An intelligent system for false alarm reduction in infrared forest-fire detection

TLDR

Forest fires cause environmental, economic, and human harm, and current automatic detection systems suffer from many false alarms that require tedious human validation, undermining reliability. The study proposes the False Alarm Reduction (FAR) system, a real‑time infrared‑visual solution designed to eliminate these false alarms. The FAR system integrates infrared image processing, artificial neural networks, meteorological and GIS data, fuses visual and infrared inputs through matching, and employs a fuzzy expert rule base to generate decisions, while also supplying operators with verification software tools.

Abstract

Forest fires cause many environmental disasters, creating economical and ecological damage as well as endangering people's lives. Heightened interest in automatic surveillance and early forest-fire detection has taken precedence over traditional human surveillance because the latter's subjectivity affects detection reliability, which is the main issue for forest-fire detection systems. In current systems, the process is tedious, and human operators must manually validate many false alarms. Our approach, the False Alarm Reduction system, proposes an alternative real-time infrared-visual system that overcomes this problem. The FAR system consists of applying new infrared-image processing techniques and artificial neural networks (ANNs), using additional information from meteorological sensors and from a geographical information database, taking advantage of the information redundancy from visual and infrared cameras through a matching process, and designing a fuzzy expert rule base to develop a decision function. Furthermore, the system provides the human operator with new software tools to verify alarms.