基于运动路径角的林火烟雾图像检测探究
|
摘要
针对林火烟雾图像检测从图像信息中提取的特征,数据记录多,存储大,消耗运算速率的问题,提出了基于运动路径角的烟雾检测探究,对烟雾特征进行优化。在真实的森林环境下,用烟饼燃烧产生的烟雾模拟森林火灾初期产生的烟雾,用视频监控记录烟雾的运动,并且搜集不同情况下烟雾图像和不同情况下天空中云的图像,应用图像处理技术分别对烟雾和云图像进行处理和运动路径角计算,对比分析烟雾和云的运动路径角范围,烟雾独特的运动路径角可以作为识别烟雾的特征。在处理烟雾数据中,将图像包含的烟雾信息转换为烟雾的代数特征,较烟雾的颜色特征、纹理特征、运动面积等特征的提取,数据量减少,存储变小,耗时少。
To solve the problems existed in the extraction of the characteristics from the smoke images of forest fire,such as image information redundancy,large storage,consumption of computing speed,this paper proposed a new way for forest fire smoke detection that was based on the motion path angle to optimize the characteristics of the smoke.In a real forest environment,smoke was produced by burning tobacco cake to simulate early forest fire smoke.Video surveillance was used to record the motion of smoke.Smoke images and images of cloud in the sky were collected under different circumstances.The motion path angle was calculated to find out the range of motion path angles of smoke and cloud which could be used as the identification feature of smoke.When dealing with smoke data,smoke image information was converted to algebraic characteristics of smoke.Compared to the extraction of other features,such as smoke color feature,texture feature,and moving area,the motion path angle based data extraction decreased the data amount and storage,and less time was needed to conduct calculation.
To solve the problems existed in the extraction of the characteristics from the smoke images of forest fire,such as image information redundancy,large storage,consumption of computing speed,this paper proposed a new way for forest fire smoke detection that was based on the motion path angle to optimize the characteristics of the smoke.In a real forest environment,smoke was produced by burning tobacco cake to simulate early forest fire smoke.Video surveillance was used to record the motion of smoke.Smoke images and images of cloud in the sky were collected under different circumstances.The motion path angle was calculated to find out the range of motion path angles of smoke and cloud which could be used as the identification feature of smoke.When dealing with smoke data,smoke image information was converted to algebraic characteristics of smoke.Compared to the extraction of other features,such as smoke color feature,texture feature,and moving area,the motion path angle based data extraction decreased the data amount and storage,and less time was needed to conduct calculation.
引文
[1]舒立福,田晓瑞.国外森林防火工作现状及展望[J].世界林业研究,1997(2):28-35.
[2]肖化顺,刘小永,曾思齐.欧美国家林火研究现状与展望[J].西北林学院学报,2012,27(2):131-136.XIAO H S,LIU X Y,ZENG S Q.Status and prospect of forest fire research in Europe and the United States[J].Journal of Northwest Forestry University,2012,27(2):131-136.(in Chinese)
[3]韩恩贤,薄颖生,韩刚.森林火灾灾害等级划分初探[J].西北林学院学报,1998,13(1):79-82.HAN E X,BO Y S,HAN G.A preliminary research on grading of forest fire calamity[J].Journal of Northwest Forestry University,1998,13(1):80-83.(in Chinese)
[4]赖小龙,于文华,赵燕东,等.基于多传感器数据融合的早期林火识别[J].西北林学院学报,2015,30(4):178-183.LAI X L,YU W H,ZHAO Y D,et al.Early forest fire detection algorithm based on multi-sensor data fusion[J].Journal of Northwest Forestry University,2015,30(4):178-183.(in Chinese)
[5]范一舟,马洪兵.基于视频的林火烟雾识别方法[J].清华大学学报:自然科学版,2015,55(2):243-250,256.FAN Y Z,MA H B.Video based forest-fire smoke detection[J].Journal of Tsinghua University:Science and Technology,2015,55(2):243-250,256.(in Chinese)
[6]饶裕平,柴红玲.林火视频监控中烟识别方法概述[J].林业调查规划,2009,34(1):59-62.
[7]兰久强,刘金清,刘引,等.基于颜色和纹理特征的林火烟雾识别[J].计算机系统应用,2016,25(3):101-106.LAN J Q,LIU J Q,LIU Y,et al.Forest fire smoke recognition based on color and texture features[J].Computer Systems&Applications,2016,25(3):101-106.(in Chinese)
[8]HIDENORI M,AKIHIRO N,FUJIO K.A new approach for smoke detection with texture analysis and support vector machine[J].International Symposium on Industrial Electronics,2010:1550-1555.
[9]ZHAO Y Q,ZHOU ZH,XU M M.Forest fire smoke video detection using spatiotemporal and dynamic texture features[J].Journal of Electrical and Computer Engineering,2015.
[10]周忠,赵亚琴,唐于维一,等.基于时空特征的林火视频烟雾区域提取[J].中国农机化学报,2016,37(2):196-199.ZHOU Z,ZHAO Y Q,TANG Y W Y,et al.Segmentation of forest fire video smoke region based on the temporal-spatital features[J].Journal of Chinese Agricultural Mechanization,2016,37(2):196-199.(in Chinese)
[11]于海晶,李桂菊.基于差分盒维数的彩色烟雾图像识别[J].山东大学学报:工学版,2014(1):35-40.YU H J,LI G J.Color smoke image recognition based on differential box-counting fractal dimension algorithm[J].Journal of Shandong University:Engineering Science,2014(1):35-40.(in Chinese)
[12]黄英来,田少卿,孙晓芳.一种基于灰度位平面的林火烟雾图像自动识别方法[J].东北林业大学学报,2013,41(8):155-159.HUANG Y L,TIAN S Q,SUN X F.An automatic recognition method based on gray bit plane for forest fire smoke feature[J].Journal of Northeast Forestry University,2013,41(8):155-159.(in Chinese)
[13]张叶.森林火情烟雾识别算法研究[J].仪器仪表学报,2014,35(S1):103-106.ZHANG Y.A study on forest fire smoke automatic recognition[J].Chinese Journal of Scientific Instrument,2014(S1):103-106.(in Chinese)
[14]黎粤华,单磊,田仲富,朱自民.基于多特征融合的视频烟雾检测[J].计算机技术与发展,2016,26(1):129-133.LI Y H,SHAN L,TIAN Z F,et al.Video smoke detection based on multi feature fusion technology[J].Computer Technology and Development,2016,26(1):129-133.(in Chinese)
[15]吴冬梅,李白萍,沈燕,等.基于多特征融合的烟雾检测[J].图学学报,2015,36(4):587-592.WU D M,LI B P,SHEN Y,et al.Smoke detection based on multi-feature fusion[J].Journal of Graphics,2015,36(4):587-592.(in Chinese)
[16]焦斌亮,董雪.基于非参数特征提取的早期林火烟雾检测[J].光学技术,2016,42(1):20-23.JIAO B L,DONG X.An early forest-fire smoke detection method based on non-parametric feature extraction[J].Optical Technique,2016,42(1):20-23.(in Chinese)
[17]毕振波,乐天,潘洪军,等.图像型火灾探测预处理方法综述[J].消防科学与技术,2016,35(1):87-91.
[18]孙玉荣,张贵.基于神经网络的森林火灾危害程度预测研究[J].西北林学院学报,2010,25(3):147-150,162.SUN Y R,ZHANG G.Forecasting study of forest-fire harm degree based on neural network[J].Journal of Northwest Forestry University,2010,25(3):147-150,162.(in Chinese)
[2]肖化顺,刘小永,曾思齐.欧美国家林火研究现状与展望[J].西北林学院学报,2012,27(2):131-136.XIAO H S,LIU X Y,ZENG S Q.Status and prospect of forest fire research in Europe and the United States[J].Journal of Northwest Forestry University,2012,27(2):131-136.(in Chinese)
[3]韩恩贤,薄颖生,韩刚.森林火灾灾害等级划分初探[J].西北林学院学报,1998,13(1):79-82.HAN E X,BO Y S,HAN G.A preliminary research on grading of forest fire calamity[J].Journal of Northwest Forestry University,1998,13(1):80-83.(in Chinese)
[4]赖小龙,于文华,赵燕东,等.基于多传感器数据融合的早期林火识别[J].西北林学院学报,2015,30(4):178-183.LAI X L,YU W H,ZHAO Y D,et al.Early forest fire detection algorithm based on multi-sensor data fusion[J].Journal of Northwest Forestry University,2015,30(4):178-183.(in Chinese)
[5]范一舟,马洪兵.基于视频的林火烟雾识别方法[J].清华大学学报:自然科学版,2015,55(2):243-250,256.FAN Y Z,MA H B.Video based forest-fire smoke detection[J].Journal of Tsinghua University:Science and Technology,2015,55(2):243-250,256.(in Chinese)
[6]饶裕平,柴红玲.林火视频监控中烟识别方法概述[J].林业调查规划,2009,34(1):59-62.
[7]兰久强,刘金清,刘引,等.基于颜色和纹理特征的林火烟雾识别[J].计算机系统应用,2016,25(3):101-106.LAN J Q,LIU J Q,LIU Y,et al.Forest fire smoke recognition based on color and texture features[J].Computer Systems&Applications,2016,25(3):101-106.(in Chinese)
[8]HIDENORI M,AKIHIRO N,FUJIO K.A new approach for smoke detection with texture analysis and support vector machine[J].International Symposium on Industrial Electronics,2010:1550-1555.
[9]ZHAO Y Q,ZHOU ZH,XU M M.Forest fire smoke video detection using spatiotemporal and dynamic texture features[J].Journal of Electrical and Computer Engineering,2015.
[10]周忠,赵亚琴,唐于维一,等.基于时空特征的林火视频烟雾区域提取[J].中国农机化学报,2016,37(2):196-199.ZHOU Z,ZHAO Y Q,TANG Y W Y,et al.Segmentation of forest fire video smoke region based on the temporal-spatital features[J].Journal of Chinese Agricultural Mechanization,2016,37(2):196-199.(in Chinese)
[11]于海晶,李桂菊.基于差分盒维数的彩色烟雾图像识别[J].山东大学学报:工学版,2014(1):35-40.YU H J,LI G J.Color smoke image recognition based on differential box-counting fractal dimension algorithm[J].Journal of Shandong University:Engineering Science,2014(1):35-40.(in Chinese)
[12]黄英来,田少卿,孙晓芳.一种基于灰度位平面的林火烟雾图像自动识别方法[J].东北林业大学学报,2013,41(8):155-159.HUANG Y L,TIAN S Q,SUN X F.An automatic recognition method based on gray bit plane for forest fire smoke feature[J].Journal of Northeast Forestry University,2013,41(8):155-159.(in Chinese)
[13]张叶.森林火情烟雾识别算法研究[J].仪器仪表学报,2014,35(S1):103-106.ZHANG Y.A study on forest fire smoke automatic recognition[J].Chinese Journal of Scientific Instrument,2014(S1):103-106.(in Chinese)
[14]黎粤华,单磊,田仲富,朱自民.基于多特征融合的视频烟雾检测[J].计算机技术与发展,2016,26(1):129-133.LI Y H,SHAN L,TIAN Z F,et al.Video smoke detection based on multi feature fusion technology[J].Computer Technology and Development,2016,26(1):129-133.(in Chinese)
[15]吴冬梅,李白萍,沈燕,等.基于多特征融合的烟雾检测[J].图学学报,2015,36(4):587-592.WU D M,LI B P,SHEN Y,et al.Smoke detection based on multi-feature fusion[J].Journal of Graphics,2015,36(4):587-592.(in Chinese)
[16]焦斌亮,董雪.基于非参数特征提取的早期林火烟雾检测[J].光学技术,2016,42(1):20-23.JIAO B L,DONG X.An early forest-fire smoke detection method based on non-parametric feature extraction[J].Optical Technique,2016,42(1):20-23.(in Chinese)
[17]毕振波,乐天,潘洪军,等.图像型火灾探测预处理方法综述[J].消防科学与技术,2016,35(1):87-91.
[18]孙玉荣,张贵.基于神经网络的森林火灾危害程度预测研究[J].西北林学院学报,2010,25(3):147-150,162.SUN Y R,ZHANG G.Forecasting study of forest-fire harm degree based on neural network[J].Journal of Northwest Forestry University,2010,25(3):147-150,162.(in Chinese)