Dissertation > Excellent graduate degree dissertation topics show

Research on the Parameters Extracting of Hand Gesture Based on Stereo Vision

Author: GaoGuoYang
Tutor: ZhouDongXiang
School: National University of Defense Science and Technology
Course: Information and Communication Engineering
Keywords: Computer stereo vision Gesture interaction Gesture motion parameters Joint angle Parameter extraction Virtual hand
CLC: TP391.41
Type: Master's thesis
Year: 2011
Downloads: 15
Quote: 0
Read: Download Dissertation

Abstract


The virtual reality technology is an advanced form of human-computer interaction techniques that can make people immersed in the virtual environment, people have the feeling of an immersive, gesture interaction is a virtual reality senior human-computer interaction. Gesture interaction in the virtual environment the input gesture motion parameters is to achieve the the gesture interaction of key technologies. Gesture input, there are two: one is based on input data glove, another computer stereo vision-based input methods. With the development of computer stereo vision technology, computer stereo vision-based gesture input enables the movement of the hand to get rid of the shackles of the data gloves, virtual reality technology has increasingly become a research focus. Extract the the gesture motion parameters is the movement of the joint angle gesture input. This paper studies gesture motion parameters based on stereo vision extracted, the main work and innovations are as follows: an in-depth study of the the staffing of Physiology structure and kinematics principle, simplified staffing physiological structure. Staffing staffing model based on a simplified virtual modeling, realistic virtual hand model parameter control. The proposed mark based on the combination of colors and shapes of gestures joint feature points set and three-dimensional coordinate reconstruction method feature points set of 23 joints gestures. The camera focal length is constant, shot from different angles, the two images simulated binocular stereo vision, the same gesture. Thresholding method and processing of the two images, respectively, and the extracted feature points of the different colors and different shapes, and then labeled feature points in the two images in the same match. Zhang Zhengyou plane template calibrated two-step method to calibrate camera intrinsic parameters, solving a projection matrix of cameras shooting two images. 23 joints feature point based on the reconstruction of three-dimensional coordinates. 3, the proposed joint movement parameters based on the 23 gestures of 3D feature points extraction algorithm, derived a formula to solve. The three-dimensional reconstruction of gestures joint feature point in world coordinates convert the wrist coordinate system based coordinates. The derivation of the formula to solve staffing thumb and four fingers joint angles, respectively, according to the principle of inverse kinematics seeking joint angles and were specific gestures angle calculation. The calculated joint angle input to the model of the virtual hand right the real manpower attitude simulation display, to achieve a real manpower posture experimental system driven by the stereoscopic virtual hand movements. 4, in order to verify the effectiveness of the method, under different experimental conditions, respectively, of different gestures conducted experiments. Specific analysis of experimental results, the experiment found that the virtual hand simulation of the effect of the image of the real gestures realistic to achieve the desired effect.

Related Dissertations

  1. High-speed train multibody dynamics parameter extraction and model transformation key technology research,TP391.72
  2. Research and Implement on the Behavior Database of Virtual Hand,TP391.9
  3. The Study and Application on Methods of Elastic Impedance Inversion and Fluid Discrimination,P631.443
  4. Gansu Province Young People Men’s Heel-to-toewalking Raceathlete Technology Movement Kinematics Research,G821
  5. Traffic Parameter Extraction Based on Target Dertection and Tracking in IR Vedio,TP391.41
  6. Action recognition technology of virtual assembly operation,TP391.4
  7. Extraction of the Wide-band Network Parameters and Transient Simulation of the Secondary Cable in the Substation,TM744
  8. The Study on Methods of Pre-stack Inversion and Fluid Discrimination in Northeast Region of Sichuan,P618.13
  9. Sub- 90 nm CMOS device modeling techniques and PSP parameter extraction studies,TN386
  10. The Study on Methods of Rock Physical Properties Extraction from Elastic Impedance and Its Application,P631.4
  11. Research and Realization of Radar Active Deceive Jamming Signal Detection System,TN974
  12. Study on Motion Video Compression and Recovery Feasibility Based on Monitoring Parameter Extraction,TN919.81
  13. RF CMOS Noise Parameters Extraction Technology and Noise Figure Automation Measurement,TN386.1
  14. Digital home devices gesture interface research and design,TN02
  15. The Modeling, Optimization Design and Applications of Rf On-chip Spiral Inductors,TM55
  16. A Study on Neuro-muscular Characters of Rowing Athletes with High Level in Pull Tache,G861.4
  17. Research on Human-Computer Interaction for Children,TP11
  18. Light detector equivalent circuit model parameter extraction,TN36
  19. Transfer Belt Crack Detection Based on Image Processing,TP274
  20. Study of the Recognition of Digital Modulation Signals Based on Modified Self-organizing Feature Map Neural Network,TN911.3

CLC: > Industrial Technology > Automation technology,computer technology > Computing technology,computer technology > Computer applications > Information processing (information processing) > Pattern Recognition and devices > Image recognition device
© 2012 www.DissertationTopic.Net  Mobile