Action Recognition in Sport through Wearable Sensors from Data Collection to Classification Models Induction

• Grant number: 22/11787-0
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Effective date (Start): March 01, 2023
• Effective date (End): February 29, 2024
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: Diego Furtado Silva
• Grantee: Leonardo Rossi Luiz
• Host Institution: Instituto de Ciências Matemáticas e de Computação (ICMC). Universidade de São Paulo (USP). São Carlos , SP, Brazil

Abstract

The collection and analysis of large databases have become a task increasingly explored by the community from different areas. As interest has grown, tools for data collection have become more accessible and less complex. On the other hand, this leads to the generation of an increasing volume of data, creating challenges for identifying interest information. Sports analytics has shown significant growth in recent years among the activities that fall into this scenario. Through data that evaluate the performance and characteristics of athletes during training or match, it is possible to perform detailed analyzes to support technical decisions for better individual and collective use. This project seeks to create models in machine learning to classify actions performed by athletes from team sports on the court. For this, several steps will be carried out, starting from data collection until the creation of these models.