A fast tracking algorithm of human head
碩士 === 輔仁大學 === 資訊工程學系 === 94 === ABSTRACT This paper purposed a fast head tracking approach using ellipse matching method. Our system contains three sub-systems. 1. Image preprocessing 2. Object extracting 3. Ellipse matching. The purpose of image preprocessing sub-system is to remove noises. The...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Published: |
2006
|
Online Access: | http://ndltd.ncl.edu.tw/handle/22278446028568187572 |
id |
ndltd-TW-094FJU00392050 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-094FJU003920502015-10-13T10:34:48Z http://ndltd.ncl.edu.tw/handle/22278446028568187572 A fast tracking algorithm of human head 快速人頭追蹤演算法 Chia-Hua Hsieh 謝家華 碩士 輔仁大學 資訊工程學系 94 ABSTRACT This paper purposed a fast head tracking approach using ellipse matching method. Our system contains three sub-systems. 1. Image preprocessing 2. Object extracting 3. Ellipse matching. The purpose of image preprocessing sub-system is to remove noises. The Object extracting sub-system extracts the possible object using frame difference techniques and locates the preliminary positioning of the object to reduce the search space of ellipse matching. In the ellipse matching we used sobel operators for edge detection of source image, after the edge detection procedure we locate the head outline using an ellipse matching to confirm if the object of interest is indeed the human head. We purpose a moving object marker algorithm for ellipse matching to reduce the time required of head tracking. Brian K. Lien 連國珍 2006 學位論文 ; thesis 42 zh-TW |
collection |
NDLTD |
language |
zh-TW |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 輔仁大學 === 資訊工程學系 === 94 === ABSTRACT
This paper purposed a fast head tracking approach using ellipse matching method. Our system contains three sub-systems. 1. Image preprocessing 2. Object extracting 3. Ellipse matching. The purpose of image preprocessing sub-system is to remove noises. The Object extracting sub-system extracts the possible object using frame difference techniques and locates the preliminary positioning of the object to reduce the search space of ellipse matching. In the ellipse matching we used sobel operators for edge detection of source image, after the edge detection procedure we locate the head outline using an ellipse matching to confirm if the object of interest is indeed the human head. We purpose a moving object marker algorithm for ellipse matching to reduce the time required of head tracking.
|
author2 |
Brian K. Lien |
author_facet |
Brian K. Lien Chia-Hua Hsieh 謝家華 |
author |
Chia-Hua Hsieh 謝家華 |
spellingShingle |
Chia-Hua Hsieh 謝家華 A fast tracking algorithm of human head |
author_sort |
Chia-Hua Hsieh |
title |
A fast tracking algorithm of human head |
title_short |
A fast tracking algorithm of human head |
title_full |
A fast tracking algorithm of human head |
title_fullStr |
A fast tracking algorithm of human head |
title_full_unstemmed |
A fast tracking algorithm of human head |
title_sort |
fast tracking algorithm of human head |
publishDate |
2006 |
url |
http://ndltd.ncl.edu.tw/handle/22278446028568187572 |
work_keys_str_mv |
AT chiahuahsieh afasttrackingalgorithmofhumanhead AT xièjiāhuá afasttrackingalgorithmofhumanhead AT chiahuahsieh kuàisùréntóuzhuīzōngyǎnsuànfǎ AT xièjiāhuá kuàisùréntóuzhuīzōngyǎnsuànfǎ AT chiahuahsieh fasttrackingalgorithmofhumanhead AT xièjiāhuá fasttrackingalgorithmofhumanhead |
_version_ |
1716830719237423104 |