Towards Automated Swimming Analytics Using Deep Neural Networks

TL;DR

This paper explores methods for automating swimming analytics by creating a comprehensive swimmer database from competition videos, enabling machine learning-based detection and tracking systems.

Contribution

It introduces a novel approach to collecting and analyzing swimmer data from videos, filling a gap in swimmer tracking research.

Findings

Developed a guide for creating a swimmer database from videos

Analyzed methods for swimmer detection and tracking

Facilitated future automation of swimming analytics

Abstract

Methods for creating a system to automate the collection of swimming analytics on a pool-wide scale are considered in this paper. There has not been much work on swimmer tracking or the creation of a swimmer database for machine learning purposes. Consequently, methods for collecting swimmer data from videos of swim competitions are explored and analyzed. The result is a guide to the creation of a comprehensive collection of swimming data suitable for training swimmer detection and tracking systems. With this database in place, systems can then be created to automate the collection of swimming analytics.