文献类型：会议论文

英文题名：Object-based analysis for Forest inventory

作者：Wang, Lu[1] Chen, Erxue[1] Li, Zenyuan[1] Yao, Wanqiang[] Li, Shiming[1]

通信作者：Wang, L[1]

机构：[1]Chinese Acad Forestry, Inst Forest Resources & Informat Technol, Beijing, Peoples R China

会议论文集：8th Symposium on Multispectral Image Processing and Pattern Recognition (MIPPR) - Remote Sensing Image Processing, Geographic Information Systems, and Other Applications

会议日期：OCT 26-27, 2013

会议地点：Wuhan, PEOPLES R CHINA

语种：英文

外文关键词：high-resolution image; decision tree; object-based analysis; forest inventory

年份：2013

摘要：As widely used today, high resolution image becomes a useful data source for forest inventory because it can show detailed information of land-cover types which is so helpful in interpreting process. And in the application of high-resolution images, the toughest problem is to find the effective characteristics group to separate each class accurately. In this paper, we tried an object-based method to get the whole forest distribution of the study area. Combining segmentation and decision tree feature selection tool, we tried to find a convenient and effective way to select useful information from such many characteristics brought by. super-pixels. after segmentation. Compared with the traditional pixel-based classification method, we found that object-based method was more appropriate not only for its nearly 10% higher classification accuracy but also providing with more detailed information lying in the image data that help.