Computer Vision Laboratory
The research at CVL covers a wide range of topics within artificial visual systems (AVS): three-dimensional computer vision, cognitive vision systems, object recognition, image analysis and medical imaging.
The design of 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.
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. Truth is that computers are better than humans in playing chess, but even a small child has better generic vision capabilities than any artificial system. CVL 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.
For more information on our research, see the publications and projects sections of the website. CVL also provides weekly seminars and teaching activities for undergraduate and graduate students, including the possibility for master students to be involved in state of the art research with their master thesis.
'He who loves practice without theory is like the sailor who
boards ship without a rudder and compass and never knows where he may
Leonardo da Vinci (1452-1519)
The paper: "Fast segmentation of sparse 3D point trajectories using group theoretical invariants" by Vasileios Zografos, Reiner Lenz, Erik Ringaby, Michael Felsberg and Klas Nordberg
has been accepted at the Asian Conference on Computer Vision (ACCV 2014), Singapore.
The paper: "Accurate scale estimation for
robust visual tracking" by Martin Danelljan, Gustav Häger, Fahad Khan and Michael Felsberg, (BMVC 2014)
won the VOT challenge 2014
- "Accurate Scale Estimation for Robust Visual Tracking" by Martin Danelljan, Gustav Häger, Fahad Khan and Michael Felsberg
- "Biologically Inspired Online Learning of Visual Autonomous Driving" by Kristoffer Öfjäll and Michael Felsberg
have been accepted at the British Machine Vision Conference (BMVC) 2014, Nottingham, UK.
The paper "Spider-based Stixel Object Segmentation" by F Erbs, A Witte, T Scharwaechter, R Mester, U Franke has been accepted at the Intelligent Vehicles Symposium (IV) 2014, Dearborn, Michigan, USA.Best Paper Award CVPR Workshop on Mobile Vision
The paper "Robust Three-view triangulation done fast" by Johan Hedborg, Andreas Robinson and Michael Felsberg was awarded "The Best Paper" at the Fourth IEEE International Workshop on Mobile Vision. See more hereNew paper accepted at ECCV 2014, Zurich
The paper "Know Your Limits: Accuracy of Long Range Stereoscopic Object Measurements in Practice" by Peter Pinggera, David Pfeiffer, Uwe Franke, and Rudolf Mester has been accepted at the European Computer Vision Conference ECCV 2014.Master Thesis Award to CVL
"Anisotropic Scattered Data Interpolation for Pushbroom Image Rectification" by Erik Ringaby et al. Paper can be accessed here.New paper at ICCP 2014 in Santa Clara, California, USA
"A Virtual Tripod for Hand-held Video Stacking on Smartphones" by Erik Ringaby and Per-Erik Forssén. Paper can be accessed here.Paper Accepted as Oral at CVPR 2014 in Columbus, Ohio, USA
The paper "Adaptive color attributes for real-time tracking" by Martin Danelljan, Fahad Khan, Michael Felsberg and Joost van de Weijer is accepted at CVPR 2014 in Columbus, Ohio, USA. See more here.Paper accepted at SPIE Medical Imaging conference 2014
The paper "Prostate tissue decomposition via DECT using the model based iterative image reconstruction algorithm DIRA" by Alexandr Malusek, Maria Magnusson, Michael Sandborg, Robin Westin and Gudrun Alm Carlsson, have been accepted at SPIE Medical Imaging 2014, 16-20 February 2014, San Diego, California, USA.2013-11-27
Due to too few registered students, we have decided to move the course "Group theoretical methods and their applications" to the Spring term.
Senast uppdaterad: 2014-07-14