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 ›› 2026, Vol. 45 ›› Issue (5): 87-93.

• • 上一篇    下一篇

图像复杂度驱动的火灾探测算法评估方法

李璞1, 张苗2   

  1. （1.郑州航空港经济综合实验区消防救援支队，河南 郑州 450000；2.天津市和平区消防救援支队，天津 300000）
  • 收稿日期:2025-02-20 修回日期:2025-10-09 出版日期:2026-05-15 发布日期:2026-05-15
  • 作者简介:李璞，郑州航空港经济综合实验区消防救援支队，主要从事消防安全方面的研究，河南省郑州市郑东新区正光路11号河南省教育厅安全管理处，450000，540537194@qq.com。

Image fire detection algorithms evaluation methods based on image complexity

Li Pu1, Zhang Miao2   

  1. (1. Zhengzhou Airport Economy Zone Fire and Rescue Division, Zhengzhou Henan 450000, China; 2. Heping Fire and Rescue Division of Tianjin, Tianjin 300000, China)
  • Received:2025-02-20 Revised:2025-10-09 Online:2026-05-15 Published:2026-05-15

摘要： 本文引入“图像复杂度”，度量图像型火灾探测算法从图像中识别火灾的难易程度。通过程序测试法获取“人类响应时间”，界定数据集中图像复杂度真实值。在此基础上，利用卷积神经网络开发能够自动预测全图综合复杂度的评估器。一致性分析后发现，Inception ResNet-v2评估器生成的全图综合复杂度度量指标表现出最高的有效性，进而提出基于图像复杂度的图像型火灾探测算法性能评估方法。该方法能够更准确地评估探测算法在不同“图像复杂度”条件下所能达到的探测水平，为火灾探测算法的开发与优化提供了重要参考。

关键词: 图像复杂度, 火灾探测, 卷积神经网络

Abstract: The "image complexity" is proposed to measure the difficulty for the algorithm to detect fire in an image. The "human response time" is obtained through the program test method, which could define the true value of the complexity of the image in the data set. Then, convolutional neural network is used to develop an evaluator that can automatically predict the comprehensive complexity of the whole image. Through the consistency analysis, the comprehensive complexity measure of the whole image generated by the Inception ResNet-v2 evaluator is the most effective measure. Furthermore, a performance evaluation method based on image complexity is proposed. This method can evaluate the detection level that the algorithm can achieve under different "image complexity" situations more accurately, providing more valuable reference for the development and optimization of fire detection algorithms.

Key words: image complexity, fire detection, convolutional neural network