A Spatio-temporal CRF Model for Multi-Focus Image Fusion
碩士 === 國立臺灣科技大學 === 資訊工程系 === 103 === The purpose of multi-focus image fusion is to integrate multiple images of different focusing goal at the same scene into a composite focusing sharp image that is more informative. Many existing methods provide good solutions for strict static scenes that do not...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | en_US |
Published: |
2015
|
Online Access: | http://ndltd.ncl.edu.tw/handle/54662200708570469232 |
id |
ndltd-TW-103NTUS5392070 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-103NTUS53920702016-11-06T04:19:40Z http://ndltd.ncl.edu.tw/handle/54662200708570469232 A Spatio-temporal CRF Model for Multi-Focus Image Fusion 基於時間空間條件隨機場的多張聚焦影像融合方法 Te-Hsiu Liao 廖得琇 碩士 國立臺灣科技大學 資訊工程系 103 The purpose of multi-focus image fusion is to integrate multiple images of different focusing goal at the same scene into a composite focusing sharp image that is more informative. Many existing methods provide good solutions for strict static scenes that do not contain any moving objects. However, in practice, these assumptions are not always realistic, and the existing methods result in ghosting artifact by the presence of moving objects. To tackle this issue, in this paper, a novel multi-focus image fusion algorithm for dynamic scenes is proposed. The proposed algorithm first detects the potential moving objects based on motion information, and then formulates the multi-focus image fusion problem into a spatial-temporal conditional random field model that considers motion, focus, and coherence factors. Finally, maximum a posteriori (MAP) and fuzzy set theory are employed to compute the weight of each pixel of each input image for the fusing the input images into an all-in-focus image. Experimental results show that the proposed method outperforms the state-of-the-art methods for both static and dynamic scenes. Kai-Lung Hua 花凱龍 2015 學位論文 ; thesis 49 en_US |
collection |
NDLTD |
language |
en_US |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立臺灣科技大學 === 資訊工程系 === 103 === The purpose of multi-focus image fusion is to integrate multiple images of different focusing goal at the same scene into a composite focusing sharp image that is more informative. Many existing methods provide good solutions for strict static scenes that do not contain any moving objects. However, in practice, these assumptions are not always realistic, and the existing methods result in ghosting artifact by the presence of moving objects. To tackle this issue, in this paper, a novel multi-focus image fusion algorithm for dynamic scenes is proposed. The proposed algorithm first detects the potential moving objects based on motion information, and then formulates the multi-focus image fusion problem into a spatial-temporal conditional random field model that considers motion, focus, and coherence factors. Finally, maximum a posteriori (MAP) and fuzzy set theory are employed to compute the weight of each pixel of each input image for the fusing the input images into an all-in-focus image. Experimental results show that the proposed method outperforms the state-of-the-art methods for both static and dynamic scenes.
|
author2 |
Kai-Lung Hua |
author_facet |
Kai-Lung Hua Te-Hsiu Liao 廖得琇 |
author |
Te-Hsiu Liao 廖得琇 |
spellingShingle |
Te-Hsiu Liao 廖得琇 A Spatio-temporal CRF Model for Multi-Focus Image Fusion |
author_sort |
Te-Hsiu Liao |
title |
A Spatio-temporal CRF Model for Multi-Focus Image Fusion |
title_short |
A Spatio-temporal CRF Model for Multi-Focus Image Fusion |
title_full |
A Spatio-temporal CRF Model for Multi-Focus Image Fusion |
title_fullStr |
A Spatio-temporal CRF Model for Multi-Focus Image Fusion |
title_full_unstemmed |
A Spatio-temporal CRF Model for Multi-Focus Image Fusion |
title_sort |
spatio-temporal crf model for multi-focus image fusion |
publishDate |
2015 |
url |
http://ndltd.ncl.edu.tw/handle/54662200708570469232 |
work_keys_str_mv |
AT tehsiuliao aspatiotemporalcrfmodelformultifocusimagefusion AT liàodéxiù aspatiotemporalcrfmodelformultifocusimagefusion AT tehsiuliao jīyúshíjiānkōngjiāntiáojiànsuíjīchǎngdeduōzhāngjùjiāoyǐngxiàngrónghéfāngfǎ AT liàodéxiù jīyúshíjiānkōngjiāntiáojiànsuíjīchǎngdeduōzhāngjùjiāoyǐngxiàngrónghéfāngfǎ AT tehsiuliao spatiotemporalcrfmodelformultifocusimagefusion AT liàodéxiù spatiotemporalcrfmodelformultifocusimagefusion |
_version_ |
1718391527133151232 |