主管：中华人民共和国应急管理部
主办：应急管理部天津消防研究所
ISSN 1009-0029  CN 12-1311/TU
消防科学与技术

消防科学与技术 ›› 2023, Vol. 42 ›› Issue (3): 314-318.

• • 上一篇    下一篇

基于轻量化神经网络的火焰识别方法研究

马成建1，王学辉2，吕玉乾3   

  1. （1.临夏州消防救援支队，甘肃 临夏 731100； 2.中国科学技术大学，安徽 合肥 230026； 3.武威市消防救援支队，甘肃 威武 733000）
  • 出版日期:2023-03-15 发布日期:2023-03-15
  • 作者简介:马成建（1986- ），男，甘肃武威人，临夏回族自治州消防救援支队中级专业技术职务，硕士，主要从事建筑防火设计、消防监督管理等方面的研究，甘肃省临夏回族自治州临夏市北滨河东路89号，731100。

Research on flame recognition method based on lightweight neural network

Ma Chengjian1， Wang Xuehui2， Lv Yuqian3   

  1. (1. Linxia Fire and Rescue Division, Gansu Linxia 731100, China; 2. University of Science and Technology of China, Anhui Hefei 230026, China; 3. Wuwei Fire and Rescue Division, Gansu Wuwei 733000, China)
  • Online:2023-03-15 Published:2023-03-15

摘要： 为了解决当前的火焰识别算法中模型不紧凑、识别精度与效率较低等问题，提出一种基于显著性目标识别理论的轻量化火焰图像分割方法。该方法基于类U-net的编码器-解码器的架构，架构内部采用了显著性目标检测的方法，引入多层注意力机制，以分层的方式检测火焰目标。该方法在公开数据集上取得了较好的识别结果，且通过对比4种经典语义分割模型可知，交并比指标提升了5.70%～16.25%，F1分数最高提升了10%，且该模型的平均绝对误差值也远远低于其他4种经典模型。表明该轻量化模型在火焰分割效果和运行速度上的指标最佳，有着较强的鲁棒性和有效性。

关键词: 轻量化神经网络, 火焰识别, 显著性目标识别

Abstract: Abstract: In order to solve the problems of non-compact models and low recognition accuracy and efficiency in current flame recognition algorithms, a lightweight flame image segmentation method based on salient target recognition theory is proposed.The method is based on a U-net-like encoder-decoder architecture, which uses salient target detection inside the architecture and introduces a multi-layer attention mechanism to detect flame targets in a hierarchical manner. The method achieves better recognition results on the public dataset. Comparing the four classical semantic segmentation models, it can be seen that the cross-comparison ratio index is improved by 5.70%~16.25%; the F1 score is improved by up to 10%; and the average absolute error value of the model in this paper is also much lower than the four classical models. It shows that the lightweight model in this paper has the best indexes in flame segmentation effect and operation speed, with strong robustness and effectiveness.

Key words: Key words: lightweight neural network, flame recognition, significant target recognition