Towards fish-eye camera based in-home activity assessment

Annu Int Conf IEEE Eng Med Biol Soc. 2008:2008:2558-61. doi: 10.1109/IEMBS.2008.4649722.


Indoors localization, activity classification, and behavioral modeling are increasingly important for surveillance applications including independent living and remote health monitoring. In this paper, we study the suitability of fish-eye cameras (high-resolution CCD sensors with very-wide-angle lenses) for the purpose of monitoring people in indoors environments. The results indicate that these sensors are very useful for automatic activity monitoring and people tracking. We identify practical and mathematical problems related to information extraction from these video sequences and identify future directions to solve these issues.

Publication types

  • Research Support, N.I.H., Extramural
  • Research Support, U.S. Gov't, Non-P.H.S.

MeSH terms

  • Algorithms
  • Artificial Intelligence
  • Environment
  • Humans
  • Image Enhancement / methods
  • Image Interpretation, Computer-Assisted / methods*
  • Imaging, Three-Dimensional / methods*
  • Information Storage and Retrieval / methods
  • Models, Biological
  • Movement / physiology*
  • Normal Distribution
  • Pattern Recognition, Automated / methods*
  • Photogrammetry / methods*
  • Reproducibility of Results
  • Video Recording / methods*