Thomas Heitzinger is a research assistant and PhD student at the Computer Vision Lab (CVL) at TU Wien. His research interests are 3D scene understanding and human behavior analysis using depth sensors and other non-RGB based visual sensors, as well as computer vision in the absence of strong textural information. At the moment he is working on the project KIIS which aims to support security personnel and reduce the number of safety-related incidents in Austrian prisons by using a 3D sensor to register critical movement and behavioral patterns in real time.
Education
| 2019 | MSc. TU Wien, Logic and Computation. Thesis title: High Accuracy Semantic Segmentation for Motor Vehicles. Thesis advisor: Martin Kampel |
| 2018 | MSc. TU Wien, Technical Mathematics. Thesis title: Complex scaling for one-dimensional resonance problems in inhomogeneous exterior domains. Thesis advisor: Lothar Nannen |
| 2016 | BSc. TU Wien, Technical Mathematics. Thesis title: Radial Perfectly Matched Layer. Thesis advisor: Lothar Nannen |
Publications
- T. Heitzinger and M. Kampel “A Fast Unified System for 3D Object Detection and Tracking”, published at the International Conference on Computer Vision (ICCV), October 2023, Paris, France
- C. Stippel and T. Heitzinger and R. Sterzinger and M. Kampel “Closing the Gap in Human Behavior Analysis: A Pipeline for Synthesizing Trimodal Data”, published at the PeRConAI Workshop, March 2024, Biarritz, France
- C. Stippel and T. Heitzinger and R. Sterzinger and M. Kampel “From RGB to Depth and Thermal: Mapping between Modalities to Alleviate Data Scarcity“, published at the OAGM Workshop, October 2023, Vienna, Austria
- C. Stippel and T. Heitzinger and M. Kampel “A Trimodal Dataset: RGB, Thermal, and Depth for Human Segmentation and Action Recognition“, published at the German Conference on Pattern Recognition (GCPR), September 2023, Heidelberg, Germany
- T. Heitzinger and M. Wödlinger and D. Stork “Artist-specific style transfer for deep net semantic segmentation of paintings: The value of large corpora of surrogate artworks“, in Electronic Imaging, January 2022
- T. Heitzinger and D. Stork “Improving semantic segmentation of fine art images using photographs rendered in a style learned from artworks”, in Electronic Imaging, January 2022
- T. Heitzinger and M. Kampel “A Foundation for 3D Human Behavior Detection in Privacy-Sensitive Domains”,
in 32nd British Machine Vision Conference (BMVC), November 2021 - T. Heitzinger and M. Kampel “IPT: A Dataset for Identity Preserved Tracking in Closed Domains”, in Proceedings of the 25th International Conference on Pattern Recognition (ICPR), January 2021, Milan, Italy
- T. Heitzinger and M. Kampel “Highly Accurate Binary Image Segmentation for Cars”, in Proceedings of the ARW & OAGM Workshop, September 2020, Graz, Austria
Awards & Achievements
- CVL Mario Kart Champion 2022 & Runner-up 2023
- Best Paper Award, ARW & OAGM Workshop 2020, September 2020