Photo of Michael Felsberg

Michael Felsberg

Professor, Head of Division

My research covers a wide range of topics within artificial visual systems (AVS): three-dimensional computer vision, computational imaging, object detection, tracking, and recognition, and robot vision and autonomous systems.

The design of artificial visual systems, (AVS), has its roots in the modelling of the human visual system (HVS); an extremely challenging task that generations of researchers have attempted with limited success.

Vision is a very natural capability and it is commonly accepted that about 80% of what we perceive is vision-based. Vision’s highly intuitive nature makes it difficult for us to understand the myriad of problems associated with designing AVS, in contrast to sophisticated analytic tasks such as playing chess.Foto: Kristoffer Öfjäll

Thus AVS became a widely underestimated scientific problem, maybe one of the most underestimated problems of the past decades.

Many AI researchers believed that the real challenges were symbolic and analytic problems and visual perception was just a simple sub-problem, to be dealt with in a summer project, which obviously failed.

The truth is that computers are better than humans at playing chess, but even a small child has better generic vision capabilities than any artificial system.

My research aims at improving AVS capabilities substantially, driven by an HVS-inspired approach, as AVS are supposed to coexist with – and therefore predict actions of – humans.

 

Michael Felsberg - Highest ranked AI researcher in Sweden, Vinnova AI report

Download my CV

Quick Facts

Scientific Merits (selection)


Over 20 000 citations, h-index 47, i10-index 126.
2020 CVPR-WS Perception Beyond the Visible Spectrum, keynote, Virtual.
2020 ISCMI, keynote, Virtual.
2021 CVPR-WS Robust Video Scene Understanding, invited speaker, Virtual.

Awards (selection)


2015 Tracking challenge winner, OpenCV, U.S..
2016 Best paper award, ICPR, Mexico.
2018 Highest ranked AI researcher in Sweden, Vinnova AI report, Sweden.
2021 Best paper award, VISAPP, Vienna.
2021 Honorable Mention, DAGM GCPR, Germany

Positions of Trust (selection)


2018 Vice-Head of Department, Electrical Engineering.
2020 WASP Executive Committee, University Representative.
2021 WASP Area Cluster Leader, Machine Learning, Deep Learning and other AI.

Selected Publications

Cover of publication ''
Bertil Grelsson, Michael Felsberg, Folke Isaksson (2016)

Journal of Field Robotics , Vol.33 , s.967-993 Continue to DOI

Cover of publication ''
Michael Felsberg, Kristoffer Öfjäll, Reiner Lenz (2015)

Frontiers in Robotics and AI , Vol.2 Continue to DOI

Cover of publication ''
Martin Danelljan, Gustav Häger, Fahad Shahbaz Khan, Michael Felsberg (2015)

Proceedings of the International Conference in Computer Vision (ICCV), 2015 , s.4310-4318 Continue to DOI

More Publications

Arvi Jonnarth, Jie Zhao, Michael Felsberg,  Learning Coverage Paths in Unknown Environments with Deep Reinforcement Learning, Proceedings of the 41st International Conference on Machine Learning, Ruslan Salakhutdinov, Zico Kolter, Katherine Heller, Adrian Weller, Nuria Oliver, Jonathan Scarlett, Felix Berkenkamp (eds.), Proceedings of Machine Learning Research, pp. 22491-22508, PMLR (2024)

Arvi Jonnarth, Ola Johansson, Michael Felsberg, Sim-to-Real Transfer of Deep Reinforcement Learning Agents for Online Coverage Path Planning (2024)  https://arxiv.org/abs/2406.04920

Arvi Jonnarth, Yushan Zhang, Michael Felsberg,  High-fidelity Pseudo-labels for Boosting Weakly-Supervised Segmentation, 2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 999-1008, Institute of Electrical and Electronics Engineers (IEEE) (2024)  https://doi.org/10.1109/WACV57701.2024.00105  https://arxiv.org/abs/2304.02621

Ioannis Athanasiadis, Shashi Nagarajan, Fredrik Lindsten, Michael Felsberg, Prior Learning in Introspective VAEs (2024)  https://arxiv.org/abs/2408.13805

Jie Zhao, Johan Edstedt, Michael Felsberg, Dong Wang, Huchuan Lu,  Leveraging the Power of Data Augmentation for Transformer-based Tracking, 2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 6455-6464, Institute of Electrical and Electronics Engineers (IEEE) (2024)  https://doi.org/10.1109/wacv57701.2024.00634

News

Two men and a woman talk in front of a screen

Machine learning can give the climate a chance

Machine learning can help us discover new patterns and better tackle the climate crisis. Researchers from all over the world meet at Linköping University with the goal of finding and deepening collaborations in this area.

The supercomputer Berzelius photographed with fisheye lens.

Swedish AI research gets more muscle

The supercomputer Berzelius was inaugurated in the spring of 2021, and was then Sweden's fastest supercomputer for AI. Yet, more power is needed to meet the needs of Swedish AI research.

Portrait of Michael Felsberg with closed eyes.

Human vision – a challenge for AI

Achieving diversity in human vision is one of the major challenges for AI research. In the vast majority of cases, we are better than machines at understanding the world around us. But machines are catching up – slowly but surely.

Michael Felsberg, professor

Michael Felsberg: Deep learning led to a gold rush

“We have been teaching deep learning in both undergraduate and postgraduate courses for several years", says Michael Felsberg, one of Sweden’s best AI researchers.

Goutam Bhat

A computer algorithm to recognise and follow objects

Master's graduate Goutam Bhat has been awarded the Christer Gilén Scholarship for 2019 in the field of statistics and machine learning. The scholarship recognises his work in computer vision.

Photo from the Piraya

Finding boat locations using images

In his doctoral thesis, Bertil Grelsson shows that it is perfectly possible to navigate at sea and in the air with the aid of images. As long as it’s not too misty. The methods provide an important component in safe and robust navigation.

Research within WASP

Research Computer Vision

Staff at CVL

About the Division

About the Department