TITRE Adaptive Packet Video Streaming Over IP Networks - LaBRI
TITRE Adaptive Packet Video Streaming Over IP Networks - LaBRI
TITRE Adaptive Packet Video Streaming Over IP Networks - LaBRI
You also want an ePaper? Increase the reach of your titles
YUMPU automatically turns print PDFs into web optimized ePapers that Google loves.
• We design an algorithm for fine grained TCP-Friendly video rate adaptation (see<br />
Section 4.3).<br />
Thus, this chapter presents our design philosophy in the transport of MPEG-4 video stream<br />
over <strong>IP</strong> network. We enhance the transport layer by building several mechanisms and algorithms<br />
that work together in order to achieve a seamless quality of service build around a cross-layer video<br />
streaming system. Each mechanism is presented and evaluated both using network simulation and /<br />
or experimental network. We finish this chapter by a conclusion which is presented in Section 4.4.<br />
In order to understand our models and mechanisms, readers are invited to examine the<br />
Appendix A which gives a consistent overview of the MPEG-4 standard.<br />
4.1 A Content-Based <strong>Video</strong> Classification Model<br />
To implements an efficient transmission of object-based MPEG-4 video over <strong>IP</strong> networks<br />
with QoS management capabilities, the MPEG-4 Audio Visual Objects (AVOs) are classified based<br />
on application-level QoS criteria and AVOs semantic descriptors according to AVOs descriptors<br />
and MPEG-7 framework [152]. Thus, the classification model lead to a relative priority score (RPS)<br />
for each AVO. The MPEG-4 AVOs requiring the same QoS performance (with the same RPS)<br />
from the network are automatically classified and multiplexed within one of the <strong>IP</strong> Diffserv Per<br />
Hop Behaviors (PHB). Object data-packets within the same class are then transmitted over the<br />
selected transport layer with the corresponding bearer capability and priority level. Thus, we<br />
propose to extend the MPEG-4 system architecture with a new “Media QoS Classification Layer”.<br />
This layer implements the content-based video classification model. In our implementation, the<br />
“Media QoS Classification Layer” makes use of a neural network classification model that is<br />
transparent to the video application and the network layers.<br />
Classification has been the subject of frequent and profound investigation. It has proved a<br />
useful tool in real world applications. In networking environment, packet classification can be used<br />
in network elements such as switch and router for packet switching, forwarding and filtering. The<br />
proposal [149] presents an architecture that meets this goal. In [150], the authors present some<br />
algorithms that can be used for packet classification and can be categorized as basic search<br />
algorithms, geometric algorithms, heuristic algorithms, or hardware-specific search algorithms.<br />
These algorithms are used in <strong>IP</strong> services such as firewalls and quality of service.<br />
In the machine-learning mechanisms, classification methods are incredibly used. One wellestablished<br />
approach is Bayesian classification, a technique that has become increasingly popular in<br />
the recent years in part due to recent developments in learning with Bayesian belief networks [151].<br />
Another classification method based on similarity such as K-NN (K-Nearest Neighbor), Naïve-<br />
Bayes and hierarchical clustering are very used in machine learning.<br />
In classification, neural networks solve many problems that conventional methods cannot, or<br />
at least not within acceptable cost or performance criteria. In our design, we have used neural<br />
network algorithms for automatic AVO classification.<br />
64