TITRE Adaptive Packet Video Streaming Over IP Networks - LaBRI

4.1.1 Video Classification Model Properties
To take benefits from the object-based compression, we propose to classify the MPEG-4
Audio Video Objects (AVOs) at the video server from most important AVO to least important
AVO. We deal with the Audio Visual Object as an independent calculation primitive. Several
methods can be used for AVOs classification. During scene creation, one can affect the adequate
priorities to each object in the scene. For scenes with no assigned object priorities, MPEG-4
objects descriptors and / or MPEG-7 [152] can provide the relevant information needed to
compute the relative priority score for each objects.
The MPEG-7 standard describes a generic Description Schemes (DSs) for image, video,
multimedia, home media, and archive content. MPEG-7 aims to create a multimedia content
description standard in order to facilitate various multimedia searching and filtering applications.
We can use this content description to do an intelligent AVOs classification. The main components
of the image, video, and multimedia DSs are objects, feature classification, object hierarchy, entityrelation
graph, code downloading, multi-abstraction levels, and modality transcoding. Each AVO
may have one or more associated features, which are grouped in the following categories: media
features, visual features, temporal features, and semantic features. Each feature is described by a set
of descriptor.
The user interacts with the MPEG-4 server and can decide at any time to choose some AVOs
among several available in the scene. This is the basic kind of classification. The automatic
classification is done in the server by the prioritization mechanism which affects a Relative Priority
Score (RPS) to each AVO. High RPS value (high priority) are affected to the important AVOs in
the scene (e.g. Base layer stream in hierarchical coding) and low RPS value are affected to the less
important AVO (e.g. Enhancement Layer stream).
The rest of this section gives the properties of the classification model for flexible, extensible,
scalable, and efficient MPEG-4 AVO classification and prioritization. This architecture is very
adapted to deal with network Quality of Service and user terminal capabilities. Figure 4-1 shows the
new MPEG-4 architecture layers. In this architecture, classification layer is developed between Sync
layer and Delivery layer. Classification layer must be aware of the transported media and the
adjacent layers. It is a media aware, delivery aware layer. This task is performed by two interfaces.
The interface between Sync Layer and Classification Layer is called “MPEG-4 AVO
Classification Interface” it performs a logical MPEG-4 Object identification and retrieval.
The interface between Classification Layer and Delivery Layer is called “MPEG-4 AVO
Mapping Interface” it is a logical interface at which the classified MPEG-4 AVO are mapped into
various QoS transport mechanism such as IP Diffserv, Intserv, MPLS, etc.
65