Continuous camera-based monitoring for assistive environments

  • Authors:

  • Guanling Chen;Prabhu Govindaswamy;Nan Li;Jie Wang

  • Affiliations:

  • University of Massachusetts Lowell, Lowell, MA;University of Massachusetts Lowell, Lowell, MA;University of Massachusetts Lowell, Lowell, MA;University of Massachusetts Lowell, Lowell, MA

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

Quantified Score

Hi-index 0.00

Visualization

Abstract

Camera-based monitoring is a valuable tool for assistive environments to meet the important needs of those who may have physical or cognitive impairment. It is, however, particularly difficult to continuously monitor a moving subject in a large facility where many cameras are deployed. In this paper, we propose Sensor-Integrated Camera Surveillance (SICS) to address this problem. SICS uses wearable wireless sensors to locate moving subjects and automatically selects the camera covering the subject, allowing human operators to focus only on one screen to monitor an individual. To improve flexibility and reduce cost, SICS connects distributed cameras through a self-organizing wireless mesh network. To reduce bandwidth consumption, SICS leverages onboard image processing on the camera for selective transmission. To enable automated reasoning, SICS uses a knowledge base for efficient rule specification and execution. Through empirical evaluation, we found that the automatic camera handoff enabled by SICS was effective for continuous camera-based monitoring. We provide quantitative performance evaluation results in this paper and discuss potential extension to the SICS infrastructure.