Basketball Player Action Recognition and Tracking Using R(2+1)D CNN With Spatial-temporal Features
Hao-Hsiang Chang, Yu-Hua Chang, Yi-Lung Shih, Cheng‐Hsun Lin, Huang-Chia Shih · 2024
This study explores the challenging and practical issue of accurately determining the categories of the basketball player action by analyzing their movement characteristics. The goal of this study is to present a system that capable of real-time human action recognition, applying to actual court strategy analysis. It enables to provide coaches and players the training guidance more precisely and offer references for further game tactic enhancement.