高级检索

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

基于分数阶微分视频融合的森林烟火检测算法

仲亭玉 刘文萍 刘鹏举

仲亭玉, 刘文萍, 刘鹏举. 基于分数阶微分视频融合的森林烟火检测算法[J]. 北京林业大学学报, 2017, 39(3): 24-31. doi: 10.13332/j.1000-1522.20160163
引用本文: 仲亭玉, 刘文萍, 刘鹏举. 基于分数阶微分视频融合的森林烟火检测算法[J]. 北京林业大学学报, 2017, 39(3): 24-31. doi: 10.13332/j.1000-1522.20160163
ZHONG Ting-yu, LIU Wen-ping, LIU Peng-ju. A forest fire smoke detection algorithm based on fractional-calculus video fusion[J]. Journal of Beijing Forestry University, 2017, 39(3): 24-31. doi: 10.13332/j.1000-1522.20160163
Citation: ZHONG Ting-yu, LIU Wen-ping, LIU Peng-ju. A forest fire smoke detection algorithm based on fractional-calculus video fusion[J]. Journal of Beijing Forestry University, 2017, 39(3): 24-31. doi: 10.13332/j.1000-1522.20160163

基于分数阶微分视频融合的森林烟火检测算法

doi: 10.13332/j.1000-1522.20160163
基金项目: 

中央高校基本科研业务费专项 2015ZCQ-XX

详细信息
    作者简介:

    仲亭玉。主要研究方向:数字图像视频处理。Email: ztyzhong@163.com  地址:100083  北京市海淀区清华东路35号北京林业大学信息学院

    责任作者:

    刘文萍,教授,博士生导师。主要研究方向:计算机图象及视频分析与处理、模式识别与人工智能。Email: wendyl@vip.163.com  地址:同上

  • 中图分类号: S762.2;TP391

A forest fire smoke detection algorithm based on fractional-calculus video fusion

  • 摘要: 森林火灾检测是国内外林业应用研究的重要课题之一。及时准确地检测到森林火灾,对于森林健康及环境安全意义重大。现有的利用视频技术检测森林火灾的方法大多针对单一波段,如可见光波段或红外波段的视频信息进行分析,然而在实际应用过程中,由于森林环境复杂,基于单一波段视频信息检测火灾的结果欠佳。现阶段,基于多个波段的森林火灾检测方法非常少。本文综合利用红外及可见光视频特征,提出了一种基于分数阶微分视频融合的森林烟火检测算法,将分数阶微分理论引入红外视频和可见光视频融合中,利用分数阶微分算子对两个波段视频进行融合,然后利用背景去除法检测融合视频中的异常帧,且对异常帧图像及其与背景帧的差分图像分别进行图像分割,最终得到检测出的森林烟火区域。采用空间频率、平均梯度、森林火灾检测准确率和森林火灾检测时间误差度4个测度对本文算法和基于区域能量融合算法、基于窗口方差融合算法、基于HSI变换融合算法进行定量分析和比较。结果表明,本文算法的融合视频的融合效果最佳,并且森林火灾检测准确率和森林火灾检测时间误差均明显优于其他3种算法,说明本文提出的算法具有较好的有效性和准确性,为森林火灾检测提供了有利的新途径。

     

  • 图  1  基于可见光和红外融合视频的森林烟火检测算法流程

    Figure  1.  Forest fire detection algorithm process based on visible light and infrared fusion video

    图  2  FCBF算法step 1实验结果

    Figure  2.  Experiment results of step 1 based on FCBF algorithm

    图  3  FCBF算法step 3至step 5实验结果

    Figure  3.  Experiment results of step 3-step 5 based on FCBF algorithm

    图  4  FCBF算法step 6和step 7实验结果

    Figure  4.  Experiment results of step 6 & step 7 based on

    图  5  本文提出的分数阶微分算子

    Figure  5.  Proposed fractional-calculus operator

    图  6  不同融合算法生成的融合图像及林区烟火检测结果(门头沟1号火点)

    Figure  6.  Results of forest fire detection based on different fusion algorithms (No.1 fire point in Mentougou District)

    图  7  不同融合算法生成的融合图像及林区烟火检测结果(门头沟2号火点)

    Figure  7.  Results of forest fire detection based on different fusion algorithms (No.2 fire point in Mentougou District)

    图  8  不同融合算法生成的融合图像及林区烟火检测结果(门头沟3号火点)

    Figure  8.  Results of forest fire detection based on different fusion algorithms (No.3 fire point in Mentougou District)

    图  9  不同融合算法生成的融合图像及林区烟火检测结果(门头沟4号火点)

    Figure  9.  Results of forest fire detection based on different fusion algorithms (No.4 fire point in Mentougou District)

    表  1  FCBF算法与其他3种算法性能比较

    Table  1.   Comparison of FCBF algorithm and other algorithms

    算法
    Algorithm
    空间频率
    Spatial frequency(S)
    平均梯度
    Average gradient(AG)
    准确率
    Detection accuracy rate(P)/%
    时间误差度
    Detection time rate(T)/%
    HSI变换融合算法HSI fusion algorithm 16.3270 7.8280 1.26 56.12
    区域能量融合算法Regional energy fusion algorithm 28.3191 12.3122 86.20 38.57
    窗口方差融合算法Regional variance fusion algorithm 32.5767 16.1555 87.13 21.14
    FCBF算法FCBF algorithm 35.9066 19.6399 91.85 2.03
    下载: 导出CSV
  • [1] 彭禹, 蔡邦成.森林火灾监测及相关技术综述[J].安徽农业科学, 2014, 42(32):11355-11357. doi: 10.3969/j.issn.0517-6611.2014.32.048

    PENG Y, CAI B C. Review of forest fire monitoring and interrelated technology[J]. Journal of Anhui Agricultural Sciences, 2014, 42(32): 11355-11357. doi: 10.3969/j.issn.0517-6611.2014.32.048
    [2] 武桂林, 吴昊, 张蓉.基于图像处理的森林烟火检测系统[J].计算机技术与发展, 2013, 10(10):227-231. http://d.old.wanfangdata.com.cn/Periodical/wjfz201310057

    WU G L, WU H, ZHANG R. Wildfire detection system based on image processing[J]. Computer Technology and Development, 2013, 10(10): 227-231. http://d.old.wanfangdata.com.cn/Periodical/wjfz201310057
    [3] JIA Y, YUAN J, WANG J, et al. A saliency-based method for early smoke detection in video sequences[J]. Fire Technology, 2016, 52(5):1-22. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=4af6d0869ff898ac610ea54a4393f8c0
    [4] KO B, KWAK J Y, NAM J Y. Wildfire smoke detection using temporospatial features and random forest classifiers[J/OL].[2016-03-10]. http://cvpr.kmu.ac.kr/papers/international-papers/0E-publication(wildfire).pdf.
    [5] KRSTINI D, STIPANICEV D, JAKOVCEVI T. Histogram-based smoke segmentation in forest fire detection system[J]. Information Technology & Control, 2009, 38(3): 237-244.
    [6] YUAN F. Video-based smoke detection with histogram sequence of LBP and LBPV pyramids[J]. Fire Safety Journal, 2011, 46(3): 132-139. doi: 10.1016/j.firesaf.2011.01.001
    [7] 邵婧, 王冠香, 郭蔚.基于视频动态纹理的火灾检测[J].中国图象图形学报, 2013, 18(6):647-653. http://d.old.wanfangdata.com.cn/Periodical/zgtxtxxb-a201306005

    SHAO J, WANG G X, GUO W. Fire detection based on video dynamic texture[J]. Journal of Image and Graphics, 2013, 18(6): 647-653. http://d.old.wanfangdata.com.cn/Periodical/zgtxtxxb-a201306005
    [8] 张红民, 谈世磊.基于邻域对比的红外林火小目标检测[J].重庆理工大学学报(自然科学版), 2015, 29(1):107-110. doi: 10.3969/j.issn.1674-8425(z).2015.01.020

    ZHANG H M, TAN S L. Small infrared forest fire target detection based on neighborhood contrast[J]. Journal of Chongqing Institute of Technology (Natural Science), 2015, 29(1): 107-110. doi: 10.3969/j.issn.1674-8425(z).2015.01.020
    [9] BOSCH I, SERRANO A, VERGARA L. Multisensor network system for wildfire detection using infrared image processing[J]. Scientific World Journal, 2013, 2013(3): 402196-402206. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=Doaj000003741061
    [10] 王进成, 张捷, 赵高鹏, 等.可见光与红外的视频火灾探测器设计[J].单片机与嵌入式系统应用, 2014(9):28-31. http://d.old.wanfangdata.com.cn/Periodical/dpjyqrsxtyy201409009

    WANG J C, ZHANG J, ZHAO G P, et al. Video fire detector based on visible light and infrared ray[J]. Microcontroller and Embedded Systems, 2014(9): 28-31. http://d.old.wanfangdata.com.cn/Periodical/dpjyqrsxtyy201409009
    [11] ZHANG Y S, ZHANG F, LI B Z. Fractional domain varying-order differential denoising method[J/OL]. Optical Engineering, 2014, 53(10).[2016-03-10]. http://opticalengineering.spiedigitallibrary.org/article.aspx?articleid=1862284.
    [12] PU Y F, ZHOU J L, SIARRY P. Fractional partial differential equation: fractional total variation and fractional steepest descent approach-based multiscale denoising model for texture image[J]. Abstract & Applied Analysis, 2013, 2013(4): 764-787. http://d.old.wanfangdata.com.cn/OAPaper/oai_doaj-articles_a88dcdc41c4220caa80d3c0a02e78b7d
    [13] YANG X Z, WANG W. Road identification in aerial images on fractional differential and one-pass ridge edge detection[J]. Journal of Applied Remote Sensing, 2014, 8(7): 4480-4494. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=12231f8fce4dfbc92233eadb9b056bc8
    [14] CHI C, GAO F. Palm print edge extraction using fractional differential algorithm[J]. Journal of Applied Mathematics, 2013, 2014(2): 1-7. http://d.old.wanfangdata.com.cn/NSTLQK/NSTL_QKJJ0232715086/
    [15] GHAMISI P, COUCEIRO M S, BENEDIKTSSON J A. An efficient method for segmentation of images based on fractional calculus and natural selection[J]. Expert Systems with Applications, 2012, 39(16): 12407-12417. doi: 10.1016/j.eswa.2012.04.078
    [16] ZHIMING W, HONG B. Entropy based multi-resolution visible-infrared image fusion[C]//Proceedings of 2012 IEEE Symposium on Electrical & Electronics Engineering (EEESYM). Boston: IEEE: 2012: 639-643.
    [17] 杨勇, 童松, 黄淑英.快速离散Curvelet变换域的图像融合[J].中国图象图形学报, 2015, 20(2):219-228. http://d.old.wanfangdata.com.cn/Periodical/zgtxtxxb-a201502008

    YANG Y, TONG S, HUANG S Y. Image fusion based on fast discrete Curvelet transform[J]. Journal of Image and Graphics, 2015, 20(2): 219-228. http://d.old.wanfangdata.com.cn/Periodical/zgtxtxxb-a201502008
  • 加载中
图(9) / 表(1)
计量
  • 文章访问数:  1048
  • HTML全文浏览量:  244
  • PDF下载量:  27
  • 被引次数: 0
出版历程
  • 收稿日期:  2016-06-24
  • 修回日期:  2017-01-10
  • 刊出日期:  2017-03-01

目录

    /

    返回文章
    返回