VIS- und Uni-Logo
Blindenversion home uni uni suche suche sitemap sitemap kontakt kontakt
unilogo Universität Stuttgart
Home | Institut | Lehre | Forschung | Aktuelles | Optionen | Unterpunkte
Institut für Visualisierung und Interaktive Systeme

Prof. Dr. Gunther Heidemann
 


   Referierte Journalartikel     
  1. S. Klenk, J. Dippon, P. Fritz, G. Heidemann.  Interactive survival analysis with the OCDM system: From development to application.   Information Systems Frontiers,  2009.
  2. G. Heidemann.  Region Saliency as a Measure for Colour Segmentation Stability.   Image and Vision Computing  26:211--227, 2008.
  3. G. Heidemann, H. Bekel, I. Bax, H. Ritter.  Interactive Online Learning.   Pattern Recognition and Image Analysis,  17(1): 146-152, 2007.
  4. C. Bauckhage, S. Wachsmuth, M. Hanheide, S. Wrede, G.Sagerer, G. Heidemann, H. Ritter.  The visual active memory perspective on integrated recognition systems.   Image and Vision Computing,  26:211-225, 2008.
  5. G. Heidemann.  The Principal Components of Natural Images Revisited.   IEEE Trans. PAMI,   28(5): 822-826, 2006.
  6. I. Bax, G. Heidemann, H. Ritter.   A Hierarchical Feed-Forward Network for Object Detection Tasks.   J. Opt. Eng.,  45(6), 2006.
  7. G. Heidemann.  The Long-Range Saliency of Edge- and Corner-Based Salient Points.   IEEE Trans. on Image Processing,  14(11): 1701-1706, 2005.
  8. H. Bekel, G. Heidemann, H. Ritter.   Interactive Image Data Labeling Using Self-Organizing Maps in an Augmented Reality Scenario.   Neural Networks,  18(5/6): 566-574, 2005.
  9. G. Heidemann.  Unsupervised image categorization.   Image and Vision Computing,  23: 861-876, 2005.
  10. G. Heidemann.  Focus-of-Attention from Local Color Symmetries.   IEEE Trans. PAMI,   26(7): 817-830, 2004.
  11. G. Heidemann.  Combining Spatial and Colour Information for Content Based Image Retrieval.   Computer Vision and Image Understanding,  94(1-3): 234--270, 2004.
  12. G. Heidemann, R. Rae, H. Bekel, I. Bax, H. Ritter.  Integrating context-free and context-dependent attentional mechanisms for gestural object reference.   Machine Vision and Applications,  16(1): 64-73, 2004.
  13. G. Heidemann, H. Ritter.  Learning to Recognise Objects and Situations to Control a Robot End-Effector.   Künstliche Intelligenz,  2: 24-29, 2003.
  14. G. Heidemann, H. Ritter.  Efficient Vector Quantization Using the WTA-rule with Activity Equalization.   Neural Processing Letters,  13(1): 17-30, 2001.
  15. E. Braun, G. Heidemann, H. Ritter, G. Sagerer.   A multi-directional multiple-path recognition scheme for complex objects applied to the domain of a wooden toy kit.   Pattern Recognition Letters,  20(11-13): 1085-1091, 1999.
  16. C. Bahlmann, G. Heidemann, H. Ritter.   Artificial neural networks for automated quality control of textile seams.   Pattern Recognition,  32: 1049-1060, 1999.
  17. C. Bauckhage, G. A. Fink, G. Heidemann, N. Jungclaus, F.Kummert, S. Posch, H. Ritter, G. Sagerer, D. Schlüter.  Towards an Image Understanding Architecture for a Situated Artificial Communicator.   Pattern Recognition and Image Analysis,  9(4): 542-548, 1999.
  18. G. Heidemann, N. Jungclaus, F. Kummert, G. Sagerer, H. Ritter.   Ein hybrides Bildanalyse-System für einen künstlichen Kommunikator.   Kognitionswissenschaften,  8(3): 101-107, 1999.
  19. G. Heidemann, M. Bode, H.-G. Purwins.   Fronts between Hopf- and Turing-type domains in a two-component reaction-diffusion system.   Physics Letters A,  177:225-230, 1993.

   Buchkapitel     
  1. G. Heidemann, H. Ritter.  Data Compression &mdash a Generic Principle of Pattern Recognition?  B. Encarnação et al., Editor,  VISGRAPH-VISAPP 2008,  Lecture Notes in Communicatios in Computer and Information Acience. Springer, 2009. To appear.
  2. G. Heidemann, H. Ritter.  Making Robots Learn to See.  In R. Kühn et al., Editor,  Perspectives on Adaptivity and Learning,  pages 285-309. Springer, 2003.
  3. G. Heidemann.  Semi-Automatic Acquisition of Visual Knowledge.  In J. Geldermann, H. Rommelfanger, Editor,  Einsatz von Fuzzy Sets, Neuronalen Netzen und Künstlicher Intelligenz in industrieller Produktion und Umweltforschung,  Nummer 725 in Fortschritt-Berichte VDI, pages 1-14. VDI-Verlag, Reihe 10 Informatik / Kommunikation, Edition, 2003.

   Referierte Konferenzbeiträge     
  1. J. Imo, S.Klenk, G.Heidemann.  Interactive Feature Visualization for Image Retrieval.    Proc. 19th Conf. of Pattern Recognition ICPR 08,  Tampa, Florida, USA, 2008. IEEE. CFP08182.
  2. B. Kaiser, G. Heidemann.  Qualitative Analysis of Spatio-Temporal Event Detectors.    Proc. 19th Conf. of Pattern Recognition ICPR 08,  Tampa, Florida, USA, 2008. IEEE. CFP08182.
  3. G. Heidemann, K. Ritter.  On the Contribution of Compression to Visual Pattern Recognition.    Proc. 3rd Int'l Conf. on Comp. Vision Theory and Applications,  volumes 2, pages 83-89, Funchal, Madeira - Portugal, 2008.Best Paper Award
  4. B. Kaiser, G. Heidemann.  A Spatio-Temporal Extension of SUSAN-Filter.    Proc. 18th Int. Conf. on Arifical Neural Networks ICANN 08  volume I, pages 867-876, Prag, 2008.
  5. S.Klenk, G.Heidemann.  A new method for principal component analysis of high-dimensional data using compressive sensing..    Proc. 4th Int. Conf. on Data Mining DMIN 08,  pages 191-196, Las Vegas, USA, 2008.
  6. G. Heidemann, K. Ritter.  Compression for Visual Pattern Recognition.    Proc. 3rd IEEE Int'l Symp. on Communnications, Control and Signal Processing,  pages 1520-1523, Malta, 2008. IEEE
  7. J. Imo, S. Klenk, G.Heidemann.  Visualization of Color and Texture Features.    Proc. 1th ACM Int. Workshop on Super-Visualization IWSV 08,  Kos, Greece, 2008. To appear.
  8. B. Kaiser, G. Heidemann.   Context-Free Detection of Events.    Proc. 15th Scandinavian Conference on Image Analysis SCIA 07,  Aalborg,Denmark,accepted, to appear 2007.
  9. S. Klenk, G.Heidemann.  Visual Analytics for Image Retrieval.  In R. Mikut and M. Reischl, editors  Proc. IEEE Int. Conf. on Robotics and Automation ICRA 07, pages 1517-1522, Rome, 2007,  Kos, Greece, 2008. To appear.
  10. M. Schöpfer, G. Heidemann, H. Ritter.  Acquisition and Application of a Tactile Database.    Proc. IEEE Int. Conf. on Robotics and Automation ICRA 07  , Rome, Italy, accepted, to appear 2007.
  11. G. Heidemann.  Color Symmetry for Interest Point Detection.    12. Workshop Farbbildverarbeitung,  pages 5-13, Ilmenau, Germany, 2006.
  12. I. Bax, G. Heidemann, H. Ritter.  A hierarchical feedforward network for object detection tasks.    Proc. SPIE,  volume 5818, pages 144-152, Orlando, USA, 2005.
  13. H. Bekel, G. Heidemann, H. Ritter.  SOM Based Image Data Structuring in an Augmented Reality Scenario.    Proc. IEEE Int. Joint Conf. on Neural Networks IJCNN 05,  pages 3278-3283, Montreal, Canada, 2005.
  14. I. Bax, G. Heidemann, H. Ritter.  Face Detection and Identification Using a Hierarchical Feed-forward Recognition Architecture.    Proc. IEEE Int. Joint Conf. on Neural Networks IJCNN 05,  pages 1675-1680,Montreal, Canada, 2005.
  15. I. Bax, G. Heidemann, H. Ritter.  Using non-negative sparse profiles in a hierarchical feature extraction network.    Proc. 9th IAPR Conf. on Machine Vision Applications MVA 05,  pages 464--467,Tsukuba Science City, Japan, 2005.
  16. G. Heidemann, I. Bax, H. Bekel, C. Bauckhage, S. Wachsmuth, G. Fink, A. Pinz, H. Ritter, G. Sagerer.  Multimodal interaction in an augmented reality scenario.    Proc. Int. Conf. on Multimodal Interfaces ICMI 04  , pages 53-60, State College, PA, USA, ACM Press,2004.
  17. G. Heidemann, M. Schöpfer.   Dynamic Tactile Sensing for Object Identification.    Proc. IEEE Int. Conf. on Robotics and Automation ICRA 04,  pages 813-818, New Orleans, USA, 2004.
  18. G. Heidemann, H. Bekel, I. Bax, A. Saalbach.  Hand Gesture Recognition: Self-Organising Maps as a Graphical User Interface for the Partitioning of Large Training Data Sets.    Proc. Int. Conf. on Pattern Recognition ICPR 04,  volume 4, pages 487-490, Cambridge, UK, 2004. IEEE-CS.
  19. H. Bekel, I. Bax, G. Heidemann, H. Ritter.  Adaptive Computer Vision: Online Learning for Object Recognition.    Proc. DAGM 04,  pages 447-454, Tübingen, Germany, 2004.
  20. G. Heidemann, H. Bekel, I. Bax, H. Ritter.  Interactive Online Learning.  7th Int. Conf. on Pattern Recognition and Image Analysis PRIA 04,  pages 44-48, St. Petersburg, Russian Fed., 2004.
  21. G. Heidemann, R. Rae, H. Bekel, I. Bax, H. Ritter.   Integrating context-free and context-dependent attentional mechanisms for gestural object reference.    Proc. IEEE Int. Conf. on Cognitive Vision Systems ICVS 03,  pages 22-33, Graz, Austria, 2003.
  22. I. Bax, H. Bekel, G. Heidemann.  Recognition of gestural object reference with auditory feedback.    Proc. Int. Conf. on Neural Networks ICANN 03,  pages 425-432, Istanbul, Turkey, 2003.
  23. G. Heidemann, A. Saalbach, H. Ritter.  Semi-automatic acquisition and labeling of image data using SOMs.    Proc. 11th European Symp. on Artificial Neural Networks ESANN 03,  pages 503-508, Bruges,Belgium, 2003.
  24. A. Saalbach, G. Heidemann, H. Ritter.  Representing Object Manifolds by Parametrized SOMs.    Proc. Int. Conf. on Pattern Recognition ICPR 02,  pages 184-187, Quebec City, Canada, 2002, IEEE-CS.
  25. A. Saalbach, G. Heidemann, H. Ritter.  Parametrized SOMs for Object Recognition and Pose Estimation.    Proc. Int. Joint Conf. on Artificial Neural Networks ICANN 02,  pages 902-907, Madrid, Spain, 2002.
  26. G. Heidemann, H. Ritter.   Combining Gestural and Contact Information for Visual Guidance of Multi-Finger Grasps.    In Proc. 10th European Symp. on Artificial Neural Networks ESANN 02,  pages 301-306, Bruges, Belgium, 2002.
  27. J. Steil, G. Heidemann, J. Jockusch, R. Rae, N.Jungclaus, H. Ritter.   Guiding Attention for Grasping Tasks by Gestural Instruction: The GRAVIS-Robot Architecture.    Proc. IEEE Int. Conf. on Intelligent Robots and Systems IROS 01,  Maui, Hawaii, USA, pages 1570-1577, 2001.
  28. G. Heidemann, H. Ritter.  Visual Checking of Grasping Positions of a Three-Fingered Robot Hand.    Proc. Int. Conf. on Neural Networks ICANN 01,  pages 891-898, Vienna, Austria, 2001.
  29. G. Sagerer, C. Bauckhage, E. Braun, G. Heidemann, F. Kummert, H. Ritter, D. Schlüter.  Integrating Recognition Paradigms in a Multiple-path Architecture.    Proc. Int. Conf. on Advances in Pattern Recognition ICAPR 01,  pages 202-211, Rio de Janeiro, Brazil, 2001.
  30. G. Heidemann.  A Multi-Purpose Visual Classification System.    Proc. 7th Fuzzy Days,  pages 305--312, Dortmund, Germany, 2001.
  31. G. Heidemann, D. Lücke, H. Ritter.   A System for Various Visual Classification Tasks Based on Neural Networks.    Proc. 15th Int. Conf. on Pattern
      Recognition ICPR 2000,      Barcelona, Spain, volume I, pages 9-12., 2000. IEEE-CS.
  32. G. Heidemann, D. Lücke, H. Ritter.  Segmentation of Partially Occluded Objects by Local Classification.    Proc IEEE-INNS-ENNS Int. Joint Conf. on Neural Networks IJCNN 2000,  volume I, pages 152-157, Como, Italy, 2000. IEEE.
  33. G. Heidemann, H. Ritter.   Combining Multiple Neural Nets for Visual Feature Selection and Classification.    Proc. 9th Int. Conf. on Artificial Neural Networks ICANN 99,  pages 365-370, Edinburgh, UK, 1999.
  34. G. Heidemann, H. Ritter.   Hybride Objekterkennung: Konstruktion einer Zwischenrepräsentation für den Übergang von holistischer zu semantischer Erkennung.    Proc. 4. Fachtagung der Gesellschaft für Kognitionswissenschaft KogWiss 99,  pages 290-291, Bielefeld, Germany, 1999.
  35. G. Heidemann, T. W. Nattkemper, H. Ritter.  Farbe und Symmetrie für die datengetriebene Generierung prägnanter Fokuspunkte.    Proc. 4. Workshop Farbbildverarbeitung,  pages 65-71, Koblenz, Germany, 1998.
  36. G. Heidemann, H. Ritter.   A Neural 3-D Object Recognition Architecture Using Optimized Gabor Filters.    Proc. 13th Int. Conf. on Pattern Recognition ICPR 96,  volume IV, pages  70-74, Vienna, Austria, 1996. IEEE-CS.
  37. G. Heidemann, F. Kummert, H. Ritter, G. Sagerer.   A hybrid object recognition architecture.    Proc. Int'l Conf. on Artificial Neural Networks ICANN 96,  pages 305-310, Bochum, Germany, 1996.
  38. G. Heidemann, H. Ritter.   A neural recognition architecture for composed objects.    Proc. 18. DAGM-Symp.,  pages 475-482, Heidelberg, Germany, 1996.
  39. G. Heidemann, T. Nattkemper, G. Menkhaus, H. Ritter.  Blicksteuerung durch präattentive Fokussierungspunkte.    Proc. in Artificial Intelligence,  pages 109-116, Hamburg, Germany, 996.
  40. R. Moratz, G. Heidemann, S. Posch, H. Ritter, G. Sagerer.  Representing procedural knowledge for semantic networks using neural nets.    Proc. 9th Scandinavian Conf. on Image Analysis SCIA 95,  pages 819-828,  Uppsala, Sweden, 1995.

   Ausgewählte Technische Berichte     
  1. I. Bax, H. Bekel, G. Heidemann, H. Ritter.  Visual Learning of Object Models and Motion Behaviours.  Technical report, Bielefeld Univ., Neuroinformatics Group, 2004.
  2. G. Heidemann, H. Ritter.  Objekterkennung mit neuronalen Netzen.  Technical Report 96/2, SFB 360, Univ. Bielefeld, 1996.

   Habilitation     
  1. G. Heidemann.  Interest Point Detection: Algorithms, Evaluation, and Application.  Habilitation, Univ. Bielefeld, Technische Fakultät, 2005.

   Dissertation     
  1. G. Heidemann.  Ein flexibel einsetzbares Objekterkennungssystem auf der Basis neuronaler Netze. Dissertation, Univ. Bielefeld, Technische Fakultät,  1998. Erschienen in Infix, DISKI 190.

   Diplomarbeit
  
  1. G. Heidemann.  Konkurrenz oszillierender und strukturierter Domänen in einem Aktivator-Inhibitor System.  Diplomarbeit, Univ. Karlsruhe, 1992.
Letzte Änderung März 05 2009 (gh) | © Universität Stuttgart | Impressum