Tracking Free-Weight Exercises

  • Keng-hao Chang
  • Mike Y. Chen
  • John Canny
Conference paper

DOI: 10.1007/978-3-540-74853-3_2

Part of the Lecture Notes in Computer Science book series (LNCS, volume 4717)
Cite this paper as:
Chang K., Chen M.Y., Canny J. (2007) Tracking Free-Weight Exercises. In: Krumm J., Abowd G.D., Seneviratne A., Strang T. (eds) UbiComp 2007: Ubiquitous Computing. UbiComp 2007. Lecture Notes in Computer Science, vol 4717. Springer, Berlin, Heidelberg

Abstract

Weight training, in addition to aerobic exercises, is an important component of a balanced exercise program. However, mechanisms for tracking free weight exercises have not yet been explored. In this paper, we study methods that automatically recognize what type of exercise you are doing and how many repetitions you have done so far. We incorporated a three-axis accelerometer into a workout glove to track hand movements and put another accelerometer on a user’s waist to track body posture. To recognize types of exercises, we tried two methods: a Naïve Bayes Classifier and Hidden Markov Models. To count repetitions developed and tested two algorithms: a peak counting algorithm and a method using the Viterbi algorithm with a Hidden Markov Model. Our experimental results showed overall recognition accuracy of around 90% over nine different exercises, and overall miscount rate of around 5%. We believe that the promising results will potentially contribute to the vision of a digital personal trainer, create a new experience for exercising, and enable physical and psychological well-being.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Keng-hao Chang
    • 1
  • Mike Y. Chen
    • 2
  • John Canny
    • 1
  1. 1.Berkeley Institute of Design, Computer Science Division, University of California, Berkeley, CA 94720USA
  2. 2.Ludic LabsUSA

Personalised recommendations