跳到主要內容

臺灣博碩士論文加值系統

(44.192.67.10) 您好!臺灣時間:2024/11/14 23:28
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:簡敬宇
研究生(外文):Ching-Yu Chien
論文名稱:以視覺為基礎之使用多重攝影機之即時手臂指向追蹤及辨識系統
論文名稱(外文):Vision-based Real-time Pointing Arm Gesture Tracking and Recognition System using Multiple Cameras
指導教授:黃仲陵黃仲陵引用關係
指導教授(外文):Chung-Lin Huang
學位類別:碩士
校院名稱:國立清華大學
系所名稱:電機工程學系
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2006
畢業學年度:94
語文別:英文
論文頁數:55
中文關鍵詞:手臂指向辨識追蹤
外文關鍵詞:armpointingrecognitiontracking
相關次數:
  • 被引用被引用:3
  • 點閱點閱:378
  • 評分評分:
  • 下載下載:111
  • 收藏至我的研究室書目清單書目收藏:0
由於人機介面的應用日益普及,包括手勢辨識、語音辨識、或是肢體語言辨識等等,都已經被廣泛研究並且應用在日常生活之中,其中以利用手勢作為輸入介面是最自然且直接的,因此手勢辨識的相關研究近年來已經有許多發展,而以手臂來指向的人機介面系統也有越來越多的研究及探討。在此篇論文中,我們發展出使用多重攝影機的手臂指向追蹤及辨識系統,主要是直接追蹤在三維空間中手臂上的兩個點,以這兩個點來代表空間中的指向線。在系統裡我們總共使用了三台攝影機來擷取影像,讓使用者在走路時,同時也能做出指向手勢。其中,影像平面和三維空間的座標轉換關係,我們利用了直接線性轉換(DLT)來求得,好處是不用預先得到攝影機之內部及外部參數。並利用這座標轉換的關係,結合使用三維參數之Particle Filter來達到手臂的追蹤,能夠有效的解決手臂被遮蔽的問題,並提升程式執行效率,最後將追蹤到的三維點投影到各影像平面上,擷取手臂形狀後,找出各影像平面上手臂之對應點,並重建三維之指向線,以此來微調手臂指向的方向,提高指向正確率。在此系統中,先定義好指向的目標物,且目標物並不一定必須出現在影像平面裡,系統執行速度約為6Hz,在對指向線之方向作微調的情況下,本系統之辨識率能達到90%。
In this thesis, we develop a real-time arm pointing system. The main contribution of the system is using three cameras to track the pointing arm and identify several pointing targets in 3-D space. The system allows the user to make the arm pointing and the walking in a work space at the same time. The novelty of our method is directly tracking two 3-D points representing the pointing line in 3-D space and then refining the tracking results. We take advantages of Direct Linear Transformation (DLT) to extend the samples of particle filter to 3-D space. In our system, the pointing targets are not necessarily visible in any one of the three views. In the experiments, we show that our system will finish analyzing each frame of video in about 1/6 second. The pointing accuracy of our system is measured by 80 times of pointing test to eight designated 3-D targets by five users. The success rate of our system is above 90%.
ABSTRACT..........................................i
LIST OF FIGURES..................................iv
LIST OF TABLES...................................vi
Chapter 1 INTRODUCTION...........................1
1.1 Motivation....................................1
1.2 Related Works.................................2
1.3 Our Proposal and System Overview .............4
1.4 Organization of this Thesis...................7
Chapter 2 CAMERA CALIBRATION AND 3-D POSITION RECONSTRUCTION....................................8
2.1 DLT Method Description........................9
2.2 Camera Calibration...........................12
2.3 3-D Position Reconstruction..................13
2.4 Implementation ...............................14
Chapter 3 ARM TRACKING WITH 3-D PARTICLE FILTER.17
3.1 Tracking with 3-D Particle Filter............17
3.2 3-D Particle Filtering.......................19
3.2.1 Overview of Particle Filter................19
3.2.2 Modify with Multi-view and 3-D Information.22
3.3 Observation Model (Color Distribution Model).27
3.3.1 Target Model...............................28
3.3.2 Candidate Model............................29
3.3.3 Observation Likelihood.....................30
3.4 Initialization ...............................31
Chapter 4 REFINE THE POINTING DIRECTION.........34
4.1 The Orientation of Arm Region................34
4.2 Finding Corresponding Points.................37
4.3 Select Two Cameras to Refine Arm Position....39
4.4 3-D Pointing.................................43
Chapter 5 EXPERIMENT RESULTS....................44
Chapter 6 CONCLUSION AND FUTURE WORK............52
REFERENCES.......................................53
[1] R. Cipolla and N.J. Hollinghurst. “A human-robot interface using pointing withuncalibrated stereo vision”, in Computer Vision for Human-Machine Interaction. Ed. R.Cipolla and A. Pentland. Cambridge University Press, 1988.
[2] Lee, M-S., Weinshall, D., Colmenarez, A., Cohen-Solal, E., Lyons, D., “A Computer Vision System for On-Screen Item Selection by Finger Pointing”, IEEE International Conference on Computer Vision and Pattern Recognition (CVPR 2001), Hawaii, December 2001.
[3] Shin Sato and Shigeyuki Sakane, “A Human-Robot Interface Using an Interactive Hand Pointer that Projects a Mark in the Real Work Space”, IEEE International Conference on Robotics and Automation (ICRA 2000), April 2000.
[4] R. Kehl and L.V. Gool, “Real-Time Pointing Gesture Recognition for an Immersive Environment”, IEEE International Conference on Face and Gesture Recognition (FGR 2004), 2004.
[5] Yi-Ping Hung, Yao-Strong Yang, Yong-Sheng Chen, Ing-Bor Hsieh, Chiou-Shann Fuh, “Free-Hand Pointer by Use of an Active Stereo Vision System,” 14th IEEE International Conference on Pattern Recognition (ICPR 98), pp. 1244-1246, Brisbane, August 1998.
[6] Kai Nickel, Edgar Seemann, and Rainer Stiefelhagen, “3D-Tracking of Head and Hands for Pointing Gesture Recognition in a Human-Robot Interaction Scenario”, IEEE International Conference on Face and Gesture Recognition (FGR 2004), 2004.
[7] Y. Yamamoto, I. Yoda et K. Sakaue, “Arm-Pointing Gesture Interface Using Surrounded Stereo Cameras System”, IEEE International Conference on Pattern Recognition (ICPR 2004), pp. 965-970, Cambridge, RU, 2004.
[8] Y. I. Abdel-Aziz and H. M. Karara, “Direct linear transformation from comparator coordinates into object-space coordinates in close-range photogrammetry”, Proceedings of the ASP Symposium on Close-Range Photogrammetry, pp. 1-18, 1971, Urbana, Illinois, USA, pp. 1-18, 1971.
[9] Young-Hoo Kwon: Kwon3D: DLT Method. <http://kwon3d.com/theories.html.>
[10] Jos�� Braz, Jo�姛 Pereira, Ant�曝io Veloso, “VIDA - Interactive Viewer of Augmented (biomechanical) Data”, in Revista VIRtual, Special Issue: Advances in Computer Graphics in Portugal (ISSN: 0873-1837), 2004.
[11] G. A. Wood and R. N. Marshall, “The accuracy of DLT extrapolation in three-dimensional film analysis,” Journal of Biomechanics, vol. 19, no. 9, pp. 781–785, 1986.
[12] M. Isard and A. Blake, “Condensation - Conditional Density Propagation for Visual Tracking”, International Journal of Computer Vision, vol. 29 (IJCV 98), no. 1, pp. 5-28, 1998.
[13] C. Shan, Y. Wei, T. Tan, and F. Ojardias, “Real Time Hand Tracking by Combining Particle Filtering and Mean Shift”, IEEE International Conference on Face and Gesture Recognition (FGR 2004), 2004.
[14] K. Nummiaro, E. Koller-Meier, Luc Van Gool, “An Adaptive Color-Based Particle Filter”, Symposium for Pattern Recognition of the DAGM Zuerich, September 2002.
[15] J. Czyz, B. Ristic and B. Macq, “A color-based particle filter for joint detection and tracking of Multiple objects”, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2005), 2005.
[16] Feng-Sheng Chen, Chih-Ming Fu, Chung-Lin Huang, “Hand gesture recognition using a real-time tracking method and hidden Markov models”, Image Vision Comput.21(8)(IVC), pp.745-758, 2003.
[17] Pitas, Digital Image Processing Algorithms and Applications, Wiley-interscience, pp.352-356, 2000.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top