INTERNATIONAL ORGANISATION FOR STANDARDISATION

ORGANISATION INTERNATIONALE DE NORMALISATION

ISO/IEC JTC1/SC29/WG11

CODING OF MOVING PICTURES AND AUDIO

ISO/IEC JTC1/SC29/WG11/N11824

January 2011, Daegu, KR

Title:               Description of MPEG-7 Tools for Video Signature Description

Source            :           Video Subgroup

Authors:         Stavros Paschalakis and Miroslaw Bober

Status:             Approved

-----------------

The amount of video content generated and consumed by users has been increasing at a spectacular pace in recent years. In 2010, according to figures provided by the company itself, people were uploading hundreds of thousands of videos daily on YouTube, at a rate of 24 hours of content every minute, and watching 2 billion videos a day. Despite the vast amount of video data in existence, there are few tools which one can use to efficiently identify or search for a specific piece of video content, possibly in an edited or modified form, either on the Internet or in one’s own personal collection. The recently standardised MPEG-7 Video Signature Tools address this problem by providing an interoperable solution for video content identification.

Unlike previous MPEG-7 visual descriptors which were designed to provide access to similar content, the Video Signature is a content-based descriptor designed specifically for content identification, i.e. designed for the fast and robust identification of the same or modified video content in web-scale or personal databases. Descriptors such as the Video Signature are also commonly known as fingerprints and have a strong advantage over watermarking techniques in that they do not require any modification of the content and can be used readily with all existing content.

The applications for the MPEG-7 Video Signature are numerous, including media usage monitoring, e.g. tracking and recording statistics such as distribution and frequency of content usage, web-page linking, e.g. using video content to imply links between web-pages, as is currently done for text, rights management and monetization, e.g. detection of possible copyright infringement or content monetization online (for content owners) or identification of the copyright owner (for content consumers), and personal video collection management and de-duplication.

The newly standardised Video Signature is the result of extensive collaborative effort within the MPEG-7 group of experts, with the common aim of delivering an optimised interoperable video content identification solution. Key technical aspects of the MPEG-7 Video Signature include a combined dense (video-frame-level) and sparse (video-segment-level) description approach, allowing flexible multi-stage matching schemes, and a custom descriptor compression scheme, to facilitate efficient storage and transmission of the Video Signature metadata. In terms of content identification performance, the MPEG-7 evaluation process tested the robustness of the Video Signature to a wide range of common modifications, such as text/logo overlay, camera capture (camcording), compression al low bitrates, resolution reduction, frame rate changes, etc., and achieved an overall success rate of ~95.49% at a false alarm rate of less than 5 parts-per-million. The Video Signature has also been designed to allow very high extraction and matching speeds and has very low storage and transmission requirements, at only ~2MB per hour of video content.

The MPEG-7 Video Signature Tools comprise four amendments to the MPEG-7 standard, specifying the extraction, decoding and syntax of the Video Signature [1], providing a reference software implementation [2], specifying the conformance conditions and dataset [3], and describing the Video Signature matching procedure that was used in the MPEG-7 evaluation process. These resources will ease the development of systems that comply with standard, and it is anticipated that the Video Signature Tools will find wide adoption in video content identification applications.

References

[1] ISO/IEC 15938-3:2002/AMD 4:2010, Information Technology – Multimedia content description interface – Part 3: Visual, Amendment 4: Video signature tools

[2] ISO/IEC 15938-6:2003/FPDAM 4, Information Technology – Multimedia content description interface – Part 6: Reference software, Amendment 4: Reference software for video signature tools

[3] ISO/IEC 15938-7:2003/FPDAM 6, Information Technology – Multimedia content description interface – Part 7: Conformance testing, Amendment 6: Conformance testing for video signature tools

[4] ISO/IEC 15938-8:2002/DAM 6, Information Technology – Multimedia content description interface – Part 8: Extraction and matching of video signature tools