Difference between revisions of "Content-Aware Adaptive Streaming"
From NMSL
| Line 15: | Line 15: | ||
== Discussion and Ideas == | == Discussion and Ideas == | ||
| − | * In video streaming we are more interested to see certain events such as a goal save. | + | * In video streaming we are more interested to see certain events such as a goal save. Frame significance does not address this. |
* 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. | * 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 | * Use HS histogram and drop V to reduce the dimension, use min function as similarity measure | ||
Revision as of 14:46, 4 March 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
- Mohamed Hefeeda (Assistant Professor)
- Wael Abd-Almageed (Assistant Research Scientist at UMD)
- Majid Bagheri (PhD Student)
Discussion and Ideas
- In video streaming we are more interested to see certain events such as a goal save. Frame significance does not address this.
- 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, Content-sensitive video streaming over low bitrate and lossy wireless network, ACM Multimedia 2001.
- X. Zhou, S. Liou, 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.
