A Future Vision for Next-generation Live Video Viewing: Richer, More Personalised and Highly Interactive Video Streaming
To research and develop innovative systems for video broadcasting / TV applied to Sports to help drove the following trends in interactive media for:
My eDirector 2012 is running a set of trials testing an idea of what TV may look like in the future. If you would like to see what it is like or tell us what you think it should be like why not get involved in out trails taking place this January-February 2011.
You will be able to access to 20 minutes live simulated sport event to test the personalisation features of My eDirector 2012 project including the recommender system.
To join these trials, you will only need to register, and we will send you details of how to access these trials. Click the register link.
The trial will take up to30 minutes where you watch and interact with an athletics event on your computer. You will experience a rich and interactive WebTV interface, which will ask you for some basic information about your interests so it can provide you with the recommendations of what it thinks you would like to see at each moment.
To take part:
Research Assistants
For participants in other organisations see http://www.myedirector2012.eu/
Semantic Restructuring of Natural Language Image Captions to Enhance Image Retrieval: The rapid growth in the volume of visual
information can make the task of finding and accessing
visual information of interest, overwhelming for users.
Semantic analysis of image captions can be used in
conjunction with image retrieval systems (IMR) to
retrieve selected images more precisely. To do this, we
first exploit a Natural Language Processing (NLP)
framework in order to extract concepts from image
captions. Next, an ontology-based framework is
deployed in order to resolve natural language
ambiguities. The novelty of the proposed framework is that the combination of LSI with the Ontology framework enables the combined framework to tolerate
ambiguities and variations in the Ontology. A key
feature is that the system can find indirectly relevant
concepts in image captions and thus leverage these to
represent the semantics of images at a higher level.
Experimental results show that the use of LSI based NLP combined with an ontological framework significantly enhances image retrieval.
Personalised Live Sports Event Viewing on Mobile Device: A personalised mobile sports event viewing system that enables users to efficiently and naturally direct movies of their own live sports events on mobile devices is described. Personalisation here focuses on the selection of live events with respect to multiple sports disciplines. An implicit user model driven approach is used to enable the system to adaptively predict users’ preferred events during live sports shows. The design of this personalisation model, developed as part of the My eDirector 2012 project, is described and an associated mobile prototype system is presented.
Use of Granularity and Coverage in a User Profile Model to Personalise Visual Content Retrieval: The enormous volume of visual content available from cameras and from recordings stored in data centres and the phenomenal number of users presents a major challenge to the research community. This major challenge is the use of adaptive techniques for personalised retrieval and filtering mechanisms in order to find relevant visual content appropriate to individual needs but without overloading users by retrieving uninteresting content. This paper presents a user modelling framework, which integrates a statistic model based upon Latent Semantic Indexing (LSI) and a First-order Logic (FOL) type knowledge-based technique, in order to acquire static and dynamic user preferences. Consequently, the framework is able to detect shifts in user interests. The framework is also able to construct a user profile at appropriate levels of granularity and coverage by taking advantage of concept properties, relations and the distance between nodes in users’ model of a domain with respect to a common or global domain model. In addition, terminological problems such as ambiguities are solved by exploiting an external lexical reference system, WordNet.
A Collective Director for Highly Interactive Viewing of Live Sports Events: New forms of personalised and interactive viewing experiences
are being developed that enable spectators to act as directors of
their own customised live sports videos. Scalability concerns for
such systems dictate that group-based streaming rather than
individual streaming can be realized in practice. In this positional
paper, the application of the group personalisation model to
enable social groups of possibly distributed individuals to
collectively direct and share a common viewing experience of a
live sports event is proposed. The design of this platform,
developed as part of the as part of the My-e-Director 2012 project,
is described and a discussion of a prototype system is given.
Directing Your Own Live and Interactive Sports Channel: The ability to mark-up live sports event content, viewed from multiple camera angles, such that athletes and other objects of interest can be tracked, facilitates an exciting new personalised and interactive viewing experience for spectators, enabling spectators to act as directors of their own customised live sports videos. In this paper, such an approach is described as part of the My-e-Director 2012 project. The design of this platform is described here and a discussion of a prototype system is given.
Project acronym: My-e-Director 2012
Project full title: My-e-Director 2012 - Real-Time Context-Aware and Personalized Media Streaming Environments for Large Scale Broadcasting Applications
Grant agreement no.: FP7 215248
Duration from 1st March 2008 for 36 months
Funding: EU IST FP7
Project Web Site: http://www.myedirector2012.eu/
The main goal of My eDirector 2012 , is to research and develop a unique interactive broadcasting service enabling end-users to select focal actors and points of interest within real-time broadcasted scenes. The service will resemble an automated ambient intelligent director that will operate with minimal or even without human intervention. Contrary to state-of-the art services of similar nature that focus on few targets and low-level activity scenes, My-e-Director 2012 will target large scale multi-actor, multi-target environments and high-activity scenes. Hence, the proposed ambient intelligent director service will provide new forms of end-user experience, while also enabling deployment of novel revenue-generating services for broadcasters and content providers.
While the project will carry out innovative research in all the above areas, its research question concerns the feasibility and potential of the My-e-Director 2012 technologies for large scale deployment of user-directed streaming services in realistic multi-camera environments. My-e-Director 2012 will concentrate on athletic events for demonstrating and evaluating its technologies and services. Large Scale Broadcasting events (such as coverage of Olympic games) provide a first class forum for demonstrating the My eDirector 2012 novel broadcasting case, given that they offer a large scale multi-venue, multi-event heterogeneous environment with many actors and high-activity scenes. The consortium will organize trials in both controlled laboratory-based environments, as well as field trials. As an ultimate target, My-e-Director 2012 endeavours to provide a unique technology showcase for the coming 2012 Olympic Games in the City of London. Such a showcase will be realized based on the “Olympic” partners of the consortium, namely ATOS Origin (the official IT provider of the 2012 Olympics) and BBC (the Olympic rights holder for broadcasting for the UK).
From a research and technological perspective the key innovative features of the My-e-Director 2012 broadcasting service are: