Automatic synchronization of wearable sensors and video-cameras for ground truth annotation - A practical approach

  • Plötz T
  • Chen C
  • Hammerla N
 et al. 
  • 31

    Readers

    Mendeley users who have this article in their library.
  • 13

    Citations

    Citations of this article.

Abstract

The common practice of manual synchronization of body- worn, logging accelerometers and video cameras is imprac- tical for integration into everyday practice for applications such as real-world behavior analysis. We significantly ex- tend an existing technique for automatic cross-modal syn- chronization and evaluate its performance in a realistic ex- perimental setting. Distinctive gestures, captured by the camera, are matched with the recorded acceleration sig- nal(s) using cross-correlation based time-delay estimation. PCA-based data pre-processing makes the procedure ro- bust against orientation mismatches between the marking gesture and the camera plane. We evaluated five different marker gestures and report very promising results for ac- tual use.

Author-supplied keywords

  • activity recognition
  • camera
  • cross-correlation
  • synchronization
  • wearable sensors

Get free article suggestions today

Mendeley saves you time finding and organizing research

Sign up here
Already have an account ?Sign in

Find this document

Authors

  • Thomas Plötz

  • Chen Chen

  • Nils Y. Hammerla

  • Gregory D. Abowd

Cite this document

Choose a citation style from the tabs below

Save time finding and organizing research with Mendeley

Sign up for free