An Automatic Depth Map Estimation System for Single-view Outdoor Images

碩士 === 國立成功大學 === 電腦與通信工程研究所 === 97 === With 3D display technology improvement, people now can perceive the 3D effect by 3D display without wearing 3D glasses. We have a huge amount of 2D video contents; however, due to 3D contents are not sufficient enough, the 2D to 3D conversion technique becomes...

Full description

Bibliographic Details
Main Authors: Chih-Wei Chen, 陳志瑋
Other Authors: Jar-Ferr Yang
Format: Others
Language:en_US
Published: 2009
Online Access:http://ndltd.ncl.edu.tw/handle/81675939549874263964
id ndltd-TW-097NCKU5652100
record_format oai_dc
spelling ndltd-TW-097NCKU56521002016-05-04T04:26:29Z http://ndltd.ncl.edu.tw/handle/81675939549874263964 An Automatic Depth Map Estimation System for Single-view Outdoor Images 用於單戶外影像之自動景深圖估測系統 Chih-Wei Chen 陳志瑋 碩士 國立成功大學 電腦與通信工程研究所 97 With 3D display technology improvement, people now can perceive the 3D effect by 3D display without wearing 3D glasses. We have a huge amount of 2D video contents; however, due to 3D contents are not sufficient enough, the 2D to 3D conversion technique becomes more and more important to promote 3D displays in the near future. In the literatures, several researches proposed depth map estimation methods if multi-view images are available. However, for those thousands 2D videos, the most demanding method is to estimate the depth map from original 2D images. In this thesis, we propose an automatic depth map generation method from general single-view outdoor background images. In the proposed automatic depth map generation system, we first develop some image landscape extractions which can detect some outdoor landscapes, such as sky, ground line, and tree, and then segment the desired objects. After segmentation, we assign the depth value to the extracted objects based on their spatial characteristics. Experimental results show that the proposed method can effectively extracted the desired landscape objects and generates their reasonable depth maps for outdoor images. Jar-Ferr Yang 楊家輝 2009 學位論文 ; thesis 52 en_US
collection NDLTD
language en_US
format Others
sources NDLTD
description 碩士 === 國立成功大學 === 電腦與通信工程研究所 === 97 === With 3D display technology improvement, people now can perceive the 3D effect by 3D display without wearing 3D glasses. We have a huge amount of 2D video contents; however, due to 3D contents are not sufficient enough, the 2D to 3D conversion technique becomes more and more important to promote 3D displays in the near future. In the literatures, several researches proposed depth map estimation methods if multi-view images are available. However, for those thousands 2D videos, the most demanding method is to estimate the depth map from original 2D images. In this thesis, we propose an automatic depth map generation method from general single-view outdoor background images. In the proposed automatic depth map generation system, we first develop some image landscape extractions which can detect some outdoor landscapes, such as sky, ground line, and tree, and then segment the desired objects. After segmentation, we assign the depth value to the extracted objects based on their spatial characteristics. Experimental results show that the proposed method can effectively extracted the desired landscape objects and generates their reasonable depth maps for outdoor images.
author2 Jar-Ferr Yang
author_facet Jar-Ferr Yang
Chih-Wei Chen
陳志瑋
author Chih-Wei Chen
陳志瑋
spellingShingle Chih-Wei Chen
陳志瑋
An Automatic Depth Map Estimation System for Single-view Outdoor Images
author_sort Chih-Wei Chen
title An Automatic Depth Map Estimation System for Single-view Outdoor Images
title_short An Automatic Depth Map Estimation System for Single-view Outdoor Images
title_full An Automatic Depth Map Estimation System for Single-view Outdoor Images
title_fullStr An Automatic Depth Map Estimation System for Single-view Outdoor Images
title_full_unstemmed An Automatic Depth Map Estimation System for Single-view Outdoor Images
title_sort automatic depth map estimation system for single-view outdoor images
publishDate 2009
url http://ndltd.ncl.edu.tw/handle/81675939549874263964
work_keys_str_mv AT chihweichen anautomaticdepthmapestimationsystemforsingleviewoutdoorimages
AT chénzhìwěi anautomaticdepthmapestimationsystemforsingleviewoutdoorimages
AT chihweichen yòngyúdānhùwàiyǐngxiàngzhīzìdòngjǐngshēntúgūcèxìtǒng
AT chénzhìwěi yòngyúdānhùwàiyǐngxiàngzhīzìdòngjǐngshēntúgūcèxìtǒng
AT chihweichen automaticdepthmapestimationsystemforsingleviewoutdoorimages
AT chénzhìwěi automaticdepthmapestimationsystemforsingleviewoutdoorimages
_version_ 1718259019785699328