Title: Recognition method of whole-body rotation in alpine skiing based on long short time memory network

Authors: Fang Yu

Addresses: Ice and Snow College, Jilin Institute of Physical Education, Changchun 130022, China

Abstract: In order to solve the problem of low recognition performance in traditional motion recognition methods, a whole-body rotation motion recognition method for alpine skiing based on long and short time memory network is proposed. This paper analyses the relationship between snowboard running route and athletes' centre of gravity track, and determines the data change of whole-body rotation in alpine skiing. It divides the initial rotation data into sections through swab algorithm to complete the whole-body rotation data collection; uses long-term and long-term memory network to classify the whole-body rotation movement of alpine skiing, and constructs the recognition model of acceleration rotation action of the whole-body rotation movement recognition of alpine skiing. The experimental results show that the accuracy, recognition rate and recall rate of the proposed method are all higher than 96%, and the recognition time is short.

Keywords: long- and short-term memory network; alpine skiing; whole-body; turning movement.

DOI: 10.1504/IJICT.2023.132166

International Journal of Information and Communication Technology, 2023 Vol.23 No.1, pp.44 - 56

Received: 11 Mar 2021
Accepted: 25 May 2021
Published online: 12 Jul 2023 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article