Abstract
We propose a new biologically motivated novelty analysis model that can give robust performance for natural scenes with affine transformed field of view as well as noisy scenes in dynamic visual environment, which can play important role for an autonomous mental development. The proposed model based on biological visual pathway uses a topology matching method of a visual scan path obtained from a low level top-down attention model in conjunction with a bottom-up saliency map model in order to detect a novelty in an input scene. In addition, the energy signature for the corresponding visual scan path is also considered to decide whether a novelty is occurred in an input scene or not. The computer experimental results show that the proposed model successfully indicates a novelty for natural color input scenes in dynamic visual environment.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Guyton, A.C.: Textbook of medical physiology, 8th edn. W.B. Saunders Co., USA (1991)
Yamaguchi, S., Hale, L.A., D’Esposito, M., Knight, R.T.: Rapid prefrontal-hippocampal habituation to novel events. The Journal of Neuroscience 24(23), 5356–5363 (2004)
Singh, S., Markou, M.: An approach to novelty detection applied to the classification of image regions. IEEE Trans. on Knowledge and Data Eng. 16(4), 396–407 (2004)
Park, S.J., An, K.H., Lee, M.: Saliency map model with adaptive masking based on independent component analysis. Neurocomputing 49, 417–422 (2002)
Lanyon, L.J., Denham, S.L.: A model of active visual search with object-based attention guiding scan paths. Neural Networks Special Issue: Vision & Brain 17(5-6), 873–897 (2004)
Ban, S.W., Niitsuma, H., Lee, M.: Biologically inspired autonomous mental development model based on visual selective attention mechanism. In: Working Notes: Developmental Robotics AAAI 2005 Spring Symposium, pp. 99–105 (2005)
Carpenter, G.A., Grossberg, S., Markuzon, N., Reynolds, J.H., Rosen, D.B.: Fuzzy ARTMAP: A neural network architecture for incremental supervised learning of analog multidimensional maps. IEEE Trans. on Neural Networks 3(5), 698–713 (1992)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ban, SW., Lee, M. (2005). Novelty Analysis in Dynamic Scene for Autonomous Mental Development. In: Duch, W., Kacprzyk, J., Oja, E., Zadrożny, S. (eds) Artificial Neural Networks: Biological Inspirations – ICANN 2005. ICANN 2005. Lecture Notes in Computer Science, vol 3696. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11550822_1
Download citation
DOI: https://doi.org/10.1007/11550822_1
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-28752-0
Online ISBN: 978-3-540-28754-4
eBook Packages: Computer ScienceComputer Science (R0)