Home // International Journal On Advances in Networks and Services, volume 3, numbers 1 and 2, 2010 // View article


Infrared wireless network sensors for imminent forest fire detection

Authors:
Ignacio Bosch Roig
Luis Vergara Domínguez

Keywords: Infrared sensors, image processing, fire detection

Abstract:
This paper presents an automatic forest fire surveillance ground system applied to early fire detection. Sensor wireless network scheme allows not only supervising remotely wide-forest area, but also to detect immediately any fire threat. A real system for forest fire detection in actual operation is presented. The system is based on advanced thermal image processing techniques with the purpose of determining the presence of fire. The projected system performs the fusion of different detectors, which exploit different expected characteristics of a real fire, like persistence and increase in time. Theoretical results, practical simulations and results in a real environment are presented to corroborate the control of the probability of false alarm (PFA) and to evaluate the probability of detection (PD) dependence on signal to noise ratio (SNR). Delays of the system for alarm detection of controlled fire have been also evaluated. And finally, temporary evolution of false and true alarms is presented to evaluate the long-term performance in a real environment.

Pages: 40 to 49

Copyright: Copyright (c) to authors, 2010. Used with permission.

Publication date: September 5, 2010

Published in: journal

ISSN: 1942-2644