Forest Fire Detection via Feature Entropy Guided Neural Network

Forest fire detection from videos or images is vital to forest firefighting. Most deep learning based approaches rely on converging image loss, which ignores the content from different fire scenes. In fact, complex content of images always has higher entropy. From this perspective, we propose a novel feature entropy guided neural network for forest fire detection, which is used to balance the content complexity of different training samples. Specifically, a larger weight is given to the feature of the sample with a high entropy source when calculating the classification loss. In addition, we also propose a color attention neural network, which mainly consists of several repeated multiple-blocks of color-attention modules (MCM). Each MCM module can extract the color feature information of fire adequately. The experimental results show that the performance of our proposed method outperforms the state-of-the-art methods.

Formal Modeling of IoT and Drone-Based Forest Fire Detection and Counteraction System

Forests are an enduring component of the natural world and perform a vital role in protecting the environment. Forests are valuable resources to control global warming and provide oxygen for the survival of human life, including wood for households. Forest fires have recently emerged as a major threat to biological processes and the ecosystem. Unfortunately, almost every year, fire damages millions of hectares of forest land due to late and inefficient detection of fire. However, it is important to identify the forest fire at the initial level before it spreads to vast areas and destroys natural resources. In this paper, a formal model of the Internet of Things (IoT) and drone-based forest fire detection and counteraction system is presented. The proposed system comprises network maintenance. Sensor deployment is on trees, the ground, and animals in the form of subnets to transmit sensed data to the control room. All subnets are connected to the control room through gateway nodes. Alarms are being used to alert human beings and animals to save their lives, which will help to initially protect them from fire. The embedded sensors collect the information and transfer it to the gateways. Drones are being used for real-time visualization of fire-affected areas and to perform actions to control fires because they play a vital role in disasters. Graph theory is used to construct an efficient model and to show the connectivity of the network. To identify failures and develop recovery procedures, the algorithm is designed through the graph-based model. The model is developed by the Vienna Development Method-Specification Language (VDM-SL), and the correctness of the model is ensured using various VDM-SL toolbox facilities.

Computer Vision Method for Forest Fires Detection Based on RGB Images Obtained by Unmanned Motor Glider

The article proposes a method (algorithm) of forest fire detection by means of RGB images obtained by using an unmanned aerial vehicle (motor glider). It includes several stages associated with background detection and subtraction and recognition of fire areas by means of RGB colour space. The proposed method was tested using images of forest fires. It is proposed to use unmanned aerial vehicles capable to monitor large areas continuously for several hours. The results of calculations are shown, which demonstrate that the proposed method allows us to detect areas of images occupied by forest fires and may be used in automatic forest fire monitoring systems.