Change search
ReferencesLink to record
Permanent link

Direct link
Adapting the Streaming Video Based on the Estimated Position of the Region of Interest
Blekinge Institute of Technology, School of Computing.
Blekinge Institute of Technology, School of Computing.
Blekinge Institute of Technology, School of Computing.
Blekinge Institute of Technology, School of Computing.
2012 (English)Conference paper (Refereed) Published
Abstract [en]

Streaming real time video over wireless networks cannot guarantee that all the frames could meet their deadlines. Wireless networks may suffer from bandwidth limitations. To reduce the streaming data over wireless networks, we propose a technique to identify, and extract the Region Of Interest (ROI), and drop the non-ROI from the frames that are between the reference frames. The Sum of Absolute Differences (SAD) will compute the consecutive video frames to identify the ROI as it considered the most motion and important region. The reconstruction mechanism to the non-ROI is performed on the mobile side by applying linear interpolation between the reference frames. We evaluate the proposed approach by using Mean Opinion Score (MOS) measurements. MOS are used to evaluate the two scenarios with equivalent encoding size, where the users observe the first scenario with a low bit rate for the original videos, while for the second scenario the users observe our proposed approach. The results show that our technique significantly reduces the amount of data, while the reconstruction mechanism provides acceptable video quality to the mobile viewers.

Place, publisher, year, edition, pages
Naples: IEEE , 2012.
Keyword [en]
streaming video, region of interest, sum of absolute differences, mean opinion scores
National Category
Computer Science
URN: urn:nbn:se:bth-6970DOI: 10.1109/SITIS.2012.11ISI: 000315360300001Local ID: 978-1-4673-5152-2OAI: diva2:834532
Eighth International Conference on Signal Image Technology and Internet Based Systems (SITIS)
Available from: 2013-05-31 Created: 2013-03-08 Last updated: 2015-06-30Bibliographically approved

Open Access in DiVA

fulltext(414 kB)17 downloads
File information
File name FULLTEXT01.pdfFile size 414 kBChecksum SHA-512
Type fulltextMimetype application/pdf

Other links

Publisher's full text

Search in DiVA

By author/editor
Fiedler, MarkusGrahn, HåkanLundberg, Lars
By organisation
School of Computing
Computer Science

Search outside of DiVA

GoogleGoogle Scholar
Total: 17 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Altmetric score

Total: 49 hits
ReferencesLink to record
Permanent link

Direct link