« View All Projects

Robust Visual Golf Club Tracking

Computer Vision Central - Posted on December 28, 2011 at 12:02 am.

  • Link: http://cvlab.epfl.ch/research/completed/golf/
  • The goal of this project was to elaborate a computer vision based method for the automatic tracking of golf clubs. It can provide additional information to the users such as club trajectory, speed and acceleration.

    We developed a new visual tracking technology that relies on the use of a global motion model to achieve robustness. The challenging problem of retrieving the club head trajectory from ordinary video sequences of golf swings is a good application to demonstrate the effectiveness of this new approach. We have integrated it into a fully automated system that requires neither user intervention nor the use of instrumented golf club or clothing, and that is usable in a natural environment with a potentially cluttered background. Our algorithm robustly fits a global swing trajectory model to club location hypotheses obtained from single frames. This process makes our approach very robust.

    Results

    mpeg - wmvmpeg - wmvmpeg - wmvmpeg - wmvmpeg - wmv
    mpeg - wmvmpeg - wmvmpeg - wmvmpeg - wmvmpeg - wmv
    mpeg - wmvmpeg - wmvmpeg - wmvmpeg - wmvmpeg - wmv
    mpeg - wmvmpeg - wmvmpeg - wmvmpeg - wmvmpeg - wmv
    mpeg - wmvmpeg - wmvmpeg - wmvmpeg - wmvmpeg - wmv

    Color-coded swing trajectories showing the local speed of the club head in terms of different speed ranges.

    Relevant Publications

    A more detailed pdf presentation of our approach.

    N. Gehrig, V. Lepetit, and P. Fua. "Golf Club Visual Tracking for Enhanced Swing Analysis Tools", In proceedings of British Machine Vision Conference, September 2003.

    V. Lepetit, A. Shahrokni, and P. Fua. "Robust Data Association For Online Applications". In Conference on Computer Vision and Pattern Recognition, Madison, WI, June 2003.


    k();} ?>