With the rapid development in the fields of computer vision and deep learning, the combination of computer and camera has been used to replace the human eye to achieve the segmentation, classification and recognition of targets, especially in the detection, tracking and action analysis of motion images. The aim of this paper is to investigate the design and implementation of a basketball-assisted training system based on 3D motion recognition technology. This paper discusses the background and significance of basketball assisted training, provides an in-depth analysis of domestic and international research on shooting and assisted training, proposes a human motion recognition model using graphical neural networks to establish spatio-temporal graphical convolutional neural networks, and designs and develops an assisted system that can help basketball players in sports training. The platform for implementing the system and the technology used are introduced, and the system is verified. The implementation platform and the technology used are presented and the effectiveness of the system is verified.
Paper
The full text of this publication is not hosted on 44B due to licensing.
Read it at OpenAlex