Visual Attention-based Small Screen Adaptation for H.264 Videos
| dc.contributor.author | Mukherjee, Abir | |
| dc.date.accessioned | 2008-08-29T13:34:44Z | |
| dc.date.available | 2008-08-29T13:34:44Z | |
| dc.date.issued | 2008-08-29T13:34:44Z | |
| dc.date.submitted | 2008 | |
| dc.description.abstract | 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. | en |
| dc.identifier.uri | http://hdl.handle.net/10012/3929 | |
| dc.language.iso | en | en |
| dc.pending | false | en |
| dc.publisher | University of Waterloo | en |
| dc.subject | visual attention | en |
| dc.subject | video adaptation | en |
| dc.subject | H.264 | en |
| dc.subject.program | Electrical and Computer Engineering | en |
| dc.title | Visual Attention-based Small Screen Adaptation for H.264 Videos | en |
| dc.type | Master Thesis | en |
| uws-etd.degree | Master of Applied Science | en |
| uws-etd.degree.department | Electrical and Computer Engineering | en |
| uws.peerReviewStatus | Unreviewed | en |
| uws.scholarLevel | Graduate | en |
| uws.typeOfResource | Text | en |