Detailed A/V Profile

NOTE: This profile is superseded by the Audiovisual Description Profile (AVDP), which has become amendment 1 to part 9 of MPEG-7 in May 2012.

Why define an MPEG-7 profile?

MPEG-7 is an excellent choice for the description of audiovisual content due to its flexibility and comprehensiveness. The drawback is that these features also increase the complexity of descriptions and cause ambiguities, as there may be multiple ways to model semantically identical descriptions. These ambiguities hinder interoperability. In order to partly solve these problems, profiles and levels have been proposed, but firstly none of the adopted profiles is sufficient for detailed description of audiovisual content and secondly the profile definitions lack semantic constraints which are necessary for interoperability of systems using MPEG-7.

We propose the Detailed Audiovisual Profile (DAVP), which aims at describing single multimedia content entities, allowing a comprehensive structural description of the content, including textual and semantic annotations as well as audio and visual feature descriptions.

Application areas

DAVP is intended for a broad range of applications that deal with the analysis, description, retrieval, summarization and exchange of audiovisual content. The profile is defined to support the use of a variety of automatic content analysis tools and content-based query paradigms such as query by example.

Application areas include:

  • audiovisual archives
  • image and video databases
  • audiovisual content production
  • educational applications

Functionality of the profile

The Detailed Audiovisual Profile covers the functionalities to describe video, audio and still image content. The requirements of archiving, search and retrieval and media monitoring systems on a comprehensive description are considered in the profile. DAVP includes tools for:

  • the description of image, audio, video and audiovisual content
  • the description of metadata of these descriptions
  • the description of the spatial, temporal and spatiotemporal structure of the types of content listed above
  • the description of media information
  • the description of creation and production information
  • the description of semantic information
  • the description of visual and audio features
  • the summarization of image, audio, video and audiovisual content