计算机与现代化

• 图像处理 • 上一篇    下一篇

一种快速火灾识别方法

  

  1. (1. 北方工业大学计算机学院,北京 100144; 2. 广东省普及型高性能计算机重点实验室,广东 深圳 518060; 3. 深圳市服务计算与应用重点实验室,广东 深圳 518060; 4. 北京邮电大学计算机学院,北京 100876)
  • 收稿日期:2015-09-25 出版日期:2016-03-17 发布日期:2016-03-17
  • 作者简介:张永梅(1967-),女,山西太原人,北方工业大学计算机学院教授,博士,研究方向:图像处理,智能识别。
  • 基金资助:
    国家自然科学基金资助项目(61371143); 北京市自然科学基金资助项目(4132026); 广东省普及型高性能计算机重点实验室/深圳市服务计算与应用重点实验室开放课题(SZU-GDPHPCL2014); 北京市教委面向虚实融合的多源图像配准与识别科研平台项目(PXM2015_014212_000024); 北京市教委多源遥感图像配准与识别科研平台项目(XN081)

A Rapid Fire Recognition Method

  1. (1. School of Computer Science, North China University of Technology, Beijing 100144, China; 2. Guangdong Key Laboratory of Popular High Performance Computers, Shenzhen 518060, China; 3. Shenzhen Key Laboratory of Service Computing and Applications, Shenzhen 518060, China; 4. School of Computer Science, Beijing University of Posts and Telecommunications, Beijing 100876, China)
  • Received:2015-09-25 Online:2016-03-17 Published:2016-03-17

摘要: 智能火灾识别系统是构建智慧城市、预防火灾发生的重要组成部分,能够在很大程度上保障人民的生命财产安全。针对图像型火灾识别方法准确度和实时性间的矛盾,本文提出一种快速火灾识别方法。采用分水岭分割与自动种子生成算法相结合的方法进行复杂环境中疑似火焰区域的分割,利用多线程处理技术,提高处理速度,有利于实时火灾识别。提取最能够描述火焰图像疑似区域的圆度、尖角、腐蚀性、焰心相对坐标、相对面积等显著特征作为火灾分类依据,降低特征空间的维数,减少计算量;采用径向基函数神经网络完成火灾识别,缩短火灾识别时间,提高火灾识别的正确率。实验结果表明,疑似区域提取的准确率为90%,火灾识别准确率为85%,在保证火灾识别精度的同时,提高了火灾识别的速度。

关键词: 火灾识别, 径向基函数, 分水岭分割, 自动种子区域生长

Abstract: Intelligent fire recognition system is an important part of constructing wisdom city and preventing fire, which can well guarantee the safety of people's lives and property. Concerning the contradiction of accuracy and real-time in image fire recognition, a rapid fire image recognition method is proposed. Firstly, the segmentation method combining watershed segmentation and automatic seeded region growing is adopted to make suspected flame region segmentation in a complex environment, and the multithreading technology is used to improve the processing speed, so it is conducive to real-time fire recognition. Then, we extract the significant characteristics such as roundness, sharp corners, corrosion resistance, flame core features such as relative coordinates, the relative area in the suspected areas as fire classification, reduce the dimension of feature space and the amount of calculation. Radial basis function (RBF) neural network is adopted to complete the fire recognition, and it shortens the time of fire recognition and improves fire recognition accuracy. The experiment results show that the suspected area extraction accuracy is 90%, the fire recognition accuracy is 85%, the method can improve the precision and speed of the fire recognition.

Key words: fire recognition, RBF, watershed segmentation, automatic seeded region growing

中图分类号: