Visual Attention Based Multiple Objects Discovery
碩士 === 國立清華大學 === 電機工程學系 === 97 === In this thesis, we present a visual attention based probabilistic framework for the video objects discovery scheme. The framework consists of three models: the appearance model use probabilistic representation to describe the consistency of object across frame; th...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | en_US |
Published: |
2009
|
Online Access: | http://ndltd.ncl.edu.tw/handle/57086558138536061762 |
id |
ndltd-TW-097NTHU5442112 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-097NTHU54421122015-11-13T04:08:49Z http://ndltd.ncl.edu.tw/handle/57086558138536061762 Visual Attention Based Multiple Objects Discovery 基於視覺焦點模型之視訊物件發掘 Liu, Yu-Cheng 劉育誠 碩士 國立清華大學 電機工程學系 97 In this thesis, we present a visual attention based probabilistic framework for the video objects discovery scheme. The framework consists of three models: the appearance model use probabilistic representation to describe the consistency of object across frame; the spatial model represents the objects’ geometric structure; the motion model establishes the temporal association of objects. In order to complete the video multiple objects discovery, we use Perceptual Quality Significance Map (PQSM) for the visual attention model. The visual attention regions from PQSM can be regarded as objects. We also use those regions to describe the appearance, size, and initial location of objects. Finally, the probabilistic parameters are obtained by Expectation-Maximization (EM) algorithm. Since the scene of video may switch between different shots, we use these probabilistic parameters to indicate which frame has the discovered objects and measure the similarity of objects in different shots. The mainly different from object tracking is object discovery can discover the object across different shots. We show the results that can be performed very well for video multiple objects discovery. And the attention regions from PQSMs are used to generate the object information for the motion model. Since the motion model is used to establish the data association, the temporal association of attention regions from PQSMs can be established by this proposed model. Lin, Chia-Wen 林嘉文 2009 學位論文 ; thesis 63 en_US |
collection |
NDLTD |
language |
en_US |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立清華大學 === 電機工程學系 === 97 === In this thesis, we present a visual attention based probabilistic framework for the video objects discovery scheme. The framework consists of three models: the appearance model use probabilistic representation to describe the consistency of object across frame; the spatial model represents the objects’ geometric structure; the motion model establishes the temporal association of objects. In order to complete the video multiple objects discovery, we use Perceptual Quality Significance Map (PQSM) for the visual attention model. The visual attention regions from PQSM can be regarded as objects. We also use those regions to describe the appearance, size, and initial location of objects. Finally, the probabilistic parameters are obtained by Expectation-Maximization (EM) algorithm. Since the scene of video may switch between different shots, we use these probabilistic parameters to indicate which frame has the discovered objects and measure the similarity of objects in different shots. The mainly different from object tracking is object discovery can discover the object across different shots. We show the results that can be performed very well for video multiple objects discovery. And the attention regions from PQSMs are used to generate the object information for the motion model. Since the motion model is used to establish the data association, the temporal association of attention regions from PQSMs can be established by this proposed model.
|
author2 |
Lin, Chia-Wen |
author_facet |
Lin, Chia-Wen Liu, Yu-Cheng 劉育誠 |
author |
Liu, Yu-Cheng 劉育誠 |
spellingShingle |
Liu, Yu-Cheng 劉育誠 Visual Attention Based Multiple Objects Discovery |
author_sort |
Liu, Yu-Cheng |
title |
Visual Attention Based Multiple Objects Discovery |
title_short |
Visual Attention Based Multiple Objects Discovery |
title_full |
Visual Attention Based Multiple Objects Discovery |
title_fullStr |
Visual Attention Based Multiple Objects Discovery |
title_full_unstemmed |
Visual Attention Based Multiple Objects Discovery |
title_sort |
visual attention based multiple objects discovery |
publishDate |
2009 |
url |
http://ndltd.ncl.edu.tw/handle/57086558138536061762 |
work_keys_str_mv |
AT liuyucheng visualattentionbasedmultipleobjectsdiscovery AT liúyùchéng visualattentionbasedmultipleobjectsdiscovery AT liuyucheng jīyúshìjuéjiāodiǎnmóxíngzhīshìxùnwùjiànfājué AT liúyùchéng jīyúshìjuéjiāodiǎnmóxíngzhīshìxùnwùjiànfājué |
_version_ |
1718128441009635328 |