Graph Cuts and Deep Neural Networks for Fire Detection

  • Davi Magalhães Pereira UFJF
  • Marcelo Bernardes Vieira UFJF
  • Saulo Moraes Villela UFJF


Computer vision methods for fire detection have made significant advancements compared to traditional fire detection systems. The incorporation of fire segmentation masks enables precise analysis, offering valuable insights into the origin and spread of fires to prevent future incidents. This paper presents a novel approach that combines deep neural networks, graph cuts, and color thresholding to achieve fine-grained fire segmentation results. By incorporating graph cuts segmentation with global and local color information, our method enhances accuracy and detailed fire detection. As our results show, our method neatly improves recall, with a competitive precision, leading to an effective fire detection framework.

Palavras-chave: fire detection, fire segmentation, image classification, graph cut, deep learning, color thresholding
PEREIRA, Davi Magalhães; VIEIRA, Marcelo Bernardes; VILLELA, Saulo Moraes. Graph Cuts and Deep Neural Networks for Fire Detection. In: CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES (SIBGRAPI), 36. , 2023, Rio Grande/RS. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2023 . p. 79-84.