Software for the automatic assessment of paddling technique as part of standardised national squad trials in canoe racing
Project duration: 04/2024 – 12/2024
Artificial intelligence (AI) methods offer great potential for automating complex image and video analyses. This BISp service research project aims to harness this potential specifically for assessing the paddling technique of young athletes in canoe racing, with a view to applying it to the nationwide state squad selection tests.
In order to consolidate, expand and sustainably secure Germany’s position in elite Olympic sport, the German Olympic Sports Confederation (DOSB) is committed to the targeted development of young elite athletes. This development is to be based on objective, nationally standardised assessment criteria. For this reason, the German Canoe Federation (DKV), as the governing body for competitive canoeing, has revised and expanded its existing standardised state squad test. Particular attention was paid to refining the assessment of paddling technique. Despite this progress, the analysis of paddling technique remains largely subjective and – as before – requires a considerable amount of manual time and effort. A fully comparable assessment can only be achieved through the greatest possible automation of this process. The image and video analysis algorithms to be developed as part of the project’s objectives are intended to make a significant contribution to the objectification of paddling technique analysis in youth development and, consequently, to the comparability of state squad tests.
The project builds on the software already developed for automated, video-based technique analysis in elite sport, which was created as part of the KInematikKanu application project funded by the BISp. As part of this project, this solution is being adapted for use in the nationwide state squad tests.
Contact
Prof. Dr.-Ing. Mirco Fuchs
Chair of Computer Vision and Machine Learning
Telephone: +49 (0)341 3076 3104
Email: mirco(dot)fuchs(at)htwk-leipzig.de
