Fine grained sport action recognition with Twin spatio-temporal convolutional neural networks - Archive ouverte HAL Access content directly
Journal Articles Multimedia Tools and Applications Year : 2020

Fine grained sport action recognition with Twin spatio-temporal convolutional neural networks

Abstract

Human action recognition in video is one of the key problems in visual data interpretation. Despite intensive research, the recognition of actions with low inter-class variability remains a challenge. This paper presents a new Siamese Spatio-Temporal Convolutional Neural Network (SSTCNN) for this purpose. When applied to table tennis, it is possible to detect and recognize 20 table tennis strokes. The model has been trained on a specific dataset, so called TTStroke-21, recorded in natural conditions at the Faculty of Sports of the University of Bordeaux. Our model takes as inputs a RGB image sequence and its computed residual Optical Flow. The proposed siamese network architecture comprises 3 spatio-temporal convolutional layers, followed by a fully connected layer where data are fused. Our method reaches an accuracy of 91.4% against 43.1% for our baseline.
Fichier principal
Vignette du fichier
MTAP.pdf (6.31 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02551019 , version 1 (16-06-2020)

Identifiers

Cite

Pierre-Etienne Martin, Jenny Benois-Pineau, Renaud Péteri, Julien Morlier. Fine grained sport action recognition with Twin spatio-temporal convolutional neural networks. Multimedia Tools and Applications, 2020, ⟨10.1007/s11042-020-08917-3⟩. ⟨hal-02551019⟩
338 View
300 Download

Altmetric

Share

Gmail Facebook X LinkedIn More