基于视频图像的林火烟雾识别方法的研究
摘要
烟雾是早期森林火灾最为突出的视觉现象。可见光视频监控技术以其成本适中、实时性强的特点已成为各类林火监控技术中的重要手段,然而目前国内外只是发展到人工监视屏幕阶段；自动监视技术由于误报率高而没有成熟的应用。因而,基于视频图像的林火烟雾机器视觉识别方法的研究更具实际意义。
本文建立了动态检测与静态分类相结合的基于视频图像的林火烟雾识别方法的系统架构,从运动目标检测、图像特征提取、模式分类识别等方面重点研究了林火烟雾识别算法,并将研究成果在鹫峰国家森林公园进行了工程应用。
本文具体研究成果有：
(1)根据烟雾的移动性,提出了改进的背景估计法结合色彩判断的林火视频图像的运动目标检测算法。引入原始背景概念改进了背景更新模型；并确定了主要参数的最优值。该算法在获得良好的烟雾捕获能力的同时初步排除了飞禽、晃动的树枝、移动的汽车之干扰。
(2)研究了基于脉冲耦合神经网络(PCNN)的图像特征提取算法。改进了基于最小均方误差准则结合梯度下降法的自适应PCNN模型调整方法,给出了适合林火烟雾图像特征提取的PCNN模型各项参数推荐值。
(3)研究林火烟雾图像特征数据的表达方法。使用了以时间序列与信息熵序列相组合的林火烟雾特征数据的表达方法；通过与灰度共生矩阵算法的比较表明PCNN算法在提高林火烟雾识别率和降低误报率方面有明显优势。
(4)进行了四种模式分类器识别能力的比较研究。设计了BP神经网络、自组织神经网络、概率神经网络、支持向量机等四种分类器模型,给出了它们的优化参数,从识别效果、分类器运行性能、特征数据归一化处理对识别效果的影响等三个方面进行的对比实验结果表明,PCNN方法提取的特征数据具有良好的适应性和稳定性；在四种分类器中,支持向量机的识别率最高,并拥有更低的漏报率与误报率,分类运行性能方面也表现出色,对于雨雪、云雾等高相似度的气象干扰得到了继续排除。
(5)设计开发了森林火灾智能识别系统。在林火视频监控平台上融合了其他多种软件工程技术,实现了基于上述算法的林火烟雾图像自动识别系统。经实地运行检验,系统运行稳定,通过了全部模拟火情测试并成功捕获一次真实森林火情。
Smoke is the most significant visible phenomenon in the early stages of forest fires, the visible light video monitoring technology for its moderate cost and real time features has become an important forest fire monitoring technology now, so video-based forest fire smoke recognition has practical significance.
In this paper, a systems framework of forest fire smoke recognition methods that integrates dynamic testing and static testing is proposed. In this framework several methods such as moving target detection, image feature extraction, pattern classification and recognition are studied. A forest fire smoke identification system based on this study has been applied in Jiufeng National Forest Park.
Major results of this study are as follows:
(1)A forest fire moving target detection algorithm. According to the moving feature of smoke, it is based on the improved background estimation and combines color criterion. The background updating model is improved by adding the original background image and the optimal values of the main parameters are identified. This algorithm has excellent smoke capture and preliminary filtration capacity of disruptors such as flying birds, swaying branches or moving cars.
(2)A forest fire smoke image feature extraction method based on the pulse coupled neural network (PCNN). The adjustment method of adaptive PCNN model is improved, and the recommended parameters' values of PCNN model for forest fire smoke detection are proposed.
(3)A forest fire smoke characteristics data expression method for the PCNN output characteristic data that is Johnson time signatures combined with entropy sequence. With a comparative study to GLCM method, PCNN method significantly improves the recognition rate of forest fire smoke and reduces the false positive rate.
(4)A comparison of classification performance of BP neural network, Self-organizing neural networks, Probabilistic neural networks and Support vector machine for the forest fire smoke characteristics data extracted by PCNN. Determined the optimization parameters of the four classifier and analyzed the experiment results from the recognition rate, operating performance and the impact of normalized operation, the experimental results show that, the feature data extracted by PCNN has excellent validity and reliability And the results also show Support vector machine obtained the highest recognition rate, at the same time, it has lower false negative rate and false alarm rate, the classification performance is also good. Support vector machine is more suitable for the classification of the forest fire smoke feature data extracted by PCNN.
(5)An automatic forest fire smoke recognition system integrated wireless networks, video monitoring and other techniques. This system implements the results of this study and now has been set in Jiufeng National Forest Park in Beijing. It successfully captured a true forest fire and through all the simulated forest fires tests.
本文建立了动态检测与静态分类相结合的基于视频图像的林火烟雾识别方法的系统架构,从运动目标检测、图像特征提取、模式分类识别等方面重点研究了林火烟雾识别算法,并将研究成果在鹫峰国家森林公园进行了工程应用。
本文具体研究成果有：
(1)根据烟雾的移动性,提出了改进的背景估计法结合色彩判断的林火视频图像的运动目标检测算法。引入原始背景概念改进了背景更新模型；并确定了主要参数的最优值。该算法在获得良好的烟雾捕获能力的同时初步排除了飞禽、晃动的树枝、移动的汽车之干扰。
(2)研究了基于脉冲耦合神经网络(PCNN)的图像特征提取算法。改进了基于最小均方误差准则结合梯度下降法的自适应PCNN模型调整方法,给出了适合林火烟雾图像特征提取的PCNN模型各项参数推荐值。
(3)研究林火烟雾图像特征数据的表达方法。使用了以时间序列与信息熵序列相组合的林火烟雾特征数据的表达方法；通过与灰度共生矩阵算法的比较表明PCNN算法在提高林火烟雾识别率和降低误报率方面有明显优势。
(4)进行了四种模式分类器识别能力的比较研究。设计了BP神经网络、自组织神经网络、概率神经网络、支持向量机等四种分类器模型,给出了它们的优化参数,从识别效果、分类器运行性能、特征数据归一化处理对识别效果的影响等三个方面进行的对比实验结果表明,PCNN方法提取的特征数据具有良好的适应性和稳定性；在四种分类器中,支持向量机的识别率最高,并拥有更低的漏报率与误报率,分类运行性能方面也表现出色,对于雨雪、云雾等高相似度的气象干扰得到了继续排除。
(5)设计开发了森林火灾智能识别系统。在林火视频监控平台上融合了其他多种软件工程技术,实现了基于上述算法的林火烟雾图像自动识别系统。经实地运行检验,系统运行稳定,通过了全部模拟火情测试并成功捕获一次真实森林火情。
Smoke is the most significant visible phenomenon in the early stages of forest fires, the visible light video monitoring technology for its moderate cost and real time features has become an important forest fire monitoring technology now, so video-based forest fire smoke recognition has practical significance.
In this paper, a systems framework of forest fire smoke recognition methods that integrates dynamic testing and static testing is proposed. In this framework several methods such as moving target detection, image feature extraction, pattern classification and recognition are studied. A forest fire smoke identification system based on this study has been applied in Jiufeng National Forest Park.
Major results of this study are as follows:
(1)A forest fire moving target detection algorithm. According to the moving feature of smoke, it is based on the improved background estimation and combines color criterion. The background updating model is improved by adding the original background image and the optimal values of the main parameters are identified. This algorithm has excellent smoke capture and preliminary filtration capacity of disruptors such as flying birds, swaying branches or moving cars.
(2)A forest fire smoke image feature extraction method based on the pulse coupled neural network (PCNN). The adjustment method of adaptive PCNN model is improved, and the recommended parameters' values of PCNN model for forest fire smoke detection are proposed.
(3)A forest fire smoke characteristics data expression method for the PCNN output characteristic data that is Johnson time signatures combined with entropy sequence. With a comparative study to GLCM method, PCNN method significantly improves the recognition rate of forest fire smoke and reduces the false positive rate.
(4)A comparison of classification performance of BP neural network, Self-organizing neural networks, Probabilistic neural networks and Support vector machine for the forest fire smoke characteristics data extracted by PCNN. Determined the optimization parameters of the four classifier and analyzed the experiment results from the recognition rate, operating performance and the impact of normalized operation, the experimental results show that, the feature data extracted by PCNN has excellent validity and reliability And the results also show Support vector machine obtained the highest recognition rate, at the same time, it has lower false negative rate and false alarm rate, the classification performance is also good. Support vector machine is more suitable for the classification of the forest fire smoke feature data extracted by PCNN.
(5)An automatic forest fire smoke recognition system integrated wireless networks, video monitoring and other techniques. This system implements the results of this study and now has been set in Jiufeng National Forest Park in Beijing. It successfully captured a true forest fire and through all the simulated forest fires tests.
引文
[1]白帆,张丽平,周大元,等.世界森林火灾预防与监控技术概述[J].林业劳动安全,2008,12(3)：20-26.
[2]边肇祺,张学工,等.模式识别(第二版)[M].北京：清华大学出版社,2000：1-30.
[3]丛爽.面向MATLAB工具箱的神经网络理论与应用(第3版)[M].北京：中国科学技术大学出版社,2009：30-150.
[4]陈杰.MATLAB宝典(第3版)[M].北京：电子工业出版社,2011：1-130.
[5]陈胜勇,刘盛.基于OpenCV的计算机视觉技术实现[M].北京：科学出版社,2008：35-75.
[6]陈东宾.基于视频图像的森林火灾监测[D].沈阳理工大学,2008：28-30.
[7]陈兴杰,柴晓冬.一种基于简化PCNN的红外图像分割方法[J].安徽大学学报(自然科学版),2010,34(1)：76-77.
[8]陈坤,许红.林火识别报警和自动定位系统在森林防火监控系统中的应用[J].As installer, 2006(5):122-125.
[9]常威威,郭雷,等.利用脉冲耦合神经网络的高光谱多波段图像融合方法[J].红外与毫米波学报,2010,29(3)：205-207.
[10]蔡曲林.基于概率神经网络的模式识别[D].国防科学技术大学,2005：5-10.
[11]程娟.复杂背景下运动目标识别算法研究[D].武汉理工大学,2008.
[12]但妮.视频序列中运动目标提取与检测算法的研究与实现[D].南京邮电大学,2009.
[13]付雪婧,王阿川.基于彩色图像的林火图像火焰分割研究[J].林业劳动安全,2009,22(2)：17-21.
[14]高锦.基于SVM的图像分类[D].西北大学,2010：7-16.
[15]龚小兵.基于BP神经网络的车辆牌照自动识别系统的研究[D].武汉理工大学,2006：34-46.
[16]关宇东,韩媞,等.基于图像识别算法的森林防火系统设计[J].科技导报,2008,26(5)：77-80.
[17]胡江林,梁益同,等.基于神经网络的气象卫星影像森林火电自动识别的实验研究[J].应用气象学报,2003,14(6)：708-713.
[18]黄亚丽.基于纹理分析和概率神经网络的肝脏B超图像识别研究[D].河北大学,2005：55-58.
[19]黄振华,李正明,等.基于图像型森林火灾无线远程监控系统[J].传感器与微系统,2009,28(3)：86-88.
[20]何立,黄永穨,等.卫星遥感图像的增强处理[J].广西气象,2006,27(3)：61-65.
[21]何鹏,李春林.热成像型森林火灾报警系统设计及其图像处理方法研究[J].微计算机信息,2006,22(1-1)：98-99.
[22]侯杰.基于视频图像的高大空间建筑火灾探测研究[D].清华大学,2010.
[23]江涛.用于特定大规模森林火灾——火源的图像处理技术[J].红外,1999(1).
[24]金顺敬.基于全方位视觉的火灾安全监控系统的研究[D].浙江工业大学.2008.
[25]姜超.视频序列中运动目标提取与跟踪技术的研究[D].大连理工大学,2009.
[26]姜东海.基于图像处理的火灾烟雾识别技术研究[D].华中科技大学,2008.
[27]蒋爱平,于洋.基于Contourlet林火图像多重分形分割的研究[J].仪器仪表学报,2010,31(4)：818-822.
[28]焦珂.基于图像的火灾烟雾识别算法研究[D].西华大学,2008.
[29]贾小军,张之江,等.基于简化PCNN模型的结构光图像自动分割方法[J].光电子·激光,2011,22(3)：457-458.
[30]贾志成,胡天翔,刘春景.基于机器视觉的森林防火监测技术初步研究[J].2008,36(10)：21-23.
[31]靳富丽.模式识别理论及其应用[J].湖北广播电视大学学报,2007,27(12)：159-160.
[32]靳大路,王德兴,杨鹏.红外热成像技术在崂山森林防火系统中的研究与应用[J].电脑知识与技术,2008,4(6)：1494-495.
[33]康锋.基于视觉特征的早期农林火灾检测方法的基础研究[D].浙江大学,2010：31-33.
[34]李百良.基于PCNN及模糊金库算法的指纹识别技术的研究[D].苏州大学,2009：25-28.
[35]李国正,王猛,等(译者).支持向量机导论[M].北京：电子工业出版社,2004：1-20.
[36]李涟凤.基于支持向量机的医学图像分割[D].苏州大学,2010：9-20.
[37]李晨雷.基于支持向量机的战场目标识别技术研究[D].哈尔滨工业大学,2009：22-24.
[38]李春宇,郭相义.基于改进型脉冲耦合神经网络的乳腺图像肿块分割[J].科技广场,2010(7)：41-43.
[39]李虎胜,王慧琴,等.基于提升小波变换的火灾图像识别[J].计算技术与自动化,2008,27(2)：81-84.
[40]李莹,许春明,等.建筑防水材料火焰视频图像特征提取[J].消防科学与技术,2011,30(5)：374-376.
[41]李彦斌,陈树越.早期森林火灾烟雾图像序列的分割算法[J].计算机工程与应用,2008,44(11)：203-204.
[42]厉谨,王慧琴,等.基于PCNN分割的火焰图像检测技术[J].西安工程大学学报,2010,24(2)：217-221.
[43]练秋生,李党.融合多种特征的烟雾图像检测算法[J].光学技术,2009,35(4)：523-528.
[44]刘瑞祯,于仕琪OpenCV教程[M].北京：北京航空航天大学出版社,2007：15-60.
[45]刘显波,聂仁灿,等.基于可变步长PCNN的图像高斯噪声滤除[J]；云南大学学报(自然科学版),2010,32(1)：26-29.
[46]刘晨晨.高分辨率成像声纳图像识别技术研究[D].哈尔滨工程大学,2007.
[47]刘听雨.基于视频特征的火灾火焰识别算法[D].西安电子科技大学.2009.
[48]刘媛军.双波段野外火灾图像识别及目标定位方法研究[D].南京航空航天大学,2009.
[49]罗四维.大规模人工神经网络理论基础[M].北京：清华大学出版社,2004：17-26.
[50]罗鹏.林火协同监测技术研究[D].中国林业科学研究院,2010.
[51]栾龙源.基于自组织神经网络与模糊算法的彩色图像聚类分割系统[D].西安电子科技大学,2010：5-8.
[52]马文生,王阿川.基于卫星影像的图像挖掘在林火行为分析中的应用[J].林业劳动安全,2008,21(1)：44-47.
[53]马义德,李廉,王亚馥,等.脉冲耦合神经网络原理及其应用[M].北京：科学出版社,2006：1-20.
[54]赖均,解梅.基于PCNN与主动轮廓的肺CT候选结节的分割方法[J].计算机应用研究,2011,28(4)：1589-1590.
[55]倪福银,张旸.基于PCNN的人脸图像分割算法研究[J].江苏技术师范学院学报,2011,17(4)：11-13.
[56]彭真明,刘世军,等.基于PCNN的遥感SAR图像桥梁目标检测与识别[J].航空科学技术,2009(5)：22-26.
[57]覃先林,张子辉,等.一种利用HJ-1B红外相机数据自动识别林火的方法[J].遥感技术与应用,2010,25(5)：700-705.
[58]任海,高昌海,顾香凤.欧美森林火灾监测新技术及设备[J].林业机械与木工设备,2005,33(5)：8-11.
[59]饶裕平,方陆明,等.林火视频监控中烟识别方法概述[J].四川林业科技,2009,30(1)：81-85.
[60]史忠植.神经网络[M].北京：高等教育出版社,2009：48-79,203-204,215-217.
[61]舒立福,王明玉,等NOAA/AVHRR和EOS/MODIS林火监测比较[J].森林防火,2005(3)：27-29.
[62]沈海峰.图像通信与处理技术在林火监测中的应用研究[D].东北林业大学.2003(6)：1-7.
[63]吴雪琼,覃先林,等.我国林火监测体系现状分析[J].内蒙古林业调查设计,2010,33(3)：69-72.
[64]王涛,刘渊,等.一种基于飘动性分析的视频烟雾检测新方法[J].电子与信息学报,2011,33(5)：1024-1029.
[65]王绍波,郭业才,等.基于模糊PCNN的小波域超声医学图像去噪方法[J].光电子.激光,2010,21(3)：477-480.
[66]王振.几种自组织神经网络及其在彩色图像分割中的应用[D].江南大学,2009：11-15.
[67]王欣刚,魏峥,等.基于烟雾动态特征分析的实时火灾检测[J].计算机技术与发展,2008,18(11)：9-12.
[68]王正林,刘明.精通MATLAB(升级版)[M].北京：电子工业出版社,2011：5-60.
[69]王伟,宋卫国,等Kmeans聚类与多光谱阈值相结合的MODIS云检测算法[J].光谱学与光谱分析,2011,31(4)：1061-1064.
[70]汪小钦,周小成MODIS林火识别算法的验证分析[J].火灾科学,2006,15(1)：31-37.
[71]武林.基于运动特征分析的森林火灾烟云实施检测方法[J].信号处理,2006,22(2)：260-263.
[72]肖霞.基于类间方差的MODIS森林火灾监测方法研究[D].中国科学技术大学,2010.
[73]肖刚.国内外森林防火技术现状及趋势探讨[D].天津大学硕士论文,2005(11)：3-65.
[74]肖淑苹.基于进化概率神经网络的纹理图像识别[D].长沙理工大学,2008：13-16.
[75]肖利,汤家法,等MODIS数据监测森林火灾方法的研究[J].四川测绘,2008,31(1)：10-13.
[76]许维胜,田长征,等.基于图像视觉特征的火灾自动识别[J].计算机工程,2003,29(18)：112-113.
[77]许志闻,纪政,等.基于小波神经网络的炉膛火焰识别和诊断[J].仪器仪表学报,2004,25(4)：376-383.
[78]熊超.模式识别理论及其应用综述[J].中国科技信息,2006(6)：171-172.
[79]徐鹏,任波.基于单高斯模型的森林火灾烟图像目标检测[J].计算机与现代化,2009(2)：18-20.
[80]徐以美.视频序列中运动目标检测与跟踪技术研究[D].西安电子科技大学,2008.
[81]徐爱俊,方陆明,等.基于可见光视频的森林火灾识别算法[J].北京林业大学学报,2010,32(2)：14-20.
[82]夏寅辉.人脸皮肤纹理测量及识别方法研究[D].燕山大学,2003.
[83]夏文文.自组织神经网络的新算法以及应用[D].江南大学,2008：11-18.
[84]叶兵.国内外森林防火技术及其发展趋势[D].中国林业科学研究院硕士论文,2000(7)：3-50.
[85]杨猛,赵春晖,等.基于小波分析的烟雾多特征融合和空间精度补偿森林火情检测算法[J].中国图象图形学报,2009,14(4)：694-700.
[86]杨合超,宋海歌,等.模式识别的主要方法及其应用[J].电脑知识与技术,2008(S2)：156-157.
[87]杨行峻,郑君里.人工神经网络与盲信号处理[M].北京：清华大学出版社,2003：114-118
[88]杨高波,杜青松MATLAB图像／视频处理应用及实例[M].北京：电子工业出版社,2010：25-90.
[89]严红平,潘春洪.模式识别简述[J].自动化博览,2006(1)：22-26.
[90]闫厚,倪金生等.基于网络摄像机的森林火灾烟火自动识别技术探讨[J].森林防火,2007(2)：25-28.
[91]姚望玲.应用遥感资料识别鄂东森林火情的方法[J].湖北气象,2002(3)：15-18.
[92]袁宏永,赵建华,等.图像型大空间建筑早期火灾智能探测报警技术[J].消防技术与产品信息,2001(2)：30-32.
[93]袁非牛,张永明,等.基于累积量和主运动方向的视频烟雾检测方法[J].中国图象图形学报,2008,13(4)：808-813.
[94]殷光.基于SVM的验证码识别算法研究[D].安徽大学,2010：8-18.
[95]兆长胜.室内条件下基于视频序列的火灾烟雾检测算法研究[D].吉林大学,2010.
[96]郑焕能.森林防火[M].哈尔滨：东北林业大学出版社,1994.
[97]郑英,张万宝,陈惠明.森林火灾地面红外探测技术的研究[J].森林防火,2006(4)：28-.30.
[98]赵文化,张鹏,等.基于MODIS地表覆盖(LC)的森林火灾识别方法[J].气象科技,2008,36(2)：210-214.
[99]赵勇.基于PCNN的医学图像分割算法研究[D].太原科技大学,2009：29-36.
[100]赵琛.用概率神经网络对混凝土拱坝进行损伤位置识别的研究[D].浙江大学,2005：14-16.
[10]] 赵翀.智能视频系统中运动物体及烟火检测的算法研究[D].哈尔滨理工大学,2009.
[102]张前园,杨娜娟.一种自适应的图像型火灾探测算法[J].现代计算机(专业版),2010(5)：68-71.
[103]张军英,卢志军,等.基于脉冲耦合神经网络的椒盐噪声图像滤波[J].中国科学E辑：信息科学,2004,34(8)：882-894.
[104]周开利,康耀红.神经网络模型及其MATLAB仿真程序设计[M].北京：清华大学出版社,2005：20-110.
[105]Abuelgasim A, Fraser R. Day and night-time active fire detection over north america using noaa-16 avhrr data [C].2002 IEEE International Conference on IGARSS Proceedings, 2002(3):1489-1491.
[106]Andrei B. Utkin,Armando Fernandes,Fernando Simoes. Feasibility of forest-fire smoke detection using lindar[J].International Journal of Wildland Fire,2003(12):159-166.
[107]B. cholkopf, J.C. Platt, J. Shawe-Taylor, A.J. Smola. Estimating the support of a high-dimensional distribution [J]. Neural Computation,2001(13):1443-1471.
[108]B. Vagvolgyi,I.Kopilovic and T.Sziranyi, Application of panoramic annular lens for motion analysis tasks:surveillance and smoke detection[C], Proceedings of 15th International Conference on Pattern Recognition,2000, Volume 4,3-7 Sept.2000:714-717.
[109]Burges C J.C. A tutorial on support vector machines for pattern recognition[J].Data Mining and Knowledge Discovery,1998,2(2):121-167
[110]Cortes C,Vapnik V.Support Vector Networks [J].Machine Learning,1995(20):272-297.
[111]Collins RT, Lipton AJ, Kanade T. A system for video surveillance and monitoring[C]. Proceedings of American nuclear society (ANS) 8th International Topical Meeting On Robotics And Remote Systems,1999.
[112]Chen T, Wu P, Chiou Y. An early fire-detection method based on image processing[C]. Proceedings of 2004 IEEE ICIP,2004:1707-1710.
[113]C.C. Chang, C.J. Lin. LIBSVM:A Library for Support Vector Machines [J/OL]. http://www.csie.ntu.edu.tw/cjlin/libsvm,2011.
[114]Chris Justice and Yoram J.Kufuman. MODIS Fire Product s [D].Algorithm Technical Background Document,1998,11 (10).
[115]C.O. Justice L,J. Kendall.,Giglio. Evaluation of global fire detection algorithms using simulated AVHRR data[J], Internat. J. Remote Sensing 20 (1999) 1947-1986.
[116]Chung YS.Satellite detection of forest fires in Korea and associated smoke plumes [J]. International Journal Of Remote Sensing,2003,24(1):1-7.
[117]da Penha Osman S. Nakamura Eduardo F. Fusing light and temperature data for fire detection [C].2010 IEEE Symposium on Computers and Communications (ISCC) Proceedings, 2010:107-112.
[118]Damir Krstinic, Darko Stipanicev, Toni Jakovcevic. Histogram-based smoke segmentation in forest fire detection system[J]. Information Technology And Control,2009,38(3):237-244.
[119]F.Gomez-Rodriguez, S.Pascual-pena,B.C.Arrue & A.Ollero.Smoke detection using image processing[C]. The IV International Conference On Forest Fire Research Proceedings,2002.
[120]Fujiwara K, Kudoh J. Siberian forest fire detection using NOAA AVHRR [C]. IEEE 2001 International IGARSS Proceedings,2001(4):1687-1689.
[121]Gunay O,Toreyin BU. Online adaptive decision fusion framework based on projections onto convex sets with application to wildfire detection in video[J]. Optical Engineering,2011,50(7): 1-7.
[122]Gomez-Rodriguez F, Arrue B C, Ollero A. Smoke monitoring and measurement using image processing[C]. Application to forest fires. In. Proc. of SPIE, Automatic Target Recognition XIII, 2003(5094):404-411.
[123]Hu Peng, Jin Li, Lili Jiang,Qingwen Qi, Xiuping Zou,Yajuan Liang. Technique for Automatic Forest Fire Surveillance Using Visible Light Image[C]. Proc. IEEE(2005):3135-3138.
[124]H. J. Grech-Cini, "Smoke Detection"[J], US Patent No. US6844818B2.
[125]Ham S.unJae,Ko Byoung-Chul,Nam Jae-Yea. Vision based forest smoke detection using analyzing of temporal patterns of smoke and their probability models [C]. Proceedings of SPIE-The International Society for Optical Engineering,2011,7877.
[126]Jerome Vicente,PhiIippe Guillemant, "An image processing technique for automatically detecting forest fire"[C], International Journal of Thermal Sciences 41(2002) 1113-1120.
[127]J.L. Johnson. Pulse-coupled neural nets:translation, rotation, scale, distortion, and intensity signal invariance for images [J]. Applied Optics,1994(33):6239-6253.
[128]Jing Wang, Weiguo Song, Wei Wang. A new algorithm for forest fire smoke detection based on MODIS data in Heilongjiang province [C].2011 International Conference on Remote Sensing,Environment and Transportation Engineering(RSETE) Proceedings,2011:5-8.
[129]Kudoh J, Hosoi K. Two dimensional Forest Fire Detection method by using NOAA AVHRR images [C].2003 IEEE IGARSS Proceedings,2003(4):2494-2495.
[130]Kohonen T. Self-organized formation of topologically correct feature maps [J]. Biological Cybernetics,1982(43):59-69.
[131]Karvonen, J. A simplified pulse-coupled neural network based sea-ice classifier with graphical interactive training[C]. Geoscience and Remote Sensing Symposium,2000. Proceedings. IGARSS 2000. IEEE 2000 International:681-684,2000.
[132]Kohonen T. Learning vector quantization for pattern recognition[R]. Technical Report TKK-F-A601, Helsinki University of Technology, Finland,1986.
[133]K.R. Muller, S. Mika, G. Ratsch, K. Tsuda. An introduction to kernel-based learning algorithms [J]. IEEE Transactions on Neural Networks,2001,12(2):181-201.
[134]Kohonen T. Improved versions of learning vector quantization [C]. IEEE International Joint Conference on Neural Network. San Diego, CA,1990(I):545-550.
[135]Kanal L. Pattern in pattern actions recognition:1968-1974[J].IEEE TransonIT,1974,20 (6):697-722.
[136]Kushida K. Detection of active wildland fires using multitemporal modis images [C]. IEEE Geoscience And Remote Sensing Letters,2010,7(2):301-305.
[137]Li Ma, Kaihua Wu, Zhu L. Fire smoke detection in video images using kalman filter and gaussian mixture color model [C].2010 International Conference on Artificial Intelligence and Computational Intelligence (AICI) Proceedings,2010(1):484-487.
[138]Lindblad T,KjnserJ M.Image proeessing using Pulse-Coupled Neural Networks[M].2th Revised Edition[J].NY.:Springer-Verlag Berlin Heidelberg,2005:3-50.
[139]Liu Shixing,Zhang Yongming, Song Weiguo, Xiao Xia. An enhanced algorithm for forest fire detection based on modis data [C].2010 International Conference on Optoelectronics and Image Processing (ICOIP) Proceedings,2010(1):200-203.
[140]Rumelhart D E, Hinton G E. Learning representations of back-propagation errors [J]. Nature, 1986(323):533-536.
[141]Raul C. Muresan Pattern recognition using pulse-coupled neural networks and discrete Fourier transforms [J]. Neurocomputing,2003(51):487-493.
[142]. Specht D F. Probabilistic neural networks [J]. Neural Networks,1990,3(1):109-118.
[143]Surit S, Chatwiriya W. Forest fire smoke detection in video based on digital image processing approach with static and dynamic characteristic analysis [C].2011 First ACIS/JNU International Conference on CNSI Proceedings,2011:35-39.
[144]Soliman H, Sudan K, Mishra A. A smart forest-fire early detection sensory system:Another approach of utilizing wireless sensor and neural networks [C].2010 IEEE Sensors Proceedings, 2010:1900-1904.
[145]Takashi Watanabe,Masaru Tanaka, Takio Kurita,Taketoshi Misllima.Autonomous foveating system based on Pulse-CouPled Neural Network[C].Proceedings of the ITC-CSCC99, 1999(01):197-200.
[146]Turgay Celik.Fast and Efficient Method for Fire Detection Using Image Processing [J]. ETRI Joumal,2010,32(6):881-890.
[147]Tung Truong Xuan,Kim Jong-Myon. An effective four-stage smoke-detection algorithm using video images for early fire-alarm systems [J]. Fire Safety Journal,2011,46(5):276-282.
[148]Wenbin Li, Junguo Zhang. The monitoring of host computer for forest fire detection system based on wireless sensor network [C].5th International Conference on Wireless Communications, Networking and Mobile Computing Proceedings,2009.
[149]Yang Chan-Yun,Tseng Wei-Wen, Yang Jr-Syu. Reducing false alarm of video-based smoke detection by support vector machine[C]. Proceedings of IEEE International Conference on Intelligence and Security Informatics,2008,5075 LNCS:102-113.
[150]Yide Ma, Li Liu. Pulse-coupled neural networks and one-class support vector machines [J]. Image and Vision Computing,2010(28):1524-1529.
[151]Yu Chunyu, Fang Jun, Wang Jinjun and Zhang Yongming. Video Fire Smoke Detection Using Motion and Color Features [J]. Fire Technology,2010(46):651-663.
[152]Zhanqing Li, Alexandre Khananian, Robert H. Fraser, Josef Cihlar. Automatic detection of fire smoke using artificial neural networks and threshold approaches appliedto avhrr imagery [C]. IEEE Transactions On Geoscience And Remote Sensing,2001,39(9):1859-1870.
[2]边肇祺,张学工,等.模式识别(第二版)[M].北京：清华大学出版社,2000：1-30.
[3]丛爽.面向MATLAB工具箱的神经网络理论与应用(第3版)[M].北京：中国科学技术大学出版社,2009：30-150.
[4]陈杰.MATLAB宝典(第3版)[M].北京：电子工业出版社,2011：1-130.
[5]陈胜勇,刘盛.基于OpenCV的计算机视觉技术实现[M].北京：科学出版社,2008：35-75.
[6]陈东宾.基于视频图像的森林火灾监测[D].沈阳理工大学,2008：28-30.
[7]陈兴杰,柴晓冬.一种基于简化PCNN的红外图像分割方法[J].安徽大学学报(自然科学版),2010,34(1)：76-77.
[8]陈坤,许红.林火识别报警和自动定位系统在森林防火监控系统中的应用[J].As installer, 2006(5):122-125.
[9]常威威,郭雷,等.利用脉冲耦合神经网络的高光谱多波段图像融合方法[J].红外与毫米波学报,2010,29(3)：205-207.
[10]蔡曲林.基于概率神经网络的模式识别[D].国防科学技术大学,2005：5-10.
[11]程娟.复杂背景下运动目标识别算法研究[D].武汉理工大学,2008.
[12]但妮.视频序列中运动目标提取与检测算法的研究与实现[D].南京邮电大学,2009.
[13]付雪婧,王阿川.基于彩色图像的林火图像火焰分割研究[J].林业劳动安全,2009,22(2)：17-21.
[14]高锦.基于SVM的图像分类[D].西北大学,2010：7-16.
[15]龚小兵.基于BP神经网络的车辆牌照自动识别系统的研究[D].武汉理工大学,2006：34-46.
[16]关宇东,韩媞,等.基于图像识别算法的森林防火系统设计[J].科技导报,2008,26(5)：77-80.
[17]胡江林,梁益同,等.基于神经网络的气象卫星影像森林火电自动识别的实验研究[J].应用气象学报,2003,14(6)：708-713.
[18]黄亚丽.基于纹理分析和概率神经网络的肝脏B超图像识别研究[D].河北大学,2005：55-58.
[19]黄振华,李正明,等.基于图像型森林火灾无线远程监控系统[J].传感器与微系统,2009,28(3)：86-88.
[20]何立,黄永穨,等.卫星遥感图像的增强处理[J].广西气象,2006,27(3)：61-65.
[21]何鹏,李春林.热成像型森林火灾报警系统设计及其图像处理方法研究[J].微计算机信息,2006,22(1-1)：98-99.
[22]侯杰.基于视频图像的高大空间建筑火灾探测研究[D].清华大学,2010.
[23]江涛.用于特定大规模森林火灾——火源的图像处理技术[J].红外,1999(1).
[24]金顺敬.基于全方位视觉的火灾安全监控系统的研究[D].浙江工业大学.2008.
[25]姜超.视频序列中运动目标提取与跟踪技术的研究[D].大连理工大学,2009.
[26]姜东海.基于图像处理的火灾烟雾识别技术研究[D].华中科技大学,2008.
[27]蒋爱平,于洋.基于Contourlet林火图像多重分形分割的研究[J].仪器仪表学报,2010,31(4)：818-822.
[28]焦珂.基于图像的火灾烟雾识别算法研究[D].西华大学,2008.
[29]贾小军,张之江,等.基于简化PCNN模型的结构光图像自动分割方法[J].光电子·激光,2011,22(3)：457-458.
[30]贾志成,胡天翔,刘春景.基于机器视觉的森林防火监测技术初步研究[J].2008,36(10)：21-23.
[31]靳富丽.模式识别理论及其应用[J].湖北广播电视大学学报,2007,27(12)：159-160.
[32]靳大路,王德兴,杨鹏.红外热成像技术在崂山森林防火系统中的研究与应用[J].电脑知识与技术,2008,4(6)：1494-495.
[33]康锋.基于视觉特征的早期农林火灾检测方法的基础研究[D].浙江大学,2010：31-33.
[34]李百良.基于PCNN及模糊金库算法的指纹识别技术的研究[D].苏州大学,2009：25-28.
[35]李国正,王猛,等(译者).支持向量机导论[M].北京：电子工业出版社,2004：1-20.
[36]李涟凤.基于支持向量机的医学图像分割[D].苏州大学,2010：9-20.
[37]李晨雷.基于支持向量机的战场目标识别技术研究[D].哈尔滨工业大学,2009：22-24.
[38]李春宇,郭相义.基于改进型脉冲耦合神经网络的乳腺图像肿块分割[J].科技广场,2010(7)：41-43.
[39]李虎胜,王慧琴,等.基于提升小波变换的火灾图像识别[J].计算技术与自动化,2008,27(2)：81-84.
[40]李莹,许春明,等.建筑防水材料火焰视频图像特征提取[J].消防科学与技术,2011,30(5)：374-376.
[41]李彦斌,陈树越.早期森林火灾烟雾图像序列的分割算法[J].计算机工程与应用,2008,44(11)：203-204.
[42]厉谨,王慧琴,等.基于PCNN分割的火焰图像检测技术[J].西安工程大学学报,2010,24(2)：217-221.
[43]练秋生,李党.融合多种特征的烟雾图像检测算法[J].光学技术,2009,35(4)：523-528.
[44]刘瑞祯,于仕琪OpenCV教程[M].北京：北京航空航天大学出版社,2007：15-60.
[45]刘显波,聂仁灿,等.基于可变步长PCNN的图像高斯噪声滤除[J]；云南大学学报(自然科学版),2010,32(1)：26-29.
[46]刘晨晨.高分辨率成像声纳图像识别技术研究[D].哈尔滨工程大学,2007.
[47]刘听雨.基于视频特征的火灾火焰识别算法[D].西安电子科技大学.2009.
[48]刘媛军.双波段野外火灾图像识别及目标定位方法研究[D].南京航空航天大学,2009.
[49]罗四维.大规模人工神经网络理论基础[M].北京：清华大学出版社,2004：17-26.
[50]罗鹏.林火协同监测技术研究[D].中国林业科学研究院,2010.
[51]栾龙源.基于自组织神经网络与模糊算法的彩色图像聚类分割系统[D].西安电子科技大学,2010：5-8.
[52]马文生,王阿川.基于卫星影像的图像挖掘在林火行为分析中的应用[J].林业劳动安全,2008,21(1)：44-47.
[53]马义德,李廉,王亚馥,等.脉冲耦合神经网络原理及其应用[M].北京：科学出版社,2006：1-20.
[54]赖均,解梅.基于PCNN与主动轮廓的肺CT候选结节的分割方法[J].计算机应用研究,2011,28(4)：1589-1590.
[55]倪福银,张旸.基于PCNN的人脸图像分割算法研究[J].江苏技术师范学院学报,2011,17(4)：11-13.
[56]彭真明,刘世军,等.基于PCNN的遥感SAR图像桥梁目标检测与识别[J].航空科学技术,2009(5)：22-26.
[57]覃先林,张子辉,等.一种利用HJ-1B红外相机数据自动识别林火的方法[J].遥感技术与应用,2010,25(5)：700-705.
[58]任海,高昌海,顾香凤.欧美森林火灾监测新技术及设备[J].林业机械与木工设备,2005,33(5)：8-11.
[59]饶裕平,方陆明,等.林火视频监控中烟识别方法概述[J].四川林业科技,2009,30(1)：81-85.
[60]史忠植.神经网络[M].北京：高等教育出版社,2009：48-79,203-204,215-217.
[61]舒立福,王明玉,等NOAA/AVHRR和EOS/MODIS林火监测比较[J].森林防火,2005(3)：27-29.
[62]沈海峰.图像通信与处理技术在林火监测中的应用研究[D].东北林业大学.2003(6)：1-7.
[63]吴雪琼,覃先林,等.我国林火监测体系现状分析[J].内蒙古林业调查设计,2010,33(3)：69-72.
[64]王涛,刘渊,等.一种基于飘动性分析的视频烟雾检测新方法[J].电子与信息学报,2011,33(5)：1024-1029.
[65]王绍波,郭业才,等.基于模糊PCNN的小波域超声医学图像去噪方法[J].光电子.激光,2010,21(3)：477-480.
[66]王振.几种自组织神经网络及其在彩色图像分割中的应用[D].江南大学,2009：11-15.
[67]王欣刚,魏峥,等.基于烟雾动态特征分析的实时火灾检测[J].计算机技术与发展,2008,18(11)：9-12.
[68]王正林,刘明.精通MATLAB(升级版)[M].北京：电子工业出版社,2011：5-60.
[69]王伟,宋卫国,等Kmeans聚类与多光谱阈值相结合的MODIS云检测算法[J].光谱学与光谱分析,2011,31(4)：1061-1064.
[70]汪小钦,周小成MODIS林火识别算法的验证分析[J].火灾科学,2006,15(1)：31-37.
[71]武林.基于运动特征分析的森林火灾烟云实施检测方法[J].信号处理,2006,22(2)：260-263.
[72]肖霞.基于类间方差的MODIS森林火灾监测方法研究[D].中国科学技术大学,2010.
[73]肖刚.国内外森林防火技术现状及趋势探讨[D].天津大学硕士论文,2005(11)：3-65.
[74]肖淑苹.基于进化概率神经网络的纹理图像识别[D].长沙理工大学,2008：13-16.
[75]肖利,汤家法,等MODIS数据监测森林火灾方法的研究[J].四川测绘,2008,31(1)：10-13.
[76]许维胜,田长征,等.基于图像视觉特征的火灾自动识别[J].计算机工程,2003,29(18)：112-113.
[77]许志闻,纪政,等.基于小波神经网络的炉膛火焰识别和诊断[J].仪器仪表学报,2004,25(4)：376-383.
[78]熊超.模式识别理论及其应用综述[J].中国科技信息,2006(6)：171-172.
[79]徐鹏,任波.基于单高斯模型的森林火灾烟图像目标检测[J].计算机与现代化,2009(2)：18-20.
[80]徐以美.视频序列中运动目标检测与跟踪技术研究[D].西安电子科技大学,2008.
[81]徐爱俊,方陆明,等.基于可见光视频的森林火灾识别算法[J].北京林业大学学报,2010,32(2)：14-20.
[82]夏寅辉.人脸皮肤纹理测量及识别方法研究[D].燕山大学,2003.
[83]夏文文.自组织神经网络的新算法以及应用[D].江南大学,2008：11-18.
[84]叶兵.国内外森林防火技术及其发展趋势[D].中国林业科学研究院硕士论文,2000(7)：3-50.
[85]杨猛,赵春晖,等.基于小波分析的烟雾多特征融合和空间精度补偿森林火情检测算法[J].中国图象图形学报,2009,14(4)：694-700.
[86]杨合超,宋海歌,等.模式识别的主要方法及其应用[J].电脑知识与技术,2008(S2)：156-157.
[87]杨行峻,郑君里.人工神经网络与盲信号处理[M].北京：清华大学出版社,2003：114-118
[88]杨高波,杜青松MATLAB图像／视频处理应用及实例[M].北京：电子工业出版社,2010：25-90.
[89]严红平,潘春洪.模式识别简述[J].自动化博览,2006(1)：22-26.
[90]闫厚,倪金生等.基于网络摄像机的森林火灾烟火自动识别技术探讨[J].森林防火,2007(2)：25-28.
[91]姚望玲.应用遥感资料识别鄂东森林火情的方法[J].湖北气象,2002(3)：15-18.
[92]袁宏永,赵建华,等.图像型大空间建筑早期火灾智能探测报警技术[J].消防技术与产品信息,2001(2)：30-32.
[93]袁非牛,张永明,等.基于累积量和主运动方向的视频烟雾检测方法[J].中国图象图形学报,2008,13(4)：808-813.
[94]殷光.基于SVM的验证码识别算法研究[D].安徽大学,2010：8-18.
[95]兆长胜.室内条件下基于视频序列的火灾烟雾检测算法研究[D].吉林大学,2010.
[96]郑焕能.森林防火[M].哈尔滨：东北林业大学出版社,1994.
[97]郑英,张万宝,陈惠明.森林火灾地面红外探测技术的研究[J].森林防火,2006(4)：28-.30.
[98]赵文化,张鹏,等.基于MODIS地表覆盖(LC)的森林火灾识别方法[J].气象科技,2008,36(2)：210-214.
[99]赵勇.基于PCNN的医学图像分割算法研究[D].太原科技大学,2009：29-36.
[100]赵琛.用概率神经网络对混凝土拱坝进行损伤位置识别的研究[D].浙江大学,2005：14-16.
[10]] 赵翀.智能视频系统中运动物体及烟火检测的算法研究[D].哈尔滨理工大学,2009.
[102]张前园,杨娜娟.一种自适应的图像型火灾探测算法[J].现代计算机(专业版),2010(5)：68-71.
[103]张军英,卢志军,等.基于脉冲耦合神经网络的椒盐噪声图像滤波[J].中国科学E辑：信息科学,2004,34(8)：882-894.
[104]周开利,康耀红.神经网络模型及其MATLAB仿真程序设计[M].北京：清华大学出版社,2005：20-110.
[105]Abuelgasim A, Fraser R. Day and night-time active fire detection over north america using noaa-16 avhrr data [C].2002 IEEE International Conference on IGARSS Proceedings, 2002(3):1489-1491.
[106]Andrei B. Utkin,Armando Fernandes,Fernando Simoes. Feasibility of forest-fire smoke detection using lindar[J].International Journal of Wildland Fire,2003(12):159-166.
[107]B. cholkopf, J.C. Platt, J. Shawe-Taylor, A.J. Smola. Estimating the support of a high-dimensional distribution [J]. Neural Computation,2001(13):1443-1471.
[108]B. Vagvolgyi,I.Kopilovic and T.Sziranyi, Application of panoramic annular lens for motion analysis tasks:surveillance and smoke detection[C], Proceedings of 15th International Conference on Pattern Recognition,2000, Volume 4,3-7 Sept.2000:714-717.
[109]Burges C J.C. A tutorial on support vector machines for pattern recognition[J].Data Mining and Knowledge Discovery,1998,2(2):121-167
[110]Cortes C,Vapnik V.Support Vector Networks [J].Machine Learning,1995(20):272-297.
[111]Collins RT, Lipton AJ, Kanade T. A system for video surveillance and monitoring[C]. Proceedings of American nuclear society (ANS) 8th International Topical Meeting On Robotics And Remote Systems,1999.
[112]Chen T, Wu P, Chiou Y. An early fire-detection method based on image processing[C]. Proceedings of 2004 IEEE ICIP,2004:1707-1710.
[113]C.C. Chang, C.J. Lin. LIBSVM:A Library for Support Vector Machines [J/OL]. http://www.csie.ntu.edu.tw/cjlin/libsvm,2011.
[114]Chris Justice and Yoram J.Kufuman. MODIS Fire Product s [D].Algorithm Technical Background Document,1998,11 (10).
[115]C.O. Justice L,J. Kendall.,Giglio. Evaluation of global fire detection algorithms using simulated AVHRR data[J], Internat. J. Remote Sensing 20 (1999) 1947-1986.
[116]Chung YS.Satellite detection of forest fires in Korea and associated smoke plumes [J]. International Journal Of Remote Sensing,2003,24(1):1-7.
[117]da Penha Osman S. Nakamura Eduardo F. Fusing light and temperature data for fire detection [C].2010 IEEE Symposium on Computers and Communications (ISCC) Proceedings, 2010:107-112.
[118]Damir Krstinic, Darko Stipanicev, Toni Jakovcevic. Histogram-based smoke segmentation in forest fire detection system[J]. Information Technology And Control,2009,38(3):237-244.
[119]F.Gomez-Rodriguez, S.Pascual-pena,B.C.Arrue & A.Ollero.Smoke detection using image processing[C]. The IV International Conference On Forest Fire Research Proceedings,2002.
[120]Fujiwara K, Kudoh J. Siberian forest fire detection using NOAA AVHRR [C]. IEEE 2001 International IGARSS Proceedings,2001(4):1687-1689.
[121]Gunay O,Toreyin BU. Online adaptive decision fusion framework based on projections onto convex sets with application to wildfire detection in video[J]. Optical Engineering,2011,50(7): 1-7.
[122]Gomez-Rodriguez F, Arrue B C, Ollero A. Smoke monitoring and measurement using image processing[C]. Application to forest fires. In. Proc. of SPIE, Automatic Target Recognition XIII, 2003(5094):404-411.
[123]Hu Peng, Jin Li, Lili Jiang,Qingwen Qi, Xiuping Zou,Yajuan Liang. Technique for Automatic Forest Fire Surveillance Using Visible Light Image[C]. Proc. IEEE(2005):3135-3138.
[124]H. J. Grech-Cini, "Smoke Detection"[J], US Patent No. US6844818B2.
[125]Ham S.unJae,Ko Byoung-Chul,Nam Jae-Yea. Vision based forest smoke detection using analyzing of temporal patterns of smoke and their probability models [C]. Proceedings of SPIE-The International Society for Optical Engineering,2011,7877.
[126]Jerome Vicente,PhiIippe Guillemant, "An image processing technique for automatically detecting forest fire"[C], International Journal of Thermal Sciences 41(2002) 1113-1120.
[127]J.L. Johnson. Pulse-coupled neural nets:translation, rotation, scale, distortion, and intensity signal invariance for images [J]. Applied Optics,1994(33):6239-6253.
[128]Jing Wang, Weiguo Song, Wei Wang. A new algorithm for forest fire smoke detection based on MODIS data in Heilongjiang province [C].2011 International Conference on Remote Sensing,Environment and Transportation Engineering(RSETE) Proceedings,2011:5-8.
[129]Kudoh J, Hosoi K. Two dimensional Forest Fire Detection method by using NOAA AVHRR images [C].2003 IEEE IGARSS Proceedings,2003(4):2494-2495.
[130]Kohonen T. Self-organized formation of topologically correct feature maps [J]. Biological Cybernetics,1982(43):59-69.
[131]Karvonen, J. A simplified pulse-coupled neural network based sea-ice classifier with graphical interactive training[C]. Geoscience and Remote Sensing Symposium,2000. Proceedings. IGARSS 2000. IEEE 2000 International:681-684,2000.
[132]Kohonen T. Learning vector quantization for pattern recognition[R]. Technical Report TKK-F-A601, Helsinki University of Technology, Finland,1986.
[133]K.R. Muller, S. Mika, G. Ratsch, K. Tsuda. An introduction to kernel-based learning algorithms [J]. IEEE Transactions on Neural Networks,2001,12(2):181-201.
[134]Kohonen T. Improved versions of learning vector quantization [C]. IEEE International Joint Conference on Neural Network. San Diego, CA,1990(I):545-550.
[135]Kanal L. Pattern in pattern actions recognition:1968-1974[J].IEEE TransonIT,1974,20 (6):697-722.
[136]Kushida K. Detection of active wildland fires using multitemporal modis images [C]. IEEE Geoscience And Remote Sensing Letters,2010,7(2):301-305.
[137]Li Ma, Kaihua Wu, Zhu L. Fire smoke detection in video images using kalman filter and gaussian mixture color model [C].2010 International Conference on Artificial Intelligence and Computational Intelligence (AICI) Proceedings,2010(1):484-487.
[138]Lindblad T,KjnserJ M.Image proeessing using Pulse-Coupled Neural Networks[M].2th Revised Edition[J].NY.:Springer-Verlag Berlin Heidelberg,2005:3-50.
[139]Liu Shixing,Zhang Yongming, Song Weiguo, Xiao Xia. An enhanced algorithm for forest fire detection based on modis data [C].2010 International Conference on Optoelectronics and Image Processing (ICOIP) Proceedings,2010(1):200-203.
[140]Rumelhart D E, Hinton G E. Learning representations of back-propagation errors [J]. Nature, 1986(323):533-536.
[141]Raul C. Muresan Pattern recognition using pulse-coupled neural networks and discrete Fourier transforms [J]. Neurocomputing,2003(51):487-493.
[142]. Specht D F. Probabilistic neural networks [J]. Neural Networks,1990,3(1):109-118.
[143]Surit S, Chatwiriya W. Forest fire smoke detection in video based on digital image processing approach with static and dynamic characteristic analysis [C].2011 First ACIS/JNU International Conference on CNSI Proceedings,2011:35-39.
[144]Soliman H, Sudan K, Mishra A. A smart forest-fire early detection sensory system:Another approach of utilizing wireless sensor and neural networks [C].2010 IEEE Sensors Proceedings, 2010:1900-1904.
[145]Takashi Watanabe,Masaru Tanaka, Takio Kurita,Taketoshi Misllima.Autonomous foveating system based on Pulse-CouPled Neural Network[C].Proceedings of the ITC-CSCC99, 1999(01):197-200.
[146]Turgay Celik.Fast and Efficient Method for Fire Detection Using Image Processing [J]. ETRI Joumal,2010,32(6):881-890.
[147]Tung Truong Xuan,Kim Jong-Myon. An effective four-stage smoke-detection algorithm using video images for early fire-alarm systems [J]. Fire Safety Journal,2011,46(5):276-282.
[148]Wenbin Li, Junguo Zhang. The monitoring of host computer for forest fire detection system based on wireless sensor network [C].5th International Conference on Wireless Communications, Networking and Mobile Computing Proceedings,2009.
[149]Yang Chan-Yun,Tseng Wei-Wen, Yang Jr-Syu. Reducing false alarm of video-based smoke detection by support vector machine[C]. Proceedings of IEEE International Conference on Intelligence and Security Informatics,2008,5075 LNCS:102-113.
[150]Yide Ma, Li Liu. Pulse-coupled neural networks and one-class support vector machines [J]. Image and Vision Computing,2010(28):1524-1529.
[151]Yu Chunyu, Fang Jun, Wang Jinjun and Zhang Yongming. Video Fire Smoke Detection Using Motion and Color Features [J]. Fire Technology,2010(46):651-663.
[152]Zhanqing Li, Alexandre Khananian, Robert H. Fraser, Josef Cihlar. Automatic detection of fire smoke using artificial neural networks and threshold approaches appliedto avhrr imagery [C]. IEEE Transactions On Geoscience And Remote Sensing,2001,39(9):1859-1870.