Research on deep learning-based action recognition and quantitative assessment method for sports skills

Abstract

The current sports training lacks data-based scientific training tools, and the use of action recognition technology to collect and mine sports data can effectively identify and evaluate sports skill actions. In this paper, a Transformer-based convolutional neural human action recognition network is proposed, which integrates the C3D convolutional network with the visual Transformer structure, using the 3D convolutional kernel for the extraction of time-domain features and using the Transformer network to accurately classify the feature sequences. The OpenPose algorithm is used to extract the essential points of the skeletal joints to estimate the human action posture. Through the dynamic time regularization algorithm, athletes’ sports movements are matched with standard movements to achieve a quantitative assessment of sports skill movements. The experimental results show that the method in this paper has better performance than similar neural network models in the task of sports action recognition and evaluation, and its class average accuracy mAP value and GFLOPs/V value are 0.9291 and 25.01, respectively, which substantially improves the recognition efficiency of sports skill actions.

Keywords

• action recognition
• transformer
• 3d convolutional kernel
• openpose
• dynamic time regularisation
• 97c70