ADVANCED FOREST FIRE DETECTION USING CONVOLUTION NEURAL NETWORK



Authors

  • 1Uma Devi Challa 2Dr. P Harini 3N Lakshmi Narayana

DOI:

https://doi.org/10.15282/jmes.17.1.2023.10.0759


Keywords:

Machine learning, deep learning, convolutional neural network, forest fire detection, object detection, YOLO, DenseNet


Abstract

Forests are vital ecosystems composed of various plant and animal species that have evolved over years to coexist. Such ecosystems are often threatened by wildfires that can start either naturally as a result of lightning strikes caused by humans. The satellite sensor is used to collect the forest thermal image in different places and analyses the data in these images to detect the fire region if they occur. Image processing technique can effectively predict the fire in the forest. Early detection of forest fires will decrease the severity preventing huge loss of ecosystems and its effect on global conditions. The forest fire detection model that is developed can be set up to analyze and process images from security cameras, drones, and satellites. Deep learning is an emerging concept based on artificial neural networks and has achieved exceptional results in various fields including computer vision. For the experiment, images from the satellite and images from the Fire Watch sensor were taken as initial data. In this work, the deep learning algorithms you only look once (YOLO), convolutional neural network (CNN), and fast recurrent neural network (FastRNN) were considered, which makes it possible to determine the accuracy of a natural fire. We are going to detect the fire in the forest result based on the accuracy which we get in train and test of the dataset-based CNN algorithm using that we show the graph result. Further the nearest authorities will soon be informed after the specifics of the incident are known.



Published

2024-06-30

How to Cite