Roman Pflugfelder




+43 1 58801 – 193103


HE 02 24

Office hours

By appointment




I offer supervision for Bachelor’s/Master’s thesis and Praktika. I am looking for students interested in Visual Motion Analysis, Tracking, Detection, Segmentation, Visual Learning, Multi-View Geometry and Non-Traditional Cameras. Topics I am offering:

Students (ongoing work)

  • Manuel Danner, Semantic Segmentation of Image Sequences Using a Spatio-Temporal U-Net, Master’s thesis
  • Julian Wagner, Detecting Vehicles in Satellite Video Using Deep Networks, Master’s thesis

Past Students

Invited Talks & Lectures (recently)

  • 10-11/03/2020, Professional course on Deep Learning together with the OVE Academy (upcoming)
  • 10/04/2019, Introducing Visual Object Tracking From Classical Views to Machine Learning, JKU Linz (Video)
  • Deep Learning / U-Net for Cell Segmentation Lecture together with Manuel Danner, Molecular Devices, Salzburg, March, 2019
  • Introducing Visual Object Tracking From Classical Views to Machine Learning, SUSTech, Shenzhen, December, 2018
  • Video Analyse und 3D Sensoren, Siemens, Vienna, April, 2018
  • Visual single and general object tracking: Where are we today?, Embedded Computer Vision Workshop, Boston, US, June, 2015


My research seeks to combine advances in (multi-view) geometry, optics, statistical decision theory and machine learning, estimation, information and complexity theory, programming, computing and sensing  as well as aspects of neuroscience and cognitive psychology. My aim is to gain (new theoretical) insight into visual learning and inference in complex dynamical systems and to design new practical algorithms for (non-traditional) cameras and potentially new computational systems in a variety of applications.

Benchmarking Tracking

In 2012, I initiated the Visual Object Tracking Challenge (VOT) and since then I have been co-organising annual challenges and workshops at ICCV and ECCV with Matej Kristan, Ales Leonardis, Jiri Matas and Michael Felsberg. VOT is de facto the international community benchmark in the field of visual tracking. Important results of our work are A-R measures for quantifying short-term tracking performance in terms of accuracy and robustness and the discovery of correlation filters as superior approach for tracking. More information can be found on our webpage. VOT is also part of the benchmark initiative for all things video.

Short Bio

Roman Pflugfelder is Scientist at the AIT Austrian Institute of Technology and lecturer at TU Wien. He received in 2002 a MSc degree in Informatics at TU Wien and in 2008 a PhD in Telematics at the TU Graz, Austria. In 2001, he was academic visitor at the Queensland University of Technology, Australia. His research focuses on visual motion analysis, tracking, recognition, and visual learning applied to automated video surveillance. He aims to combine sciences and theories in novel ways to gain theoretical insights into learning and inference in complex dynamical systems and to develop practical algorithms and computing systems. Roman contributed with 60+ papers and patents to research fields such as camera calibration, object detection, object tracking, event recognition where he received awareness of media as well as several awards and grants for his scientific achievements. Roman is also senior project manager at AIT where he has led cooperations among universities, companies and governmental institutions. Roman co-organised the Visual Object Tracking Challenges VOT’13-14 and VOT’16-19 and was program chair of AVSS’15. Currently he is steering committee member of AVSS. He is regular reviewer for major computer vision conferences and journals.

Please, see my CV and my publication list for more details.