Announcement for Downloading full text filePlease respect the Copyright Act.
All digital full text dissertation and theses from this website are authorized the copyright owners. These copyrighted full-text dissertation and theses can be only used for academic, research and non-commercial purposes. Users of this website can search, read, and print for personal usage. In respect of the Copyright Act of the Republic of China, please do not reproduce, distribute, change, or edit the content of these dissertations and theses without any permission. Please do not create any work based upon a pre-existing work by reproduction, Adaptation, Distribution or other means.
URN etd-0812114-191515 Statistics This thesis had been viewed 2122 times. Download 1852 times. Author Chih-Yuan Hsu Author's Email Address No Public. Department Computer Science and Enginerring Year 2013 Semester 2 Degree Master Type of Document Master's Thesis Language zh-TW.Big5 Chinese Page Count 72 Title Human Motion Capture and Mistake Correction Using Kinect Camera Keyword inverse kinematics motion capture Kinect OpenNI self-occlusion self-occlusion OpenNI Kinect motion capture inverse kinematics Abstract Human motion capture has been an important research topic in computer vision and computer graphics. It is used in military, entertainment, sports, and medical applications. The traditional motion capture equipment are not affordable for ordinary people. With the advent of Kinect, low-cost human motion analysis and capture becomes possible.
In this paper, using Kinect and OpenNI making human motion capture system. This solves the problem of motion capture equipment costs. Use four algorithms to carry on judging and correction error motion (such as self-occlusion and image noise...etc. produced of the error capture). But these four algorithms can not act on real-time environment. Therefore the development predicts algorithms way to carry out real-time correction effect.
In four methods, damped least squares inverse kinematics algorithm differs from previous correction methods. Compared with the other methods, damped least squares algorithm corrects the result could be better.
Advisor Committee Jyun-Ming Chen - advisor
Chun-Fong You - co-chair
Shang-Lin Hsieh - co-chair
Files Date of Defense 2014-07-28 Date of Submission 2014-08-12