• Home
  • Search
  • Enhanced fire detection in new dataset: a fine-grained and multiscale-optimized architecture
  • https://doi.org/10.1117/1.jei.35.4.041406Copy DOI Icon

Enhanced fire detection in new dataset: a fine-grained and multiscale-optimized architecture

Show More
  • Abstract
  • Literature Map
  • Similar Papers
Abstract

Most existing deep learning methods are confined to single-scenario detection or coarse-grained binary classification tasks (fire/nonfire), often overlooking the critical value of fine-grained fire type classification in smart city development. However, when confronting flame targets with significant scale variations, existing models face severe challenges regarding feature extraction and multiscale adaptability, impeding precise detection. Addressing these issues, we propose EFDC-YOLO, an improved framework built upon YOLOv8. Specifically, we integrate a dynamic ghost convolution module with SS2D into the backbone network and embed a strip large kernel spatial module into the neck network. By effectively capturing discriminative spatial context information and enhancing multiscale feature representation capabilities, this architecture significantly elevates the model’s recognition precision and robustness. In addition, we release a diverse dataset covering building, vehicle, and forest fires. Experimental results demonstrate that EFDC-YOLO outperforms the original YOLOv8, achieving mAP0.5 improvements of 3.2% and 1.7% on the public M4SFWD dataset and our self-constructed dataset, respectively. These results robustly demonstrate the immense potential of EFDC-YOLO for achieving high-precision, multitype fire monitoring in complex real-world scenarios. Our codes and dataset are publicly available at https://github.com/Administor123/EFDC-YOLO/

Similar Papers
  • PDF
  • Peer Review Report

Request for Dataset for my Thesis on Fire Detection

  • May 26, 2023
  • Wang, Ming +4
  • Conference Article
  • Citations49

Unmanned aerial vehicle based forest fire monitoring and detection using image processing technique

  • Aug 01, 2016
  • Chi Yuan +3
  • Research Article
  • Citations23

Multiscale network based on feature fusion for fire disaster detection in complex scenes

  • Nov 09, 2023
  • Expert Systems With Applications
  • Jian Feng +1
  • Research Article
  • Citations8

Real-time smoke and fire detection using you only look once v8-based advanced computer vision and deep learning

  • Dec 01, 2024
  • International Journal of Advances in Applied Sciences
  • Shakila Rahman +5
  • PDF
  • Research Article
  • Citations43

FCDM: An Improved Forest Fire Classification and Detection Model Based on YOLOv5

  • Dec 12, 2022
  • Forests
  • Qilin Xue +2
  • Conference Article
  • Citations4

Real-time fire detection network for intelligent surveillance systems

  • Oct 05, 2021
  • Ruqi Liu +2
  • PDF
  • Peer Review Report

Reply on CC2

  • May 27, 2023
  • Wang, Ming +4
  • Research Article
  • Citations2

Artificial intelligence based real-time smoke and fire detection and security management algorithms

  • Mar 26, 2025
  • VFAST Transactions on Software Engineering
  • Khurram Iqbal +5
  • PDF
  • Peer Review Report

Comment on essd-2023-73

  • Jun 21, 2023
  • Wang, Ming +4
  • PDF
  • Peer Review Report

Reply on RC1

  • May 29, 2023
  • Ming Wang
  • Research Article
  • Citations3

영상기반 자동 화재감지시스템의 감지성능 특성 분석 연구

  • Oct 31, 2013
  • Journal of korean society of hazard mitigation
  • Jae-Hyun Ku
  • PDF
  • Peer Review Report

Comment on essd-2023-73

  • May 29, 2023
  • Ming Wang +4
  • PDF
  • Peer Review Report

Comment on essd-2023-73

  • Mar 29, 2023
  • Wang, Ming +4
  • Peer Review Report

Reply on CC5

  • Jun 23, 2023
  • Ming Wang
  • PDF
  • Peer Review Report

Reply on CC1

  • Mar 29, 2023
  • Ming Wang
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.