News
- I am co-organiser of the ninth VOT Visual Object Tracking challenge and workshop at ICCV’21
- I am co-organiser of the twentieth IEEE International Workshop on Performance Evaluation of Tracking and Surveillance PETS at AVSS’21
- I am serving 2021 as
A list and ranking of computer vision journals and conferences.
Research
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.
Teaching
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:
- Visual Object Tracking
- Visual Person Detection
- Deep Learning Object Detection in Satellite Video
- Detection, Segmentation and Tracking of Cells
- Self-supervised (internal) visual learning
- Combining Deep Learning and Probabilistic Filtering for Tracking
- Using Julia to implement vision algorithms
- VOT challenge participation
- Implementing spatiotemporal CNNs for CPU and not for GPU using neural magic
Students (ongoing work)
- Jonas Auer, Robust Object Detection under Occlusion, Master’s thesis
- Michael Kammerhofer, Empirical Analysis of Foveanet’s generalisability, Bachelor’s thesis
Past Students
- Èric Quintana Aguasca, Tracking by Detection Using Yolo and a Kalman Filter, Bachelor’s thesis, 2021 – Erasmus cooperation with Xavier Giro, UPC Barcelona
- Caroline Magg, Deep Image Prior for Microscopy Images, Praktika, 2021
- Gustav Häger, Learning Visual Perception for Autonomous Systems, Opponent in his Doctoral Defense at Linköping University, June, 2021
- Julian Wagner, Detecting Vehicles in Satellite Video Using Deep Networks, Master’s thesis, 2020
- Manuel Danner, Semantic Segmentation of Image Sequences Using a Spatio-Temporal U-Net, Master’s thesis, Code, 2020 – now at Trayport
- Sergi Deutsch, Siamese networks for visual tracking, Bachelor’s thesis, Code, 2019 – Erasmus cooperation with Xavier Giro, UPC Barcelona – now at i2CAT Foundation
- Julian Wagner, Detecting Moving Vehicles in Satellite Videos, Praktika, 2018
- Manuel Danner, Cell Segmentation with the U-Net Convolutional Network, Praktika, 2018
- Georg Nebehay, A Deformable Parts Model for One-Shot Object Tracking, Doctoral thesis, Code, 2016 – now at Locatee, Zurich
- Georg Sperl, Person Classification with Convolutional Neural Networks, Master’s thesis, 2016 – now at IST Austria
- Clemens Korner, Object Tracking using Projective Invariants, Bachelor’s thesis, 2016
- Timo Kropp, Matching Omnidirectional Images in Indoor Environments, Master’s thesis, 2013 – now at MeisterLabs, Munich
- Georg Nebehay, Robust Object Tracking Based on Tracking-Learning-Detection, Master’s thesis, 2012
- Michael Boula, Time sync. of networked cameras with non- overlapping views using TTA, Bachelor’s thesis, 2011
- Timo Kropp, Visualiserung von Trajektorien live in Microsoft Bing Maps, Bachelor’s thesis, 2009
Invited Talks & Lectures (recently)
- The importance of motion perception in visual recognition, IARAI, Vienna, August, 2021
- Learning Visual Perception for Autonomous Systems, Linköping University, Sweden, June, 2021
- Vehicle Detection in Satellite Video, Helmholtz AI Virtual Conference, April, 2021
- Vehicle Detection in Satellite Video, Planet Labs, Berlin, March, 2021
- 30/09-01/10/2020, Second professional course on Deep Learning together with the OVE Academy (canceled)
- 5/06/2020, UPC Barcelona (postponed)
- 28/05/2020, DSS DSAI Tech Talk, Vehicle Detection in Satellite Video
- 10-11/03/2020, Professional course on Deep Learning together with the OVE Academy
- 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
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’16-21 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 for more details.