ASTN & TNG Tech Webinar: From Athlete to Algorithm: Transforming Canoe Technique Analysis with AI

Our method employs foreground-background separation for canoe detection and waterline derivation. Through pose detection, we identify the paddle and have trained a neural network to recognise essential paddle positions for routine training analysis. Additionally, we incorporate biomechanical insights in a post-processing step to refine AI results and enhance analysis accuracy. Traditionally, biomechanics engineers manually screen training videos frame by frame to locate specific paddle positions and measure the paddle's angle relative to the waterline; a process taking about 20 minutes per athlete. Our approach significantly streamlines this process, reducing the workload by an order of magnitude.

Dr. Marc Schuh

Dr. Marc Schuh is a Principal Consultant at TNG Technology Consulting in Munich. In addition to managing customer projects, ranging from the development of a Data Lake in the AWS Cloud to the migration of legacy applications (e.g. Visual Basic) to Azure, he works on various innovative prototype projects together with the Innovation Hacking. Among them are the automated technical analysis of high-performance canoe athletes of the German National Team, and experiments with a Brain Computer Interface. Prior to his start at TNG, Marc Schuh received his doctorate in physics and was a wheelchair sprinter over 400m at three Paralympic Games, in addition to being a World Champion and holding the European record.

Supported by

This event is part of Australia's AI Month 2024 and details are listed on https://www.industry.gov.au/news/athlete-algorithm-transforming-canoe-technique-analysis-ai