Mountain fire identification and fire area estimation method based on multi-source heterogeneous data fusion

• Main Authors: LUO RUIXIANG, HUANG MENGHAN, CHEN SHAOYANG, WANG CHENG, ZANG YU, CHEN LONGBIAO, WENG LIJUAN, CHENG MING
• Format: Patent
• Language: Chinese; English
• Published: 07.04.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; PHYSICS

The invention provides a forest fire identification and fire passing area estimation method based on multi-source heterogeneous data fusion, and the method comprises the steps: obtaining a satellite remote sensing image containing a hot target, and carrying out the preprocessing; the method comprises the following steps: performing hotspot target detection on a satellite remote sensing image by adopting Faster R-CNN to obtain an image containing a hotspot prediction frame and a corresponding prediction frame coordinate; performing coordinate transformation on the prediction frame, and performing multi-source data fusion by using a global forest coverage map to realize non-mountain fire region filtering; an NDVI threshold value method and an NBR threshold value method are adopted to estimate the fire passing area; satellite thermal infrared remote sensing data are used for detecting the forest fire, thermal infrared remote sensing is sensitive to high-temperature target recognition, fire points are effectively