Sporting success thanks to artificial intelligence?
The Institute for Training Science and Sports Informatics of the German Sports University Cologne and the L3S Research Centre of the Leibniz University of Hanover have successfully raised project funding from the Federal Ministry of Education and Research (BMBF). The MM4Sports project is a transfer project in the field of sports data analysis, which uses data from football, basketball and handball.
The project has been positively assessed under the funding line "Application of Artificial Intelligence Methods in Practice" and will be funded with more than 800,000 euros over a two-year project period (2020-2022). With this funding line, the BMBF supports projects aimed at transferring innovative research results from the field of artificial intelligence to practice.
Another project partner is the Munich-based technology company KINEXON, an expert in the field of real-time collection and processing of sports performance data, with which the Institute for Training Science and Sports Informatics has been working for two years. In the course of this cooperation, the institute is one of the few research institutes in the world where position data can be collected in indoor and outdoor sports. "Based on KINEXON's existing position data solution, there is still no automated merging of position and video data at sports games, which is important for fundamental and application-oriented research projects in the field of sports analytics for the future market," says Univ.-Prof. Dr. Daniel Memmert, Managing Director of the Institute for Training Science and Sports Informatics at the German Sports University Cologne. He and his team have been working for years on the analysis (e.B. with SOCCER©) as well as simulation of complex position data (so-called big data) and have developed and validated theoretical framework models for this purpose. (DFG-Projekt „e-Science“).
The aim of the new project is now to integrate machine learning methods into KINEXON's existing analysis platform. "At the heart of our solutions is our in-house sensor network for capturing accurate and reliable live data in indoor and outdoor environments. In the future, we want to push ahead with the integration of additional data sources in real time and further develop the automatic translation of the data into sound analyses and recommendations for action," says Dr. Maximilian Schmidt, Managing Director of KINEXON Sports & Media.
The expertise in dealing with video data and information in the age of the Internet and digitalization comes from the l3S research center, located at the Leibniz University of Hanover. For many years, the computer scientist Prof. Dr. Ralph Ewerth and his research group "Visual Analytics" have been working on the analysis of videos and data that are available in several modalities (e..B. language and image) or were collected with different sensors (multimodal data). Among other things, the working group researches and develops methods of automatic video analysis and artificial vision in conjunction with machine learning techniques. "The automatic enrichment and visualization of position and video data as well as their analysis by machine learning methods supports sports analysts in the preparation of important sports-relevant questions about team and individual tactics. This can increase the success of teams in high-performance sports," says Prof. Ewerth, outlining the field of application.
Contacts for more information: