Rapid Prototyping of Activity Recognition Applications

  • Authors:
  • David Bannach;Oliver Amft;Paul Lukowicz

  • Affiliations:
  • University of Passau;ETH Zurich;University of Passau

  • Venue:
  • IEEE Pervasive Computing
  • Year:
  • 2008

Quantified Score

Hi-index 0.00

Visualization

Abstract

The Context Recognition Network (CRN) Toolbox permits fast implementation of activity and context recognition systems. Using parameterizable and reusable software components, it provides a broad set of online algorithms for multimodal sensor input, signal processing, and pattern recognition. The CRN Toolbox also features mechanisms for distributed processing and support for mobile and wearable devices. Three case studies demonstrate its versatility. In these case studies, the CRN Toolbox supports information flow in hospitals, monitors walking habits to help prevent cardiovascular diseases, and recognizes hand gestures in a car-parking game. This article is part of a special issue on activity-based computing.