A Study on Camera Motion Estimation in MPEG Video
碩士 === 國立成功大學 === 工程科學系碩博士班 === 95 === Camera motion estimation is very important from a video processing view. Video application, including object segmentation and tracking, mosaic and content-based video indexing and retrieval, based on the video content should represent motion efficiently. Since,...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Published: |
2007
|
Online Access: | http://ndltd.ncl.edu.tw/handle/97174028743945158542 |
id |
ndltd-TW-095NCKU5028008 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-095NCKU50280082015-12-11T04:04:29Z http://ndltd.ncl.edu.tw/handle/97174028743945158542 A Study on Camera Motion Estimation in MPEG Video MPEG影片中攝影機運動參數估測之研究 Chien-Ming Lai 賴建明 碩士 國立成功大學 工程科學系碩博士班 95 Camera motion estimation is very important from a video processing view. Video application, including object segmentation and tracking, mosaic and content-based video indexing and retrieval, based on the video content should represent motion efficiently. Since, to decode MPEG video and estimate camera motion is extremely time-consuming. To obtain efficient estimates of camera motion by directly processing data easily obtained from MPEG-compressed video becomes more important. In this thesis, two main concerns of camera motion estimation from motion vector are addressed. Firstly, we introduce the connection from a GOP to next GOP by B-frame bidirectional reference. Secondly, we propose a 2-pass camera motion estimation to cope with outliers caused by the uncertainty of motion vectors directly from MPEG video format. Experiment results show that the 2-pass camera motion estimation method is reliable. Finally, we have developed a mosaic system by applying the proposed method. Ming-Shi Wang 王明習 2007 學位論文 ; thesis 51 zh-TW |
collection |
NDLTD |
language |
zh-TW |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立成功大學 === 工程科學系碩博士班 === 95 === Camera motion estimation is very important from a video processing view. Video application, including object segmentation and tracking, mosaic and content-based video indexing and retrieval, based on the video content should represent motion efficiently. Since, to decode MPEG video and estimate camera motion is extremely time-consuming. To obtain efficient estimates of camera motion by directly processing data easily obtained from MPEG-compressed video becomes more important.
In this thesis, two main concerns of camera motion estimation from motion vector are addressed. Firstly, we introduce the connection from a GOP to next GOP by B-frame bidirectional reference. Secondly, we propose a 2-pass camera motion estimation to cope with outliers caused by the uncertainty of motion vectors directly from MPEG video format. Experiment results show that the 2-pass camera motion estimation method is reliable. Finally, we have developed a mosaic system by applying the proposed method.
|
author2 |
Ming-Shi Wang |
author_facet |
Ming-Shi Wang Chien-Ming Lai 賴建明 |
author |
Chien-Ming Lai 賴建明 |
spellingShingle |
Chien-Ming Lai 賴建明 A Study on Camera Motion Estimation in MPEG Video |
author_sort |
Chien-Ming Lai |
title |
A Study on Camera Motion Estimation in MPEG Video |
title_short |
A Study on Camera Motion Estimation in MPEG Video |
title_full |
A Study on Camera Motion Estimation in MPEG Video |
title_fullStr |
A Study on Camera Motion Estimation in MPEG Video |
title_full_unstemmed |
A Study on Camera Motion Estimation in MPEG Video |
title_sort |
study on camera motion estimation in mpeg video |
publishDate |
2007 |
url |
http://ndltd.ncl.edu.tw/handle/97174028743945158542 |
work_keys_str_mv |
AT chienminglai astudyoncameramotionestimationinmpegvideo AT làijiànmíng astudyoncameramotionestimationinmpegvideo AT chienminglai mpegyǐngpiànzhōngshèyǐngjīyùndòngcānshùgūcèzhīyánjiū AT làijiànmíng mpegyǐngpiànzhōngshèyǐngjīyùndòngcānshùgūcèzhīyánjiū AT chienminglai studyoncameramotionestimationinmpegvideo AT làijiànmíng studyoncameramotionestimationinmpegvideo |
_version_ |
1718147812428873728 |