Navigation and service

Susanne Wenzel

Dr. Susanne Wenzel

Scientific Coordinator

Academic degree: Dipl.-Ing. Geodesy, University of Bonn

Research group Big Data Analytics

Scientific Coordination:

I am coordinating FZJ's Helmholtz AI Local Unit at INM-1 and Jülich Supercomputing Centre (JSC) and its interaction and cooperation with the Helmholtz wide AI platform Helmholtz AI.
Closely related to that, I am also coordinating the new Helmholtz International BigBrain Analytics and Learning Laboratory (HIBALL), a collaboration between McGill university (MNI, BIC) and INM-1 that will reinforce utilization and co-development of the latest AI and high-performance computing technologies for building highly detailed 3D brain models, in close collaboration with CIFAR and MILA in Canada, and Helmholtz AI .

Research:

In my research I dealt with semantic image interpretation focusing on the combination of bottom-up image interpretation and high-level image interpretation methods from top-down.

Methods and tools:

  • Pattern recognition and image interpretation
  • Machine Learning
  • Markov Marked Point Processes
  • Deep Learning
  • Hierarchical image features
  • Symmetries and repeated structures in images

Publications before I joined INM-1

Thesis

S. Wenzel (2016): High-Level Facade Image Interpretation using Marked Point Processes
University of Bonn

Journal Publications

S. Wenzel, D. Bulatov (2019): ‘Simultaneous Chain-Forming and Generalization of Road Networks’, Photogrammetric Engineering & Remote Sensing, Volume 85, Number 1, January 2019, pp. 19-28(10). DOI: 10.14358/PERS.85.1.19

L. Drees, R. Roscher, and S. Wenzel (2018): ’Archetypal Analysis for Sparse Representation based Hyperspectral Sub-Pixel Quantification’, Photogrammetric Engineering & Remote Sensing, Volume 84, Number 5, May 2018, pp. 279-286(8). DOI: 10.14358/PERS.84.5.279

S. Wenzel and W. Förstner (2013): ’Finding Poly-Curves of Straight Line and Ellipse Segments in Images’, Photogrammetrie, Fernerkundung, Geoinformation (PFG), vol. 4, pp. 297-308, doi:10.1127/1432-8364/2013/0178

S. Wenzel, M. Drauschke, and W. Förstner (2008): ’Detection of repeated structures in facade images’, Pattern Recognition and Image Analysis, vol. 18, iss. 3, pp. 406-411. doi:10.1134/S1054661808030073

Proceedings

K. Franz, R. Roscher, A. Milioto, S. Wenzel, and J. Kusche (2018): ’Ocean Eddy Identification and Tracking using Neural Networks’, IEEE International Geoscience and Remote Sensing Symposium (IGARSS), DOI: 10.1109/IGARSS.2018.8519261

D. Bulatov, S. Wenzel, G. Häufel, and J. Meidow (2017): ’Chain-Wise Generalization of Road Nerworks Using Model Selection’, ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences, pp. 59-66. doi:10.5194/isprs-annals-IV-1-W1-59-2017

A. Bettge, R. Roscher, and S. Wenzel (2017): ’Deep self-taught learning for remote sensing image classification’, Proc. Conference on Big Data from Space. DOI: 10.2760/383579.

A. Braakmann-Folgmann, R. Roscher, S. Wenzel, B. Uebbing, and J. Kusche (2017): ’Sea level anomaly prediction using recurrent neural networks’, Proc. of the Conference on Big Data from Space. DOI: 10.2760/383579.

R. Roscher, L. Drees, and S. Wenzel (2017): ’Sparse representation-based archetypal graphs for spectral clustering’, IEEE International Geoscience and Remote Sensing Symposium (IGARSS). DOI: 10.1109/IGARSS.2017.8127425

R. Roscher, S. Wenzel, and B. Waske (2016): ’Discriminative Archetypal Self-taught Learning for Multispectral Landcover Classification’, Proc. of 9th IAPR Workshop on Pattern Recogniton in Remote Sensing (PRRS). DOI: 10.1109/PRRS.2016.7867022

T. Schubert, S. Wenzel, R. Roscher, and C. Stachniss (2016): ’Investigation of Latent Traces Using Infrared Reflectance Hyperspectral Imaging’, ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences, pp. 97-102. doi:10.5194/isprs-annals-III-7-97-2016

S. Wenzel and W. Förstner (2016): ’Facade Interpretation Using a Marked Point Process’, ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences, pp. 363-370. doi:10.5194/isprs-annals-III-3-363-2016

S. Wenzel and W. Förstner (2012): ’Learning a compositional representation for facade object categorization’, ISPRS Annals of Photogrammetry, Remote Sensing and the Spatial Information Sciences; Proc. of 22nd Congress of the International Society for Photogrammetry and Remote Sensing (ISPRS), pp. 197-202. doi:10.5194/isprsannals-I-3-197-2012

Address

Institute of Neuroscience and Medicine (INM-1)
Forschungszentrum Jülich
52425 Jülich

Contact

Phone: +49 2461 61-96306
Fax: +49 2461 61-3483
email: s.wenzel@fz-juelich.de