|
for autonomous and/or personalized production of video summaries for controlled scenarios (sports events or surveillance).
Democratic and personalized production of multimedia content is one of the most exciting challenges that content providers will have to face in the near future. APIDIS has addressed this challenge by proposing a framework to automate the collection and distribution of digital content. As a federating objective, APIDIS targets cost-effective autonomous production, so as to make the creation of audiovisual reports profitable, even in case of small- or medium-size audience.
First, APIDIS is investigating the automatic extraction of intelligent content from networks of multi-modal sensors. Intelligence refers here to the identification of salient segments within the audiovisual content, using distributed scene analysis algorithms.
Second, APIDIS exploits that knowledge to automate the production of video content for specific scenarios, e.g. most notably sports events or surveillance. It considers personalized and potentially interactive content summarization mechanisms, to address professional and non-professional needs.
The potential applications of the integrated technology and methodologies developed within APIDIS are numerous, ranging from personalized access to local sport events through a web portal or a mobile hand-set; cost-effective and fully automated production of content dedicated to small-audience, e.g. souvenirs DVD, university lectures, etc; but also interactive browsing and automated summarization for video surveillance.
The results of this project will soon be exploited through a startup that will propose the system as a whole with the associated services. Please contact the coordinator if you are interested in acquiring parts of the project results. He will forward your request to the partners that own of the corresponding IPR.
Autonomous acquisition and production of content.
? Personalized summarization of events.
? Interactive browsing/remixing solutions.
In today's society, content production and content consumption are confronted with a fundamental mutation. Two complementary trends are observed. On the one hand, individuals and organizations become more and more heterogeneous in the way they access the content. They want to access dedicated content through a personalized service, able to provide what they are interested in, when they want it and through the distribution channel of their choice. On the other hand, individuals get easier access to the technical support and facilities required to be involved in the content creation and distribution process. The success of You Tube illustrates the emergence of such an individual and personalized implication of end-users in the task of producing and making available video content.
APIDIS research plan anticipates this trend, and prepares future evolutions of the content production industry towards automated infrastructures allowing content to be produced, stored, and accessed at low cost and in a personalized and dedicated way.
APIDIS is an ambitious and challenging project that builds on recent scientific and technological breakthroughs in the fields of user-centric design, signal processing, computer vision, machine learning, and also planning and optimized decision process.
Scientific innovations achieved towards:
- generic and cost-effective distributed scene analysis, including omnidirectional signal processing;
- autonomous and personalized content production;
- high dimensional state space handling in decision processes.
Potential commercial valorizations of the APIDIS framework likely include solutions to:
- Distribute the content about local sport events through a sports journal website;
- Provide cheap and dedicated content to the users of mobile hand-sets;
- Facilitate videosurveillance content browsing, via summarization and interactive access capabilities.
- Remix conventional TV content.
|
|
