The Image Group – University of Copenhagen

The Image Group
Homepage of Kim Steenstrup Pedersen

Kim Steenstrup Pedersen

Kim Steenstrup Pedersen, Associate Professor (Lektor)

Affiliations: Image Section
  Department of computer science, University of Copenhagen
  E-science center
  Space science center
Email: kimstp@di.ku.dk
Office: Room 0.08 (Ground floor)
  Sigurdsgade 41, DK-2100 Copenhagen, Denmark
See also: Official home page
  Google Scholar profile
  LinkedIn profile
  ORCiD profile
  ReSearcher.cc profile

 

Biography

Kim Steenstrup Pedersen received a M.Sc. degree in 1999 and a Ph.D. degree in 2003 both in computer science from DIKU, Department of Computer Science, University of Copenhagen, Denmark and he also holds a B.Sc. degree in physics from the University of Copenhagen. During his Ph.D. studies he spent half a year in 2001 at Division of Applied Mathematics, Brown University, Rhode Island, USA. After his Ph.D. he was briefly employed as an assistant research professor at DIKU. From spring 2003 throughout 2006 he was assistant professor at the IT University of Copenhagen, Denmark. He currently holds a position as associate professor at DIKU, Department of Computer Science, University of Copenhagen. Presently (from November 2009), he also holds the position of Deputy Head of Department for Teaching at Department of Computer Science, University of Copenhagen. His primary research interests include topics from computer vision and image analysis, especially scale-space theories, natural image statistics, stochastic image models, and image features.

Selected current research interests:

Recent Publications

  • Kim Steenstrup Pedersen, Kristoffer Stensbo-Smidt, Andrew Zirm, and Christian Igel.
    Shape Index Descriptors Applied to Texture-Based Galaxy Analysis.
    In Proceedings of International Conference on Computer Vision (ICCV 2013), 2013.
  • Kristoffer Stensbo-Smidt, Christian Igel, Andrew Zirm, and Kim Steenstrup Pedersen.
    Nearest Neighbour Regression Outperforms Model-based Prediction of Specific Star Formation Rate.
    In Proceedings of IEEE Big Data 2013 Workshop on Scalable Machine Learning, 2013.
  • Cristina Manfredotti, Kim Steenstrup Pedersen, Howard J. Hamilton, Sandra Zilles
    Learning Models of Activities Involving Interacting Objects.
    In Advances in Intelligent Data Analysis XII, 12th International Symposium, IDA 2013, London, UK, October 17-19, 2013, Proceedings (IDA 2013), volume 8207 of Lecture Notes in Computer Science, 2013.
  • Anders Boesen Lindbo Larsen, Sune Darkner, Anders Lindbjerg Dahl and Kim Steenstrup Pedersen.
    Jet-Based Local Image Descriptors. [PDF]
    In Proceedings of European Conference on Computer Vision (ECCV), volume 7574 of Lecture Notes in Computer Science, pages 638-650. Springer Berlin / Heidelberg, 2012.
  • Søren Hauberg, Francois Lauze, and Kim Steenstrup Pedersen.
    Unscented Kalman Filtering on Riemannian Manifolds.
    Journal of Mathematical Imaging and Vision, 46(1): 103--120, 2013.
    http://dx.doi.org/10.1007/s10851-012-0372-9.
  • Henrik Aanæs, Anders Lindbjerg Dahl, and Kim Steenstrup Pedersen.
    Interesting interest points: A comparative study of interest point performance on a unique data set.
    International Journal of Computer Vision, 97(1):18-35, 2012.
    http://dx.doi.org/10.1007/s11263-011-0473-8.
  • Søren Hauberg, Stefan Sommer, and Kim Steenstrup Pedersen.
    Natural metrics and least-committed priors for articulated tracking.
    Image and Vision Computing, 30(6-7):453-461, June 2012.
    http://dx.doi.org/10.1016/j.imavis.2011.11.009.
  • Søren Hauberg and Kim Steenstrup Pedersen.
    Spatial Measures between Human Poses for Classification and Understanding.
    In Articulated Motion and Deformable Objects (AMDO), volume 7378 of Lecture Notes in Computer Science, pages 26-36. Springer Berlin / Heidelberg, 2012.
  • Søren Hauberg and Kim Steenstrup Pedersen.
    Predicting articulated human motion from spatial processes.
    International Journal of Computer Vision, 94(3):317-334, 2011.
  • Anders Lindbjerg Dahl, Henrik Aanæs, and Kim Steenstrup Pedersen.
    Finding the best feature detector-descriptor combination.
    In Electronic proceedings of 3DIMPVT 2011, 2011.
  • Søren Hauberg and Kim Steenstrup Pedersen.
    Data-driven importance distributions for articulated tracking.
    In Proceedings of EMMCVPR, volume 6819 of Lecture Notes in Computer Science, pages 287-299. SpringerLink Springer Berlin / Heidelberg, 2011.
  • Søren Hauberg and Kim Steenstrup Pedersen.
    Stick it! articulated tracking using spatial rigid object priors.
    In ACCV 2010, volume LNCS 6494 of Lecture Notes in Computer Science, pages 758-769. Springer, Heidelberg, 2011.
  • Søren Hauberg and Kim Steenstrup Pedersen.
    A physically natural metric for human motion and the associated brownian motion model.
    In Abstract at 1st IEEE Workshop on Kernels and Distances for Computer Vision (ICCV workshop), 2011.
  • Anders Boesen Lindbo Larsen, Søren Hauberg, and Kim Steenstrup Pedersen.
    Unscented kalman filtering for articulated human tracking.
    In Proceedings of SCIA 2011, volume 6688 of Lecture Notes in Computer Science, pages 228-237. Springer, 2011.
  • Peter Mysling, Søren Hauberg, and Kim Steenstrup Pedersen.
    An empirical study on the performance of spectral manifold learning techniques.
    In Proceedings of ICANN, volume 6791 of Lecture Notes in Computer Science, pages 347-354. SpringerLink Springer Berlin / Heidelberg, 2011.
For more publications see my publications list.

Ph.D. students

Present: Past:

Supervision of Post Doc. researchers

Present:
  • Cristina Elena Manfredotti: Relational models for tracking and evaluation of physiotherapeutic exercises. March 2011 - August 2012.
Past:
  • Jérôme Lapuyade-Lahorgue: Human motion modelling with long range dependent stochastic processes. ERCIM Post Doc. fellowship. Nov. 2008 - Sept. 2009
  • Anne Cuzol: Image inpainting. VISIONTRAIN Post Doc. Jan. 2007 - Aug. 2007

Research projects

Current and future courses

Graduate: Bachelor:
  • Object Oriented Programming and Design, Q2, 2007
Project supervision: I currently supervise projects on topics within the fields of image analysis as well as computer vision as well as applications of machine learning mainly within image analysis, e-science related problems, and computer science. Examples of projects include:
  • Articulated figure tracking (Human motion modeling and tracking)
  • Interest point detectors and descriptors
  • Modeling of activation patterns in neuron cell networks
  • Space Science related topics such as: Automated analysis of Laser Induced Breakdown Spectroscopy (LIBS)
  • Web page classification and inference of page relationships