Layered motion segmentation with a competitive recurrent network

Authors:
Julian Eggert;Joerg Deigmoeller;Volker Willert
Affiliations:
Honda Research Institute, Europe GmbH, Offenbach, Germany;Honda Research Institute, Europe GmbH, Offenbach, Germany;Technical University of Darmstadt, Control Theory and Robotics Lab, Darmstadt, Germany
Venue:
ICANN'10 Proceedings of the 20th international conference on Artificial neural networks: Part II
Year:
2010

Citing 6
Cited 0

Direct incremental model-based image motion segmentation for video analysis

Signal Processing - Video segmentation for content-based processing manipulation
A Unified Mixture Framework for Motion Segmentation: Incorporating Spatial Coherence and Estimating the Number of Models

CVPR '96 Proceedings of the 1996 Conference on Computer Vision and Pattern Recognition (CVPR '96)
Skin and Bones: Multi-layer, Locally Affine, Optical Flow and Regularization with Transparency

CVPR '96 Proceedings of the 1996 Conference on Computer Vision and Pattern Recognition (CVPR '96)
Layered representation of motion video using robust maximum-likelihood estimation of mixture models and MDL encoding

ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
A Competitive-Layer Model for Feature Binding and Sensory Segmentation

Neural Computation
Non-Gaussian velocity distributions integrated over space, time, and scales

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

Quantified Score

Hi-index	0.00

Visualization

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.