A topological approach for human movement classification and anticipation

Chakib Arslane Bensekka (1) , Christophe Guillet (1) , Frederic Merienne (1) , Thierry Pozzo (2)

1 Le2i - Laboratoire d'Electronique, d'Informatique et d'Image [EA 7508]
2 CAPS - Cognition, Action, et Plasticité Sensorimotrice [Dijon - U1093]

The motion capture systems are increasingly used for biomedical purposes. In order to recognize and classify the movements, however whole-body movements using passive markers, generate a huge amount of data. Can topological data analysis methods improve the recognition of movements? Can we use the results of this analysis combined with particular types of neural networks to anticipate the continuation of a movement?

Mots clés: Human movement analysis; Anticipation

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]; Traitement des images [eess.IV]

Chakib Arslane Bensekka, Christophe Guillet, Frederic Merienne, Thierry Pozzo. A topological approach for human movement classification and anticipation. Gait & Posture, 2017, 57, supplément 1, pp.229-230. ⟨10.1016/j.gaitpost.2017.06.387⟩. ⟨hal-01588554⟩