高级检索

  • ISSN 1006-3080
  • CN 31-1691/TQ

基于Ohta颜色空间的多信息融合火焰检测

刘佳丽 叶炯耀

刘佳丽, 叶炯耀. 基于Ohta颜色空间的多信息融合火焰检测[J]. 华东理工大学学报(自然科学版), 2019, 45(6): 962-969. doi: 10.14135/j.cnki.1006-3080.20180910001
引用本文: 刘佳丽, 叶炯耀. 基于Ohta颜色空间的多信息融合火焰检测[J]. 华东理工大学学报(自然科学版), 2019, 45(6): 962-969. doi: 10.14135/j.cnki.1006-3080.20180910001
LIU Jiali, YE Jiongyao. Multi-information Fusion Flame Detection Based on Ohta Color Space[J]. Journal of East China University of Science and Technology, 2019, 45(6): 962-969. doi: 10.14135/j.cnki.1006-3080.20180910001
Citation: LIU Jiali, YE Jiongyao. Multi-information Fusion Flame Detection Based on Ohta Color Space[J]. Journal of East China University of Science and Technology, 2019, 45(6): 962-969. doi: 10.14135/j.cnki.1006-3080.20180910001

基于Ohta颜色空间的多信息融合火焰检测

doi: 10.14135/j.cnki.1006-3080.20180910001
详细信息
    作者简介:

    刘佳丽(1991-),女,河南人,硕士生,主要研究方向为视频图像处理。E-mail:18817312119@163.com

    通讯作者:

    叶炯耀,E-mail:yejy@ecust.edu.cn

  • 中图分类号: TP391

Multi-information Fusion Flame Detection Based on Ohta Color Space

  • 摘要: 为了能够快速准确地检测到火焰,预防火灾的发生,提出了一种在Ohta颜色检测的基础上使用饱和度和Otsu阈值分割法相结合的算法。采用该算法可以实时、准确地检测出疑似火焰区域,然后对其进行圆形度、矩形度、重心高度系数特征分析,并结合LBP纹理分析,最后再通过SVM进行判定。实验结果表明,该算法能够准确地检测出火焰,且实时性和准确率都得到了显著提高。

     

  • 图  1  火焰检测流程图

    Figure  1.  Flow chart of flame detection

    图  2  不同方法的火焰运动检测结果

    Figure  2.  Results of flame motion detection by different methods

    图  3  ${I_1}$${I_2}$取值不同时火焰的检测结果

    Figure  3.  Flame detection results of different ${I_1}$ and ${I_2}$ values

    图  4  火焰直方图与r直方图的对比

    Figure  4.  Comparison of flame histogram and r histogram

    图  5  火焰颜色检测结果

    Figure  5.  Detection results of flame color

    图  6  火焰视频检测结果

    Figure  6.  Flame video detection results

    表  1  SVM不同核函数的分类结果

    Table  1.   Classification results of different kernel functions of SVM

    Kernel functionCorrectly classified picturesMisclassified picturesTotal picturesAccuracy rate/%
    Polynomial1 0101901 20084.2
    RBF1 0801201 20090.0
    Sigmoid1 0391611 20086.6
    下载: 导出CSV

    表  2  火焰场景描述

    Table  2.   Flame scene description

    VideoDescription
    1The color behind the wall of the flame is similar to the flame, fluttering with the wind
    2A person walking with a torch and a red object similar to a flame
    3A large area of water on the ground and glass through the sun. There is no fire period
    4Grass flame, flames constantly drifting and shaking with the wind
    5Fire in the forest and accompanied by heavy smoke
    6Indoor flames and a man with red shirt walking around
    7Car lights in the night
    8Five-star red flag fluttering in the wind
    下载: 导出CSV

    表  3  不同算法的火焰视频检测结果

    Table  3.   Flame video detection results of different algorithms

    VideoTotal frameFlame frameLiterature[16]Literature[20]This paper
    Accuracy/%Miss rate/%Error rate/%Accuracy/%Miss rate/%Error rate/%Accuracy/%Miss rate/%Error rate/%
    120720791.51.237.2794.93.81.397.30.582.12
    262462484.312.812.8982.613.34.190.78.291.01
    316513575.021.893.1181.817.780.4288.610.241.16
    448348395.33.681.0296.42.431.1798.20.820.98
    531631685.713.790.5185.312.761.9490.28.970.83
    614514590.51.537.9789.55.714.7993.40.436.17
    下载: 导出CSV

    表  4  不同算法的非火焰视频检测结果

    Table  4.   Non-flame video detection results of different algorithms

    VideoTotal frameNon-flame framesLiterature[16]Literature[20]This paper
    Accuracy/%Error rate/%Accuracy/%Error rate/%Accuracy/%Error rate/%
    713013092.37.768.731.395.74.3
    815615687.412.685.914.190.49.6
    下载: 导出CSV
  • [1] 李正周, 方朝阳, 顾园山, 等. 基于无线多传感器信息融合的火灾检测系统[J]. 数据采集与处理, 2014, 29(5): 694-699. doi: 10.3969/j.issn.1004-9037.2014.05.005
    [2] 余启明.基于背景减法和帧差法的运动目标检测算法研究[D].江西赣州: 江西理工大学, 2013.
    [3] 严红亮, 王福龙, 刘志煌. 结合三帧差分的ViBe运动检测算法[J]. 计算机系统应用, 2014, 23(11): 105-110. doi: 10.3969/j.issn.1003-3254.2014.11.019
    [4] 赵建. 基于三帧差法的运动目标检测方法研究[D].西安: 西安电子科技大学, 2013.
    [5] STAUFFER C, GRIMSON W E L. Adaptive background mixture models for real-time tracking[C]//IEEE Conference on Computer Vision and Pattern Recognition. USA: IEEE, 1999: 246-252.
    [6] DU S Y, LIU Z G. A comparative study of different color spaces in computer-vision-based flame detection[J]. Multimedia Tools & Applications, 2015, 75(17): 1-20.
    [7] KO B C, CHEONG K H, NAM J Y. Early fire detection algorithm based on irregular patterns of flames and hierarchical Bayesian networks[J]. Fire Safety Journal, 2010, 45(4): 262-270. doi: 10.1016/j.firesaf.2010.04.001
    [8] HORNG W B, PENG J W, CHEN C Y. A new image-based real-time flame detection method using color analysis[C]//Proceedings of IEEE International Conference on Networking, Sensing and Control. USA: IEEE, 2005: 100-105.
    [9] HAMME D V, VEELAERT P, PHILIPS W, et al. Fire detection in color images using Markov random fields[C]// International Conference on Advanced Concepts for Intelligent Vision Systems. Berlin Heidelberg : Springer, 2010: 88-97.
    [10] LIU Z G, YANG Y, JI X H. Flame detection algorithm based on a saliency detection technique and the uniform local binary pattern in the YCbCr color space[J]. Signal Image Video Process, 2016, 10(2): 277-284. doi: 10.1007/s11760-014-0738-0
    [11] 郭峰, 曹其新, 谢国俊, 等. 基于OHTA颜色空间的瓜果轮廓提取方法[J]. 农业机械学报, 2005, 36(11): 119-122.
    [12] 严云洋, 唐岩岩, 郭志波, 等. 融合色彩和轮廓特征的火焰检测[J]. 微电子学与计算机, 2011, 28(10): 137-141.
    [13] HORNG W B, PENG J W, CHEN C Y. A new image-based real-time flame detection method using color analysis [C]//Proceedings of the 2005 IEEE International Conference on Networking, Sensing and Control. New York: IEEE, 2005: 100-105.
    [14] QI X, EBERT J. A computer vision based method for fire detection in color videos[J]. International Journal of Imaging, 2009, 2(9): 22-34.
    [15] CHEN T H, WU P H, CHIOU Y C. An early fire-detection method based on image processing[C]// 2004 International Conference on Image Processing. USA: IEEE, 2004: 1707-1710.
    [16] 吴冬梅, 杨娟利, 王静. 基于Ohta颜色空间的火焰检测[J]. 电视技术, 2016, 40(6): 140-143.
    [17] KANG M, TUNG T X, KIM J. Efficient video-equipped fire detection approach for automatic fire alarm systems[J]. Optical Engineering, 2013, 52(1): 177-182.
    [18] KO B C, CHEONG K H, NAM J Y. Fire detection based on vision sensor a support vector machines[J]. Fire Safety Journal, 2009, 44(3): 322-329. doi: 10.1016/j.firesaf.2008.07.006
    [19] LEI W, LIU J. Early fire detection in coalmine based on video processing[C]//International Conference on Communication, Electronics and Automation Engineering. Berlin, German: Springer, 2013: 239-245.
    [20] YANG X, WANG J, HE S. A SVM approach for vessel fire detection based on image processing[C]//Proceedings of International Conference on Modelling, Identification & Control(ICMIC). Wuhan, China: IEEE, 2012: 150-153.
    [21] OJALA T, PIETIKAINEN M, MAENPAA T. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(7): 971-987. doi: 10.1109/TPAMI.2002.1017623
    [22] 吴茜茵, 严云洋, 杜静, 等. 多特征融合的火焰检测算法[J]. 智能系统学报, 2015, 10(2): 240-247.
  • 加载中
图(6) / 表(4)
计量
  • 文章访问数:  7370
  • HTML全文浏览量:  2735
  • PDF下载量:  14
  • 被引次数: 0
出版历程
  • 收稿日期:  2018-09-10
  • 网络出版日期:  2019-07-18
  • 刊出日期:  2019-12-01

目录

    /

    返回文章
    返回