Difference between revisions of "Content-Aware Adaptive Streaming"

From NMSL
 
(47 intermediate revisions by 2 users not shown)
Line 10: Line 10:
 
* Majid Bagheri (PhD Student)
 
* Majid Bagheri (PhD Student)
  
 +
== Discussion and Ideas ==
 +
* Building Hierarchical Summaries: [[media:discussion_18apr08.pdf | discussion_18apr08.pdf]]
 +
* Histogram-based Quality Metric: [[media:discussion_10apr08.pdf | discussion_10apr08.pdf]]
 +
* [[media:discussion_07apr08.pdf | discussion_07apr08.pdf]]
 +
* [[media:discussion_25mar08.pdf | discussion_25mar08.pdf]]
 +
* [[media:discussion_17mar08.pdf | discussion_17mar08.pdf]]
 +
* Explore video quality measures
 +
* Online Summary Generator (submit a video, get the summary)
 +
* Investigate MPEG CLD and MAD features
 +
* Compared to clustering approaches we may produce more key frames for a dialog sequence that alternates between two persons?
 +
* Integration with encoded video (MPEG)
 +
* [[Private:Surveillance| Initial Results on Video Summarization (Login Required)]]
 +
* [[ACMM08| ACMM07]]
  
 +
== References and Links==
  
 +
* Sanghoon Sull, Jung-Rim Kim, Yunam Kim, Hyun Sung Chang, Sang Uk Lee, [http://mpeg.korea.ac.kr/publication/international.php Scalable Hierarchical Video Summary and Search], Proc. SPIE, Vol. 4315, Storage and Retrieval for Media Databases, pp.553-561, Jan 2001. [[media:spie2001.pdf | local copy]]
  
== Discussion and Ideas ==
+
* B. Troung and S. Venkatesh, [http://portal.acm.org/ft_gateway.cfm?id=1198305&type=pdf&coll=GUIDE&dl=GUIDE&CFID=23556435&CFTOKEN=82587997  Video abstraction: A systematic review and classification], ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP), Feb 2007, 3(1)
  
* In video streaming we are more interested to see certain events such as a goal save. Frame significance does not address this.
+
* Y. Gong and X. Liu, [http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=854772 Video summarization using singular value decomposition], in Proc. of IEEE Conference on Computer Vision and Pattern Recognition, Hilton Head Island, SC, June 2000, pp. 174–180.
* For stored videos a profile is produced showing the percentage of frames above certain thresholds. This profile can be used to determine the threshold value for a given limited bandwidth.
 
* Use HS histogram and drop V to reduce the dimension, use min function as similarity measure
 
* Sending high significance frames results in a worse PSNR compared to temporal down sampling
 
* Sending high significance frames ignores large portions of video, and sacrifices the temporal quality (motion)
 
* Explore video quality measures
 
 
 
== References and Links==
 
  
 
* K. Tan, R. Ribier, S. Liou, [http://portal.acm.org/citation.cfm?id=500141.500227 Content-sensitive video streaming over low bitrate and lossy wireless network], ACM Multimedia 2001.
 
* K. Tan, R. Ribier, S. Liou, [http://portal.acm.org/citation.cfm?id=500141.500227 Content-sensitive video streaming over low bitrate and lossy wireless network], ACM Multimedia 2001.
  
 
*  X. Zhou,  S. Liou,  [http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=1013858 Optimal nonlinear sampling for video streaming at low bit rates], IEEE Transactions on Circuits and Systems for Video Technology, Jun 2002, 12(6), pp. 535-544.
 
*  X. Zhou,  S. Liou,  [http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=1013858 Optimal nonlinear sampling for video streaming at low bit rates], IEEE Transactions on Circuits and Systems for Video Technology, Jun 2002, 12(6), pp. 535-544.
 +
 +
* ITU-T Tutorial: [http://www.itu.int/ITU-T/studygroups/com09/docs/tutorial_opavc.pdf  Objective perceptual assessment of video quality: Full reference television], International Telecommunication Union, Geneva, Switzerland, 2004.
 +
 +
* ITU-R Recommendation BT.500-11: [http://www.dii.unisi.it/~menegaz/DoctoralSchool2004/papers/ITU-R_BT.500-11.pdf Methodology for the subjective assessment of the quality of television pictures], International Telecommunication Union, Geneva, Switzerland, 2002.

Latest revision as of 21:28, 22 April 2008

We are designing adaptive streaming algorithms that are based on the visual content of the video streams. The goal is to adaptively transmit the most important frames to clients to yield the best quality. Several ideas are being explored, including: real time and offline processing of video streams, summarization of sports videos, and adaptation of multi-layer scalable video streams.


People

  • Majid Bagheri (PhD Student)

Discussion and Ideas

References and Links