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]
Department of Informatics [Hamburg]
2 Mnemosyne - Mnemonic Synergy
LaBRI - Laboratoire Bordelais de Recherche en Informatique, Inria Bordeaux - Sud-Ouest, IMN - Institut des Maladies Neurodégénératives [Bordeaux]
Abstract : 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.
Keywords : 3D body joints activity recognition reservoir computing echo state networks recurrent neural network
Document type :
Conference papers
Complete list of metadatas

Cited literature [13 references]  Display  Hide  Download
https://hal.inria.fr/hal-01417710
Contributor : Xavier Hinaut <>
Submitted on : Friday, December 16, 2016 - 9:48:17 AM
Last modification on : Thursday, February 7, 2019 - 2:22:42 PM

File

Mici_ESANN_2016.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01417710, version 1

Collections

INRIA-BORDEAUX | UNIV-BORDEAUX | LABRI | INRIA

Citation

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⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

389

Files downloads

240

Contact


archive-ouverte@inria.fr