Forest fires represent a constant threat to ecological systems, infrastructure and human lives. Great efforts are therefore made to achieve early forest fire detection, which is traditionally based on human surveillance. Today, however, in almost every country which encounters high risk of forest fires, automatic systems are being developed and proposed. In Croatia exists one such system called Intelligent Forest Fire Monitoring System (iForestFire® ) developed at Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture University of Split. By now it was successfully implemented in various Croatian regions and National and Nature Parks. This paper describes one particular problem encountered with practical implementation of iForestFire® system and that is the adjustment of detection algorithm parameters in order to minimize the false alarms. The false alarm rate could be greatly diminished by appropriate adjustment of detection algorithms parameters according to local meteorological conditions, but also having in mind the assessment of forest fire risk degree for that particular location.

Computer science