Project Details
Projekt Print View

SportVid: A portal to support the search and analysis of videos in sport and exercise science

Subject Area Image and Language Processing, Computer Graphics and Visualisation, Human Computer Interaction, Ubiquitous and Wearable Computing
Term since 2024
Project identifier Deutsche Forschungsgemeinschaft (DFG) - Project number 541944920
 
The analysis of videos plays a very important role in sports sciences as well as in competitive sports. Almost all scientists and coaches use videos to evaluate research subjects, visualize movement sequences and study opponents in detail. In Germany, there are some major sports science databases, but they either do not contain videos or do not provide functionality for content-based search in or AI-based analysis of sports videos. The research infrastructure SportVid proposed here aims to expand the ecosystem of sports science infrastructures by providing 1) a search capability in a large sports science video collection and 2) comparative analysis and evaluation using AI-based computer vision approaches. For this purpose, a corresponding infrastructure (SportVid) is being developed for the Central Library of Sports (ZBS) at the German Sport University (DSHS) Cologne, which includes a web-based research and analysis portal for sports, training and exercise videos for sports science. The goals of the project include 1) developing a video portal infrastructure including 2) content-based search in the videos, 3) enabling domain-specific (semi-automatic) annotation of sports videos, 4) developing usable tools for researchers from sports science to train AI models, 5) interaction possibilities to explore the video data, and 6) ensuring sustainability. The expertise of the project partners complements each other well: DSHS's ZBS has expertise in portal development and is providing the target platform, while both scientific partners have excellent track records in the fields of sports science and informatics (DSHS) and multimedia and digital libraries (TIB), respectively.
DFG Programme Research data and software (Scientific Library Services and Information Systems)
 
 

Additional Information

Textvergrößerung und Kontrastanpassung