Monitoring human behavior in an assistive environment using multiple views

  • Authors:
  • Dimitrios Kosmopoulos;Panagiota Antonakaki;Konstandinos Valasoulis;Dimitrios Katsoulas

  • Affiliations:
  • Institute of Informatics and Telecommunications, NCSR Demokritos, Agia Paraskevi, Greece;Institute of Informatics and Telecommunications, NCSR Demokritos, Agia Paraskevi, Greece;Institute of Informatics and Telecommunications, NCSR Demokritos, Agia Paraskevi, Greece;Institute of Informatics and Telecommunications, NCSR Demokritos, Agia Paraskevi, Greece

  • Venue:
  • Proceedings of the 1st international conference on PErvasive Technologies Related to Assistive Environments
  • Year:
  • 2008

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper presents our approach in understanding the behavior of humans moving on a plane using multiple cameras. This approach is appropriate for monitoring people in an assistive enivronment for the purpose of issuing alerts in cases of abnormal behavior. We perform camera registration based on homography estimation and we extract position on 2D projection map. We use the output of multiple classifiers to model and extract abnormal behaviour from both the target trajectory and the target short term activity (i.e., walking, running, abrupt motion etc). The proposed approach is verified experimentally in an indoor environment. The experiments are performed with a single moving target, however the method can be generalised to multiple moving targets, which may occlude each other, due to the use of multiple cameras.