基于CART方法的果园信息提取研究  

Orchard Extraction Based on CART

作　　者：王大鹏[1] 

机构地区：[1]枣庄学院旅游与资源环境系,山东枣庄277160

出　　处：《农机化研究》2009年第9期52-54,共3页Journal of Agricultural Mechanization Research

基　　金：山东省自然科学基金项目(Z2003E01)

摘　　要：利用遥感手段快速、准确地获取果园分布和面积等信息对于以水果为主产业的地区来说意义重大,而目前国内此类研究尚不多见。为此,以SPOT-5遥感影像为数据源,利用CART(分类回归树)方法从训练样本中发现地物分类规则,结合目标地物的光谱特征、纹理特征、地形坡度信息等专家知识,进行果园信息提取实验,取得了86.72%的分类精度,这说明用CART方法进行果园信息提取是可行的。Gaining the orchard information promptly and effectively is significant to instruct fruit production and local planning. In this paper, we investigate orchard extraction model from SPOT -5 image based on classification and regres- sion tree （CART）. Classification rules are discovered from these samples through classification and regression tree （CART） , which integrates spectral, textural, DEM and slop characters. Finally, it get an accuracy of 86.72% and it was felt that it is a good way to extraction orchard information.

关 键 词：果园 CART 信息提取 

分 类 号：S126[农业科学—农业基础科学]