Research Projects
- Show Keywords
- 3D Computer Vision 3D reconstruction Aerial Vision Augmented Reality Augmented Video Best Paper Award Biometrics Caleydo Computational Photography Computer Graphics Computer Vision Convex Optimization Coordinate transformations detection face Fingerprint Georeferencing GPU GUI HOG Human Computer Interaction Image Labelling Industrial Applications Information Visualization integral imaging Interaction Interaction Design Machine Learning Medical computer vision Medical Visualization Mixed Reality Mobile computing Mobile phone Model Multi-Display Environments Multiple Perspectives Object detection Object recognition Object reconstruction Object Tracking On-Line Learning Robotics Segmentation Shape analysis shape from focus SLAM Software Projects Structure from Motion Surveillance SVM Symmetry Tracking Fusion Tracking, Action Recognition User Interfaces Variational Methods Virtual reality and augmented reality Visual Tracking Visualization
| Title | Abstract |
Start
|
End |
|---|---|---|---|
|
Diagnostik der Tumorheterogenität – ein neuer Steuerfaktor für die Therapie des Dickdarmkarzinoms?
(details) |
Das Kolonkarzinom ist weltweit eine der häufigsten Krebserkrankungen, die trotz Fortschritte in der Behandlung nach Ausbildung von Metastasen fast immer zum Tod führt. Gemäß internationalen Standards ist derzeit die pathohistologische Untersuchung entscheidend für das therapeutische Vorgehen. Für Patienten in fortgeschrittenen Tumorstadien wurden kürzlich Therapien verfügbar, die auf den Mutationsstatus des Tumors ausgerichtet sind, jedoch eine mögliche Tumorheterogenität nicht berücksichtigen. Derzeit nicht detektierte Tumorklone werden für das oft fehlende Therapieansprechen und die Tumorprogression verantwortlich gemacht. Das beantragte Projekt soll durch Anwendung neuer sensorischer Verfahren zur kosteneffizienten und verlässlichen Bestimmung der genetischen Diversität von Dickdarmkarzinomen beitragen. Mittels statistischer Verfahren und bioinformatischer Analyse der genetischen Profile werden die Häufigkeit sowie die prognostische Bedeutung der Tumorheterogenität für das biologische Verhalten der Tumore sowie ihr Ansprechen auf spezifische onkologische Therapien ermittelt. Durch spezielle, an der TUG entwickelte Visualisierungstechniken wird die erhobene Datenfülle für Pathologen und klinische Onkologen verständlich und verwertbar gemacht. Eine umfassende genetische Tumoranalyse setzt das vollinhaltliche Einverständnis des Patienten voraus, welches untrennbar mit dem Verständnis und der Zustimmung zu den hierzu verwendeten Methoden verbunden ist. Ein weiteres Projektziel ist daher die Untersuchung von Erwartungen und Hoffnungen aber auch von Vorbehalten bzw. Befürchtungen, die in die Beratung und Aufklärung des Patienten Eingang finden sollen und die die unterschiedlichen Einstellungen der Patienten zu den diagnostischen Verfahren berücksichtigen. Diese neuen Diagnoseverfahren werden ein Ansprechen auf eine Therapie wesentlich gezielter voraussagen können als die derzeitigen Methoden, den Patienten Nebenwirkungen unwirksamer Medikamente ersparen und damit nicht zuletzt zu einer Kostenreduktion im Gesundheitssystem beitragen. | 2012 | 2014 |
|
Caleydoplex- Information Exploration in Teams
(details) |
Critical decisions involving a lot of data are rarely made by a single person, but are rather discussed and evaluated by a team of experts. Examples are doctors deciding for treatment of severe illness, emergency services having to react to ongoing crises, or engineers collaborating to make technical decisions concerning expensive products. These activities can be assisted by information visualization tools. However, traditional information visualization rarely considers the collaborative nature of data analysis tasks. The foundation of our research proposal is the extension of a multiple view visualization system to a multi-display environment. Multiple view visualization shows data in different representations and thereby accommodates for different knowledge backgrounds and user preferences. Multi-display environments turn unused wall and table spaces into interactive surfaces using off-the-shelf projection technology and integrate private workstations smoothly into this shared interactive workspace. Our research aim is the design and creation of a co-located collaborative information visualization workspace dealing with two principal challenges: display space management and collaborative interaction techniques. Intelligent display space management adopts information visualizations and placement of views automatically to the physical display properties and supports the users interacting with the environment. Combined with visual linking of related data entities distributed across the environment, it will help to establish a common knowledge ground. Collaborative interaction techniques are required to organize such a rich, but potentially complex environment. We will investigate high-level activity support for typical tasks in shared information workspaces and how users can maintain awareness of each other’s activities. The proposed research benefits from two ongoing projects at Graz University of Technology: Deskotheque delivers the basic technology necessary for collaborative work in multi-display environments, while Caleydo, a visualization project from the biomedical domain, provides an excellent use case, including the necessary experts willing to collaborate in studies. Using these frameworks, we plan to conduct several usability studies, with prototypes of different levels of sophistication. This research is part of the project Caleydo. |
2011 | 2014 |
|
Managed Volume Processing (MVP)
(details) |
Volumetric data is very common in medicine, geology or engineering, but the high complexity in data and algorithms has prevented widespread use of volume graphics. Recently, however, 3D image processing and visualization algorithms have been parallelized and ported to graphics processing units (GPUs). This proposal is concerned with new ways of designing volume graphics algorithms for the GPU that can interactively cope with these huge problems by better utilization of GPU capacity. Unfortunately, only certain parts of common image or volume processing algorithms can be mapped to the standard GPU stream processing model. For most real-world problems, writing programs for this architecture is a tedious task. As a result, most algorithms use the available processing power only for small subtasks -- the number crunching in inner loops. For example, direct volume rendering (DVR) methods send rays into a volumetric object, accumulate intensities, divide rays into sub-rays, scatter rays in materials and/or extract certain features. All GPU implementations of DVR use one processing unit for one pixel, regardless of whether the pixel will require very complex calculations or not. This strategy frequently leads to strong load imbalances. A particular problem of interactive applications such as volume graphics is that they are not traditional number crunching tasks, which only require optimal computational throughput, while having relaxed or no constraints concerning latency. On the contrary, interactive applications demand meeting real-time deadlines to ensure interactive response. This is a classical real-time resource scheduling problem. It can only be achieved by adaptive algorithms that rely on complex flow control and memory management decisions during the parallel execution. Both is currently only available on the CPU, which allows access to privileged mode through the operating system. On the GPU, components for high level scheduling involving latency hiding and memory management are missing or inaccessible. The desired full utilization of the GPU is very difficult to achieve for complex graphics algorithms with real-time demands. Building a toolset that allows harvesting the full GPU power for a general class of real-time volume graphics algorithms is the main goal of this proposal. We propose a managed volume processing system that incorporates the missing components. Its key modules are a task model, a workload scheduler with real-time capabilities and a virtual memory management system executed in tandem on the GPU and CPU. We will rely on the most recent hardware developments and use OpenCL as the standardized interface to access them. | 2011 | 2014 |
|
inGeneious - Holistic Visualization of Biomolecular and Clinical Data
(details) |
Ziel des Projekts inGeneious ist es, Visualisierungsmethoden und Work-Flows zu entwickeln, die Biologen und Medizinern bei der Analyse biomolekulare Daten im Kontext von klinischen Faktoren sowie biologischen Prozesse unterstützen. Die Berücksichtigung dieser Faktoren bei der Analyse von zum Beispiel Genexpressionsdaten ist entscheidend, da auf diese Weise Rückschlüsse über Zusammenhänge von genetischer Predisposition und Krankheitsverlauf gewonnen werden können. Zwei zentrale Forschungsfragen sind Gegenstand des inGeneious-Projektes. Zunächst soll eine ganzheitliche Betrachtungsweise der drei Datenräume durch Multiple-View-Verfahren und effizientes visuelles Verbinden von Informationen ermöglicht werden. Darauf aufbauend soll eine vergleichende Analyse divergierender Gruppen durch neue, vergleichende Visualisierungsmethoden ermöglicht werden. Experten erhalten damit ein Werkzeug um die immer größer werdende Menge biomolekularer Daten effizient verwenden zu können. Diese Forschungsarbeit wird innerhalb des Projekts Caleydo durchgeführt. |
2009 | 2011 |
|
SMART Vidente - Subsurface Mobile Augmented Reality Technology for Outdoor Infrastructure Workers
(details) |
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. |
2009 | 2011 |
|
MARCUS - Mobile Augmented Reality and Context in Urban Scenarios
(details) |
MARCUS is an exchange program with the Human Interface Technologies Laboratory (Christchurch, NZ) and the University of Otago (Otago, NZ). Its aim is to extend the scope of the research work performed in the EU Integrated Project "IPCity" with researchers in New Zealand. The focus of research will be on how mobile devices can create new types of interactive urban experiences. For example, location specific information overlaid on the real world can be used to aid navigation through cities, in outdoor game play, or for providing user supplied comments at certain sites. |
2008 | 2010 |
|
Ludwig Boltzmann Institut für Klinisch-Forensische Bildgebung
(details) |
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. |
2008 | 2015 |
|
Christian Doppler Laboratory for Handheld Augmented Reality
(details) |
Augmented Reality (AR) combines real and virtual in a single view, putting information right were it belongs - into the real world. AR is still a young research field and hence strongly driven by basic research and experimental methods, while only few successful commercial applications have been deployed. One of the reasons is that past hardware (such as head-mounted displays and Tablet PCs) have not been sufficiently inexpensive and ergonomically satisfactory. Therefore, recent AR research shows a trends towards deploying AR on advanced mobile phones, using the phone camera as video see-through interface for a “magic lens” style of AR. Recent research in the proposer’s group has first the first time established a baseline technology for achieving real-time performance AR on mobile phones, and this development has been meet with great interest from industry. This proposal the logical consequence of this development. It is concerned with extending this research in several directions, in particular making techniques more scalable (sometimes several orders of magnitude), so that realistic real world scenarios interesting for commercial applications can be attacked by industry. Firstly, we want to expand our real-time computer-vision based pose tracking and object recognition techniques. Secondly, we propose to develop realistic AR image synthesis and visualization methods. Thirdly, we suggest an investigation into efficient 3D interaction techniques with and for AR phones. Finally, we suggest the creation of a distributed infrastructure based on Web 2.0 technology for scalable content creation and deployment of geo-referenced AR applications on phones. |
2008 | 2015 |
|
Doctoral Program for the Confluence of Graphics and Vision
(details) |
Computer vision and computer graphics constitute two closely related areas of research: Though both fields rely on the same physical and mathematical principles and on a common set of representations, they mainly differ in how these representations are built. Traditionally these two fields have been treated as separate academic discipline. Exploiting the commonalities between vision and graphics turns out to be a scientifically profitable endeavour. There are many examples of fruitfull combination of graphics and vision, but there is no systematic education of students (especially in Austria). Therefore, the goal of this doctoral program Confluence of Vision and Graphics is to educate highly talented PhD students in this interdisciplinary field and to teach them a common view of this challenging topic from the start. All proposed topics require a significant amount of vision and graphics. The students will be co-supervised jointly by one professor with vision and one professor with graphics expertise. The proposed educational program will ensure that the students will be trained to become future leading scientists, which will face the challenges of research excellence in the interdisciplinary area of graphics and vision, academic leadership, and social competence as a member of a particular research group as well as being a part of the global research network. |
2007 | 2019 |
|
VIPEM - Visual Analytics for Personalized Medicine
(details) |
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. |
2007 | 2009 |
|
POMAR 3D - Position and Orientation Measurement in 3D for Augmented Reality
(details) |
Positionierungs- und Orientierungsmodul für einen Mobilen Augmented Reality- Client zur 3D-Echtzeitvisualisierung unterirdischer Ver- und Entsorgungsinfrastruktur |
2007 | 2008 |
|
Genoptikum - Interactive Biomedical Information Visualization
(details) |
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. |
2007 | 2009 |
|
Deskotheque - Collaborative Interaction in Multi Display Environments
(details) |
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. |
2007 | 2011 |
|
Presenccia - Presence: Research Encompassing Sensory Enhancement, Neurosciense, Cerebral-Computer Interfaces and Applications
(details) |
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. |
2006 | 2009 |
|
IPCity - Interaction and Presence in Urban Environments
(details) |
The research aim of the IPCity project is to investigate analytical and technological approaches to presence in real life settings. Analytically, this includes extending the approaches to presence accounting for the participative and social constitution of presence, the multiplicity and distribution of events in time and space. Technologically, this translates into developing portable environments for on-site configuration, mobile and light-weight mixed reality interfaces with the ambition to weave them into "the fabric of everyday life". Methodologically, this calls for moving "out of the lab" with field trials in real settings, applying a triangulation of disciplines and methods for evaluation. These range from interpretative-ethnographic to quasi-experimental approaches and include cognitive science, social-psychological, and cultural-anthropological disciplines. The vision of the IPCity project is to provide citizens, visitors, as well as professionals involved in city development or the organization of events with a set of technologies that enable them to collaboratively envision, debate emerging developments, experience past and future views or happenings of their local urban environment, discovering new aspects of their city. This includes:
The showcases include urban renewal projects, large scale events, and explorative edutainment and story telling applications. |
2006 | 2010 |
|
Vidente - An Augmented Reality System for Visualisation of Subsurface Utility Networks
(details) |
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 |
2006 | 2008 |
|
GenView - Visualization of Genetic Data
(details) |
This project is concerned with the visualization of Micro Array data using multiple displays and visual data mining techniques. It was the first research activity that led to the project Caleydo. |
2005 | 2006 |
|
CashFlow - A visualization framework for 3D Flow
(details) |
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. |
2005 | 2006 |
|
ARIS*ER - Augmented Reality in Surgery
(details) |
ARIS*ER is a Marie Curie Research Training Network addressing a cross-disciplinary area, critically in need of developing researchers with the understanding of the cross-cutting issues involved in developing tools for Minimally Invasive Therapy. The multidisciplinary consortium, aims at providing training for young researchers through a structured training and knowledge transfer program – that will provide Europe with human resources with knowledge that will lead to better healthcare to citizens in Europe. The particular focus of the research training and joint project will be software that is user-friendly, fast and reliable for the practitioners of minimal invasive therapy (MIT). MIT is a compound of minimally invasive surgery, image guided surgery and interventional radiology. MIT makes use of numerous sources of information including multi-modal images and patient information systems. Intelligent processing of this information comprises a vast pool of knowledge that can aid the operator in his decisions. The ultimate goal of the joint project, which will give the recruited researcher training-by-doing, is to create an Augmented Reality system for interactive image guided therapy providing the clinical user with a new generation of decision support tools. This system will integrate intra-operative and pre-operative image-information and enable the user to see beyond the organ surface to inner structures and pathology. An intuitive human computer interface consisting of 3D display systems, haptics and robotics will hide the underpinning complexity of the decision support tools. Demonstrators will be made aiming at providing a seamless workflow for the clinical user conducting image-guided therapy. |
2005 | 2009 |
|
Indoor Modelling and Tracking
(details) |
Precise indoor localisation is an important issue for Augmented Reality. The two major ingredients necessary to experiment with "location aware" Augmented Reality applications are
The localized device is often held by an individual, allowing applications to interact with the physical environment. Various Augmented Reality setups have been build during this project. Additionally work is shown to answer the question how to accurately and rapidliy survey an indoor environment. Next to manual strategies there automated aproaches of surveying are shown. Furthermore hybrid tracking approaches are demonstrated where heterogeneous tracking sensors are attached to handheld devices (UMPCs, micro PCs). In this context the sensor data is fused, which leads to a seamless tracking experience. |
2004 | 2008 |
