Abstract

Minimizing the number of bandwidth changes of individual stream and enabling the transmission schedule flexible can benefit increasing the number of concurrent multiplexed streams in periodic network without degrading quality of video. However, minimum change bandwidth allocation (MCBA) only provides a fixed transmission schedule for given video and client buffer although it achieves the minimum number of rate changes and the minimum peak rate. So the MCBA schedule cannot be adjusted when multiple streams are multiplexed over a limited bandwidth shared link. In this paper, we propose a relaxing transmission schedule that provides a range of rates for each interval and preserves the minimum number of rate changes without increasing any rate. As a result, the individual schedule can be adjusted by network service to try to satisfy bandwidth constraint when the total required bandwidth of multiplexed streams exceeds the available network capacity. First, we underline that the key of MCBA is to segment video with making each linear trajectory as long as possible. Then we use linear separability and support vector machine under the classification model to compute the longest interval and the required rate, respectively. Due to our proposed decoupled form between segmentation and rate computation, finally, we construct the relaxing schedule bounded by the original MCBA rate and the minimum rate. The simulation using real MPEG4 and H.264 video traces confirms the philosophy and evaluates the relaxing performance of our proposed algorithm.

Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.