Memory consistency validation in a cognitive vision system

Ensuring the consistency of memory content is a key feature of cognitive vision systems. This work presents an approach to deal with functional dependencies of hypotheses stored in a visual active memory. By means of Bayesian networks a probabilistic approach is used to incorporate uncertainty of observations. Furthermore, a measurement to detect inconsistencies in the memory is introduced. The benefit of this validation module as part of an integrated system is shown for the task of visual surveillance in an office scenario.

[1]  Jannik Fritsch,et al.  Vision based recognition of gestures with context , 2003 .

[2]  Paul A. Viola,et al.  Rapid object detection using a boosted cascade of simple features , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[3]  Helge J. Ritter,et al.  Integrating Context-Free and Context-Dependent Attentional Mechanisms for Gestural Object Reference , 2003, ICVS.

[4]  James M. Rehg,et al.  Vision-based speaker detection using Bayesian networks , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[5]  Finn V. Jensen,et al.  Bayesian Networks and Decision Graphs , 2001, Statistics for Engineering and Information Science.

[6]  Marek R. Ogiela,et al.  Cognitive Vision Systems in Medical Applications , 2003, ISMIS.

[7]  Sven Wachsmuth,et al.  Bayesian networks for speech and image integration , 2002, AAAI/IAAI.

[8]  Antonio Torralba,et al.  Using the Forest to See the Trees: A Graphical Model Relating Features, Objects, and Scenes , 2003, NIPS.

[9]  Heinrich Niemann,et al.  Illumination Insensitive Template Matching with Hyperplanes , 2003, DAGM-Symposium.

[10]  Justus H. Piater,et al.  Feature learning for recognition with Bayesian networks , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[11]  S. Lauritzen.  The EM algorithm for graphical association models with missing data , 1995 .

[12]  Nir Friedman,et al.  On the Sample Complexity of Learning Bayesian Networks , 1996, UAI.

[13]  Christian Bauckhage,et al.  An XML based framework for cognitive vision architectures , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..