Research Projects

This project aims to develop portable measurement tools with in-situ visualization for the construction industry. A future measurement tool will provide a direct augmented reality view of measured properties over the real environment together with instructions as to where and how a certain task can be completed. For example, a metal detection tool should be able to provide direct visual feedback on the location of hidden metallic structures over a live video view of the inspected wall area. Furthermore it can guide a construction engineer to the optimal position for drilling a hole, avoiding any damage to existing structures.

Thus the tools should combine information from several sources to provide interactive and contextaware

guidance: Measurements from built-in sensors; location-aware through online tracking and registration; spatial, semantic information retrieved from a building information system (BIM). At the same time, future tools need to be simple to be used by non-expert users; therefore the system needs to be intuitive and guide users in the correct operation to fulfil their tasks. To accomplish this goal, The project addresses the following challenges:

• Tracking for mobile devices in changing and unknown environments for correct visual overlays. We will investigate the combination of visual online reconstruction methods with range finders and coarse models for absolute registration.
• X-Ray visualization of hidden and abstract information in unknown environments. Here we will investigate automatic approaches that take the environment’s appearance and the virtual information into account to select the best visualization method.
• User guidance based on measured and plan information requires automatic analysis of the spatial arrangements and automatic visualization.

The aim of this research project is holistic scene understanding in large aerial datasets, consisting of thousands of massively redundant high-resolution images. Holistic scene understanding is one of the major problems in computer vision and photogrammetry and has recently got a lot of attention. The problem of holistic image understanding includes two fundamental tasks: 3D scene reconstruction and semantic interpretation of the imaged content at the level of pixels. The tight interaction between semantic classification and 3D reconstruction is often ignored by state of the art aerial image processing workflows, due to the lack of computational power, the absence of efficient algorithms or the enormous effort of manual intervention. However, these tasks are mutually informative and should be solved jointly as a correct class labelling is a valuable source of information for reconstruction, and 3D information can help to improve the semantic interpretation. For instance, a correct classification is a valuable source of information for reconstruction in regions where dense matching methods fail (e.g. sheets of water and reflecting windows / facades), and 3D information can be used as a prior to improve classification (e.g. building and road detection). The high resolution and redundancy due to large overlaps of aerial images requires massive processing power which will be handled by taking advantage of graphic processing units that have proved to give a significant speedup compared to single core machines. In particular, we will focus on algorithms based on variational methods, which provide a high degree of parallelization capability. In order to reduce cost-intensive manual interaction, we further will exploit publicly available user-data from the Internet to improve both interpretation and 3D reconstruction.

In the HOLISTIC project we will provide a flexible framework for scene classification and 3D reconstruction from aerial images that outperforms current state-of-the art and delivers interpretable models at highest possible accuracy. To achieve this goal, we will focus our attention on the following two research subjects: (i) the joint optimization of geometry and semantic classification from aerial images in a unified framework, and (ii) the exploitation of existing geographic information systems and web data to support these two sub-tasks. In addition, we will use web-based standard to efficiently represent the obtained results for fast modeling and data parsing.

Smartphones have evolved considerably in processing power over the last years. They now feature multi-core CPUs as well as GPUs and consumer-quality cameras up to HD resolution. This makes them an interesting platform for graphics and vision and opens new opportunities for research.

The aim of AR4DOC is to facilitate the task of document inspection by a human operator. This requires the person to have detailed knowledge about the nature of a document, which may be outdated or even unavailable at the time of inspection.

We seek to provide this information in an interactive way using Mobile Augmented Reality (AR), so that a well-grounded decision on the vailidity of a document is possible. This involves several tasks such as document localization, recognition, tracking, presentation as well as interaction.

The focus of the project is outdoor mobile computer vision with all of its challenges. Mobile systems need to be compact and energy efficient and are frequently changing locations. Therefore they must be autonomous and perform processing locally. A number of challenges arise from these requirements for which the project aims to provide solutions: Being compact, there is not much space for a large number of sensors such as laser scanners, radar antennas and the like. The work in this project will focus on stereo vision but with two different types of cameras. Often a second camera is already available and stereo information increases detection accuracies. Each time the system moves it needs to adapt to the changing situation. This requires adaptive calibration and online learning. Mobile systems often work from batteries. In addition, there is not much space to include intricate cooling systems. Thus, the system must be designed to be very energy efficient. New approaches for dynamic power management will be explored in the project. To put the work into context, several applications from the area of traffic surveillance/toll enforcement will be implemented and tested in an application oriented setting.

Current traffic enforcement solutions are either very large and costly (section control, toll enforcement) or do not offer much in terms of image processing (radar speed control). The technological output of Mobi Trick makes it possible to design mobile solutions for traffic monitoring, vehicle identification and classification, intelligent incident detection and observation of driver behavior. Mobile devices are also more efficient in enforcement. Their transient nature makes them less predictable. Mobile systems can also react more flexibly to changing road situations such as construction sites.

This research project is devoted to the study of higher order convex variational methods for problems in computer vision. First order methods, i.e. methods which take into account first order derivatives have shown a great success for a variety of inverse computer vision problems. This success is mostly due to the introduction of total variation methods by Rudin, Osher and Fatemi in 1992. Total variation methods exhibit the important property to preserve sharp discontinuities in the solution while the associated optimization problem is still convex. This leads to robust problem solutions, independent of any initialization. Besides this, total variation methods also exhibit some disadvantages. First, total variation methods favor piecewise constant solutions which leads to staircaising artifacts in image restoration problems and to the preference of fronto‐parallel structures in stereo problems. Second, total variation methods introduce a shrinking bias in shape optimization problems. The aim of this project is therefore to study higher order convex variational methods in order to improve the shortcomings of first order methods. We therefore propose to investigate two approaches. The first approach is based on the so‐called generalized total variation method, recently introduced by Bredies, Kunisch and Pock. It provides a framework to recover piecewise polynomial functions based on a convex functional. We expect that this method leads to significant improvements of stereo and motion estimation problems. The second approach is based on the so‐called roto‐translation space introduced by Citti and Sarti in 2006. It allows to rewrite functionals incorporating curvature regularity by means of a convex first order functional in higher dimensions. We expect that this approach will significantly improve the performance of various shape optimization problems.

The goal of this project is to study statistical learning methods in particular boosting and random forest for computer vision tasks. We are especially interested in on-line learning.

The potential for integration of multimedia content into the analysis of security relevant affairs is researched for the first time within the scope of Austrian security research efforts. The project’s goal is to harvest audio-visual information from specified open multimedia sources such as TV broadcasts and allow for integration into existing environments at user sites. The intended use of the system is to allow experts to efficiently generate more realistic and high-quality situation reports in the face of critical situations. Subsequently, these can be employed for communication with the population of Austria and to increase its security and sense of security - target goals of the KIRAS framework. An exemplary implementation of a prototype will be installed at the Zentraldokumentation of the Austrian Armed Forces. In terms of audio-processing the project builds upon existing technologies of the industrial partner, while the visual processing is investigated by ICG as academic partner and will mainly deal with person/face detection, tracking and recognition methods.

SMART VIDENTE focuses on research on the next-generation field information system for utility companies, providing mobile workforces with capabilities for on-site inspection and planning, data capture and as-built surveying. For achieving this aim, handheld Augmented Reality technology is used for on-site modification and surveying of geometric and semantic attributes of geospatial 3D models on the user’s handheld device. The project aims at providing a fully functional handheld Augmented Reality device for utility field workers. To achieve this goal, we require a software solution that can visualize registered three-dimensional underground models in real time. Registration in 3D requires being able to perform accurate global localization and posing tracking in real time without relying on unrealistic assumptions concerning prior scene knowledge. We will address this issue through fusion of vision, inertial and GPS sensors. Visualization requires the rendering of complex 3D models of underground infrastructure in a way that is easily comprehensible and useful to the mobile worker. This requires visualization techniques for geometric as well as non-geometric information from the geo-database, in particular of hidden objects through so-called “X-ray vision”. These visualization techniques need to be adaptive to scene complexity and environmental conditions. The three-dimensional geometry to be shown is not available per default, but must be extracted from a conventional database system and interpreted on-the-fly as a 3D visualization using procedural modeling techniques. We want to support annotation and even surveying tasks in the field, so the system must also allow to write information back to the geo-database. Finally, we will work with three large Austrian infrastructure companies to assess the usability of our solutions.

The goal of this project is to develop and analyze methods for analyzing textual information. This should be realized by using semi-supervised learning methods, which use labeled as well as unlabeled data. In particular, existing methods which are already applied for pattern recognition should be adapted such that those can also be applied for textual data. For a practical analysis comparisons to SVM and k-NN classifier using a boosting algorithm should be performed, the influence of the amount of labeled/unlabeled data and the convergence should be analyzed. Moreover, a fair comparative study between batch and on-line methods is performed.

Die klinische Rechtsmedizin gewann in den letzten Jahren aufgrund einer Sensibilisierung der Öffentlichkeit gegenüber häuslicher und sexueller Gewalt, Gewalt gegenüber Kindern und Verdachtsfällen von medizinischen Behandlungsfehlern stark an Bedeutung. Die forensische Untersuchung von Lebenden ist bis heute jedoch auf eine äussere Besichtigung des Körpers beschränkt.

Das neue Ludwig-Boltzmann-Institut (LBI) für klinisch-forensische Bildgebung hat zum Ziel, Verfahren zur Erfassung von inneren Verletzungsbefunden als Grundlage für forensische Gutachten zu entwickeln. Mittels Computertomographie (CT) und Magnetresonanztomographie (MRT), welche in der Klinik etabliert sind, können zusätzliche, objektiv nachweisbare innere Verletzungsbefunde erhoben werden, die eine verbesserte Einschätzung der ausgeübten Gewalt gegen die untersuchte Person ermöglichen. Die Methoden sind jedoch auf klinische Diagnostik ausgerichtet, während forensisch wichtige Befunde nicht oder nicht optimal dargestellt werden.

Das Institut fuer Maschinelles Sehen und Darstellen kooperiert mit dem LBI zur Entwicklung neuer Methoden der Bildverarbeitung und Computergrafik zum Zwecke der Bildgebung.

The research aim of the project is to provide a system infrastructure to support teams of users in the on-site monitoring of events and analysis of natural resources. The project will introduce the innovative concept of event-driven campaigns using handheld devices, potentially supported by an unmanned aerial vehicle (UAV). Event-driven campaigns provide users the capacity to analyse and predict environmental changes on-site, supporting the process of taking appropriate countermeasures to avoid environmental degradation. During these campaigns, users will be able to setup and retrieve data from mobile sensorstations, the UAV and external sources (such as permanent sensor networks) in order to generate dense information on a small area. The whole sensor network system will gather and store sensor data, and process simulations based on physical process models. Hence, a shared information system fusing heterogeneous data sources will be provided that supports teams of stakeholders to monitor environmental processes on-site, complementing remote monitoring and management. To enrich the data sets from a specific location, additional remotely controlled cameras will be deployed, mounted on sensorstations and below the UAV. Users will be able to analyse the environment using mobile phones and handheld computers, supported by advanced user interface techniques.

The project will improve monitoring and management for environmental scientists, institutions, service providers, engineering companies and municipalities through its strong integration of handhelds and sensor networks. The project will progress well beyond the current state in the art, by dealing with short-term events and detailed analysis of small sites. The analysis of such events is hardly supported by current methods, but has a large impact on environmental degradation. Furthermore, information is made available to citizens by providing mechanisms to access top-level environmental data. Within the project, cutting edge inter-disciplinary research will be performed to develop user-centered solutions. When the data is integrated with analytical tools in a shared information space it will also aid a wide range of managers and planners pursuing more environmentally sensitive solutions to engineering problems. To aid the process, the research is steered by considerable end-user involvement in all its phases.

The generation of realistic 3D models of whole cities has become a vibrant and highly competitive market through the recent activities of, most notably, Goggle Earth and Microsoft Virtual Earth. While the first generation of these systems only delivered high-quality zoomable images of the ground, the current trend is heavily geared towards 3D – that is, users can access three-dimensional height- fields of the terrain, and even 3D models of individual buildings. Simple building models, basically extruded polygons with different types of roofs, can be generated today from aerial images completely automatically. This is a solved problem. Far from solved, however, is the problem of generating automatically detailed buildings with façades. Input data for this problem are registered range maps obtained by stereo matching and sequences of highly overlapping thus redundant images (taken from a car driving in the road) where each pixel has not only a color but also a depth, a z-value. Although range maps can be directly rendered in principle, the data size is huge and, more importantly, the pixels have no semantics: A priori there is no difference between a pixel on the floor, on the wall, or on a door. But these shape semantics are required by all downstream applications using the city model. Shape grammars, on the other hand, have recently become (again) a popular method in research for representing 3D buildings. Their great advantage is that they allow to parameterize buildings, which can be used for populating virtual cities with believable architectural buildings, e.g., for 3D games. The goal of the CITYFIT project is, given highly redundant input imagery and range maps from an arbitrary building in Graz, to synthesize a shape grammar that, when evaluated, creates a clean, CAD- quality reconstruction of that building that fits the original data very closely and makes the semantics of all major architectural features explicit. These shape semantics can even be transferred back to inform the original data, so each of these “semantically enriched” data points can tell whether it belongs to ground, wall, or door.

The use of augmented reality in medicine is an important field, especially in teaching and training of sensitive tasks. To support teaching and training of neonatal cranial sonography, an augmented reality simulator was developed. Physical models of a newborn and an ultrasound probe were tracked and their movements displayed in their virtual representation. The head of the newborn model was augmented with a 3D volume, reconstructed from ultrasound images of a real patient. Reconstructing a 3D volume from irregular source data takes a special focus on positioning the images and the subsequent interpolation. Moving the physical model towards each other, the according slices are generated in realtime.

VIPEM ist ein System zur hypothesengesteuerten Analyse multidimensionaler Datenräume im Gebiet der personalisierten Medizin. Ein multidimensionaler Datenraum, bestehend aus molekularen und klinischen Daten, wird unter gleichzeitiger Anwendung algorithmischer Verfahren und direkter Benutzerinteraktion gefiltert und hierarchisch strukturiert. Ein zentrales Forschungsproblem der personalisierten Medizin ist die Frage, wie die Verknüpfungen zwischen genetischen Variationen und Krankheiten, bzw. dem Ansprechen auf bestimmte Medikamente, gefunden werden können. Dazu gilt es, z.B. Gendaten mit klinischen Daten zu verknüpfen und in Folge spezifische Patientengruppen zu identifizieren. Die großen Datenmengen der molekularen Analyseverfahren (genetische Polymorphismen, Genexpressionsdaten, Proteomics) können nur mehr mit Methoden der Bioinformatik und Statistik bewältigt werden. Aber auch Standardmethoden der Statistik und der Bioinformatik versagen, wenn die Daten sehr inhomogen strukturiert sind dies ist bei den klinischen Daten der Fall und wenn Strukturen in den Daten durch Rauschen bzw. dominante Muster verdeckt werden. VIPEM soll mit Hilfe von Visualierungsmethoden die Struktur in den Datenräumen sichtbar machen und eine interaktive Navigation und Strukturierung sowohl der molekularen, als auch der klinischen Daten erlauben. VIPEM baut auf Grundlagenergebnissen in den Bereichen Informations-Visualisierung und multimodale Benutzerschittstellen auf. Durch eine enge Verknüpfung mehrerer gleichzeitig wirksamer Eingabekanäle und die sofortige Sichtbarkeit der Analyseschritte in der Visualisierung steht dem Experten ein Werkzeug zu interaktiven Erkundung von komplexen Datenräumen zur Verfügung. Als Eingabeparameter für Analysealgorithmen nutzt VIPEM hierbei die menschliche Fähigkeit, komplexe Muster und Zusammenhänge visuell bereits in Ansätzen zu erfassen, und erlaubt dadurch das Freilegen sonst verdeckter Strukturen. VIPEM fokussiert auf die hohe Nachfrage nach visualisierter Analytik im Bereich der Bioinformatik. Der innovative Zugang von VIPEM versteht sich als einmaliges Verkaufsargument, zumal sich mit VIPEM ein viel versprechendes Produkt abzeichnet, welches sicher innerhalb der nächsten zwei bis drei Jahre seinen Stellenwert als verwertbares Produkt am Markt behaupten könnte. Diese Forschungsarbeit wird als Teil des Projekts Caleydo durchgeführt.

Genoptikum is an interactive data exploration system for the visualization of and navigation in molecular and clinical data in the field of personalized medicine. Genoptikum addresses the essential but to date unsolved problem of how to identify connections between genetic variants and their corresponding diseases or the response to certain drugs and treatments, respectively. It is, therefore, necessary to connect gene data and clinical data in order to categorise specific subgroups of patients with certain disease features. The huge amount of data provided by molecular analytical methods (genetic polymorphisms, gene expression data, proteomics) can only be analysed by applying statistical methods and bioinformatics. However, even standard methods of statistics and bioinformatics fail when the data are inhomogeneous as is the case with clinical data and when data structures are obscured by noise and dominant patterns. Genoptikum should make the structure of the data spaces visible by using innovative methods of visualisation based on multiple high resolution displays in combination with data projection technologies. Genoptikum is bases on fundamental results in the fields of visualisation of information and multimodal user interfaces which enable an interactive navigation and structuring of both molecular and clinical data. Through a close link between several input channels, which are simultaneously active, and by immediate visualisation of the steps of the analysis, the expert is provides with a tool for the interactive exploration of complex data spaces. As input parameter for analysis algorithms Genoptikum makes use of the human visual capacity to grasp complex patterns to reveal hidden structures and correlations in large data spaces. This research is part of the project Caleydo.

Office space usually consists of private single-user workstations. Team work takes place on separate locations, usually supported by analogue media like printed paper. Digital data exchanges is accomplished through designated channels like e-mail or instant messengers.

Deskotheque is an ongoing project aiming to extend personal workspaces to enhance team work. It represents a flexible, interactive environment for team work, conference and meeting rooms. Unused surfaces in the room, such as empty wall space and table surfaces, can be turned into interactive, digital displays to be used for multi-user co-located teamwork.

The systematic creation of models of the real world to support the locational awareness on the Internet can be achieved if previously required massive manual labor gets replaced by automated procedures. A particular challenge exists in the automation of the extraction of the 4 classical map features buildings, circulation spaces (e.g. road networks), vegetation and water bodies, as well as their interaction. Decennia of research have been unable to automate the extraction of these features from classical aerial photography towards an economically viable result. However, we believe that we can succeed in the proposed project to develop automated procedures to create feature data for three reasons. First is the recent advent of digital aerial sensors producing highly redundant digital large format aerial photography. Redundancy will be obtained by using high forward and side overlaps, say at 80% and 60%, so that every point in the terrain is imaged at least 10 times, and any algorithm can rely on multiple analysis results that then can either reinforce or cancel one another. Second, the geometric redundancy gets augmented by a radiometric redundancy using 4 spectral bands, adding an infrared band to the classical red, green and blue color channels. Third, we will combine the classical "object reconstruction" approach available from stereo procedures, by new recognition methods. While classically a "car" on a street may have been seen via a "point cloud" and would have to get recognized simply by a representation of local height anomaly on an otherwise flat reference surface, recognition includes the use of stored images of cars in a data base to actually recognize a car as a human would do when inspecting an aerial image. The project is split up into five work packages which will focus on how reconstruction and recognition techniques can help each other and how additional information either from a previous mission or GIS can be integrated in the 3D modeling framework. One work package will address the assessment of the obtained quality, another will address project management and dissemination activities. Within the project we will develop an extensive library of combined recognition/reconstruction methods, and apply them to a range of test data sets. Test data will vary in geometric resolution (pixel size), overlaps, and types of terrain scenarios.

The trend in video surveillance is an ever increasing number of (digital) cameras for surveying complex scenarios (e.g. crowds). Currently available video surveillance systems cannot cope with this increased complexity, the detection rates are too low and the systems are not reliable enough. This hinders the broad use of automatic surveillance systems. AUTOVISTA proposes to use modern visual computing technologies to advance the state-of-the-art of video surveillance considerably. In order to cope with the increasing number of cameras, AUTOVISTA will (1) use novel on-line learning techniques to increase the detection rate and decrease the false alarm rate, while the camera adapts in an unsupervised manner to the surveyed scene. Besides an increased performance, this has the additional advantage that the installation and maintenance effort will be substantially decreased; (2) exploit novel visualization and interaction techniques to support the human operator. Furthermore two complementary visualization modes are proposed, blending smoothly between these allows the operator to maintain coherence. These techniques will enable a single operator to cope simultaneously with a large amount of cameras. AUTOVISTA will tackle the problem of increased people densities and highly cluttered scenes in a novel manner. Instead of relying on single person detection and tracking (which is not feasible for high people density scenarios), methods will be investigated to handle the crowd as a whole. AUTOVISTA will derive spatio-temporal crowd statistics, describe normal crowd behavior and use this for unusual event detection.

This Integrated Project will undertake a research programme that has as its major goal the understanding and exploitation of brain mechanisms for the enhancement of presence and interaction in mixed and virtual reality. The project is highly interdisciplinary, combining neuroscience, computer science, psychiatry, psychology, psychophysics, mechanical engineering, philosophy and drama. By presence we mean the propensity of humans to respond to fake stimuli as if they were real, something observed daily in every virtual reality laboratory. Understanding the neural basis of this ‘presence response’ its enhancement and its application is the fundamental object of study within the IP from many different points of view, and including visual, haptic and auditory modalities. The most interesting, challenging and useful mixed environments are social. The types of interaction we plan in mixed reality are those supporting interactions between real people and other remote real people, real people and virtual people, and between virtual people and virtual people. The aim is to make people’s responses real even if the perception of the reality is based on virtual stimuli. The project will carry out fundamental research adopting a neuroscience methodology and theoretical standpoint combined with research in the delivery of presence through multisensory modelling and rendering, and wide area tracking and display systems. A substantial part of the project is concerned with interaction through brain-computer interfaces. The whole will be brought together through a number of applications, in particular a persistent virtual community that represents the project itself, methods for projecting sensations of ownership to virtual representations of self, and the exploitation of neurofeedback for the enhancement of creativity through mixed reality environments.

The objective of VIDENTE is the creation of a prototype for a mobile Augmented Reality (AR) solution for utility companies. This system will provide real time visualisation of up-to-date data of subsurface utility networks for maintenance purposes. AR enables will enable outdoor users on location to see information that they would otherwise have to retrieve from hardcopy or non-registered on-screen visualisations. The prototype mobile system will visualise 3D and semantic information derived from data stored in an underlying Geographic Information System (GIS).

Partner Company: Grintec

MRI is widely accepted as a non-invasive technique for visualizing the morphology of healthy and damaged of degenerate articular cartilage. In order to visualize early pathological changes of in vivo cartilage, use of parameter selective MR imaging is combined with relaxation time and diffusion constant mapping which makes it possible for the first time to perform a biochemical evaluation of cartilage in vivo. As well as assessing the biochemical properties, it is important to assess the biomechanical properties of cartilage, to make a full functional assessment of articular cartilage, this is particularly important in cartilage implants.

The aim of this project is to further develop and validate individual MR parameters for evaluating biomechanical properties of cartilage, in particular cartilage stiffness. In order to fore fill the aims of this project we propose a 3 phase approach with in vitro, in situ and in vivo studies. MRI techniques including T1 and T2 relaxation time mapping, diffusion measurements, and sodium MRI will evaluate cartilage under controlled mechanical loading. The parameters measured in normal and degenerative cartilage using MRI will be correlated to the results of biochemical, histological and biomechanical tests. In vivo MRI studies of the biochemical and biomechanical properties of articular cartilage and cartilage implants require the application of controlled reproducible loads throughout the range of movement; therefore, as part of the project we will develop an MRI compatible kinematic device.

For the planned MR visualization of the biomechanical properties of cartilage, optimal 3D segmentation and 3D reconstruction techniques of the cartilage layers must be developed. Image analysis will allow dynamic visualization of joint motion as well as determination of quantitative parameters including thickness, volume, surface area and joint contact area under physiological loading. This 3D visualization approach ensures that the evaluation of biochemical and biomechanical properties of articular cartilage can be performed under realistic mechanical loading of the joint.

So far, such information has only been available through arthroscopic surgery. Thus, along with the basic science research on the biomechanics of articular cartilage, this non-invasive MR method also offers improved diagnosis, follow-up and rehabilitation of patients with cartilage disorders or implants.

Austrian Science Fund FWF P18110-B15

Austrian Science Fund FWF L243-B15

The main aim of the project is to create a novel method for automated game analysis, which offers new insights in the structure of sport games. The first type of sport investigated will be beach volleyball which offers a not too complex structure(4 players, 1 ball and a rather small field) and is similar to several other types of sport.
Technical aims:

• Tracking of players: All four players should be tracked most of the time. The most important point is not to loose a player or to confuse him with another because this would spoil the whole subsequent analysis. Tracking the players, should also record their positions on the field.
• Tracking of the ball: For understanding the structure of the game it is important to keep track of the ball (though the exact trajectory is not of relevance).
• Event Recognition: Based on the video analysis events such as attack, defence etc. should be recognized automatically.

All this functionality need to be offered in a software tool that can be used by sports scientists.

ListOfPublications

FWF.
Institut für Sportwissenschaften.

CashFlow is an open source flow visualization system extending Open Inventor and Coin3D toolkit by System In Motion with new features for visualization and rendering of arbitrary grids and vector data sets.

Using a PDA based digital tour guide, visitors to Technisches Museum Wien and Landesmuseum Kaernten, Klagenfurt, are engaged in an entertaining and educational quest that uses Augmented Reality presentation as a medium.

Automatic detection and tracking of vehicles entering a crossroads during red-light phase. Traffic-light regulated crossroads in urban regions are monitored. Vehicles entering the crossroads while the traffic light is red are detected and a video sequence is stored for further prosecution of the driver.

Development of a vision system for accurate calibration of the kinematic chain of an articulated robot arm.

The absolute positioning error of articulated robot arms is typically by an order of ten higher than their repeatability error. Inaccurate blueprint kinematic models typically account for 90% of this discrepancy. In this work a calibration procedure is developed which calibrates the kinematic model of a robot arm using fixed stereo rig and a calibration target mounted on the robot hand. In a single calibration framework the following parameters are automatically determined:

• DH-parameters of the robot arm
• Relative pose of calibration target and tooltip
• Relative pose of stereo rig and robot coordinate frame
• Interior camera parameters
• Lens distortion parameters of both cameras
• Relative pose of the stereo cameras
• Inaccuracies/deformation of the calibration target

The procedure is fully automatic and does not require expensive, precalibrated equipment.

Development of Computer Vision Algorithms for Robust Object Detection and Tracking on an Embedded DSP Platform. FREQUENTIS was working on an embedded platform called "TRICam". The platform is capable of acting as a high quality Motion-JPEG or MPEG4 Encoder or Decoder; furthermore, it can perform a set of selected image processing algorithms for object detection and tracking in real-time. The focus was mainly put on traffic monitoring, vehicle detection and tracking. The goal was to also deal with various algorithms for video surveillance in public places and public transport.

Multimedia data has a rich and complex structure in terms of inter- and intra-document references and can be an extremely valuable source of information. However, this potential is severely limited until and unless effective methods for semantic extraction and semantic-based cross-media exploration and retrieval can be devised. Today’s leading-edge techniques in this area are working well for low-level feature extraction (e.g. colour histograms), are focussing on narrow aspects of isolated collections of multimedia data, and are dealing only with single media types. MISTRAL follows the following lines of radically new research: MISTRAL will extract a large variety of semantically relevant metadata from one media type and integrate it closely with semantic concepts derived from other media types. Eventually, the results from this cross-media semantic integration will also be fed back to the semantic extraction processes of the different media types so as to enhance the quality of the results of these processes. MISTRAL will focus on most innovative, semantic-based cross-media exploration and retrieval techniques employing concepts at different semantic levels. MISTRAL addresses the specifics of multimedia data in the global, networked context employing semantic web technologies. The MISTRAL results for semantic-based multimedia retrieval will contribute to a significant improvement of today’s human-computer interaction in multimedia retrieval and exploration applications. New types of functionalities include but are not limited to:

• cross-media-based automatic detection of objects in multimedia data: For example, if a video contains an audio stream with barking together with a particular constellation of video features, the system can automatically consider the features in the video as an object "dog".
• semantic-enriched cross-media queries: A sample query could be "find all videos with a barking dog in the background and playing children in the foreground".
• cross-media synchronisation: The idea is to synchronize independent types of media according to the extracted semantic concepts. For example, if users see somebody walking in a video, they should also hear footfall from an audio.

Introduction

Research interests in single-modality nonlinear registration include four different kinds of subproblems. Deformable registration of two or more CT lung data sets at different states in the breathing cycle going from Functional Residual Capacity (FRC, expiration) to Total Lung Capacity (TLC, inspiration) for modelling breathing motion and deriving lung ventilation. Deformable registration of a contrast-enhanced and a native CT lung data set for deriving lung perfusion. Deformable registration of contrast-enhanced and native CT liver data sets at one or several phases in the contrast-uptake cycle for liver perfusion. And finally, highly accurate partially rigid bone registration for head and neck CT-Angiography applications to extract bone structures from CTA images.

Deformable Lung Registration

The input for this task consists of native CT thorax scans at two or more different breathing states between Total Lung Capacity (TLC, inspiration) and Functional Residual Capacity (FRC, expiration). Deformable registration of distinct breathing states is a prerequisite for deriving ventilation information by simple subtraction of expiration from inspiration data or by fusion with special functional scans and it leads to models of breathing motion in the lung. For this purpose we have available high resolution sheep lung data at up to five distinct static breathing states and human lung data at inspiration/expiration. Another application of deformable lung registration is the fusion of native and contrast-enhanced CT lung data to show perfusion information again either by subtraction or by fusion with a special scan. A notion of vessel consistency should be included in the deformable registration, since it is important that the same amount of vessels is regarded before and after registration.

Deformable Liver Registration

Similar to the lung registration, liver registration for perfusion measurements is a topic of interest. Contrast-enhancing techniques are used to get up to 8 liver images at different phases of the contrast uptake cycle. Each of these images has to be registered to a native scan to correct motions due to breathing. Afterwards subtraction techniques are used to derive the amount of perfusion in the liver. The setup of the registration algorithm is very similar to the lung registration problem.

Partially Rigid Bone Registration

The intended application of rigid bone registration is a very accurate registration of bones from native and contrast-enhanced CT images of the head and the neck. In contrast-enhanced images vessels and bones have very similar intensities, such that simple segmentation algorithms like thresholding do not work which are frequently used for CTA image studies. The intended strategy for the removal of bone structures is to take a simple (threshold-based) bone segmentation taken from the native image and register it to the contrast-enhanced image. Registration is necessarysince small patient movements may occur (especially in the neck and shoulder area) between the acquisition of both kinds of images. Registration has to be very accurate in this area, since there are vessel structures that lie close to or inside the bone structures as well. It can be assumed that the bones themselves are rigid but the relative position of bones to each other may change. Pairs of bones should be registered rigidly but the relative bone movements are taken into account leading to a partially rigid registration scheme.

When a dust laden gas is sucked through a filter, the dust remains on its surface and forms a compact dust layer called filter cake. Periodically the filter cake is at least partially removed by inverse high pressure air pulses to allow continuous operation of the filter. Knowledge of the distribution of the filter cake on the filter surface at different stages of operation is decisive for filter operation. It is shown that the principle of calibrated shape from stereo with pattern projection for generating texture on the surface gives a robust 3D reconstruction of the filter surface when accessing through a glass window. Rigid registration of surface patches using landmark points, combined with an Iterative Closest Point Algorithm as a refinement procedure gives a continuous 3D model of the entire visible filter surface. Cake thickness is calculated by taking the height difference of two surface models, acquired before and after dust deposition. The challenging problem is to account for the non-rigid deformation of the filter cloth. A global deformation model is estimated using Thin Plate Spline Interpolation based on landmark points on the filter surface.

(Matlab) - collection of some most promising methods and algorithms related to appearance based object recognition.

Most technological paper qualities are directly or indirectly influenced by the three-dimensional paper structure which means the spatial arrangement of fibres, fillers, pores and if necessary of the coating. In the area of the structure analysis, two main groups can be distinguished: destructive and non-destructive approaches.

The paper structure analysis methods have to fulfil the following basic requirements. The quality of the 3D data must be high enough to make an exact delimitation between the relevant paper contents possible. Furthermore the spatial resolution must at least lie in the area of a micron. In order to be able to make statistically reasonable statements for the complete paper sample, sizes of the range of at least one square centimetre must be analyzed. To conclude, the time expenditure to the digitalization of the paper sample should also lie within a practicable area of hours.

Primary objective of the project is the detailed analysis of the fibre network structure of a paper sample by means of image analysis methods. Still this application is an extremely complex problem and in this resolution (microns) and sample size (square centimetre) unsolved. Therefore the development of a completely new concept is necessary. This concept should finally make a general assignment of the three-dimensional paper structure to pre-defined paper-ingredients classes possible. As a final result the segmentation of single fibres and their three-dimensional tracking is realizable.

Soft tissue like tendons, arteries, veins or skins are important biological materials. A greater understanding of the foundations and interactions of structure and function of soft tissue, and, in particular, the associated mechanobiology is of great interest in the field. A thorough understanding of the complex interrelations between mechanical factors and the associated biological responses may help to improve diagnostics which allow disease and injury to be treated earlier. The research proposed here will develop a fully automatic system for analyzing macroscopic structures obtained from histological images of arteries by means of modern computer vision techniques. Besides being interesting from the mechanobiological point of view the structural analysis of images of collagen fibers poses also several challenging questions from a computer vision point of view. In particular, due to the wide variety of different appearances of collagen fibers in images this task is non trivial. The main task of this research is the development of novel segmentation techniques for robustly segmenting individual fibril bundles and estimating their parameters, like location and shape, fibril density, mean fibril orientation, wriggling of fibrils etc. This will be achieved by developing novel perceptual grouping methods operating on the extracted orientation data of fibrils. Another major challenge of this research is to extend the structural analysis from 2D to 3D.

Current paper and corresponding presentation

The concept of "directed evolution" is dependent on the availability of systems that allow the identification of interesting enzyme variants within a large, artificially generated diversity. Thus, one prerequisite is the availability of systems that allow the detection of specific enzyme features such as activity, selectivity, stability etc. at smallest culture scales and at high-throughput conditions. Therefore, focus is put on the development of methods witch are rapid, sensitive and cost-effective and preferably work at the microwell-plate, single colony or even single cell level.

Surrogate substrate analogues which would allow easy detection of reaction products by e.g. fluorescence techniques are not feasible due to the "First Law of Directed Evolution" which says "you get what you screen for". The "real" substrates should be converted or at least derivatives that are very close to these substrates have to be used in such systems. Therefore, general analytical methods which allow following the enzyme-catalyzed reaction of any desired substrate are developed.

Another important prerequisite is the availability of methods that allow a high degree of automation. Such methods include high throughput detection systems based on image analysis and software for accurately recognizing hits. In addition, statistical methods and systems for data management are developed to properly set up and evaluate the results of screening programs and to handle large data volumes.

Robust and Adaptive Approaches to Scene and Object Recognition: The goal of this joint project is to investigate new robust and adaptive approaches in the area of object and scene recognition. Object and scene recognition is a necessary requirement for developing truly cognitive systems as well as for the development of advanced and novel multimodal interfaces leading to ambient intelligence. Having a robust object and scene recognition system the following applications will greatly benefit: novel user interfaces which understand human activities, intelligent surveillance, indexing multi-media databases and content analysis of images, autonomous mobile systems and robotics, industrial inspection and robotics, etc. The goal is to develop computer vision based systems that can recognize objects, and in the context of environment perform localization and navigation. The major challenge is to develop systems and methods that can work under realistic unconstrained conditions (i.e., outside the lab). The three partners proposing this project (Center for Machine Perception, Czech Technical University Prague, CMP, Computer Vision Lab, Faculty of Computer and Information Science, University of Ljubljana, CVL, and Institute for Computer Graphics and Vision, Graz University of Technology ICG) have considerable expertise in this area and developed complementary methods and techniques. The goal of the project is to join the efforts and combine the expertise. In particular, we do the following activities:

• Organization of joint workshops and colloquia
• Exchange of PhD. students
• Joint research/joint papers

The aim of this project is the development of an imaging system for an industrial partner. The developed system should survey entrances using video images and register the people passing the entrance. The system has to operate under outdoor conditions (sun light, fog, etc.).

The ultimate limit of today‘s user interfaces lies in the used two-dimensional abstractions that are only effective for their original domain of document-centric work. In contrast, in our everyday world we are not limited to our desktop surface. Information in the real world is perceived and processed in three dimensions, continuously and in real time. A human-computer interface that can capture these properties will be able to render a new level of services to the user, enabling the use of computers for new application domains and for new user populations. This „anywhere“ and „anytime“ requirement for pervasive computing cannot be fulfilled with miniature versions of desktop environments. A new style of user interface, a paradigm shift is needed. Therefore, the core of the proposed research is the following thesis: Augmented reality (AR), i. e., enhancing a user‘s perception of the real world with computer generated graphics and annotations, can make working with computers in 3D as productive as the desktop metaphor in 2D. This thesis is motivated by the fact that AR allows to integrate the whole world into the interface – the world essentially becomes the interface. Therefore users are able to leave their physical desktops and computer desktops to interact with their environment and with other users. The AR platform Studierstube lead by the proposer is world-wide unique in its combination of augmented reality, 3D display and groupware elements. Studierstube, the study room where Faust was searching for enlightenment, describes the philosphy of using the place as a mediator to information and insight. We are currently developing a wearable augmented reality system, which allows the user interface to be in any place, with and for anybody. Within the proposed augmented reality/pervasive computing infrastructure, an environment can be turned into a virtual „ether“ encompassing users that are enabled to interact with the computer through realworld objects. The proposed project work will expand the augmented reality platform Studierstube into a pervasive computing environment built on a variety emerging technologies. A number of promising application areas is selected, for which applications will be developed that try out the new style of interfacing with the computer in practice. Influence

The scanning electron microscope (SEM) is an important tool to examine very small structures. Its large magnification combined with good contrast and large depth of view make it possible to view and characterize microscopic structures in the sub-micron scale. In the recent years, the problem of dense surface reconstruction from multiple SEM images was a research topic on this institute. Reconstruction approaches like shape from stereo and shape from photometric stereo have been evaluated. This work presents a framework for automatic scene reconstruction from three images acquired by a scanning electron microscope. The basic assumption is that the specimen is tilted eucentrically in front of the camera, camera geometry is assumed to be unknown but constant over all views. It is shown that methods for estimating the trifocal tensor as well as modern auto-calibration approaches can be adapted to the imaging conditions in the SEM, and Euclidean scene structure can be retrieved from three uncalibrated views. The performance of the proposed framework is evaluated on synthetic data as well as real images. It is shown that Euclidean scene structure can be retrieved robustly under varying image noise and inaccurate initialization.

Resection is the treatment of choice for patients suffering from liver tumors. Knowledge about involved liver segments, tumor size and topographic relationship of the tumor to vessels is needed for the decision if sufficient liver function capacity is guaranteed after a resection and for detailed planning of a possible resection. The main information sources are cross sectional imaging modalities like CT which deliver 2D images. The radiologist has thus to put all the information of the cross sectional images together in order to provide the surgeons with the needed information about the 3D topology. This process is difficult, tedious and time consuming. Combining the methods of medical computer vision and graphics a liver surgery planning system can be developed that enables a better overview and thus helps unfolding the full potential of surgical methods. Available approaches show that a number of improvements, specially on the fields of automation of segmentation and user friendly visualization are necessary to attain clinical applicability and gain the full acceptance by radiologists and surgeons. The goal of this research project is to develop an experimental environment for the staging of liver operations. Special efforts will be put on two issues. First, a fully automated segmentation of the liver, its vessels and tumors will be studied. Second, the environment for the interactive, cooperative visualization of the medical sensor data, the extracted anatomical structures, and for the use of tools to assess the best surgical approach will be developed and assessed. After development, the approaches for segmentation/partitioning, visualization and interactive resection will undergo a careful validation procedure.

In the process of packaging high quality apples the proper placement of the fruit in the tray is critical (i.e. the most appealing side should face towards the customer, all stalks should face into the same direction). Currently this sorting is done manually, at an additional cost of about 36 Euro (500 Schillings) per ton of apples. The automation of this process should result in a significant cost reduction. The first step of the packaging process rotates the apple so that its symmetry axis is vertical with either stalk or bloom facing upwards. This is done mechanically. The next step determines the position of the most appealing side of the apple (i.e. the horizontal angle) and decides whether stalk or bloom is facing upwards (the vertical angle). This is done by digital image processing. The apple is rotated by 360 degrees. A digital camera captures a sequence of images at different orientations and the image processing software measures fruit quality and vertical orientation in real-time. In the last step, a robot brings the apple to its ideal position and puts it into the tray.

Partnerlist:

Schuster Messtechnik

During an exhibition time of 5 months the whole internet as seen from one internet node should be visualized.

The visitors can interact with the scene in the following ways: free 3D navigation, guided navigation (following the node links) and virtually send email (the user will fly behind an email package following a route from sender node to the recipient node).

Since the number of expected nodes exceeds the limit of rendering performance multiresolution analysis must be employed. A spatially immersive display is used to let the visitors experience the wideness of the internet.

Tools will be developed for the reconstruction of a currently excavated archaeological site for different periods throughout the time of its occupation. This includes the development of 3D acquisition systems that can measure a range of objects of different dimensions to produce accurate and realistic looking 3D models and of tools for virtual reconstruction, documentation and classification of objects ranging from pottery sherds to entire urban building complexes. The project will provide archaeologists with the tools to support the analysis and restoration of their finds. The virtual artefacts and buildings together with the related information will be stored in a multimedia database with appropriate searching and querying functionality. 3D visualisation technologies will be developed for the interactive presentation of archaeological results in museums and via the internet, to the broad public as well as to experts. To provide Europe with an archaeological lead.

Partner:

Departement Elektrotechniek ESAT-PSI, Katholieke Universiteit Leuven

Building reconstruction, IFSAR, man-made objects, multiple view fusion","SAR imagery has begun to get consideration as a source for three-dimensional building models. High resolutions at pixel sizes of 30cm to 10cm and single pass interferometry support the geometric reconstruction of various small man-made objects. Our work aims at the detection and reconstruction of the structure of building ensembles from high resolution inerferometric and slant range SAR data. To fully automate the building reconstruction procedure we use a phenomenological approach, using layover and shadow boundaries together with edge information and intelligent combinations of measurements from all IFSAR data sources available.

The purpose of the project is to develop a powerful tool for the investigation of the deformation and fracture behaviour of materials. It is an interdisciplinary project combining the fields of materials science and computer science. The aim of the project related to computer science, more precisely to computer vision is: To develop a system for the automatic reconstruction of surfaces from scanning electron stereophotograms, integrating various reconstruction techniques (shape from stereo, photometric stereo etc.). The system shall be especially appropriate for analyzing fracture surfaces and for recording the local deformation fields during in-situ loading experiments in the scanning electron microscope.

**Partnerlist:**

"Erich-Schmid-Institute for Solid State Physics, Austria":http://www.oeaw.ac.at/esi/

Um die Durchführung von numerischen Berechnungen basierend auf objektivierten, vollständigen und problemorientierten Daten zu ermöglichen, ist die Entwicklung von verbesserten Dokumentationsmethoden erforderlich. Diese sollen durch dreidimensionale Modellierung und Darstellung des Gebirges erreicht werden. Mittels stereographischer Aufnahmemethoden sowie dem Einsatz von entsprechenden Datenbanksystemen sollen die für die Erstellung von numerischen Modellen zur Beschreibung der angetroffenen geologisch-geotechnischen Verhältnisse erforderlichen Daten erfaßt, verwaltet und für weitere Bearbeitungen zur Verfügung gestellt werden.

Partnerlist:

Institut für Felsmechanik und Tunnelbau (220)

The Digital Interactive Venus Atlas (DIVA) is a remote sensing information system for a catalog of SAR radar image data from the Magellan mission to the planet Venus (1990--1994). The system consists of a Java based user interface accessible via the WWW, an image pyramid covering almost the entire Venusian surface, a remote interface to a data archive and a metadata catalog to retrieve quicklooks and information about available data sets.

DIVA makes intensive use of Java's multi-threading capabilities to avoid the performance penalties of traditional WWW-based interfaces. Its state of the art user interface combined with a scaleable, clickable image map for interactively formulating spatial queries provides fast and easy access to the image catalog in a platform-independent way.

In our everyday world we are not limited to our computer desktop. Information in the real world is perceived and processed in three dimensions, continuously and in real time. A human-computer interface that can capture these properties will be able to deliver new computer applications and services anywhere and anytime. Augmented reality (AR), which enhances a user's perception of the real world with computer generated information, can turn the everyday world into a user interface for ubiquitous computing applications. STUDIERSTUBE is a leading framework for the development of mobile, collaborative and ubiquitous AR applications.

The project aims at the creation of a computer image analysis workstation for clinical application. The workstation will receive Epiluminescence Microscopy digital images of pigmented skin lesions and information pertaining to a patient. This input will be converted into a proposed diagnosis of a lesion as malignant, benign or dysplastic, with an associated error probability.

Uncalibrated stereo, or more precisely the recovery of the epipolar geometry and the projective structure of a real world object purely from the knowledge of homologue points, is an active field of research. The application is mainly found in robot vision as one has to deal with a permanently changing image acquiring situation not allowing an absolute calibration. The aim of the project is to apply this technique for stationary cameras for which an absolute calibration is hard to perform or even impossible (for example a scanning electron microscope). The core of the system is the integration of physics based vision and shape from stereo in the uncalibrated case. For this purpose robust shape from stereo techniques are developed. The physics based vision algorithms are especially adapted to the situation in the scanning electron microscope. The project is strongly related to the project "Application of Image Processing in Materials Science"

Interactive multimedia, based on computer networks, may be of great benefit for many disciplines. That is in specific true for remote sensing (earth observation), where daily a large amount of image-data is collected over the entire globe. By multimedia, the most recent satellite data and associated meta-information is available to every potential user.

Within this project, key services and tools are implemented, in order to keep the Austrian user community up-to-date and to support them on the fast developing international market.

Another goal is performed in cooperation with the "Environmental Planning" division at Austrian Research Centers / Seibersdorf: By merging multisensoral (radar/optical) and multitemporal data, new methods for monitoring agricultural sites are being developed.

The goal of the VIRGO network is to coordinate European research and postgraduate training activities that address the development of intelligent robotic systems able to navigate in unknown and possibly dynamic environments. This goal will be achieved through a framework which enhances RTD activities in European laboratories, already established in the aforementioned scientific area. Specifically alternative environment representations based on visual information will be studied and methods to process these representations and use them to control the motion of a robot will be developed. Environment learning issues will also be considered, aiming at autonomous acquisition of the discriminating environment features. The task of ICG in the network is to coordinate research in Fusion.

Partnerlist: List of partners maintained by project coordinator

The series production of parts with a small to medium number of units requires a fast and inexpensive adaption to new parts. A pure hardware solution, as it is common for example in the motor industry, is contrary to the above requirement. The goal of this project is to develop a vision driven, flexible and automatic assembling unit. In order to solve this demanding task, the separation into three, from the viewpoint of vision almost independent steps is proposed. The first step is to isolate one part from the pile. This task is generally referred as binpicking. Where the task of step one was to detect one plane among many parts of one class the task now is to determine the exact position of one known part (step 2). And the third step is the surveillance of the assembling itself.

Large image data sets are typical for remote sensing. A unique such dataset was generated by the radar sensor of NASA's Magellan probe covering planet Venus. Processing this data set is challenging because of its size, algorithmic complexity and a world-wide demand for accessing the data.

We design and prototype a system where users submit tasks within a GUI based entirely on common Internet services. Then, the broker queries the Distributed Method Base and schedules the jobs across available back-end computers minimizing a cost function. The back-end may be a conglomerate of computers of any size, accessed through the queuing system DQS and connected to the broker via CORBA.

Our design is fairly general and may be applied to any other tasks of managing large data sets.

Partnerlist:

European Centre for Parallel Computing at Vienna (VCPC)

Radar interferometry is capable of yielding extremely high accuracies in observing horizontal and vertical motion even from space platforms, since it is capable of measurements in the sub-wavelength domain (at the cm to mm-level). This information is collected over the entire image, so that also the actual spatial distribution of height differences or horizontal motion is being observed. A radar system uses bursts of microwave energy to scan the terrain on the ground and produces a backscatter image of the reflected microwave energy. In so called "repeat-pass" radar interferometry, two takes obtained from orbits close together are required. The received signals of a certain location in both images have different phases. This is used to compute the direction towards the object point (or its velocity in between). Most crucial step of the required processing chain is the phase unwrapping which is to solve the ambiguity of the differential phase numbers. This exploitation is based on certain a priori assumptions and stochastic processing.

During the last fifty years the occurrence of melanoma has increased dramatically. Whereas in the thirties of this century one out of 100 000 people living in the United States or Europe suffered from melanoma, this number has risen to 15 out of 100 000 nowadays and is still increasing.

Because of the curability of melanoma by surgical excision in the early stages of tumor development, early tumor recognition is of utmost importance. During the last few years a significant improvement in early tumor recognition has been achieved by using the so-called epiluminescence microscopy (ELM). This technique uses oil immersion to render the epidermis translucent, thus giving insight into sub-surface structures of the skin which are not visible otherwise.

This project deals with the computerized analysis of digitized ELM-images of pigmented skin lesions, the final goal being the automatic classification of the lesions as benign or malignant (i.e. melanoma).

The analysis is carried out in several steps: The first step is the segmentation process, in which the skin lesion is extracted from the background in the ELM-image.

In the next step, a set of parameters which contain information about the malignity of the skin lesion are determined. The choice of the appropriate parameters is based on information found in medical literature, as well as on personal discussions with experienced dermatologists.

Finally, a classification based on the previously extracted parameters is carried out. The evaluated results show that the initial efforts already provide the correct result in 86% of all cases examined thus far.

In many applications of the scanning electron microscope a user needs to know the three dimensional shape of the examined object. The conventional way to obtain such a digital elevation model (DEM) is the manual evaluation of stereoscopic images by photogrammetric methods. To get around such a time consuming procedure a prototype system for automated digital surface reconstruction and analysis was developed in cooperation with the Erich-Schmid-Institut (Leoben).

As part of a coordinated CD-I and computer-based public representation of the Austrian National Library Vienna, we created a 3-dimensional phototextured model of the library's Great Hall.

Imagine in a vehicle based scanner system producing image stripes of facades under motion distortion caused by the roughness of the street.

This system allows the continuous recording of the facades enabling us to retrieve the photo texture and calculating a refined geometric model of the assumed building box using 3 stereo pairs.

The aim was to visualize an office room (situated at the ICG) as realistic as possible.
The 4 basic steps were: modelling the office room using AutoCAD; radiometric modelling of the room (i.e. determine color, specularity and roughness of all surfaces); add light to the scene (natural and/or artificial); raytrace the whole scene using RADIANCE

In this project we describe the problems which arise in realistic renderings of existing objects on computers. The complete process from the generation of the scene to computer generated images will be explained. This involves the extraction of geometry, surface properties and illumination as well as the rendering using global illumination models and the tone reproduction in the displaying step on output devices.

Current approaches of image understanding and object recognition are generally limited to very restricted types of scenes, objects and scenarios. Thus, the resulting implemented techniques are limited and provide poor performances when they are tested outside their original context. The ambitious goal of the Micro Image Understanding Environment (µUE) project is to demonstrate that it is feasible to specify and create a small and useful image understanding/object recognition system. In order to avoid the common mistake of constantly reimplementing the same code, our system will try to optimize the research efforts productivity by massively relying on market products and image understanding research standards. That's why we think that the software development efforts will be limited. In this way our system can be considered as small.

The main goal of this project is to develop a new system for information fusion in image understanding which can deal with selection and combination of uncertain visual information. The system is active in the sense that at each step of processing it can select and request the most promising next source of information. Thus, it will be a powerful new mechanism for the efficient control of an image understanding system.

Occlusion plays an important role in recovering relevant structure from a dynamic scene. In the region near the edges it causes a change of visual information that is implicitly modeled by projective relations between two viewpoints in a stereo camera setting. In the case of uncalibrated images, a new contribution is to apply the framework of plane homographies in projective space under epipolar constraints to define a rule base for edge classification.

The goal of the project is to create a portable system for scanner evaluation based on test targets, algorithms and procedures which give us adequate tools for testing the performance of various types of scanners, but in particular high performance film scanners (e.g. photogrammetric scanners, graphic art scanners). This evaluation has to be done in an objective manner which is independent of the operator of the device. Different measurement and analysis methods by which specific elements of a scanners performance can be quantified have been found and implemented in our scanner evaluation system. The system gives us the possibility to perform automated but also interactive scanner evaluation. Issues of concern are geometric resolution, geometric accuracy, radiometric resolution and range, colour reproduction, scanning speed and sustained throughput.