基于神经网络和分形纹理的夜间浓雾遥感监测技术
REMOTE SENSINGMONITORING TECHNOLOGY OF THICK FOG AT NIGHT BASED ON NEURAL NETWORKS AND FRACTAL GRAIN
-
摘要: 利用地物光谱信息和图像纹理信息作为地物分类识别标志,将分形理论和BP神经网络应用于夜间浓雾的遥感监测,使夜间浓雾的监测精度明显提高。与传统最大似然法(MLC)比较,晴空地表、雾区、云区的识别精度均有提高,特别是云区的识别精度提高了10%,基于灰度连通域的灰度加权计盒维数图像纹理提取技术使云雾边界的提取更加合理,文章最后对类的归并作了讨论。Abstract: In terms of the ground-object spectrum information and the image-grain information as symbols to distinguish the ground-objects, fractal theory and BP neural networks are used to monitor thick fog at night, which increases the monitoring precision of thick fog obviously. Compared with the traditional Maximum Likelihood Classifying (MLC), the identified precision of clear sky ground, fog areas, cloud areas is increased, especially that of the cloud areas is increased by 10%. The image-grain extraction technology of grey-power box-counting dimension basing on grey degree connected region made extracting the borderline of cloud and fog more reasonable. Also, the merger of kings is discussed。
-
表 1 MLC与BP 分类法精度对比表
-
[1] 刘健,许健民,方宗义.利用NOAA卫星的AVHRR资料试分析云和雾顶部粒子的尺度特征.应用气象学报,1999,10(1):28-33。 http://qikan.camscma.cn/jams/ch/reader/view_abstract.aspx?file_no=19990132&flag=1 [2] Eyre J R,Brownscombe J L,Allam R J.Detection of fog at night using Advanced Very High Resolution Radiometer(AVHRR) imagery.Meteor Mag,1984,113:266-271。 http://cn.bing.com/academic/profile?id=4a9daea6fdf1fdad2376a259e7712459&encoded=0&v=paper_preview&mkt=zh-cn [3] Turner J,Allam R J,Maine D R.A case study of the detection of fog at night using channels 3 and 4 on the Advanced Very High Resolution Radiometer (AVHRR).Meteor Mag,1986,115:285-97。 https://www.researchgate.net/publication/285778426_A_case_study_of_the_detection_of_fog_at_night_using_channels_3_and_4_on_the_Advanced_Very_High_Resolution_Radiometer_AVHRR [4] d'Entremont R R.Low and mid level cloud analysis using nighttime multispectral imagery.J Clim Appl Meteor,1986,25:1853-1869。 doi: 10.1175/1520-0450(1986)025<1853:LAMCAU>2.0.CO;2 [5] 李亚春,孙涵,徐萌.卫星遥感在大雾生消动态监测中的应用.灾害学,2001,16(1):45-49。 http://www.cnki.com.cn/Article/CJFDTOTAL-ZHXU200101009.htm [6] 陈伟,周红妹,袁志康,等.基于气象卫星分形纹理的云雾分离研究.自然灾害学报,2003,12(2):133-139。 http://www.cnki.com.cn/Article/CJFDTOTAL-ZRZH200302023.htm [7] 王淑华,赵宇明,周小四,等.基于灰度连通域加权分数维的云雾自动分离算法.红外与激光工程,2002,31(2):18-22。 http://www.cnki.com.cn/Article/CJFDTOTAL-HWYJ200201004.htm [8] 骆剑承,周成虎,杨艳.人工神经网络遥感影像分类模型及其与知识集成方法研究.遥感学报,2001,5(2):122-129。 http://www.cnki.com.cn/Article/CJFDTOTAL-YGXB200102009.htm [9] 周成虎,骆剑承,杨晓梅,等.遥感影像地学理解与分析.北京:科学出版社,2001.23-24。