International Journal For Multidisciplinary Research

E-ISSN: 2582-2160     Impact Factor: 9.24

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Call for Paper Volume 7, Issue 4 (July-August 2025) Submit your research before last 3 days of August to publish your research paper in the issue of July-August.

FOREST FIRE DETECTION USING CONVOLUTIONAL NEURAL NETWORKS (CNN)

Author(s) Ms. P. SUBASRI suba, Mx. B.NITHYA nithya
Country India
Abstract One of the most frequent yet undesirable phenomena brought on by climate change and rising temperatures is wildfires. Due to the regular occurrence of these extremely strong wildfire episodes, flora and fauna are suffering significant degradation. Therefore, there is a growing need for advanced yet user-friendly systems that enable the effective use of contemporary tools and solutions. Fire and smoke detection are crucial tasks in ensuring the safety and security of various environments. In this project, we present a comprehensive solution for fire and smoke detection using deep learning techniques. The project is developed in Python, utilizing the powerful and efficient YOLOv8 (You Only Look Once version 8) architecture. The main objective of this project is to accurately detect and classify fire and smoke instances across different scenarios, including static images, pre-recorded videos, and real-time webcam feeds. To achieve this, a robust deep learning model was trained on a diverse dataset consisting of 3,825 images representing fire, smoke, and normal situations. The implemented model demonstrates impressive performance, achieving a training accuracy of 97.00% and a validation accuracy of 94.00%. These high accuracy metrics reflect the model's capability to reliably distinguish between fire, smoke, and non-hazardous scenes, making it highly effective for practical deployments. The proposed system supports multi-purpose detection, providing real-time analysis of visual data from images, videos, and live webcam streams. This versatility ensures the system's applicability in a broad range of use cases, such as surveillance networks, fire alarm systems, and emergency response operations. In summary, this project contributes to the domain of fire and smoke detection by employing YOLOv8, one of the most advanced object detection architectures available. The resulting system offers a fast, accurate, and scalable solution for identifying fire and smoke in various media types, thereby enhancing safety and preparedness in vulnerable environments.
Keywords YOLOv8 architecture, 97.00% accuracy, Validation accuracy of 94.00%, Python, Fire and Smoke
Field Computer > Artificial Intelligence / Simulation / Virtual Reality
Published In Volume 7, Issue 4, July-August 2025
Published On 2025-07-29
DOI https://doi.org/10.36948/ijfmr.2025.v07i04.52281
Short DOI https://doi.org/g9vpq9

Share this