loading page

DeepFire: Enhanced Fire Detection using VGG16 Convolutional Neural Networks
  • Yassmine guerbai ,
  • Asma Saibi
Yassmine guerbai
Author Profile
Asma Saibi
Author Profile

Abstract

This study explores the application of the VGG16 convolutional neural network for accurate fire detection, par- ticularly in forest fire scenarios, using images and videos. The urgency of timely fire detection, given the significant threats to life and property, underscores the importance of this research. Lever- aging transfer learning, VGG16 is fine-tuned with a comprehen- sive dataset, including forest fire data. The model demonstrates outstanding performance, with high accuracy in recognizing fire- related patterns, especially within forest landscapes. Key aspects of this research involve pre-trained weights, deep architecture, and data augmentation to enhance generalization. The proposed methodology not only provides an effective fire detection solution but also holds promise for applications in forest fire monitoring, where drones can offer critical imagery and data for improved situational awareness and response coordination.