Scholarlink

<p>The implementation of smoke and fire detection systems based on image processing and machine learning still present research challenges for certain biomes, such as the cerrado where video-based fire smoke detection using cameras could be more efficient than sensor-based systems. This work presents the SEMFOGO-DF fire monitoring system, a solution composed of a distributed processing architecture and a deep-learning computer vision algorithm for smoke detection and emergency alert generation. The solution performs smoke detection on image sequences using a two-phase algorithm. The first phase analyzes image sequences and classifies regions of the image with a high probability of fire and in the second phase, a smoke classification is conducted on a zoomed image. Experimental results show that the two-phase algorithm can consistently reduce the number of false alerts generated by the first phase alone, with a relatively low reduction in the detection rate. The development of the solution also allowed the creation of two novel datasets. The first dataset consists of image sequences of the cerrado biome, annotated with smoke contours. The second dataset includes zoomed images of the cerrado landscape, annotated with labels indicating smoke and non-smoke occurrences.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A fire management intelligent system for the Brazilian cerrado biome based on a deep learning two phase detection method

  • 期刊论文

  • 发表日期：

    2025年2月7日

查看全文
  • Natalia Borges,
  • Lívia Fonseca,
  • Priscila Solis Barreto,
  • Eduardo Alchieri,
  • Marcos Fagundes Caetano,
  • Paulo Resende,
  • Leonardo Brandão,
  • Lucas Vieira

摘要

The implementation of smoke and fire detection systems based on image processing and machine learning still present research challenges for certain biomes, such as the cerrado where video-based fire smoke detection using cameras could be more efficient than sensor-based systems. This work presents the SEMFOGO-DF fire monitoring system, a solution composed of a distributed processing architecture and a deep-learning computer vision algorithm for smoke detection and emergency alert generation. The solution performs smoke detection on image sequences using a two-phase algorithm. The first phase analyzes image sequences and classifies regions of the image with a high probability of fire and in the second phase, a smoke classification is conducted on a zoomed image. Experimental results show that the two-phase algorithm can consistently reduce the number of false alerts generated by the first phase alone, with a relatively low reduction in the detection rate. The development of the solution also allowed the creation of two novel datasets. The first dataset consists of image sequences of the cerrado biome, annotated with smoke contours. The second dataset includes zoomed images of the cerrado landscape, annotated with labels indicating smoke and non-smoke occurrences.