Semi-automatic 2D-to-3D Video Conversion Technique Based on Multi-layer Background Sprite Generation
碩士 === 國立中正大學 === 電機工程研究所 === 104 === This paper presents the 2D to 3D conversion technology based on background multi-sprite model, the video is divided into foreground and background, and separately through different algorithms to generate the depth information and combine to the depth map. First...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Published: |
2016
|
Online Access: | http://ndltd.ncl.edu.tw/handle/81020284906558118142 |
id |
ndltd-TW-104CCU00442076 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-104CCU004420762017-05-07T04:26:36Z http://ndltd.ncl.edu.tw/handle/81020284906558118142 Semi-automatic 2D-to-3D Video Conversion Technique Based on Multi-layer Background Sprite Generation 基於多層次背景 Sprite 模型建立之半自動2D轉3D視訊技術 HU, CHIH-HAO 胡智皓 碩士 國立中正大學 電機工程研究所 104 This paper presents the 2D to 3D conversion technology based on background multi-sprite model, the video is divided into foreground and background, and separately through different algorithms to generate the depth information and combine to the depth map. First, we segmentation key-frame to foreground and background by graph-cut, and using label propagation and GMM to get the non key-frame foreground/background segmentation result.In foreground location, we using block matching to propagation foreground depth map from key-frame.In background, we combine the background at all frames into multi-sprite model, after user draw the depth map of the model, we can get the background depth map at all frames. Finally, we combine foreground and background depth map into the final depth map. LIE, WEN-NUNG 賴文能 2016 學位論文 ; thesis 86 zh-TW |
collection |
NDLTD |
language |
zh-TW |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立中正大學 === 電機工程研究所 === 104 === This paper presents the 2D to 3D conversion technology based on background multi-sprite model, the video is divided into foreground and background, and separately through different algorithms to generate the depth information and combine to the depth map. First, we segmentation key-frame to foreground and background by graph-cut, and using label propagation and GMM to get the non key-frame foreground/background segmentation result.In foreground location, we using block matching to propagation foreground depth map from key-frame.In background, we combine the background at all frames into multi-sprite model, after user draw the depth map of the model, we can get the background depth map at all frames. Finally, we combine foreground and background depth map into the final depth map.
|
author2 |
LIE, WEN-NUNG |
author_facet |
LIE, WEN-NUNG HU, CHIH-HAO 胡智皓 |
author |
HU, CHIH-HAO 胡智皓 |
spellingShingle |
HU, CHIH-HAO 胡智皓 Semi-automatic 2D-to-3D Video Conversion Technique Based on Multi-layer Background Sprite Generation |
author_sort |
HU, CHIH-HAO |
title |
Semi-automatic 2D-to-3D Video Conversion Technique Based on Multi-layer Background Sprite Generation |
title_short |
Semi-automatic 2D-to-3D Video Conversion Technique Based on Multi-layer Background Sprite Generation |
title_full |
Semi-automatic 2D-to-3D Video Conversion Technique Based on Multi-layer Background Sprite Generation |
title_fullStr |
Semi-automatic 2D-to-3D Video Conversion Technique Based on Multi-layer Background Sprite Generation |
title_full_unstemmed |
Semi-automatic 2D-to-3D Video Conversion Technique Based on Multi-layer Background Sprite Generation |
title_sort |
semi-automatic 2d-to-3d video conversion technique based on multi-layer background sprite generation |
publishDate |
2016 |
url |
http://ndltd.ncl.edu.tw/handle/81020284906558118142 |
work_keys_str_mv |
AT huchihhao semiautomatic2dto3dvideoconversiontechniquebasedonmultilayerbackgroundspritegeneration AT húzhìhào semiautomatic2dto3dvideoconversiontechniquebasedonmultilayerbackgroundspritegeneration AT huchihhao jīyúduōcéngcìbèijǐngspritemóxíngjiànlìzhībànzìdòng2dzhuǎn3dshìxùnjìshù AT húzhìhào jīyúduōcéngcìbèijǐngspritemóxíngjiànlìzhībànzìdòng2dzhuǎn3dshìxùnjìshù |
_version_ |
1718447334902202368 |