Abstract
Using local motion information data such as that obtained from optical flow, we present a network for a multilayered segmentation into motion regions that are governed by affine motion patterns. Using an energy-based competitive multilayer architecture based on non-negative activations and multiplicative update rules, we show how the network can perform segmentation tasks that require a combination of affine estimation with local integration and competition constraints.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Wang, J.Y.A., Adelson, E.H.: Representing moving images with layers. IEEE Transactions on Image Processing 3(5) (1994)
Ju, S.X., Black, M.J., Jepson, A.D.: Skin and bones: multi-layer, locally affine, optical flow and regularization with transparency. In: IEEE Conference on Computer Vision and Pattern Recognition, San Francisco (1996)
Weiss, Y., Adelson, E.H.: Perceptually organized EM: A framework for motion segmentation that combines information about form and motion. M.I.T. Media Lab Perceptual Computing Section Technical Report No. 315, Cambridge (1995)
Ayer, S., Sawhney, H.S.: Layered Representation of Motion Video using Robust Maximum-Likelihood Estimation of Mixture Models and MDL Encoding. In: Proceedings of the Fifth International Conference on Computer Vision, Washington (1995)
Weiss, Y., Adelson, E.H.: A unified mixture framework for motion segmentation: incorporating spatial coherence and estimating the number of models. In: IEEE Conference on Computer Vision and Pattern Recognition, San Francisco, Ca (1996)
Odobez, J.-M., Bouthemy, P.: Direct incremental model-based image motion segmentation for video analysis. Signal Processing 66(2) (1998)
Wersing, H., Steil, J.J., Ritter, H.: A Competitive Layer Model for Feature Binding and Sensory Segmentation. Neural Computation (2001)
Willert, V., Eggert, J., Adamy, J., Korner, E.: Non-Gaussian velocity distributions integrated over space, time, and scales. IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics (2006)
Eggert, J., Koerner, E.: Sparse coding and NMF. In: IEEE International Joint Conference on Neural Networks, Budapest (2004)
Human-Assisted Motion Annotation, http://people.csail.mit.edu/celiu/motionAnnotation/index.html
Image Sequences, http://www.cs.brown.edu/~black/images.html
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Eggert, J., Deigmoeller, J., Willert, V. (2010). Layered Motion Segmentation with a Competitive Recurrent Network. In: Diamantaras, K., Duch, W., Iliadis, L.S. (eds) Artificial Neural Networks – ICANN 2010. ICANN 2010. Lecture Notes in Computer Science, vol 6353. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-15822-3_15
Download citation
DOI: https://doi.org/10.1007/978-3-642-15822-3_15
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-15821-6
Online ISBN: 978-3-642-15822-3
eBook Packages: Computer ScienceComputer Science (R0)