Abstract
Human movement analysis is very often applied to sport, which has seen great achievements in assessing an athlete’s progress, giving further training tips and in movement recognition. In tennis, there are two basic shots: forehand and backhand, which are performed during all matches and training sessions. Recognition of these movements is important in the quantitative analysis of a tennis game. In this paper, the authors propose using Spatial-Temporal Graph Neural Networks (ST-GCN) to challenge the above task. Recognition of the shots is performed on the basis of images obtained from 3D tennis movements (forehands and backhands) recorded by the Vicon motion capture system (Oxford Metrics Ltd, Oxford, UK), where both the player and the racket were recorded. Two methods of putting data into the ST-GCN network were compared: with and without fuzzying of data. The obtained results confirm that the use of fuzzy input graphs for ST-GCNs is a better tool for recognition of forehand and backhand tennis shots relative to graphs without fuzzy input.
Highlights
Human action recognition is a dynamically developing field of computer vision
The main aim of this paper is to prove the thesis that “the use of fuzzy input graphs for Spatial-Temporal Graph Neural Networks (ST-GNNs) are connected with convolutional networks (GCNs) improves the recognition of forehand and backhand tennis shots relative to graphs without fuzzy input”
The analysis consists of two approaches: one applying fuzzy input to the graph (Fuzzy ST-GCN) and one without it (ST-GCN)
Summary
Human action recognition is a dynamically developing field of computer vision. It has reached a great interest in sport analysis, especially in video analysis. This technology has gained a great popularity in obtaining statistics of sports, sports techniques analysis, and understanding sports tactics [1]. Optical motion capture systems are a very popular method of precisely recording an athlete’s movements. The obtained information is often used to verify movements and the athlete’s progress, and develop a new training method or adjust the current one to the newest requirements. Changing the three-dimensional position of the markers allows to observe even the smallest movements with high accuracy. The whole set gives a sophisticated tool for sport analysis
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call