Siamese Spatio-temporal convolutional neural network for stroke classification in Table Tennis games

Pierre-Etienne Martin (1, 2) , Jenny Benois-Pineau (1, 2) , Boris Mansencal (1, 3) , Renaud Péteri , Julien Morlier

1 LaBRI - Laboratoire Bordelais de Recherche en Informatique
2 UB - Université de Bordeaux
3 Bordeaux INP - Institut Polytechnique de Bordeaux

This work presents a Table Tennis stroke classification approach through a siamese spatio-temporal convolutional neural network-SSTCNN. The videos are recorded at 120 frames per second with players performing in natural conditions. The frames are extracted, resized and processed to compute the optical flow. From the optical flow, a region of interest-ROI-is inferred. The SSTCNN is then feed by RGB and optical flow ROIs stream to give a probabilistic classification over all the table tennis strokes.

Domaines: Réseau de neurones [cs.NE]; Traitement des images [eess.IV]; Traitement du signal et de l'image [eess.SP]; Multimédia [cs.MM]; Apprentissage [cs.LG]; Interface homme-machine [cs.HC]; Informatique [cs]; Intelligence artificielle [cs.AI]; Vision par ordinateur et reconnaissance de formes [cs.CV]

Pierre-Etienne Martin, Jenny Benois-Pineau, Boris Mansencal, Renaud Péteri, Julien Morlier. Siamese Spatio-temporal convolutional neural network for stroke classification in Table Tennis games. MediaEval 2019 Workshop, Oct 2019, Sophia Antipolis, France. ⟨hal-02937668⟩