. Retinex Algorithm KMMS, 28~29 May.2010, Cheong-ju Univ., “Interactive Contents development Using Motion Tracking and Physics” –I i (x,y) : 입력영상 –R i (x,y): 출력영상 – Gaussian function: F(x,y)=Ke -(x2+y2)/c2 K determined by: C is the Gaussian surround space constant

4. Motion Tracking Analysis 4.2. Retinex Algorithm KMMS, 28~29 May.2010, Cheong-ju Univ., “Interactive Contents development Using Motion Tracking and Physics” K = 정규화 계수 σ = 가우시안 함수의 표준 편차 σ 의 크기에 따라 Retinex 결과 영상의 디테일이 증가 하거나 감소

4. Motion Tracking Analysis 4.3. Retinex Algorithm 적용 KMMS, 28~29 May.2010, Cheong-ju Univ., “Interactive Contents development Using Motion Tracking and Physics” 실험 결과 : 정지 영상에서의 Retinex 적용 (8bit)

4. Motion Tracking Analysis 4.3. Retinex Algorithm 적용 KMMS, 28~29 May.2010, Cheong-ju Univ., “Interactive Contents development Using Motion Tracking and Physics” 실험 결과 : 정지 영상에서의 Retinex 적용 (8bit)

4. Motion Tracking Analysis 4.3. Retinex Algorithm 적용 KMMS, 28~29 May.2010, Cheong-ju Univ., “Interactive Contents development Using Motion Tracking and Physics” 실험 결과 : 리얼 타임상에서의 Retinex 적용 (8bit)

4. Motion Tracking Analysis 4.3. Retinex Algorithm 적용 KMMS, 28~29 May.2010, Cheong-ju Univ., “Interactive Contents development Using Motion Tracking and Physics” 실험 결과 : 리얼 타임상에서의 Retinex 적용 (8bit)

4. Motion Tracking Analysis 4.3. Retinex Algorithm 적용 KMMS, 28~29 May.2010, Cheong-ju Univ., “Interactive Contents development Using Motion Tracking and Physics” 실험 결과 : 리얼 타임상에서의 Retinex 적용 (8bit)

4. Motion Tracking Analysis 4.3. Retinex Algorithm 적용 KMMS, 28~29 May.2010, Cheong-ju Univ., “Interactive Contents development Using Motion Tracking and Physics” 실험 결과 : 리얼 타임상에서의 Retinex 적용 (8bit)

4. Motion Tracking Analysis 4.4. Blob Analysis KMMS, 28~29 May.2010, Cheong-ju Univ., “Interactive Contents development Using Motion Tracking and Physics”

4. Motion Tracking Analysis 4.4. Blob Analysis KMMS, 28~29 May.2010, Cheong-ju Univ., “Interactive Contents development Using Motion Tracking and Physics”

4.5. Morphology Analysis - BLOB 연산 후 남은 노이즈 제거를 위한 기법 KMMS, 28~29 May.2010, Cheong-ju Univ., “Interactive Contents development Using Motion Tracking and Physics” 4. Motion Tracking Analysis 팽창연산 침식연산 열림연산 닫힘연산

KMMS, 28~29 May.2010, Cheong-ju Univ., “Interactive Contents development Using Motion Tracking and Physics” 4. Motion Tracking Analysis 4.5. Morphology Analysis B=constant=0 인 경우 팽창연산 - 침식연산 - 열림연산 - 닫힘연산 -

4.5. Morphology Analysis 침식 연산 팽창 연산 닫힘 연산 Blob 연산 + Morphology KMMS, 28~29 May.2010, Cheong-ju Univ., “Interactive Contents development Using Motion Tracking and Physics” 4. Motion Tracking Analysis

KMMS, 28~29 May.2010, Cheong-ju Univ., “Interactive Contents development Using Motion Tracking and Physics” 4. Motion Tracking Analysis 4.5. Morphology Analysis 역할효과 침식 연산 Object 를 축소시키고 배경을 강조하는 역할 영상의 노이즈제거와 배경 강조에 효과적 팽창 연산 객체를 확대시키고 배경을 축소시키는 역할 객체의 내부의 구멍을 채우거나 짧게 끊어진 영역을 연결시킴 열림 연산침식연산 수회 후 팽창 연산 배경의 노이즈를 제거하고 객체를 부 드럽게 얻음 닫힘 연산팽창연산 수회 후 침식 연산 대상의 확장을 통해 구멍을 메우고 침 식으로 원영상을 축소함

KMMS, 28~29 May.2010, Cheong-ju Univ., “Interactive Contents development Using Motion Tracking and Physics” 4. Motion Tracking Analysis 4.5. Morphology Analysis

4.6. Contour Tracking - Blob 과 Morphology 과정을 끝낸 이미지에서 객체의 외곽선을 분리해내기 위한 연산 작업 start 이웃 연결성 KMMS, 28~29 May.2010, Cheong-ju Univ., “Interactive Contents development Using Motion Tracking and Physics” 4. Motion Tracking Analysis

4.7. OpenGL 매핑 & 오브젝트 생성 - 본 시스템은 OpenGL 로 표시하며 낙하하는 오브젝트는.TGA 포맷 사용 한글날 영상 작가전 사용 이미지서울 빛 축제 사용 이미지 KMMS, 28~29 May.2010, Cheong-ju Univ., “Interactive Contents development Using Motion Tracking and Physics” 4. Motion Tracking Analysis

Physics

5. Physics 5.1. Dynamic Mass-Spring - 생성된 오브젝트의 자유낙하 운동을 구현하기 위해 사용 탄성 미적용 탄성 적용 KMMS, 28~29 May.2010, Cheong-ju Univ., “Interactive Contents development Using Motion Tracking and Physics”

5.2. Physics A A’ (1) KMMS, 28~29 May.2010, Cheong-ju Univ., “Interactive Contents development Using Motion Tracking and Physics” 5. Physics

5.2. Physics - 방향성과 기울기, 운동 에너지 등을 실제와 같이 적용하기 위해 라그랑제 - 오일러 공식을 사용하였다. (1) 의 공식을 라그랑제 - 오일러 공식에 적용 KMMS, 28~29 May.2010, Cheong-ju Univ., “Interactive Contents development Using Motion Tracking and Physics” 5. Physics

5.2. Physics Differentiating with ( 이동거리 ) ( 시간 ) ( 속도 ) Differentiating with ( 속도 )( 시간 ) ( 가속도 ) KMMS, 28~29 May.2010, Cheong-ju Univ., “Interactive Contents development Using Motion Tracking and Physics”

5. Physics 5.2. Physics - 다음 공식들을 조합하여 다음시간에 대해 다음 위치와 속도를 알아낼 수 있다. A 의 다음위치 A 의 다음속도 A A’A’ KMMS, 28~29 May.2010, Cheong-ju Univ., “Interactive Contents development Using Motion Tracking and Physics”

5. Physics 5.3. 충돌 이벤트 - 컨투어 트래킹으로 찾은 외곽 선과 오브젝트가 충돌시 이벤트 KMMS, 28~29 May.2010, Cheong-ju Univ., “Interactive Contents development Using Motion Tracking and Physics” θ θ

전시 사진 한글날 행사 ( 자모향유 ) KMMS, 28~29 May.2010, Cheong-ju Univ., “Interactive Contents development Using Motion Tracking and Physics”

전시 사진 서울 빛 축제 (Shadow Garden) KMMS, 28~29 May.2010, Cheong-ju Univ., “Interactive Contents development Using Motion Tracking and Physics”

결 론

6. 결론 여러 가지 향상된 알고리즘을 사용하여 객체를 추적 시스템과 사용자 간의 상호작용 컨트롤러 없이 직접 몸으로 조작 가능 인터렉션 형식면에서 직감적인 사용자 몰입감을 주는 콘텐츠 콘텐츠 시장의 변화에 한 발 앞서 대비하는 계기 KMMS, 28~29 May.2010, Cheong-ju Univ., “Interactive Contents development Using Motion Tracking and Physics”

7. 레퍼런스 Anurag Mittal, Nikos Paragios, "Motion-Based Background Subtraction Using Adaptiv e Kernel Density Estimation," IEEEE Computer Society, vol.2,pp , 2004 ShahzadMalik, “Real-time Hand Tracking and Finger Tracking for Interaction”, CSC2 503F Project Report, December 18, Dung Duc Nguyen, Thien Cong Pham, Xuan Dai Pham, " Finger Extraction from Sce ne with Grayscale Morphology and BLOB Analysis", IEEE International Conference on Robotics and Biomimetics 이흥규, 디지털 영상처리 이론 및 구현 Visual C++ 접근 방법, 사이텍미디어, 파주시, 2007 Min Gyu Choi, "Introduction to Static/Dynamic Deformation with Mass-Spring System s KMMS, 28~29 May.2010, Cheong-ju Univ., “Interactive Contents development Using Motion Tracking and Physics”

THANK YOU Q / A