K.U.Leuven > ESAT > PSI > Visics > Research > Projects > European

European Projects

You can reach the web site of the project, if available, by clicking the project title.

EPOCH

EPOCH is a network of about a hundred European cultural institutions joining their efforts to improve the quality and effectiveness of the use of Information and Communication Technology for Cultural Heritage. Participants include university departments, research centres, heritage institutions, such as museums or national heritage agencies, and commercial enterprises, together endeavouring to overcome the fragmentation of current research in this field.

REVEAL-THIS

REVEAL THIS addresses a basic need underlying content organisation, filtering, consumption and enjoyment by developing content programming systems that will help European citizens keep up with the explosion of digital content scattered over different platforms (radio, TV, World Wide Web, etc), different media (speech, text, image, video) and different languages. People should be spending most of their leisure time enjoying the content, not searching for it.

REVEAL THIS aims at developing content programming technology able to capture, semantically index, categorise and cross-link multiplatform, multimedia and multilingual digital content, as well as provide the system user with semantic search, retrieval, summarisation and translation functionalities

DIRAC

Today’s computers can do many amazing things but there are still many “trivial” but important tasks they cannot do well. In particular, current information extraction techniques perform well when event types are well represented in the training data but often fail when encountering information-rich unexpected rare events. DIRAC project addresses this crucial machine weakness and aims at designing and developing an environment-adaptive autonomous artificial cognitive system that will detect, identify and classify possibly threatening rare events from the information derived by multiple active information-seeking audio-visual sensors.

CLASS

Class will develop a basic cognitive ability for use in intelligent content analysis: the automatic discovery of content categories and attributes from unstructured content streams. The demonstrators will focus on object recognition and scene analysis in images and video with accompanying text streams. Autonomous learning will make recognition more adaptive and allow more general classes and much larger and more varied data sets to be handled.

Technically, the work will combine latent structure models and semi-supervised learning methods from machine learning with advanced visual descriptors from computer vision and state-of-the-art text analysis techniques. Three levels of abstraction will be studied: new individuals (specific people, objects, scenes, actions); new object classes and attributes; and hierarchical categories and relations between entities.

PASCAL

The objective is to build a Europe-wide Distributed Institute which will pioneer principled methods of pattern analysis, statistical modelling and computational learning as core enabling technologies for multimodal interfaces that are capable of natural and seamless interaction with and among individual human users.

At each stage in the process, machine learning has a crucial role to play. It is proving an increasingly important tool in Machine Vision, Speech, Haptics, Brain Computer Interfaces, Information Extraction and Natural Language Processing; it provides a uniform methodology for multimodal integration; it is an invaluable tool in information extraction; while on-line learning provides the techniques needed for adaptively modelling the requirements of individual users. Though machine learning has such potential to improve the quality of multimodal interfaces, significant advances are needed, in both the fundamental techniques and their tailoring to the various aspects of the applications, before this vision can become a reality.

SAFERDRILL

In this project a remotely controlled autonomous walking and climbing robot for faster and safer landslide monitoring, slope stability analysis and consolidation is built. One of the key-parts in this is the development of a navigation sensorial system able to provide the operator with real-time information on slope morphology and obstacles. The KUL will build a device that can reconstruct 3D information from stereo imagery and will provide software that can register different reconstructions together in one coordinate system.

Completed Projects

ERMIS

Linguistic and paralinguistic analysis of speech will be investigated systematically, creating a prototype that is able to analyse and respond to its users' commands, taking into account the cues about their emotional state. Analysis of facial expressions, especially in the framework of the MPEG-4 standard, constitutes another input for retrieving cues about the user's emotional state. Facial expression analysis will be applied separately, or combined with emotional speech analysis.

COGVISYS

The central goal of the project is to build a vision system that can be used in a wider variety of fields and that is re-usable by introducing self-adaptation at the level of perception, by providing categorisation capabilities, and by making explicit the knowledge base at the level of reasoning, and thereby enabling the knowledge base to be changed. In order to make these ideas concrete Cognitive Vision Systems (CogViSys) aims at developing a virtual commentator which is able to translate visual information into a textual description.

STAR

A major research goal during the last decade has been to create photo-realistic interactive synthetic worlds. This has resulted in Virtual Reality (VR) simulations of virtual worlds. Recently, Augmented Reality (AR) has emerged has an attractive alternative that yields both increased realism and lower computational cost: It involves mixing graphics, for example in the form of virtual objects, with real images taken from existing environments on the same display. The real images lend realism to the display, while graphics are used to simulate virtual objects that do not exist in the real scene or are to be moved. STAR will focus on developing Augmented Reality techniques with a view to developing commercial products for training, on-line documentation and planning purposes. With its two industrial partners, the Services and Training through Augmented Reality (STAR) project will focus on developing the technology so that it is applicable to the industrial world.

INVIEW

The interactive video system we are aiming for in the Interactive and Immersive Video from Multiple Images (INVIEW) project, will provide tele-reality, immersive scenarios, and the impression that the user is navigating in a real 3D environment. No explicit 3D model will be built. Instead, images will be processed in such a way that it will be possible to navigate through them with arbitrarily movements, and it will give the impression of navigation in a real environment. New images will be synthesized from viewpoints that were not previously recorded, in terms of image synthesizing/interpolation from original ones and, most important, the physical validity of the newly created image is assured. This will allow immersive 3D environments to be constructed for real places, enabling a new class of applications in entertainment, virtual tourism, telemedicine, telecollaboration and teleoperation.

VIBES

Video provide continues coverage of scenes over an extended region both in time and in space. That is what makes it more than a plain collection of images. In VIBES, our objective is to make video a first class data type, which can be searched on content, annotated, hyper-linked, and edited much as text can be now. Furthermore video has many more modes of information than simple text. For example, it contains scene geometry and extended actions over multiple frames.
Our objectives are also to extract and use these 'modes'. With these aims, VIBES proposes new ways of exploring and using video that have the potential of leading to significant breakthroughs in video consumption and new industrial, commercial, and home entertainment applications. The tools we develop will enable cut detection, indexing, synthesis, and classification of non-static and non-rigid scenes.

ATTEST

The ATTEST project aimed to design an open, flexible and modular 3D-TV system, which can be used in a broadcast environment. It is based on the concept of 2D video and synchronised depth information, assuring full compatibility with digital 2D-TV available today. Finally, as consumer acceptance will ultimately decide on its commercial success, requirements for optimal 3D enjoyment will be assessed through human perception studies.

CIMWOS

This project aims to facilitate repetitious processes involving the storage and retrieval of audiovisual material. The objective of the project is to develop and complete a search algorithm, without the restrictions of key-words as well as an efficient image-retrieval algorithm involving digitalized audio-visual material. The algorithms are designed to operate in a demonstrable system for efficient retrieval from multimedia databases.
More specifically, a system will be developed for automatically retrieving voice fragments, images and videos from an audio-visual database, based on the user's input in the form of typed or spoken words. The aim of the Combined IMage and WOrd Spotting (CIMWOS) System is to be a valuable assistant in the process of reusing existent audio-visual material, thus limiting the expenses in new producers' the budgets.

3D MURALE

The currently excavated archaeological site of Sagalassos will be reconstructed for the different periods throughout the complete time of its occupation. The development of 3D acquisition systems that can measure a range of objects of different dimensions to produce accurate and convincing results will be made. Precise and realistic looking 3D models of the natural environment and the urban development of the site will be made. Documentation and classification of pottery sherds will be made. The 3D-MURALE project will provide archaeologists with the tools to support the analysis and restoration of their finds. The virtual artefacts and building information will be stored in a database extended with MPEG-7 compatible features. Searching on the basis of 3D shape will be one of the innovative features. High levels of realism and precision will be reached by the integrated visualisation of landscape, buildings, and artefacts - all true to the era that they represent.

SOQUETEC

SOQUETEC develops technology for the inspection of discrete mass products. Increasing the speed of such processes should increase productivity. Advanced quality control methods are to be developed, that combine low-cost hardware and modular software. Different sensing modalities will be elaborated and integrated through a neural network based decision process. They include weighing, high-resolution vision, and non-contact acoustic analysis. The application of these innovations will be demonstrated for four example systems, that each focus on a different type of industry: eggs, tile glazing, seed germination quality and meat tenderness.

BEYOND

The BEYOND project aims at making human machine interaction more natural and thus providing a good basis for making better products, that benefit the users and enhance the competitive position of European Information Technology industries in the world markets. In this project we want to explore such natural forms of interaction between people and the products and services they use. We want to do this in a user centred way, starting from real user needs and proving the benefits in their domains of use.

IMPROOFS

An increasing number of crimes and accidents have silent witnesses in the form of surveillnce and monitoring cameras. Concurrently, developments in image processing and computer vision have enabled far more practical applications. The IMPROOFS project aims at exploiting these advances for the forensic sciences. Research teams working in the forensic sciences and computer vision have joined forces to develop new tools for forensic image processing that will complement the existing ones. The emphasis is on three strands; 1) image enhancement and restoration; 2) extracting measurements from images like length or heighths and even complete 3D scene layouts; and 3) person identification.

IMPACT

The central theme of the IMPACT project is the development of powerful tools for carthographic applications. In particular, image processing methods will be devloped that delineate and detect man-made structures - mainly buildings - in aerial imagery. The main emphasis will be on digital urban mapping.

VANGUARD

VANGUARD aims at powerful visualisation techniques, that draw together expertise from both graphics and computer vision. The project will build three-dimensional models of objects and scenes, and will extract surface characteristics such as reflectance. This technology will be applied to extract graphical model of real objects, to render novel views and sequences of views of scenes, and to integrate synthetic and real models into single renderings.

Vision and interactive autonomy bi-lateral experiment on ETS-VIII 2 (VIABLE)

A robot on a satellite platform is programmed to perform assembly tasks. In order to increase the flexibility of such a process vision is used. The second stage of the project is aimed at implementing the suggested improvements in the software and making the robot platform operational on board of the ETS-VII satellite.