Author: Zeng, Cong
Title: Personalized 3D human body modelling and real-time motion tracking based on kinect v2
Advisors: Shi, Wenzhong (LSGI)
Degree: M.Sc.
Year: 2017
Subject: Human locomotion -- Computer simulation
Human locomotion -- Analysis -- Data processing
Hong Kong Polytechnic University -- Dissertations
Department: Faculty of Construction and Environment
Department of Land Surveying and Geo-Informatics
Pages: x, 129 pages : color illustrations
Language: English
Abstract: With the coming of network information technology times, 3D virtual human modelling techniques have been utilized extensively in the fields of computer vision, film and television production, game designing, etc. So how to obtain a more realistic 3D virtual human model, and track the person's motion in real time effectively, are the research targets and hot topic in the area of computer graphics and computer vision currently. And the virtual human model is a technology branch of virtual reality. It can emulate the human body to do a variety of perilous experiment. And the real-time motion tracking technology can be used in virtual fitting, virtual meeting and some other areas. Therefore, the research of studying 3D human body modelling and real-time motion tracking has sufficient theoretical significance and practical value. This dissertation proposed a method of 3D human body modelling and then realize real-time motion tracking based on Unity3D. This method use Kinect v2 sensor to capture the raw data and then the mesh model is created by three steps: point cloud generation, Point cloud registration and model surface reconstruction. After the human body model reconstructed, some problems in the mesh model need to be solved. The holes in the model is filled based on minimum angle algorithm. Finally, the optimized 3D human body model is finished. Then, this dissertation proposed a method of real-time motion tracking. It firstly designs a virtual skeleton for the mesh model and then set the weight of each joints in the skeleton. Secondly, it combines the skeleton inside the model to the skeleton detected by the Kinect v2 sensor to realize real-time motion tracking. Finally, the 3D human body model can track the motion of the person in real time based on Unity3D. Lastly, this dissertation develops a simple application about virtual fitting. A blue T-shirt is designed and then combined with the skeleton inside the human body model. Then, the human model with blue T-shirt is put into the project. The people can see the dress look in any perspective they want. The experimental result show that, through the reconstruction of the model and the optimization process, we can acquire a more realistic virtual human body model. At the same time, the real-time motion tracking also performs good.
Rights: All rights reserved
Access: restricted access

Files in This Item:
File Description SizeFormat 
991022385850903411.pdfFor All Users (off-campus access for PolyU Staff & Students only)2.99 MBAdobe PDFView/Open

Copyright Undertaking

As a bona fide Library user, I declare that:

  1. I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
  2. I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
  3. I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.

By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.

Show full item record

Please use this identifier to cite or link to this item: