期刊
JOURNAL OF SPATIAL SCIENCE
卷 55, 期 1, 页码 69-79出版社
TAYLOR & FRANCIS LTD
DOI: 10.1080/14498596.2010.487851
关键词
segmentation; optimization; Random Forest; variable selection; classification
This paper describes an approach to using the Random Forest classification algorithm to quantitatively evaluate a range of potential image segmentation scale alternatives in order to identify the segmentation scale(s) that best pi edict land covet classes or interest The image segmentation scale selection process was used to identify three critical image object scales that when combined produced need an optimal level of land cove, classification accuracy. Following segmentation scale optimization, the Random Forest classifier was then used to assign land cover classes to 11 scenes or SPOT satellite imagery in North and South Dakota with an average overall accuracy or 85 2 percent
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据