Considering to the texture differences among foresty types, texture features of forestry were firstly extracted from remote sensing imagery with discrete wavelet transformation, and the imagery was then classified combining objectoriented classification method with the original spectral values and texture features. Six texture measure factors which can reflect the difference efficiently among plant difference are sieved out based on analyzing of wavelet decomposition level, sliding window and texture measure. This method could solve the problems of forestry type classification, tree species classification, etc. The overall classification accuracy reached 92.7 %, and it is much better than traditional method of classification based on pixel values.
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
References
[1]戴昌达,姜小光,唐伶俐. 遥感图像应用处理与分析[M]. 北京:清华大学出版社,2000.
[2]赵英时. 遥感应用分析原理与方法[M]. 北京:科技出版社,2002.
[3]孙家抦. 遥感原理与应用[M]. 武汉:武汉大学出版社,2002.
[4]朱长青,杨启和,朱文忠. 基于小波变换特征的遥感地貌影像纹理分析和分类[J]. 测绘学报,1996(25):252-256.
[5]曾福年. 新技术在土地调查中的应用与土地科学技术发展2005年中国土地学会学术年会综述[R]. 北京:中国土地学会,2006.
[6]刘泓,莫玉龙. 改进的多分辨率纹理图像分割算法[J]. 光学学报,2000(6):16-20.
[7]陈杉,秦其明. 基于小波变换的多分辨率影像纹理结构分类方法[J]. 地理与地理信息科学,2003(19):6-9.
[8]金炜,俞建定. 基于EBPOP算法于纹理特征的图像检索[J]. 计算机工程与应用,2002(8):54-58.
[9]周延刚,郭达志,盛业华. 灰度矢量多波段遥感影像纹理特征及其描述[J]. 西安科技学院学报,2000(20):336-338.
[10]蔡艳,傅德胜. 基于卫星遥感图像纹理特征的云类识别方法及软件设计[J]. 南京气象学院学报,1999(9):38-43.
[11]容观澳. 计算机图像处理[M]. 北京:清华大学出版社,1998.
PDF(1403751 KB)
