Journal of Computer Applications ›› 2017, Vol. 37 ›› Issue (7): 1989-1993.DOI: 10.11772/j.issn.1001-9081.2017.07.1989

Previous Articles     Next Articles

Fast fire flame recognition algorithm based on multi-feature logarithmic regression

XI Tingyu1, QIU Xuanbing1, SUN Dongyuan1, LI Ning1, LI Chuanliang1, WANG Gao2, YAN Yu3   

  1. 1. School of Applied Science, Taiyuan University of Science and Technology, Taiyuan Shanxi 030024, China;
    2. National Defense Key Laboratory for Electronic Test Technology, North University of China, Taiyuan Shanxi 030051, China;
    3. Automobile Engineering Department, Hebei College of Industry and Technology, Shijiazhuang Hebei 050091, China
  • Received:2016-12-26 Revised:2017-02-26 Online:2017-07-10 Published:2017-07-18
  • Supported by:
    This work is partially supported by the National Natural Science Foundation of China (U1610117, 11504256, 61573323), the National College Students Innovation and Entrepreneurship Training Program of China (2016264), Scientific and Technological Innovation Program of Higher Education Institutions in Shanxi (2015166).


席廷宇1, 邱选兵1, 孙冬远1, 李宁1, 李传亮1, 王高2, 鄢玉3   

  1. 1. 太原科技大学 应用科学学院, 太原 030024;
    2. 中北大学 电子测试技术国防科技重点实验室, 太原 030051;
    3. 河北工业职业技术学院 汽车工程系, 石家庄 050091
  • 通讯作者: 邱选兵
  • 作者简介:席廷宇(1995-),男,山西运城人,硕士研究生,主要研究方向:嵌入式系统、图像处理;邱选兵(1980-),男,四川内江人,副教授,博士,主要研究方向:激光光谱、嵌入式系统;孙冬远(1992-),男(满族),河北承德人,硕士研究生,主要研究方向:激光光谱、嵌入式系统;李宁(1994-),男,河北邯郸人,主要研究方向:嵌入式系统;李传亮(1983-),男,山东淄博人,副教授,博士,主要研究方向:激光光谱;王高(1973-),男,山西侯马人,教授,博士,主要研究方向:高温测量;鄢玉(1979-),女,四川资阳人,讲师,硕士,主要研究方向:汽车电子。
  • 基金资助:

Abstract: To improve the recognition rate and reduce the false-recognition rate in real-time detection of flame in video surveillance, a fast flame recognition algorithm based on multi-feature logarithm regression model was proposed. Firstly, the image was segmented according to the chromaticity of the flame, and the Candidate Fire Region (CFR) was obtained by subtracting the moving target image with reference image. Secondly the features of the CRF such as area change rate, circularity, number of sharp corners and centroid displacement were extracted to establish the logarithmic regression model. Then, a total of 300 images including flame and non-flame images, which were got from National Institute of Standards and Technology (NIST), Computer Vision laboratory of Inha University (ICV), Fire detection based on computer Vision (VisiFire) and the experimental library consisting of the candle and paper combustion were used to parametric learning. Finally, 8 video clips including 11071 images were used to validate the proposed algorithm. The experimental results show that the True Positive Rate (TPR) and True Negative Rate (TNR) of the proposed algorithm are 93% and 98% respectively. The average time of identification is 0.058 s/frame. Because of its fast identification and high recognition rate, the proposed algorithm can be applied in embedded real-time flame image recognition.

Key words: flame recognition, multi-feature, logarithmic regression, embedded video, real-time fire alarm

摘要: 为了提高实时视频监控中火焰识别率和降低误识率,提出了一种基于多特征量对数回归模型的火焰快速识别算法。首先,根据火焰的色度特征进行图像分割,通过运动目标与参考图像差分运算获取火焰候选区域(CFR);然后提取候选区域的面积变化率、圆形度、尖角个数以及质心位移等特征量,建立火焰的对数回归快速识别模型;其次采用美国国家标准与技术研究院(NIST)、仁荷大学计算机视觉实验室(ICV)和基于计算机视觉的火灾探测(VisiFire)实验库以及自制蜡烛、纸燃烧火焰中的火焰和非火焰图像中的300幅进行参数学习;最后选取实验数据库中8段视频共11071幅图像进行识别算法检验。测试结果表明,所提算法的真正率(TPR)达到93%、真负率(TNR)达到98%,识别平均用时0.058 s/帧。所提算法识别速度快且识别率高,可以应用于嵌入式实时图像火焰识别。

关键词: 火焰识别, 多特征量, 对数回归, 嵌入式视频, 实时火灾预警

CLC Number: