Forest fire recognition system based on forest fire unmanned aerial vehicle

Abstract

The present application relates to the fire identification technology field of unmanned aerial vehicle, and particularly relates to a fire identification system based on forest fire unmanned aerial vehicle. The system comprises a thermal infrared image acquisition module, which is used for collecting a thermal infrared image sequence through unmanned aerial vehicle scanning flight in a forest area; a thermal anomaly candidate region extraction module, which is used for image pre-processing each thermal infrared image in the thermal infrared image sequence to obtain a thermal anomaly candidate region; a canopy gap exposure event reconstruction module, which is used for taking the thermal anomaly candidate region as a seed point, region growing the thermal infrared image sequence to obtain a high-temperature connected region, and event aggregation through spatiotemporal continuity to obtain a canopy gap exposure event, wherein the canopy gap exposure event comprises a temperature sequence; a forest fire identification module, which is used for warming trend testing the canopy gap exposure event to obtain a forest warming heat source exposure event, and identifying a fire according to the forest warming heat source exposure event. The present application reduces the false negative rate of forest fire identification and improves the accuracy of fire identification.

Images