Adaptive learning in motion analysis with self-organising maps

Angelopoulou, A., Garcia-Rodriguez, J., Psarrou, A., Gupta, G. and Mentzelopoulos, M. (2013) Adaptive learning in motion analysis with self-organising maps. In: International Joint Conference on Neural Networks (IJCNN), 04 Aug 2013, Dallas, TX.

Full text not available from this repository.
Official URL: https://dx.doi.org/10.1109/IJCNN.2013.6707135

Abstract

Growing models have been widely used for clustering or topology learning. Traditionally these models work on stationary environments, grow incrementally and adapt their nodes to a given distribution based on global parameters. In this paper, we present an enhanced unsupervised self-organising network for the modelling of visual objects. We first develop a framework for building non-rigid shapes using the growth mechanism of the self-organising maps, and then we define an optimal number of nodes without overfitting or underfitting the network based on the knowledge obtained from information-theoretic considerations. This model is used to the representation of motion in image sequences by initialising a suitable segmentation. We present experimental results for hands and we quantitatively evaluate the matching capabilities of the proposed method with the topographic product.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Image Sequences
Subjects: University of Westminster > Science and Technology
SWORD Depositor: repository@westminster.ac.uk
Depositing User: repository@westminster.ac.uk
Date Deposited: 29 Oct 2015 15:37
Last Modified: 29 Oct 2015 15:37
URI: http://westminsterresearch.wmin.ac.uk/id/eprint/15860

Actions (login required)

Edit Item (Repository staff only) Edit Item (Repository staff only)