基于多尺度纹理与光谱特征的马尾松毛虫虫害信息提取方法研究
|
摘要
以福建沙县为研究区,融合SPOT-5多光谱影像与全色影像,基于灰度共生矩阵法提取纹理量,与光谱波段组合,采用支持向量机分类方法提取虫害信息,探讨纹理特征对于虫害监测信息提取精度的影响。结果表明:结合多尺度纹理与光谱特征的支持向量机分类方法,其虫害信息提取总精度最高,为80.48%;结合单尺度纹理与光谱特征的支持向量机分类器方法,其虫害信息提取总精度次之,为78.81%;基于光谱特征的最大似然法,其虫害信息提取总精度最低,为70.48%。结合多尺度纹理与光谱特征的支持向量机分类器方法,其图面表现也较好,减少了图面的细碎斑点。因此,提取多尺度纹理与光谱特征结合,丰富了图像信息量,有助于提高虫害信息的提取精度。
Taking Shaxian County of Fujian Province as the research area, the SPOT-5 multi-spectral image and panchromatic image were merged, the texture quantity was extracted based on the gray level co-occurrence matrix method, and the spectral band was combined. The support vector machine classification method was used to extract the pest information. Exploring the influence of texture features on the accuracy of pest monitoring information extraction. The results show that the support vector machine classification method combining multiscale texture and spectral features has the highest total accuracy of pest information extraction, which is 80.48%.The support vector machine classifier method combined with single-scale texture and spectral features has the second highest accuracy of pest information extraction, which is 78.81%. Based on the maximum likelihood method of spectral features, the total accuracy of pest information extraction is the lowest, which is 70.48%. The support vector machine classifier method combining multi-scale texture and spectral features has better surface performance and reduces the fine spots on the surface. Therefore, extracting multi-scale textures combined with spectral features enriches the amount of image information and helps to improve the extraction accuracy of pest information.
Taking Shaxian County of Fujian Province as the research area, the SPOT-5 multi-spectral image and panchromatic image were merged, the texture quantity was extracted based on the gray level co-occurrence matrix method, and the spectral band was combined. The support vector machine classification method was used to extract the pest information. Exploring the influence of texture features on the accuracy of pest monitoring information extraction. The results show that the support vector machine classification method combining multiscale texture and spectral features has the highest total accuracy of pest information extraction, which is 80.48%.The support vector machine classifier method combined with single-scale texture and spectral features has the second highest accuracy of pest information extraction, which is 78.81%. Based on the maximum likelihood method of spectral features, the total accuracy of pest information extraction is the lowest, which is 70.48%. The support vector machine classifier method combining multi-scale texture and spectral features has better surface performance and reduces the fine spots on the surface. Therefore, extracting multi-scale textures combined with spectral features enriches the amount of image information and helps to improve the extraction accuracy of pest information.
引文
[1]庞正轰.马尾松毛虫灾害预测预报综合技术研究[D].北京:北京林业大学,2004.
[2]孙福洋,王建和,付伟,等.基于MODIS-NDVI数据的大区域森林病虫害理赔指数构建及应用[J].林业资源管理,2017(6):149-152,158.
[3]刘文雅.松材线虫病胁迫下松树生理参数的高光谱遥感估测模型研究[D].南京:南京林业大学,2017.
[4]朱程浩,瞿帅,张晓丽.油松毛虫灾害遥感监测及其影响因子分析[J].遥感学报,2016,20(4):653-664.
[5]王震,张晓丽,安树杰.松材线虫病危害的马尾松林木光谱特征分析[J].遥感技术与应用,2007,22(3):367-370.
[6]王胜,潘洁,张衡,等.基于高光谱遥感影像的森林病虫害监测研究进展[J].林业资源管理,2014(3):134-140.
[7]Johnson P D Jr,Harris G A,Hankerson D C.Introduction to Information Theory and Data Compression[M].New York:Chapman and Hall/CRC,2003.
[8]谭永生.像素级中高分辨率遥感影像融合研究[D].杭州:浙江大学,2007.
[9]Ehlers M.Multisensor image fusion techniques in remote sensing[J].ISPRS Journal of Photogrammetry and Remote Sensing,1991,46(1):19-30.
[10]Harris J R,Murray R,Hirose T.IHS transform for the integration of radar imagery with other remotely sensed data[J].Photogrammetric Engineering and Remote Sensing,1990,56:1631-1641.
[11]陈超,江涛,岳远平,等.像素级遥感图像融合方法研究[J].国土资源信息化,2008(5):30-34.
[12]陈超.遥感数据融合智能化处理方法研究[D].青岛:山东科技大学,2009.
[13]陈德超,周海波,陈中原,等.TM与SPOT影像融合算法比较研究[J].遥感技术与应用,2001,16(2):110-115.
[14]亓兴兰.SPOT-5遥感影像马尾松毛虫害信息提取技术研究[D].福州:福建农林大学,2011.
[15]国家林业局植树造林司,国家林业局森林病虫害防治总站.森林病虫害防治知识问答[M].北京:中国林业出版社,1999:2-5.
[16]陈晨,张友静.基于多尺度纹理和光谱信息的SVM分类研究[J].测绘科学,2009,34(1):29-31.
[17]沈璐,权亚楠,禹哲珠,等.一种结合纹理特征的极化SAR图像SVM分类方法[J].北京测绘,2018(10):1235-1239.
[18]王宏胜.基于面向对象的两阶段村域无人机影像土地利用分类研究[D].成都:西南交通大学,2018.
[19]王美雅,许章华.马尾松毛虫危害下的马尾松纹理特征分析[J].江西农业大学学报,2015,37(4):653-662.
[20]Caccetta P A,Campbell N A,Evans F H,et al.Mapping and monitoring land use and condition change in theSouth-West of Western Australia using remote sensing and other data[C]//Proceedings of the Information Security Solutions Europe(ISSE2000)Conference,Barcelona,27-29 September 2000.
[21]万意,李长春,赵旭辉,等.基于SVM的光学遥感影像分类与评价[J].测绘地理信息,2018,43(6):74-77.
[2]孙福洋,王建和,付伟,等.基于MODIS-NDVI数据的大区域森林病虫害理赔指数构建及应用[J].林业资源管理,2017(6):149-152,158.
[3]刘文雅.松材线虫病胁迫下松树生理参数的高光谱遥感估测模型研究[D].南京:南京林业大学,2017.
[4]朱程浩,瞿帅,张晓丽.油松毛虫灾害遥感监测及其影响因子分析[J].遥感学报,2016,20(4):653-664.
[5]王震,张晓丽,安树杰.松材线虫病危害的马尾松林木光谱特征分析[J].遥感技术与应用,2007,22(3):367-370.
[6]王胜,潘洁,张衡,等.基于高光谱遥感影像的森林病虫害监测研究进展[J].林业资源管理,2014(3):134-140.
[7]Johnson P D Jr,Harris G A,Hankerson D C.Introduction to Information Theory and Data Compression[M].New York:Chapman and Hall/CRC,2003.
[8]谭永生.像素级中高分辨率遥感影像融合研究[D].杭州:浙江大学,2007.
[9]Ehlers M.Multisensor image fusion techniques in remote sensing[J].ISPRS Journal of Photogrammetry and Remote Sensing,1991,46(1):19-30.
[10]Harris J R,Murray R,Hirose T.IHS transform for the integration of radar imagery with other remotely sensed data[J].Photogrammetric Engineering and Remote Sensing,1990,56:1631-1641.
[11]陈超,江涛,岳远平,等.像素级遥感图像融合方法研究[J].国土资源信息化,2008(5):30-34.
[12]陈超.遥感数据融合智能化处理方法研究[D].青岛:山东科技大学,2009.
[13]陈德超,周海波,陈中原,等.TM与SPOT影像融合算法比较研究[J].遥感技术与应用,2001,16(2):110-115.
[14]亓兴兰.SPOT-5遥感影像马尾松毛虫害信息提取技术研究[D].福州:福建农林大学,2011.
[15]国家林业局植树造林司,国家林业局森林病虫害防治总站.森林病虫害防治知识问答[M].北京:中国林业出版社,1999:2-5.
[16]陈晨,张友静.基于多尺度纹理和光谱信息的SVM分类研究[J].测绘科学,2009,34(1):29-31.
[17]沈璐,权亚楠,禹哲珠,等.一种结合纹理特征的极化SAR图像SVM分类方法[J].北京测绘,2018(10):1235-1239.
[18]王宏胜.基于面向对象的两阶段村域无人机影像土地利用分类研究[D].成都:西南交通大学,2018.
[19]王美雅,许章华.马尾松毛虫危害下的马尾松纹理特征分析[J].江西农业大学学报,2015,37(4):653-662.
[20]Caccetta P A,Campbell N A,Evans F H,et al.Mapping and monitoring land use and condition change in theSouth-West of Western Australia using remote sensing and other data[C]//Proceedings of the Information Security Solutions Europe(ISSE2000)Conference,Barcelona,27-29 September 2000.
[21]万意,李长春,赵旭辉,等.基于SVM的光学遥感影像分类与评价[J].测绘地理信息,2018,43(6):74-77.