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 ›› 2022, Vol. 41 ›› Issue (6): 807-811.

• • 上一篇    下一篇

基于目标检测卷积神经网络的图像型火灾探测算法

张 苗1，李 璞2，杨 漪3，宋文华4   

  1. （1.天津市和平区消防救援支队，天津 300090； 2.郑州航空港经济综合实验区消防救援支队，河南 郑州 450000；3.西安科技大学，陕西 西安 710054； 4.天津工业大学 环境科学与工程学院,天津 300387）
  • 出版日期:2022-06-15 发布日期:2022-06-15
  • 作者简介:张 苗（1986-），女，天津人，天津市和平区消防救援支队工程师,主要从事消防监督执法管理及消防信息化建设工作，天津市和平区新华路与佳木斯道交口，300090。
  • 基金资助:
    天津市科技重大专项与工程(16ZXHLSF00290)

Image fire detection algorithms based on object detection convolutional neural networks

ZHANG Miao1, LI Pu2, YANG Yi3, SONG Wen-hua4   

  1. (1. Tianjin Heping Fire and Rescue Division, Tianjin 300090, China; 2. Zhengzhou Airport Economy Zone Fire and Rescue Division, He'nan Zhengzhou 450000, China; 3. Xi'an University of Science and Technology, Shaanxi Xi'an 710054, China; 4. School of Environmental Science and Engineering, Tianjin Polytechnic University, Tianjin 300387, China)
  • Online:2022-06-15 Published:2022-06-15

摘要： 摘 要：针对传统图像型火灾探测算法误差率高、延迟探测、计算量大等问题，提出了基于目标检测卷积神经网络（Faster-RCNN、R-FCN、SSD和YOLO v3）的图像型火灾探测算法。通过对比实验表明，基于目标检测卷积神经网络的探测算法准确性较高。其中，YOLO v3探测算法的平均精度为84.5%，探测速度为28帧/s，具有更高的稳定性，更适用于图像型火灾探测系统的开发。

关键词: 关键词：卷积神经网络, 深度学习, 火灾探测

Abstract: Abstract: The existing image fire detection algorithms have the problems of weak generalization ability, high false alarm rate, and low practicality. Based on four advanced object detection convolutional neural networks (e.g. Faster-RCNN, R-FCN, SSD and YOLO v3), new image fire detection algorithms were developed. The comparison of the proposed and current algorithms reveals that the algorithms based on object detection CNNs have significant advantages. Especially, the average precision of the algorithm based on YOLO v3 reaches to 84.5%, and the detection velocity is 28 frame/s. Besides, the YOLO v3 also has stronger robustness of detection performance, and is suitable for developing fire detection system.

Key words: Key words: convolutional neural networks, deep learning, fire detection