Leading-Supporting Dual-Camera HDR Synthesis with ROI-Based Alignment

碩士 === 國立中正大學 === 電機工程研究所 === 101 === Most of the existing methods are focused on global HDR image generation for static scenes. However, these methods are not effective for the dynamic scenes. In this paper we present a method that generates High Dynamic Range (HDR) images from two differently expo...

Full description

Bibliographic Details
Main Authors: Shawn Chiang, 江宗翰
Other Authors: Ching-Wei Yeh
Format: Others
Language:en_US
Published: 2013
Online Access:http://ndltd.ncl.edu.tw/handle/75188181667817790076
id ndltd-TW-101CCU00442076
record_format oai_dc
spelling ndltd-TW-101CCU004420762015-10-13T22:23:52Z http://ndltd.ncl.edu.tw/handle/75188181667817790076 Leading-Supporting Dual-Camera HDR Synthesis with ROI-Based Alignment 基於ROI校準之主輔雙鏡頭高動態範圍合成 Shawn Chiang 江宗翰 碩士 國立中正大學 電機工程研究所 101 Most of the existing methods are focused on global HDR image generation for static scenes. However, these methods are not effective for the dynamic scenes. In this paper we present a method that generates High Dynamic Range (HDR) images from two differently exposed Low Dynamic Range (LDR) images taken from different overexposed ROI. It allows generating HDR images for scenes with fast motion or from moving vehicle. Image alignment is based on optimized SIFT methodology. Chromatic aberration compensation for overexposed ROI of the scene is solved by using CAC mask and luminance smoothing weight. Less feature elements information generation technique is applied to aligned images in order to produce HDR image. Ching-Wei Yeh 葉經緯 2013 學位論文 ; thesis 38 en_US
collection NDLTD
language en_US
format Others
sources NDLTD
description 碩士 === 國立中正大學 === 電機工程研究所 === 101 === Most of the existing methods are focused on global HDR image generation for static scenes. However, these methods are not effective for the dynamic scenes. In this paper we present a method that generates High Dynamic Range (HDR) images from two differently exposed Low Dynamic Range (LDR) images taken from different overexposed ROI. It allows generating HDR images for scenes with fast motion or from moving vehicle. Image alignment is based on optimized SIFT methodology. Chromatic aberration compensation for overexposed ROI of the scene is solved by using CAC mask and luminance smoothing weight. Less feature elements information generation technique is applied to aligned images in order to produce HDR image.
author2 Ching-Wei Yeh
author_facet Ching-Wei Yeh
Shawn Chiang
江宗翰
author Shawn Chiang
江宗翰
spellingShingle Shawn Chiang
江宗翰
Leading-Supporting Dual-Camera HDR Synthesis with ROI-Based Alignment
author_sort Shawn Chiang
title Leading-Supporting Dual-Camera HDR Synthesis with ROI-Based Alignment
title_short Leading-Supporting Dual-Camera HDR Synthesis with ROI-Based Alignment
title_full Leading-Supporting Dual-Camera HDR Synthesis with ROI-Based Alignment
title_fullStr Leading-Supporting Dual-Camera HDR Synthesis with ROI-Based Alignment
title_full_unstemmed Leading-Supporting Dual-Camera HDR Synthesis with ROI-Based Alignment
title_sort leading-supporting dual-camera hdr synthesis with roi-based alignment
publishDate 2013
url http://ndltd.ncl.edu.tw/handle/75188181667817790076
work_keys_str_mv AT shawnchiang leadingsupportingdualcamerahdrsynthesiswithroibasedalignment
AT jiāngzōnghàn leadingsupportingdualcamerahdrsynthesiswithroibasedalignment
AT shawnchiang jīyúroixiàozhǔnzhīzhǔfǔshuāngjìngtóugāodòngtàifànwéihéchéng
AT jiāngzōnghàn jīyúroixiàozhǔnzhīzhǔfǔshuāngjìngtóugāodòngtàifànwéihéchéng
_version_ 1718075510686220288