Navigation

You are here: Home / Research

Research Projects

by year:  all years   2016   2015   2014   2013   2012   2011   2010   2009   2008   2007   2006   2005   2004   2003   2002   2001   2000   1999   1998   1997   prior projects
by contact:  all contacts
Show Contacts
Maurer Michael Poier Georg Saffari Amir Schulter Samuel Seichter Hartmut Voglreiter Philip Zeisl Bernhard Lex Alexander Armagan Anil Arth Clemens Barakonyi István Bauer Joachim Beichel Reinhard Bischof Horst Boechat Pedro Bornik Alexander Reitinger Bernhard Bauer Christian Gruber Lukas Kainz Bernhard Pirchheim Christian Daftry Shreyansh Wagner Daniel Kalkofen Denis Dokter Mark Donoser Michael Elbischger Pierre Ferstl David Fleck Philipp Fraundorfer Friedrich Reitmayr Gerhard Geymayer Thomas Godec Martin Munda Gottfried Grabner Markus Grubert Jens Hammernik Kerstin Hartl Andreas Daniel Hauswiesner Stefan Riemenschneider Hayko Grabner Helmut Hirzer Martin Hofer Manuel Holzmann Thomas Hoppe Christof Irschara Arnold Isop Werner Alexander Jampour Mahdi Newman Joseph Junghanns Sebastian Khan Inayatullah Kalkusch Michael Karner Konrad Kenzel Michael Kerbl Bernhard Khlebnikov Rostislav Klatzer Teresa Klaus Andreas Klopschitz Manfred Kluckner Stefan Knöbelreiter Patrick Köstinger Martin Kontschieder Peter Pirker Katrin Kruijff Ernst Langlotz Tobias Langs Georg Leberl Franz Lee Felix Leistner Christian Leitner Raimund Lenz Martin Lepetit Vincent Mauthner Thomas Meixner Philipp Mendez Erick Grabner Michael Heber Markus Mohr Peter Mostegel Christian Mühl Judith Mulloni Alessandro Ober Sandra Oberweger Markus Opitz Michael Pacher Georg Partl Christian Pflugfelder Roman Pinz Axel Roth Peter M. Pock Thomas Poier Georg Possegger Horst Pestana Puerta Jesús Puff Werner Pan Qi Ram Surinder Ranftl René Grasset Raphael Recky Michal Regenbrecht Holger Reinbacher Christian Riegler Gernot Rüther Matthias Rumpler Markus Santner Jakob Sareika Markus Schall Gerhard Schenk Fabian Schmalstieg Dieter Schulz Hans-Jörg Shekhovtsov Alexander Sormann Mario Steinberger Markus Stern Darko Sternig Sabine Storer Markus Straka Matthias Streit Marc Tatzgern Markus Nguyen Thanh Nguyen Thuy Trobin Werner Unger Markus Uray Martina Urschler Martin Veas Eduardo Ventura Jonathan Waldner Manuela Waltner Georg Wendel Andreas Werlberger Manuel Winter Martin Wohlhart Paul Zach Christopher Zebedin Lukas Zollmann Stefanie
by keyword:  all keywords
Show Keywords
3D Computer Vision 3D reconstruction Aerial Vision Augmented Reality Augmented Video Best Paper Award best paper award Biometrics C++ Caleydo Classification Computational Photography Computer Graphics Computer Vision Computer Vison Convex Optimization Coordinate transformations Dataset acquisition detection Discrete Optimization Experimental Robotics face Fingerprint Forensic Image Analysis Frozen Georeferencing GPU GUI HOG Human Computer Interaction Human Machine Interaction Image Labelling Image restoration Industrial Applications Information Visualization integral imaging Interaction Interaction Design Light estimation Machine Learning Medical computer vision Medical Image Analysis Medical Visualization Mixed Reality Mobile computing Mobile phone Model Multi-Display Environments Multiple Perspectives Multithreading Non-convex optimization Object detection Object recognition Object reconstruction Object Tracking Offline On-Line Learning Paid Thesis Perception Photorealism Pose Estimation Procedural Modeling Robotics Segmentation Shape analysis shape from focus Simulation SLAM Software Projects Solar Physics Structure from Motion Surveillance SVM Symmetry Tracking Fusion Tracking, Action Recognition User Interfaces Variational Methods View Management Virtual Copy Virtual Reality Virtual reality and augmented reality Visual Tracking Visualization
per page:    all   50   20
  Title     Abstract     Start     End  
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
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
IMPPACT - Image-based Multi-scale Physiological Planning for Ablation Cancer Treatment
(details)

IMPPACT is a European research project, which develops an intervention planning system for Radiofrequency Ablation of malignant liver tumours. TU Graz is dealing with medical visualization and augmented reality in the project. Problem or Context Radiofrequency Ablation (RFA) is a minimally invasive form to treat cancer without open surgery, by placing a needle inside the malignancy and destroying it through intensive heating. Though the advantages of this approach are obvious, the intervention is currently hard to plan, almost impossible to monitor or assess, and therefore is not the first choice for treatment. Project IMPPACT will develop a physiological model of the liver and simulate the RFA intervention result, accounting for patient specific physiological factors.

  • Closing gaps in the understanding of particular aspects of the RFA treatment by multi-scale studies on cells and animals
  • Transforming microscopic findings and into macroscopic equations
  • Extending the long-established bio-heat equation to incorporate multiple scales
  • Validating results at multiple levels
  • Cross checking validity for human physiology by comparison to images from ongoing patient treatment
  • Visual comparison of simulation and treatment results gathered in animal studies and during patient treatment
  • Extensive validation together with a user-centred software design approach guarantee suitability of the solution for clinical practice

Mathematical modelling together with experimental validation lead to a patient specific intervention planning system. read more Expected Results & Impacts IMPPACT will be modelling a physiological organ including the metabolism and patient specific tissue properties. This alone is a huge step forward as compared to the state-of-the-art intervention planning systems that do not address this issue.

The IPS will allow prediction of treatment results on a patient specific base. It will therefore bring down the risk of local recurrences and eliminate the nowadays so common repeated treatments of the same tumour, making RFA an as effective treatment as resection.

2008 2011
CranUS - Cranial Ultrasound Simulation
(details)

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.

2007 2008
Virtual Liver Surgery Planning
(details)

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.

2001 2003

[Powered by Plone]