Exploiting drone images for forest fire detection using metaheuristics with deep learning model

Abstract

Forest fires are a global natural calamity causing significant economic damage and loss of lives. Professionals forecast that forest fires would raise in the future because of climate change. Early prediction and identification of fire spread would enhance firefighting and reduce affected zones. Several systems have been advanced to detect fire. Recently, Unmanned Aerial Vehicles (UAVs) can be used for forest fire detection due to their ability, high flexibility, and inexpensive to cover vast areas. But still, they are limited by difficulties like image degradation, small fire size, and background complexity. This study develops an automated Forest Fire Detection using Metaheuristics with Deep Learning (FFDMDL-DI) model. The presented FFDMDL-DI technique exploits the DL concepts on drone images to identify the occurrence of fire. To accomplish this, the FFDMDL-DI technique makes use of the Capsule Network (CapNet) model for feature extraction purposes with a biogeography-based optimization (BBO) algorithm-based hyperparameter optimizer. For accurate forest fire detection, the FFDMDL-DI technique uses a unified deep neural network (DNN) model. Finally, the tree growth optimization (TGO) technique is utilized for the parameter adjustment of the DNN method. To depict the enhanced detection efficiency of the FFDMDL-DI approach, a series of simulations were performed on the FLAME dataset, comprising 6000 samples. The experimental results stated the improvements in the FFDMDL-DI method over other DL models with maximum accuracy of 99.76%.