Nowadays, video analysis systems are widely used in sports. To be able to quickly review and compare recordings they need to be stored in a structured database. For this, the contents of the recordings must be determined. However, manual classification has proven to be a time consuming process.
To efficiently handle large amounts of video data in gymnastics, Rick Oppedijk developed an Automatic Classification System for Vault (ACSV). The ACSV is based on video analysis and pattern recognition, which allows for automatic recognition and classification of vault recordings.
The ACSV is the first step towards fully automatic movement analysis of a gymnast. The next step is automatic recognition of the individual athlete. This, together with the ACSV, enables clubs to make optimal use of their video data.
Oppedijk Sports Engineering, InnoSportLab ‘s-Hertogenbosch, VU Amsterdam, TU Delft.