Human motion capture data compression
Motion capture is becoming more and more important in current society and has been used in many sectors of industry, agriculture, transport, education, health and sports, especially in the medicine industry, sports science, sports coaching, modern animation and video game production and oth...
Saved in:
Main Author: | |
---|---|
Other Authors: | |
Format: | Theses and Dissertations |
Language: | English |
Published: |
2015
|
Subjects: | |
Online Access: | http://hdl.handle.net/10356/64827 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-64827 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-648272023-07-04T15:47:06Z Human motion capture data compression Wang, Dian Chau Lap Pui School of Electrical and Electronic Engineering DRNTU::Engineering::Electrical and electronic engineering::Electronic systems::Signal processing Motion capture is becoming more and more important in current society and has been used in many sectors of industry, agriculture, transport, education, health and sports, especially in the medicine industry, sports science, sports coaching, modern animation and video game production and other fields. Three main categories of motion capture systems in modern society are optical systems, magnetic systems and mechanical systems. This project uses two kinds of motion capture data as experiment materials, namely, data from Kinect and data from CMU database. The dissertation contains the study of kinematics related to the data format of motion capture, the filtering technology to pre-process and post-process the motion capture data, and the various compression technology to do the motion data processing experiments. According to the compression result, SNR and MAE performance has been discussed to estimate the methods. The result is analyzed horizontally and vertically while seen horizontally, the performance comparison are conducted between data from Kinect and data from database and seen vertically, the performance comparison are conducted between different types of motions, such as walk, jump, dance and run. In the same time, some important parameters are estimated according to the effect on the exercise performance. Master of Science (Signal Processing) 2015-06-04T08:31:00Z 2015-06-04T08:31:00Z 2014 2014 Thesis http://hdl.handle.net/10356/64827 en 79 p. application/pdf |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
DRNTU::Engineering::Electrical and electronic engineering::Electronic systems::Signal processing |
spellingShingle |
DRNTU::Engineering::Electrical and electronic engineering::Electronic systems::Signal processing Wang, Dian Human motion capture data compression |
description |
Motion capture is becoming more and more important in current society and has
been used in many sectors of industry, agriculture, transport, education, health and
sports, especially in the medicine industry, sports science, sports coaching, modern
animation and video game production and other fields.
Three main categories of motion capture systems in modern society are optical
systems, magnetic systems and mechanical systems. This project uses two kinds of
motion capture data as experiment materials, namely, data from Kinect and data from
CMU database.
The dissertation contains the study of kinematics related to the data format of motion
capture, the filtering technology to pre-process and post-process the motion capture
data, and the various compression technology to do the motion data processing
experiments.
According to the compression result, SNR and MAE performance has been discussed
to estimate the methods. The result is analyzed horizontally and vertically while seen
horizontally, the performance comparison are conducted between data from Kinect
and data from database and seen vertically, the performance comparison are
conducted between different types of motions, such as walk, jump, dance and run. In
the same time, some important parameters are estimated according to the effect on
the exercise performance. |
author2 |
Chau Lap Pui |
author_facet |
Chau Lap Pui Wang, Dian |
format |
Theses and Dissertations |
author |
Wang, Dian |
author_sort |
Wang, Dian |
title |
Human motion capture data compression |
title_short |
Human motion capture data compression |
title_full |
Human motion capture data compression |
title_fullStr |
Human motion capture data compression |
title_full_unstemmed |
Human motion capture data compression |
title_sort |
human motion capture data compression |
publishDate |
2015 |
url |
http://hdl.handle.net/10356/64827 |
_version_ |
1772828717974814720 |