Activity recognition with echo state networks using 3D body joints and objects category

Luiza Mici (1) , Xavier Hinaut (2, 1) , Stefan Wermter (1)

1 KT - Knowledge Technology group [Hamburg]
2 Mnemosyne - Mnemonic Synergy

In this paper we present our experiments with an echo state network (ESN) for the task of classifying high-level human activities from video data. ESNs are recurrent neural networks which are biologically plausible, fast to train and they perform well in processing arbitrary sequential data. We focus on the integration of body motion with the information on objects manipulated during the activity, in order to overcome the visual ambiguities introduced by the processing of articulated body motion. We investigate the outputs learned and the accuracy of classification obtained with ESNs by using a challenging dataset of long high-level activities. We finally report the results achieved on this dataset.

Mots clés: 3D body joints; reservoir computing; activity recognition; echo state networks; recurrent neural network

Domaines: Réseau de neurones [cs.NE]; Apprentissage [cs.LG]; Vision par ordinateur et reconnaissance de formes [cs.CV]

Luiza Mici, Xavier Hinaut, Stefan Wermter. Activity recognition with echo state networks using 3D body joints and objects category. European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN), Apr 2016, Bruges, Belgium. pp.465 - 470. ⟨hal-01417710⟩