TU Wien Informatics

Margrit Gelautz

Ao.Univ.Prof.in Dipl.-Ing. Mag.a rer.nat. Dr.in techn.

Research Focus

Research Areas

  • Stereo Vision, Human Motion, Computer Vision, Motion Analysis, Video Analysis, Assisted/Autonomous Driving, Robotics, 3D TV
Margrit Gelautz

About

I perform research in the field of Computer Vision with a focus on 3D scene reconstruction (especially, stereo analysis), video object segmentation, image matting and motion estimation. Currently, my research interests revolve around the application fields of assisted/autonomous driving and motion studies for human-robot interaction. I am a partner in the TrustRobots Doctoral College (www.trustrobots.eu) and the FWF ConnectingMinds project CaringRobots // RoboticCare (www.caringrobots.eu).

In collaboration with Microsoft Research Cambridge, our group has set up and maintains the alphamatting benchmark (www.alphamatting.com) for the evaluation of image matting algorithms.

Our research activities led to the foundation of the spin-off company emotion3D in 2010.

Role

Note: Due to the rollout of TU Wien’s new publication database, the list below may be slightly outdated. Once APIs for the new database have been released, everything will be up to date again.

2022

  • Camera Pose Estimation using Human Head Pose Estimation / R. Fischer, M. Hödlmoser, M. Gelautz / Talk: 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, Online; 2022-02-06 - 2022-02-08; in: "Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP", SCITEPRESS, 4/Setúbal, Portugal (2022), ISBN: 978-989-758-555-5; 877 - 886

2021

2020

  • Body Language in Affective Human-Robot Interaction / D. Stoeva, M. Gelautz / Talk: ACM/IEEE International Conference on Human-Robot Interaction - HRI Pioneers Worksop 2020, Cambridge, United Kingdom; 2020-03-24 - 2020-03-26; in: "Companion of the 2020 ACM/IEEE International Conference on Human-Robot Interaction", (2020), ISBN: 9781450370578; 606 - 608
  • Objective and Subjective Evaluation of a Multi-Stereo 3D Reconstruction System / C. Kapeller, B. Sespede, M. Nezveda, M. Labschütz, S. Flöry, F. Seitner, M. Gelautz / Talk: IS&T International Symposium on Electronic Imaging - Stereoscopic Displays and Applications, Burlingame, USA; 2020-01-26 - 2020-01-30; in: "Electronic Imaging, Stereoscopic Displays and Applications XXXI", (2020), ISSN: 2470-1173; 138-1 - 138-7
  • A Study on Training Data Selection for Object Detection in Nighttime Traffic Scenes / A. Unger, M. Gelautz, F. Seitner, M. Hödlmoser / Talk: IS&T International Symposium on Electronic Imaging - Autonomous Vehicles and Machines 2020, Burlingame, USA; 2020-01-26 - 2020-01-30; in: "IS&T International Symposium on Electronic Imaging", (2020), 203-1 - 203-6
  • A Tool for Semi-Automatic Ground Truth Annotation of Traffic Videos / F. Groh, D. Schörkhuber, M. Gelautz / Talk: IS&T International Symposium on Electronic Imaging - Autonomous Vehicles and Machines 2020, Burlingame, USA; 2020-01-26 - 2020-01-30; in: "IS&T International Symposium on Electronic Imaging", (2020), 200-1 - 200-7

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

2008

2007

2006

2005

2004

2003

2002

 

Note: Due to the rollout of TU Wien’s new publication database, the list below may be slightly outdated. Once APIs for the new database have been released, everything will be up to date again.

2021

2020

2019

2018

2016

2015

2014

2013

2012

2011

2010

2009

2008

2007

2006

2005

 

  • Shortlisted for VISAPP 2022 Best Student Paper Award (4 shortlisted papers out of 154 registered student papers) - "Camera pose estimation using human head pose estimation", R. Fischer, M. Hödlmoser, and M. Gelautz
    2022 / International Conference on Computer Vision Theory and Applications (VISAPP) 2022 / Portugal / Project
  • Nomination for Austrian State Prize Innovation ECONOVIUS (emotion3D GmbH)
    2012 / Austrian Chamber of Commerce / Austria / Project
  • "MARIO" Award at NAB Show, Las Vegas (emotion3D GmbH)
    2012 / TV Technology / USA / Project
  • Best Paper Award - "Segmentation-based depth propagation in videos", N. Brosch, C. Rhemann and M. Gelautz
    2011 / ÖAGM/AAPR Workshop / Austria / Project
  • Mercur Econovius Prize (emotion3D KG)
    2011 / Vienna Chamber of Commerce / Austria / Project
  • Nomination for "RIZ Genius Ideenpreis" (emotion3D KG)
    2010 / RIZ - Gründeragentur Niederösterreich / Austria
  • U.V. Helava Award - Best Paper Volume 59 (2004) - "A layered stereo matching algorithm using image segmentation and global visibility constraints", M. Bleyer and M. Gelautz
    2008 / International Society for Photogrammetry and Remote Sensing - Elsevier B.V. and Leica Geosystems GIS & Mapping / Netherlands / Website
  • Second place in "Selection of Best FIT-IT Projects (Systems on Chip)" of the Year 2006
    2007 / Austrian Research Promotion Agency (FFG) / Austria / Project
  • FEMtech Expert of the Month (September 07)
    2007 / Federal Ministry for Transport, Innovation and Technology, ÖGUT / Austria / Website
  • Microsoft Research European PhD Scholarship (PI: Margrit Gelautz, PhD student: Christoph Rhemann) - First Austrian Research Group to Win the Scholarship
    2006 / Microsoft Research Cambridge / UK / Website / Project
  • Semifinal IBM Best Student Paper Award and rated among top 10% of conference contributions - "A layered stereo matching algorithm using image segmentation and global visibility constraints", M. Bleyer and M. Gelautz
    2004 / International Conference of Image Processing (ICIP) 2004 / Singapore
  • Max Kade Fellowship of the Austrian Academy of Sciences and Max Kade Foundation, New York, for postdoctoral research stay at Stanford University, USA
    1997 / Austria

Soon, this page will include additional information such as reference projects, activities as journal reviewer and editor, memberships in councils and committees, and other research activities.

Until then, please visit Margrit Gelautz’s research profile in TISS .