Human Behavior Recognition Algorithms Based on Neural Network
碩士 === 國立高雄應用科技大學 === 電子工程系 === 100 === This thesis suggested that there are three main parts in the algorithm structure inclnding Feature Extraction , Behavior Recognition, and Moving Object Detection, we used the KTH human behavior database for experiment. The database included six motions—boxing,...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Published: |
101
|
Online Access: | http://ndltd.ncl.edu.tw/handle/26376583697781126759 |
id |
ndltd-TW-100KUAS8393094 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-100KUAS83930942016-08-26T04:12:12Z http://ndltd.ncl.edu.tw/handle/26376583697781126759 Human Behavior Recognition Algorithms Based on Neural Network 植基於類神經網路之人體行為辨識演算法 Yan-Jun Chen 陳彥君 碩士 國立高雄應用科技大學 電子工程系 100 This thesis suggested that there are three main parts in the algorithm structure inclnding Feature Extraction , Behavior Recognition, and Moving Object Detection, we used the KTH human behavior database for experiment. The database included six motions—boxing, hand–clapping, hand-waving, running, jogging, walking—and 25 people in four scenarios and Weizmann database. Firstly, used the method of Moving Object Detection is need to detect continuous images, and then the detected images exclusive or compressed into binary sequence compressed images to show the traced traits in their outlines. Finally, the Artificial Neural Network, using the the Back-Propagation Network along with the training of Scaled Conjugate Gradient Algorithm to speed up the convergence rate. Conparecl with the tracutional methods, the recognition rate is improved. Jeng-Shyang Pan Bin-Yih Liao 潘正祥 廖斌毅 101 學位論文 ; thesis 99 zh-TW |
collection |
NDLTD |
language |
zh-TW |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立高雄應用科技大學 === 電子工程系 === 100 === This thesis suggested that there are three main parts in the algorithm structure inclnding Feature Extraction , Behavior Recognition, and Moving Object Detection, we used the KTH human behavior database for experiment. The database included six motions—boxing, hand–clapping, hand-waving, running, jogging, walking—and 25 people in four scenarios and Weizmann database. Firstly, used the method of Moving Object Detection is need to detect continuous images, and then the detected images exclusive or compressed into binary sequence compressed images to show the traced traits in their outlines. Finally, the Artificial Neural Network, using the the Back-Propagation Network along with the training of Scaled Conjugate Gradient Algorithm to speed up the convergence rate. Conparecl with the tracutional methods, the recognition rate is improved.
|
author2 |
Jeng-Shyang Pan |
author_facet |
Jeng-Shyang Pan Yan-Jun Chen 陳彥君 |
author |
Yan-Jun Chen 陳彥君 |
spellingShingle |
Yan-Jun Chen 陳彥君 Human Behavior Recognition Algorithms Based on Neural Network |
author_sort |
Yan-Jun Chen |
title |
Human Behavior Recognition Algorithms Based on Neural Network |
title_short |
Human Behavior Recognition Algorithms Based on Neural Network |
title_full |
Human Behavior Recognition Algorithms Based on Neural Network |
title_fullStr |
Human Behavior Recognition Algorithms Based on Neural Network |
title_full_unstemmed |
Human Behavior Recognition Algorithms Based on Neural Network |
title_sort |
human behavior recognition algorithms based on neural network |
publishDate |
101 |
url |
http://ndltd.ncl.edu.tw/handle/26376583697781126759 |
work_keys_str_mv |
AT yanjunchen humanbehaviorrecognitionalgorithmsbasedonneuralnetwork AT chényànjūn humanbehaviorrecognitionalgorithmsbasedonneuralnetwork AT yanjunchen zhíjīyúlèishénjīngwǎnglùzhīréntǐxíngwèibiànshíyǎnsuànfǎ AT chényànjūn zhíjīyúlèishénjīngwǎnglùzhīréntǐxíngwèibiànshíyǎnsuànfǎ |
_version_ |
1718379851138727936 |