Visual Attention-based Small Screen Adaptation for H.264 Videos

Visual Attention-based Small Screen Adaptation for H.264 Videos

Show other versions (1)

We develop a framework that uses visual attention analysis combined with temporal coherence to detect the attended region from a H.264 video bitstream, and display it on a small screen. A visual attention module based upon Walther and Koch's model gives us the attended region in I-frames. We pr...

Full description

Bibliographic Details
Main Author: Mukherjee, Abir
Language:en
Published: 2008
Subjects:
visual attention
video adaptation
H.264
Electrical and Computer Engineering
Online Access:http://hdl.handle.net/10012/3929
id ndltd-LACETR-oai-collectionscanada.gc.ca-OWTU.10012-3929
record_format oai_dc
spelling ndltd-LACETR-oai-collectionscanada.gc.ca-OWTU.10012-39292013-10-04T04:08:40ZMukherjee, Abir2008-08-29T13:34:44Z2008-08-29T13:34:44Z2008-08-29T13:34:44Z2008http://hdl.handle.net/10012/3929We develop a framework that uses visual attention analysis combined with temporal coherence to detect the attended region from a H.264 video bitstream, and display it on a small screen. A visual attention module based upon Walther and Koch's model gives us the attended region in I-frames. We propose a temporal coherence matching framework that uses the motion information in P-frames to extend the attended region over the H.264 video sequence. Evaluations show encouraging results with over 80% successful detection rate for objects of interest, and 85% respondents claiming satisfactory output.envisual attentionvideo adaptationH.264Visual Attention-based Small Screen Adaptation for H.264 VideosThesis or DissertationElectrical and Computer EngineeringMaster of Applied ScienceElectrical and Computer Engineering
collection NDLTD
language en
sources NDLTD
topic visual attention
video adaptation
H.264
Electrical and Computer Engineering
spellingShingle visual attention
video adaptation
H.264
Electrical and Computer Engineering
Mukherjee, Abir
Visual Attention-based Small Screen Adaptation for H.264 Videos
description We develop a framework that uses visual attention analysis combined with temporal coherence to detect the attended region from a H.264 video bitstream, and display it on a small screen. A visual attention module based upon Walther and Koch's model gives us the attended region in I-frames. We propose a temporal coherence matching framework that uses the motion information in P-frames to extend the attended region over the H.264 video sequence. Evaluations show encouraging results with over 80% successful detection rate for objects of interest, and 85% respondents claiming satisfactory output.
author Mukherjee, Abir
author_facet Mukherjee, Abir
author_sort Mukherjee, Abir
title Visual Attention-based Small Screen Adaptation for H.264 Videos
title_short Visual Attention-based Small Screen Adaptation for H.264 Videos
title_full Visual Attention-based Small Screen Adaptation for H.264 Videos
title_fullStr Visual Attention-based Small Screen Adaptation for H.264 Videos
title_full_unstemmed Visual Attention-based Small Screen Adaptation for H.264 Videos
title_sort visual attention-based small screen adaptation for h.264 videos
publishDate 2008
url http://hdl.handle.net/10012/3929
work_keys_str_mv AT mukherjeeabir visualattentionbasedsmallscreenadaptationforh264videos
_version_ 1716600046217068544

Similar Items