作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2012, Vol. 38 ›› Issue (04): 196-198. doi: 10.3969/j.issn.1000-3428.2012.04.064

• 图形图像处理 • 上一篇    下一篇

基于模糊聚类的图像型火灾检测

梁俊山 a,王慧琴 a,b,胡 燕 a,b,邹 婷 a,吴 萌 a,b   

  1. (西安建筑科技大学 a. 信息与控制工程学院;b. 管理学院,西安 710055)
  • 收稿日期:2011-08-04 出版日期:2012-02-20 发布日期:2012-02-20
  • 作者简介:梁俊山(1981-),男,硕士研究生,主研方向:图像处 理,火灾探测;王慧琴,教授、博士生导师;胡 燕,博士研究生;邹 婷,硕士研究生;吴 萌,博士研究生
  • 基金资助:
    西安市碑林区科技计划基金资助项目(GX1104);陕西省科学技术研究发展计划基金资助项目(2011K17-04-01);西安建筑科技大学青年科技基金资助项目(QN1025)

Image Type Fire Detection Based on Fuzzy Clustering

LIANG Jun-shan a, WANG Hui-qin a,b, HU Yan a,b, ZOU Ting a, WU Meng a,b   

  1. (a. School of Information and Control Engineering; b. School of Management, Xi’an University of Architecture and Technology, Xi’an 710055, China)
  • Received:2011-08-04 Online:2012-02-20 Published:2012-02-20

摘要: 提出一种基于模糊聚类的图像型火灾检测算法。建立火焰颜色模型,利用像素运动累积法获取疑似目标的闪烁频率,借助有监督模糊聚类法合并同一疑似火焰区域中的不连通部分,依据火焰的运动特征进行火灾判定。实验结果表明,该算法误报率较低,运行效率较高,适用于多种场景的火灾检测。

关键词: 火灾检测, 颜色模型, 模糊聚类, 闪烁频率

Abstract: This paper proposes an image type fire detection algorithm based on fuzzy clustering. Flame color model is established. The pulsation frequency of fire-like regions is obtained by pixel motion accumulation method. The fire-like regions which are not connected but belong to the same flame are merged with supervisory and fuzzy clustering. A judgment is made by the movement characteristics of flame. Experimental results demonstrate that the algorithm has low misstatement rate and high efficiency, it can be used in most environments of fire detection.

Key words: fire detection, color model, fuzzy clustering, pulsation frequency

中图分类号: