Knowledge Base

No albums or photos uploaded yet.

Series of LIVE postcards: A series of 7 LIVE postcards promoting the main objectives of the project.
Concepts for Semantic Search in Audio-visual Repositories: Eine auch fuer Anwender spuerbaren Auswirkungen semantischer Technologien besteht im verbesserten Zugang zu Information. Auf diesem Grundgedanken basieren nicht nur semantische Suchmaschinen (z.B. Swoogle), sondern es gibt auch eine Reihe von Content Management Systemen, die derzeit an einem „Semantic Lifting“ ihrer Middleware arbeiten, um die Suche und den Zugang zur Information aufgrund formaler Modelle fuer die Bedeutung der (meist) unstrukturierten Inhalte zu erleichtern. Der Beitrag umreißt die Grundlagen der semantischen Suche als eine Anwendungsmoeglichkeit fuer die Technologien des Semantic Web und zeigt anhand eines Fallbeispieles, wie semantische Technologien zur Indizierung von audiovisuellen Archiven in einem Projekt am Kompetenzzentrum fuer Neue Medien (Salzburg NewMediaLab) mit der Bezeichnung „Smart Content Factory“ genutzt werden koennen.
LIVE Newsletter Issue 1: The aim of this publication is to report on the progress and results of the LIVE project as they happen. Each edition will briefly report on the progress of each work area as well as present a selection of articles from the consortium on a specific research theme being addressed in the project. This first edition provides an introductory overview of the nine main research and development work areas in the project, along with their respective research focus and expected outcomes.
An Intelligent Media Framework for Multimedia Content: Search, retrieval and navigation in multimedia repositories is a task common to all multimedia management systems: Users are supported by a wide range of features which are traditionally based on full text search and metadata queries. However generating metadata is an error-prune and work-intensive task, that for multimedia content cannot yet be made fully automatically. In this position paper we describe our vision of an Intelligent Media Framework that is capable of combining metadata and knowledge about media items in order to support user- orientation, search and retrieval in media-rich information spaces: We try to integrate heterogeneous sources to create an Intelligent Media Framework containing Intelligent Media Objects carrying behavioural knowledge and capable of fully describing themselves. The properties of these objects amongst others serve to the fact that users more likely search by the ”meaning” of audiovisual objects and what is represented tby them respectively, than by their pure low-level features.
Mind the Gap - Requirements for the combination of content and knowledge: Semantic enrichment of content can be done manually, which is expensive, or automatically, which is error-prone. In particular, automatic semantic enrichment must be aware of the gap between the semantics that are directly retrievable from the content and those which can be inferred within a given interpretative context. We report on a model for content and knowledge which distinguishes between three descriptive levels: information relating directly to the resource, to the metadata of the resource and to the subject matter addressed by the content. This model addresses five fundamental requirements for automation: formality, interoperability, multiple interpretations, contextualization, and independence of knowledge items from the resource’s content.
Smart Content Factory - Assisting Search for Digital Objects by Generic Linking Concepts to Multimedia Content: Search, retrieval and navigation in audiovisual repositories is a task common to all media asset management systems: Users are supported by a wide range of features which are traditionally based on full text search and metadata queries. In this paper we describe an approach to superimpose a semantic indexing infrastructure over the media assets and the metadata associated with them. The infrastructure is based on formal knowledge models and facilitates the use of further navigation dimensions: By identifying semantic concepts we are able to create a dynamic navigation structure which is based on the underlying knowledge model and the conceptual relations defined therein.
Smart Content Factory - Approaching the Vision: In this paper we describe the objectives and achievements in developing the vision of a “Smart Content Factory”. The “Smart Content Factory” aims at the creation of a knowledge-aware system infrastructure to improve the utilization (re-use and adaptation) of audiovisual content. We will provide an overview of the project objectives and introduce “digital content engineering” as a scientific discipline dealing with concepts, methodologies, techniques and tools for a quantifiable approach towards the vision of smart content, thereby addressing future scenarios of electronic publishing, especially for embedded publishers. We will further take a look at the user and system requirements of the “Smart Content Factory” and their impact on the architecture of the system prototype.
A Management System for Distributed Knowledge and Content Objects: We present the results of a European research project which developed specifications for so-called Knowledge Content Objects (KCO) and for an attendant infrastructure, the Knowledge Content Carrier Architecture (KCCA). The work addresses the problem that while there are many standards for content and for meta data, there is at present, no suitable framework that enables organizations to manage knowledge alongside content, in a coherent manner. Our approach postulates the KCO as a common structural entity which can be recognized and manipulated by a KCCA enabled system.
Smart Content – Scenarios and Technologies for a Knowledge-based Audiovisual Archive: In our paper we present the intermediate results of a project aiming at the creation of a knowledge-based infrastructure for search and navigation in audiovisual repositories. The approach is based on highly automated media processing and is therefore specifically targeted to historically grown archives (broadcasters, universities, public and corporate media archives, etc.) lacking the time and/or the financial means to manually annotate their digital media assets. In the project a conceptual architecture was developed to meet the requirements of a set of knowledge-intensive user scenarios for the utilization of rich media content in the B2B and B2C areas. Pluggable RDF knowledge components act as a link between a semantic indexing and knowledge-based navigation.
The Role of MPEG-7 in Semantic Annotation and the Cross-Media Publishing Process: During the development of a knowledge-based audio-visual information system the authors of this article defined a conceptual system architecture based on MPEG-7 as the general description scheme for the media assets in the middleware. This concept was not only used to achieve a high abstraction and independence of the underlying media asset management system, it was also and primarily used as the basis of a semantic indexing process. Based on lightweight ontologies the descriptions of the media assets were associated with semantic concepts. Semantically annotated MPEG-7 assets were then propagated to the presentation layer, thus allowing the implementation of a variety of publication scenarios, including cross-media scenarios for the creation of concise video summaries.
An end to interactive television production? Just the opposite: All stories have one beginning, one middle and one end. But with MECiTV’s interactive television (iTV) authoring platform, producers can easily create programmes in which viewers choose how the story unravels and ends.
Identification of Dramaturgical Principles: Identification of Dramaturgical Principles, Deliverable D2.2 of the MECiTV IST Research Project in FP5
Guidelines and Methods for Staging Live Media Events: D4.1 Guidelines and Methods for Staging Live Media Events, Deliverable of WP4 in LIVE. Ee explain our LIVE WP4 research roadmap for staging live digital TV content. The role of the Video Conductor at this stage of development should be seen as a visionary goal guiding our work. The user tests will help us to clarify and form the role of the Video Conductor in the first project phase. We are staging constructive test scenarios (bottom up approach), which will lead us to new methods and guidelines for live staging.
Video Composer and Live Video Conductor: Future Professions for the Interactive Digital Broadcasting Industry: Paper presented the EuroITV 2006: Beyond Usability, Broadcast, and TV - Fourth European Conference on Interactive Television, May 25 - 26, 2006, Athens, Greece. Proceedings pp. 32-38.
Methods, Design Guidelines and Workflows for Online Staging: EU Information Society Technologies – FP6-27312, Report D4.3, EU-IST Project 'Live: Live Staging of Media Events', 2006. After describing the conceptual background which is necessary for the development of future live staging TV formats, this document proposes both visionary as well as first concrete methods and design guidelines for online staging. In addition considerations on the respective future workflows and the results of a first survey on suitable live video performance tools are presented.
EU-IST Project LIVE: Live Staging of Media Events: Paper presented at the SAMT 2006: First International Conference on Semantics and Digital Media Technology, December 6 - 8, 2006, Athens, Greece.
Future Live iTV Production: Challenges and Opportunities: Paper presented at the AXMEDIS 2006: Second International Conference on Automated Production of Cross Media Content for Multi-Channel Distribution, December 13 - 15, 2006, Leeds, UK. Proceedings pp. 325-328. Today's TV broadcasting companies are highly professionalized in the production of linear TV formats. Workflows and technologies for these linear formats are reliable, the production personnel is highly skilled and we can trust in well-known viewing habits of the consumers. The key issue of this paper is: how do we enable such a broadcasting working environment to produce by far more variable, multi-perspective or interactive TV formats? We are especially interested in formats entailing a multitude of live audiovisual material like for example sport events or elections, which shall be transformed into an interactive TV event for the consumer at home. This paper is not concerned with the variety of technical problems the interactive TV paradigm leads to, but with questions of future tools and practices on the producers' side, levels of consumer personalization and the respective consumer interfaces to make digital content accessible.
Virtual Personalised Channels: Video Conducting of Future iTV: Paper presented at the EWIMT 2005: Second European Workshop on the Integration of Knowledge, Semantic and Digital Media Technologies, 30 November - 1 December, 2005, IEE Savoy Place, London. Proceedings pp. 381-382. Abstract: Television is undergoing a historical change. Interactive Digital Broadcasting will be reality in 2010+. Heaps of video material will be produced by TV broadcasters, which will overwhelm both the producers as well as the consumers. Current TV formats and forms of broadcasting do not satisfy the personal moods and interests of the consumer. We hence propose the development of a TV environment which allows for the establishment of 'virtual personalised channels'. To do so, (live) semantic annotation of video material as well as methods for live staging of media events have to be designed. The resulting drastically different process of content production and consuming will lead to the satisfaction of individual human needs. The approaches outlined in this extended abstract are the basis for our upcoming IST research project LIVE.
Afuzzy logic approach for detection of video shot boundaries: Video temporal segmentation is normally the first and important step for content-based video applications. Many features including the pixel difference, colour histogram, motion, and edge information etc. have been widely used and reported in the literature to detect shot cuts inside videos. Although existing research on shot cut detection is active and extensive, it still remains a challenge to achieve accurate detection of all types of shot boundaries with one single algorithm. In this paper, we propose a fuzzy logic approach to integrate hybrid features for detecting shot boundaries inside general videos. The fuzzy logic approach contains two processing modes, where one is dedicated to detection of abrupt shot cuts including those short dissolved shots, and the other for detection of gradual shot cuts. These two modes are unified by a mode-selector to decide which mode the scheme should work on in order to achieve the best possible detection performances. By using the publicly available test data set from Carleton University, extensive experiments were carried out and the test results illustrate that the proposed algorithm outperforms the representative existing algorithms in terms of the precision and recall rates. 2006 Pattern Recognition Society. Published by Elsevier Ltd. All rights reserved.
Video Indexing and Retrieval in Compressed Domain Using Fuzzy-Categorization: There has been an increased interest in video indexing and retrieval in recent years. In this work, indexing and retrieval system of the visual contents is based on feature extracted from the compressed domain. Direct possessing of the compressed domain spares the decoding time, which is extremely important when indexing large number of multimedia archives. A fuzzycategorizing structure is designed in this paper to improve the retrieval performance. In our experiment, a database that consists of basketball videos has been constructed for our study. This database includes three categories: fullcourt match, penalty and close-up. First, spatial and temporal feature extraction is applied to train the fuzzy membership functions using the minimum entropy optimal algorithm. Then, the max composition operation is used to generate a new fuzzy feature to represent the content of the shots. Finally, the fuzzy-based representation becomes the indexing feature for the content-based video retrieval system. The experimental results show that the proposal algorithm is quite promising for semantic-based video retrieval.
An Effective and Fast Scene Change Detection Algorithm for MPEG Compressed Videos: In this paper, we propose an effective and fast scene change detection algorithm directly in MPEG compressed domain. The proposed scene change detection exploits the MPEG motion estimation and compensation scheme by examining the prediction status for each macro-block inside B frames and P frames. As a result, locating both abrupt and dissolved scene changes is operated by a sequence of comparison tests, and no feature extraction or histogram differentiation is needed. Therefore, the proposed algorithm can operate in compressed domain, and suitable for real-time implementations. Extensive experiments illustrate that the proposed algorithm achieves up to 94% precision for abrupt scene change detection and 100% for gradual scene change detection. In comparison with similar existing techniques, the proposed algorithm achieves superiority measured by recall and precision rates.
DCT-Domain Image Retrieval Via Block-Edge-Patterns: A new algorithm for compressed image retrieval is proposed in this paper based on DCT block edge patterns. This algorithm directly extract three edge patterns from compressed image data to construct an edge pattern histogram as an indexing key to retrieve images based on their content features. Three feature-based indexing keys are described, which include: (i) the first two features are represented by 3-D and 4-D histograms respectively; and (ii) the third feature is constructed by following the spirit of run-length coding, which is performed on consecutive horizontal and vertical edges. To test and evaluate the proposed algorithms, we carried out two-stage experiments. The results show that our proposed methods are robust to color changes and varied noise. In comparison with existing representative techniques, the proposed algorithms achieves superior performances in terms of retrieval precision and processing speed.
Constrained Region-Growing and Edge Enhancement Towards Automated Semantic Video Object Segmentation: Most existing object segmentation algorithms suffer from a so-called under-segmentation problem, where parts of the segmented object are missing and holes often occur inside the object region. This problem becomes even more serious when the object pixels have similar intensity values as that of backgrounds. To resolve the problem, we propose a constrained region-growing and contrast enhancement to recover those missing parts and fill in the holes inside the segmented objects. Our proposed scheme consists of three elements: (i) a simple linear transform for contrast enhancement to enable stronger edge detection; (ii) an 8-connected linking regional filter for noise removal; and (iii) a constrained region-growing for elimination of those internal holes. Our experiments show that the proposed scheme is effective towards revolving the undersegmentation problem, in which a representative existing algorithm with edgemap based segmentation technique is used as our benchmark.
Adding Lossless Video Compression to MPEGs: In this correspondence, we propose to add a lossless compression functionality into existing MPEGs by developing a new context tree to drive arithmetic coding for lossless video compression. In comparison with the existing work on context tree design, the proposed algorithm features in 1) prefix sequence matching to locate the statistics model at the internal node nearest to the stopping point, where successful match of context sequence is broken; 2) traversing the context tree along a fixed order of context structure with a maximum number of four motion compensated errors; and 3) context thresholding to quantize the higher end of error values into a single statistics cluster. As a result, the proposed algorithm is able to achieve competitive processing speed, low computational complexity and high compression performances, which bridges the gap between universal statistics modeling and practical compression techniques. Extensive experiments show that the proposed algorithm outperforms JPEG-LS by up to 24% and CALIC by up to 22%, yet the processing time ranges from less than 2 seconds per frame to 6 seconds per frame on a typical PC computing platform.
LIVE press release at Salzburg Road Bicycle World World Championships in September 2006: A LIVE press release to inform the industry of LIVE's objectives and participation at the Salzburg Road Bicycle World World Championships in September 2006. The LIVE project took advantage of the fact that its partner ORF as the host broadcaster of the UCI Road World Bicycle Championships in Salzburg to gain unique access to the live sporting production and broadcasting environment. This experience will be the basis for the first LIVE prototype testing phase in October 2006.
LIVE press release at Salzburg Road Bicycle World World Championships in September 2006: German Version: A LIVE press release to inform the industry of LIVE's objectives and participation at the Salzburg Road Bicycle World World Championships in September 2006. The LIVE project took advantage of the fact that its partner ORF as the host broadcaster of the UCI Road World Bicycle Championships in Salzburg to gain unique access to the live sporting production and broadcasting environment. This experience will be the basis for the first LIVE prototype testing phase in October 2006.
End-user interactive view: A poster demonstrating end-user interactive concepts of the LIVE system
Draft Plan for Using and Disseminating: The LIVE Plan for Using and Disseminating Knowledge (PUDiK) is the operational framework to protect, manage, communicate and exploit the LIVE project’s results (knowledge) within the principles and rules set out by the EC Contract and LIVE Consortium. It is to be seen as a living document, meaning that it will be updated during the life of the project. PUDiK is separated into three sections, this document introduces the first two components Part A and B. Part A deals with the protection and management of knowledge represented by the activities declaration, documentation and reporting, and Part B deals with the task of knowledge dissemination. Each section establishes a framework to integrate the workflow, procedures and division of responsibilities within that area.
State of the Art Report Intelligent Media Framework (Deliverable 7.1): The integrated project “LIVE Staging of Media Events” (LIVE; FP6-27312) aims at the creation of novel intelligent content production methods and tools for interactive digital broadcasters to stage live media events in the area of sports, such as the 2008 Olympic Games. This report presents the state of the art of the concepts, technologies and standards related to one of the core subsystems developed in the LIVE project: The “Intelligent Media Framework” provides a robust framework for the creation, management and delivery of so called “Intelligent Media Assets” under real-time conditions. Topics covered in this report are: - Selected technologies in the area of (semantic) media asset management, recommender systems, metadata generation systems, video conducting systems and interface technologies. - Selected standards in the broadcasting domain and for knowledge representation. - Derived architectural requirements as well as requirements for content model of the envisaged Intelligent Media Framework - An assessment and comparison of selected intelligent content models.
First Specification of the Personalized Content Recommender System (Deliverable 6.1): This document describes the first specification of the Recommender System, which is one of the five basic system components of the LIVE system. The specification is the result of the work carried out within the WP6, Personalization and Feedback. The specification is based on the user requirements described in the Deliverable 9.1, and the basic system architecture, de-fined in D9.2. The document provides a general view of the Recommender System which should allow for different usage scenarios. It represents the WP6’s current view of the final, fully functional Recommender System to be used in the production of LIVE TV programs. The document includes: • User requirements. Users of the Recommender System services and the functionalities that they require are defined. • Usage scenarios are proposed both for Video Conductor as well as for the Consumer. • Functionalities. A list of functionalities provided by the Recommender system is de-fined. • Based on the scenarios, six use cases of RS are defined in more detail. • Internal system architecture of the RS is defined including components that comprise the Recommender System. • Services and Interfaces. Services which are offered by the RS are described together with proposed interfaces. • Activity diagrams. The activity diagrams define workflows that are performed inside the recommender system.
Video & iTV Technology (Deliverable 3.6): This market report collects the most relevant players of each allotment of the iTV industry as we have found to classify. We have been unable to determine other classification structure that would really make more sense than the one provided in this document. Nevertheless, the structure of the document is also based on some written demands, as for example the IPTV and VoD services were too large to include them under network operators and were moved into a section of their own. In addition to the short description of each technology area, the document also includes a short section under each area analysing the technology area regarding LIVE project.
Socioeconomic Impact Report (Deliverable 3.8): In this first socioeconomic report, we aim to pull together the general insights into a future progressive study of LIVE’s socioeconomical impact aspects. To this end, the report provides an initial introduction to the socioeconomic aspects of the project, including an overview of iTV technology from a consumer’s point of view. Furthermore there is a short section describing the use of iTV in society to learn about the needs and patterns that trigger audience increase and iTV services consumption.
Basic System Architecture (D9.2): The goal of this deliverable is to provide a high-level overview of the idea of the LIVE project and its basic system architecture. The description goes to the level of detail that is needed to understand the basic architecture. For more detailed descriptions, particularly of the subsystems, the reader is referred to the respective subsystem deliverables. The described first basic system architecture of this document was developed including the results of the first six months of research within the LIVE project. Derived from the basic idea of a system - whereby an interactive digital broadcaster should be able to create a non-linear multi-stream video show in real-time, which changes due the consumers’ interests - first user tests were made and analysed at the public Austrian broadcaster ORF (Österreichischer Rundfunk). These tests resulted in a set of initial requirements (compare deliverable D9.1 “Results from the initial requirement analysis”). Based on these requirements, actors of the LIVE System and their basic use cases were identified. This finally results in the basic system architecture which is briefly described in this deliverable. For this deliverable a public synopsis (D9.3) is available too.
Public Video iTV Technology (Deliverable 3.7): This report tries to identify the companies, markets and environments surrounding the iTV industry. The report classifies the main actors depending on the nature of their product or service technology. In addition to the short description of each technology area, this document also includes chapter subdivisions analysing the possible implications of technology for the LIVE project.
User Scenarios and Personalization (presentation): Proposal on user scenarios, LIVE services and the use of personalization - presentation at Vienna meeting, March 2006.
Public Synopsis on Basic System Architecture (D9.3): The goal of this public deliverable is to provide a high-level overview of the idea of the LIVE project and its basic system architecture. The description goes to the level of detail that is needed to understand the basic architecture. For more detailed descriptions, particularly of the subsystems, the reader is referred to the respective subsystem deliverables. The described first basic system architecture of this document was developed including the results of the first six months of research within the LIVE project. Derived from the basic idea of a system - whereby an interactive digital broadcaster should be able to create a non-linear multi-stream video show in real-time, which changes due the consumers’ interests - first user tests were made and analyzed at the public Austrian broadcaster ORF (Österreichischer Rund-funk). These tests resulted in a set of initial requirements (compare deliverable D9.1 “Results from the initial requirement analysis”). Based on these requirements, actors of the LIVE Sys-tem and their basic use cases were identified. This finally results in the basic system architec-ture which is briefly described in this deliverable. The target audience for this document is any person inside or outside of the LIVE project in-terested in learning about the proposed functionality and architecture of LIVE.
Description of the overall implementation and integration plan (D8.1): The document D8.1 is the first deliverable from work package 8 (Integration). While other technical work packages are about researching and developing innovative techniques for the application area, WP8 deals with the more mundane tasks of integrating those software pack-ages with each other and into an existing broadcast environment. So the work underlying this document consisted of the following tasks: isolate some attractive usage scenarios showing several of the components working in concert, coordinate the partners efforts on specifying interfaces between their respective components, study the existing target environment at the broadcasters premises and finally develop some missing glue necessary to make a first running prototype feasible as early as possible. The glue mentioned in the preceding paragraph consists of some additional “orphaned” components not included in some other work package, plus some common infrastructure (e.g. standard middleware) on which all components can be based. Both types of software packages are described in this document as well. The document describes the objectives of the prototype and summarises some of its features; the prototype's components and their internal and external interfaces, as well as how the sys-tem will be embedded into the broadcaster’s workflow and infrastructure are explained. Besides, a list of the envisaged implementation techniques and tools is given. The document ends with a presentation of the schedule for the necessary implementation steps.
Design of Interactive Knowledge Map (Deliverable 2.4): In support of -and in addition to the general information available on the LIVE website, LIVE will create an easily accessible and navigable 'Interactive Knowledge Map' (IKM) for the information space spanned by the research domain of the project for both professional and academic users. The tool is designed to support multiple search and inquiry strategies, present contextual relationships between LIVE knowledge products, and provide metadata information to knowledge in process, or not open for public viewing. The major goal of this document is to layout the design approach of the IKM, which will be a part of the LIVE Knowledge Management and Dissemination System (KMDS), which is envisaged as a semi- automatic solution to support the process of declaration, documentation, and reporting of know-how and knowledge in the project. A Knowledge Visualization Framework will be applied for gathering the main requirements for the IKM (section 4), this involves taking a look at the State of the Art in Knowledge Visualization that documents available tools and visualization strategies that could be adapted in the realization of the IKM (section 5). Section 7 outlines the approaches for the visualization of knowledge in LIVE, which includes the basic envisaged functionalities and components. Finally, an approach on how to seamlessly integrate the IKM in the LIVE website is provided. The LIVE IKM will provide three approaches for the visualization of knowledge. The first approach as introduced in section 6.1 is based on an automatic analysis of the document collection of LIVE. The second approach will model the LIVE knowledge domain by use of a taxonomy at a coarse level of granularity (section 6.2). And, the third approach will model a specific selection of the knowledge domain at a finer level of granularity expressed in an ontology (section 6.3). The design of the ontology will be based on the deliverable D3.2 (Technology Market Watch).
Recommender System Evaluation : Scenarios and User interface: A presentation of WP6 plans and their development status. Evaluation of developed tools and scenarios.
Personalised content search: An overview of different personalization approaches (content-based, collaborative.based, feedback gathering mechanisms, existing standards). How can this approaches be used in LIVE environment.
Overall system and Recommender System: An overview of the achieved system development. Presentation of current ideas for the system as a whole and also for the recommender system module.
Personalised content search overwiev: Additional information about usage of personalization approaches in LIVE environment.
WP 6 – Personalization and Feedback: Presentation of possible recommender system usage scenarios in LIVE. Integration of WP9 and WP5 (content description requirements and system specification). Indication of research needed for this integration.
Recommender System: First Specification: Presentation of proposed system design, module structure and functions performed by each module.
Recommender System Interfaces: Discussion of open issues such as input content format, staging workflow, Programme planning tools and user interfaces.
Recommender System Data Models: This specification defines the data models which are used within the Recommender System. First specification on data models of RS was prepared on 10-10-2006, file LIVE_RS_DataModels.xls. Further version of the specification was available in the document LIVE-WP6-TED-Recommender_System_Interfaces-061020.doc.
Recommender System Prototype: This technical document defines the scenarios for the demonstration of the Recommender sys-tem prototype at the Review meeting in March 2007.
Personalization and Feedback, Introduction, Scenarios and Functionalities: This document is intended to serve as an introduction into WP6 Personalization and Feed-back. It gives an overview of the goals of the work within WP6, collects the requirements for personalization and feedback, and gives a proposal on possible solutions to the personalized content recommendations within LIVE framework. A first draft of a work plan is included.
Initial LIVE Exploitation Plan (Deliverable 3.1): This “Initial LIVE Exploitation Plan” is the Part C of the overall Plan for Using and Disseminating Knowledge (PUDiK) which therefore completes the definition of the dissemination and knowledge management strategy. The first section of this document explains the consortium approach to develop a project policy regarding the exploitation of project results. It is foreseen that the development of an Exploitation Agreement is needed to guarantee the appropriate exploitation of the project results.
Consumer Recommender and Feed-back demonstrator: The purpose of the iTV demonstrator is to show the possibilities that can be provided by ad-vanced iTV services. The first prototype described in this document is based on the back-ground architecture work developed at the Laboratory for digital signal, image and video processing , University of Ljubljana and on the JAME Author software, which was developed by the Fraunhofer-Institut für Medienkommunikation IMK (FhG). The prototype is used for demonstration of basic functionalities that are interesting for the coming iTV services such as video on demand, automatic recommendation of interesting TV programmes, acquisition of additional data for particular TV programme, etc.
Recommender System Interfaces and Data Models: This document provides input to the work on interfaces within WP8. It provides first specifi-cation of interfaces of the Recommender System module. The RS interfaces are developed according to the proposed Use cases of the RS, defined in the D6.1. It provides the first speci-fication of the data models used and / or maintained by the RS.
Recommender System Interfaces: This document provides input to the work on interfaces within WP8. It provides first specifica-tion of interfaces of the Recommender System module. The RS interfaces are developed according to the proposed Use cases of the RS, defined in the D6.1.
Sport Database metadata retrieval scenarios: In this document we suppose that the content domain is limited to the sport domain. We only use terms available and defined by the SportML schema. We propose that the first demon-strator capabilities are limited to the sport domain.
Input to Deliverable 9.1: Results from initial requirements analysis: This document includes answers to some questions within WP9.
LIVE Staging and Directing System - a proposal: This document is intended to serve as an input for the definition of LIVE Conducting (Stag-ing) system. It describes envisioned functionalities, user interfaces for the LIVE Professional user, and proposes architecture of the Staging system
System arhitecture proposal: This file present a proposal for architecture of LIVE system and some of it's modules.
System modules: A scheme of modules divided by workpackages
The evaluation of a hybrid recommender system for recommendation of movies: In this paper we present our approach to generation of movie recommendations. The idea of our hybrid approach is to first separately generate predicted ratings for movies using the contentbased and collaborative recommender modules. Predicted ratings from both recommender engines are then combined into final classification by the hybrid recommender using weighted voting scheme. The basis for the calculations are Pearson’s correlation coefficient, True Bayesian prediction and M5Rules decision rules. The evaluation of the system performance was based on the EachMovie data corpus, for around 7000 users. Preliminary results show that this approach works really well, while there is still some room for improvement.
Personal content recommender based on a hierarchical user model for the selection of TV programmes: In this paper we present our approach to user modeling for a personalized selection of multimedia content tested on a corpus of TV programmes. The idea of this approach is to classify content (TV programmes) based on the calculation of similarities between the description of content and the user model for each descrip- tion attribute. Calculated similarities are then combined into a classi¯cation decision using the Support Vector Machines. The basis for the calculation of similarities is a hierarchical structure of the user model, overlaid upon a taxonomy of TV pro- gramme genres. Preliminary results show that it works well with a varying quality of content descriptions including incomplete genre classi¯cation and arbitrary number of description attributes. The evaluation of the system performance was based on content described using the TV-Anytime standard, but the approach can be adapted for search of other types of content with multi-attribute descriptions.
Analysis of cluttered scenes using an elastic matching approach for stereo images.: We present a system for the automatic interpretation of cluttered scenes containing multiple partly occluded objects in front of unknown, complex backgrounds. The system is based on an extended elastic graph matching algorithm that allows the explicit modeling of partial occlusions. Our approach extends an earlier system in two ways. First, we use elastic graph matching in stereo image pairs to increase matching robustness and disambiguate occlusion relations. Second, we use richer feature descriptions in the object models by integrating shape and texture with color features. We demonstrate that the combination of both extensions substantially increases recognition performance. The system learns about new objects in a simple one-shot learning approach. Despite the lack of statistical information in the object models and the lack of an explicit background model, our system performs surprisingly well for this very difficult task. Our results underscore the advantages of view-based feature constellation representations for difficult object recognition problems.
Improvement Speaker Clustering Using Global Similarity Features: In this paper global similarity features that improve speaker clustering based on standard bottom-up clustering are proposed. The novelty of this approach lies in the fact that it exploits the hypothesis that audio segments belonging to the same speaker cluster should demonstrate similar global behavior, i.e. in a way exhibit the same similarity and dissimilarity with all the other segments. Every segment is represented by a global similarity vector whose components are encoded by the distance between that segment and each of the other segments to be clustered. The distance between global similarity vectors is used for pre-selection of segment pairs having high global similarity for further merging. In this paper inter-segment distance for global similarity vectors based on Bayesian Information Criterion (BIC) and based on adapted cross likelihood ratio (CLR) are investigated. The evaluation, performed on radio programs, shows that the proposed approach represents an improvement in comparison with the baseline clustering.
Unsupervised Speaker Clustering Using a Global Similarity and F0 Features: This paper investigates an unsupervised speaker clustering approach that exploits global similarity and also proposes extending the standard cepstal feature set used for speaker clustering with prosodic features, extracted from F0. The global-similarity-based speaker clustering algorithm, initially proposed by the authors in [6], leverages the insight that audio segments within a single cluster are not only similar to one another, but also display the same patterns of similarities and differences with audio segments belonging to all other clusters. First, speaker clustering performance using the standard Bayesian Information Criterion (BIC) is compared to the performance achieved using a BIC-based algorithm incorporating global similarity. Then both clustering techniques are tested using an extended feature set including F0-derived features in addition to the standard cepstral features. The evaluation, which is performed on data recorded from German language radio, shows the clear benefits of using global information when performing clustering. It also demonstrates that in most cases F0-features outperform the cepstral feature set both in standard BIC clustering and in the BIC global-similarity-based approach.
MPEG-2 Compressed-Domain Algorithms for Video Analysis: This paper presents new algorithms for extracting metadata from video sequences in the MPEG-2 compressed domain. Three algorithms for efficient low-level metadata extraction in preprocessing stages are described. The first algorithm detects camera motion using the motion vector field of an MPEG-2 video. The second method extends the idea of motion detection to a limited region of interest, yielding an efficient algorithm to track objects inside video sequences. The third algorithm performs a cut detection using macroblock types and motion vectors.
Annual Public Report (D1.3): This document gives a report on the work and the results of the first year (2006) of the project.
Speaker Clustering via Bayesian Information Criterion using a Global Similarity Constraint: In this paper we proposed a global similarity constraint that improves speaker clustering as standardly performed using the Bayesian Information Criterion (BIC). The novelty of our approach lies in the fact that it exploits the hypothesis that audio segments belonging to the same speaker cluster should demonstrate similar global behavior, i.e. exhibit approximately the same pattern of similarity and dissimilarity with the all other segments. Every segment is represented by a global similarity vector whose components encode the BIC-based local similarity between that segment and each of the other segments to be clustered. Speaker clustering is performed bottom up using the BIC to compare each pair of segments and determine if their similarity is high enough to merge them. We use the global similarity vectors to constrain merging to segment pairs that have approximately the same patterns of global similarity. The evaluation, performed on audio data from 4 different German-language radio programs, shows that the proposed approach represents an improvement on the standard BIC clustering.
Object recognition with deformable feature graphs: A fundamental question in invariant object recognition is that of representation. This chapter reviews object representation based on deformable graphs that describe particular views of an object as a spatial constallation of image features. These representations are particular useful in situations of high clutter and partial occlusions. We demonstrate the benfits of these representations in three recognition applications: face analysis, hand gesture recognition and the interpretation of cluttered scenes composed of mutible partly occluded objects. We conclude by discussing current trends and open challenges.
Automatische Medienanalyse im digitalen Archiv durch Einsatz von MPEG-7 und MXF: Die Rolle des Archivs in den Arbeitsabläufen der Rundfunkanstalten wird mit der Konvergenz von IT-, Kommunikations- und A/V-Technik immer bedeutender. Die Wiederverwertbarkeit von Beiträgen ist zu einem wichtigen Ziel der Medienindustrie geworden. Digitale Archive erlauben den direkten und gleichzeitigen Zugriff auf gespeicherten Content. Damit Inhalte schnell und zielgenau gefunden werden können, werden qualitativ hochwerige Metadaten benötigt. Im vorliegenden Beitrag wird das Medienanalysesystem iFinderSDK zur automatischen Erzeugung von MPEG-7-Metadaten vorgestellt. MPEG-7 bietet ein sehr detailliertes XML-basiertes Metadatenmodell zur effektiven Suche in großen multimedialen Archiven. Zur Integration der Medienanalyse in den digitalen Produktions- und Archivierungsworkflow der Rundfunkunternehmen ist jedoch auch ein Standardformat zum Austausch von A/V-Material nötig. MXF bietet sich für diesen Zweck als eine gute Lösung an. Ein Konzept zur Integration einer MXF-Schnittstelle in das bestehende Medienanalysesystem iFinderSDK wird im folgenden genauer beschrieben.
An Extraction of Speech Data from Audio Stream Using Unsupervised Pre-Segmentaiton: In this paper we investigate an extraction of speech data from audio stream. Our method includes unsupervised optimal self-segmentation of the audio stream into small, homogeneous segments. The homogeneity is defined on a base of the average amplitude and a zero-crossing in a frame. A measure of the homogeneity is entropy. In our approach we calculate a relative ratio between the average amplitudes of the neighboring homogeneous segments. For a speech signal this ratio is less than a threshold defined on a short pure speech signal. As a discriminative feature we use a percent of the homogeneous segments within 1 sec interval having high relative amplitude ratio. In the process of the classification each 1 sec is labeled incrementally as a speech or a non-speech segment. The discrimination technique shows high performance for more than six-hour data that include different types of audio.
Automatic Extraction of MPEG-7 Audio Metadata Using the Media Asset Management System iFinder: This paper describes the MPEG-7 compliant media asset management system iFinder, which provides a set of automatic methods and software tools for media analysis, archiving and retrieval. The iFinder was developed for use in the media industry and consists of the iFinderSDK and the iFinder retrieval engine. The iFinderSDK is composed of a bundle of modules that realize individual technologies for audio and video metadata extraction. In this paper we present the audio content processing workflow and the pattern recognition methods implemented in iFinder. In particular, a technique for precise audio/text alignment and a browser that displays the synchronized media channels of the retrieval results are discussed. This paper also provides practical insight into how to use MPEG-7 as a standardized metadata format for media asset management.
Radio Relief: Radio Archives Departments Benefit from Digital Audio Processing: The archives departments of radio broadcasters are currently facing two significant challenges, namely, how to store rapidly increasing amounts of radio content, and how to satisfy the rising demand for easy retrieval of audio clips that can be recycled into new programs. A pilot project demonstrates that digital audio processing techniques have the potential to provide much-needed support.
Technology Market Watch (Deliverable 3.3): This document provides an overview of the existing technologies relevant to the LIVE project and especially to the future exploitation of the overall LIVE’s platform and other project results. Since the LIVE project is related to advance interactive content that relays on interactive digital television infrastructure, and in order to provide the full potential of the solutions that currently are under research, this document focuses on the study of interactive digital television.
Public Synopsis Interactive Digital Television (Deliverable 3.5): This Public Synopsis on Interactive Digital Television provides an overview of the iDTV market including a short background introduction and outline of interactive features. The different sections in which the document is divided cover the different types of existing services and solutions as well as market trends.
Public Synopsis Initial LIVE Exploitation Plan (Deliverable 3.2): This document is a public synopsis of the first “Initial LIVE Exploitation Plan” which is the Part C of the overall Plan for Using and Disseminating Knowledge (PUDiK). This document is the first step to prepare the LIVE consortium for the exploitation of the project’s results; it provides a detailed work roadmap for the Phase I & II of the project and some initial guidelines for Phase III (M37-45).
Interactive Digital Television (Deliverable 3.4): This document provides an overview of the Interactive Digital Television market including a short background introduction and synopsis of interactive features. The different sections in which the document is divided cover the different types of existing services and solutions as well as market trends; aiming to introduce the LIVE project to the current market depiction.
Risk Plan: This risk plan describes how we plan to assess and maintain possible risks within LIVE. Beside the general plans on how to handle the risk information, it mainly contains the risk table. Each risk entry is described with the following fields: • ID – a unique identifier for the detected risk. • Factor – a short description of the risk • Description – a more explanatory description of the risk • Grading – comprised by likelihood and seriousness (low, medium, high) • Ownership – who is responsible to keep an eye on the risk • Countermeasure – possible strategies to avoid or at least mitigate the risk or to react when the risk turned into a problem.
Quality Plan: The quality plan describes the main streams of LIVE that should be accompanied by QA activities: 1. Research and technical development The main activity to produce results such as know-how, tools, or services. 2. Field tests and analysis of user requirements The practical part for proof of concept and to verify the usability of developed tools. 3. Dissemination and Exploitation The valorisation of all project results. 4. Management The overall control of all activities. Strategies within LIVE are described to keep the project quality at a high level or improve it wherever possible.
Presentation of LIVE at the IST 2006: This is an extract from the presentation given at the IST 2006 conference in Helsinki.
JAME – System Concepts and New Technologies for iTV Services: This paper gives an overview on the JAME technology and its appropriate tools namely, JAME Producer and JAME Author, which constitute two different solutions for the production of so called page based iTV services.
JAME Author - An iTV Authoring System: JAME Author is an advanced MHP/OCAP authoring system for the straightforward creation of sophisticated, well-designed iTV services. By combining the efficiency, reliability and flexibility of JAME with the advantages of an easy-to-use graphical authoring tool, JAME Author adresses the needs of iTV designers, editors and many other media professionals. An assortment of features well-known from popular graphics tools and special TV/MHP related functions such as a built-in emulator for testing during creation right on-site ease and accelerate the process. This makes JAME Author a valuable tool for drafting first ideas and creating complete services. By using JAME Author, you define the design and behaviour of separate pages and connect them to a comprehensive iTV service by an inter page navigation structure. The integrated template and resource management allows the reuse of given and proven looks and helps you to support your branding. After finishing, the project can be deployed by transferring an archive, including all the created data and the MHP application JAME Engine, into an MHP compliant playout system. Further information and a free 30-days trial version can be found at http://www.jame.tv
Initial Requirements Analysis: This deliverable was created out of the very first anaysis of the LIVE-requirements. On the one hand there are the requirements for the staging concepts and on the other hand the supporting and necessary technical requirements to fulfill the new developed workflows and tasks.
Report on Test and Evaluation Methods: The present document provides an overview of approved testing and evaluation methods likely to be applied in the LIVE Project. Aiming at the LIVE System, the User Interfaces (UI) and the production workflow, the methods are adjusted to meet the specific requirements of the different sections.
Evaluation and Validation Plan: On the basis of Deliverable D10.1 this document describes the methods of usability evaluation and testing used for the LIVE System (the LIVE Methodology) and the organisation, consisting of management, communication, accomplishment and the schedule concerning the evaluation and testing of the LIVE System. The schedule is in accordance with the De-liverable 8.1 Description of the overall Implementation and Integration Plan.
Field Survey of Broadcaster (Field Trial Olympic Games Beijing 2008): By a first field survey, this deliverable describes the first outline on the way to the olympic broadcast operation of ORF and the EU-Live project. It gives also further details of the planning phase of the Beijing Broadcast Organisation (called BOB) as well as the planning of the broadcast intensions of ORF. This document is a living document.
IPTV - Definition and scope (Deliverable 3.9): IPTV is one of the biggest challenges of the broadcasting market. It offers various opportunities. This white paper aims to give an overview about these possibilities. IPTV distinguishes itself from several other new broadcasting formats. A short overview about IPTV markets in Europe as well as over its technical basis is given. Finally, the challenges for interface design and user experience are presented.
OCGen - MHP Object carousel generator: OCGen is a software tool generating MHP-compliant object carousels from a given directory structure. Object carousels are used to transmit MHP related data (application code and resources) to a compliant receiver. The tool creates a single or multi PID MPEG-2 transport stream ready for multiplexing with audio and video streams. Please note, that the documentation of the software is only available in German.
LIVE: Bringing broadcasting to the next level: Broadcasting is changing. With the advent of everything from set-up boxes, IPTV and 3DTV what can we expect the viewing experience of the future to be like? One IST project which is gathering steam is LIVE, which could prove to be TV’s most interactive ‘real-time’ experience.
Overview of LIVE Work Package 6, Personalisation and Feedback: Public overview of objectives and results of the work package 6, Personalisation and Feedback.
LIVE Overview Review Presentation 220307: The central idea of Live is to create: • Novel content production methods for live events • Tools for Interactive Digital Broadcasters • New ITV video formats and services • Non-linear, multi-stream formats to stage Live Media Events such as the 2008 Olympic Games
LIVE: Bringing broadcasting to the next level / June Edition: Broadcasting is changing. With the advent of everything from set-up boxes, IPTV and 3DTV what can we expect the viewing experience of the future to be like? One IST project which is gathering steam is LIVE, which could prove to be TV’s most interactive ‘real-time’ experience.
Presentation on integration work in LIVE: The following presentation is a public, shortened version of the presentation given at the review meeting in March 2007 at the ORF.
WP4 - Staging and Content Research - Consumer interfaces: The central aspect of this presentation is the conceptualisation of visions of consumer interfaces. It is based on the scribbles and screens provided on the review meeting in Vienna in March 2007. It envisages propositions of interfaces for two possible iTV (interactive Televi-sion) platforms, namely MHP (Multimedia Home Platform) and IPTV (Internet Protocol Television). The interface proposals rest upon the implications that both platforms provide.
Interaktives Livefernsehen der Zukunft: Mittendrin statt nur dabei: Interaktivität gilt als eine der "Killerapplikationen" der multimedialen Zukunft. Bisher konnten Zuschauer jedoch nur auf vorproduzierte TV-Inhalte Einfluss nehmen. Nun arbeiten Forscher in fünf europäischen Ländern daran auch LIVE-Fernsehen interaktiv zu machen.
Archives Poster: Poster used at the LIVE review meeting in March 2007 to explain the role of the archives in the LIVE system
Editor Room Poster: Poster used at the LIVE review in March 2007 to explain the role of the editor room in the LIVE system
Control Room Poster: Poster used at the LIVE review in March 2007 to explain the role of the control room in the LIVE system
Short Project Description for EU Unit E2 brochure 2007: Putting the viewer where the action is The LIVE project attempts to radically improve on the linear approach to TV broadcasting of live sporting events to deliver digital technologies and content formats that enable viewers to shape their own personal and highly interactive viewing experience as they watch the broadcast. The main idea of LIVE is to provide novel content production methods and new iTV video formats and services to enable interactive digital broadcasters to produce new non-linear multi-stream ‘shows’ to stage live media events such as the 2008 Olympic Games.
Content Recommendation System in the Production of Multi-Channel TV Programs: This paper presents the concept of content recommendations for the production of multi-channel TV shows. Within the 6th Framework project “LIVE – Live Staging of Media Events” [3] we are developing a production support system which will have a functionality of content recommendations and will support production of multi-channels programs. The paper outlines a concept of a multi-channel show and presents a possible workflow scenario on how to use content recommendations in the production. The details of the semantic content annotations are given and an example on computation of personalized recommendation of archive content is presented.
OCGen - MHP Object carousel generator (Software package): OCGen is a software tool generating MHP-compliant object carousels from a given directory structure. Object carousels are used to transmit MHP related data (application code and resources) to a compliant receiver. The tool creates a single or multi PID MPEG-2 transport stream ready for multiplexing with audio and video streams. This entry comprises the software package including the documentation.
D7.2 Basic Specification of the Intelligent Media Framework: This report presents the basic sp

IST LIVE

Sections

Personal tools

Views

Knowledge Base