Loughborough University
Browse

Video-based detection of hurdle crossings by athletes to gather intermediate race timings

Download (1.51 MB)
conference contribution
posted on 2024-09-26, 15:18 authored by Aele Le Sommer, Jelle Vanhaeverbeke, Robbe Decorte, Maarten Slembrouck, Steven Verstockt

Engineering of Sport 15 - Proceedings from the 15th International Conference on the Engineering of Sport (ISEA 2024)

The 400 meter hurdles is an athletics event where athletes stay within their designated lanes, running 400 meters while clearing ten evenly spaced hurdles. To evaluate the speed of an athlete between two consecutive hurdles or to evaluate the time difference between two athletes at a hurdle, this work proposes a methodology to automatically detect the hurdle crossings. Whether by biomechanical analysis or by using video-based pose estimation algorithms, the technique of crossing hurdles has been studied in literature. However, methods to extract hurdle crossing timings in an automatic way seem not to have been investigated yet. The proposed method is based on: the detection of athletes and hurdles, the extraction of the lanes from the athletic track and hurdle crossing detection methods based on the athlete, hurdle and lane relationships.  

History

Usage metrics

    Mechanical, Electrical and Manufacturing Engineering

    Categories

    No categories selected

    Licence

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC