[1]于书媛,骆佳骥,杨源源.基于高分卫星遥感影像的城市建筑物提取研究[J].华南地震,2019,39(02):26-33.[doi:10.13512/j.hndz.2019.02.005]
YU Shuyuan,LUO Jiaji,YANG Yuanyuan.Research on Extraction of Urban Buildings based on High Satellite Remote Sensing Images[J].,2019,39(02):26-33.[doi:10.13512/j.hndz.2019.02.005]
点击复制
基于高分卫星遥感影像的城市建筑物提取研究(
)
华南地震[ISSN:1006-6977/CN:61-1281/TN]
- 卷:
-
39
- 期数:
-
2019年02期
- 页码:
-
26-33
- 栏目:
-
华南地震
- 出版日期:
-
2019-06-30
文章信息/Info
- Title:
-
Research on Extraction of Urban Buildings based on High Satellite Remote Sensing Images
- 作者:
-
于书媛; 骆佳骥; 杨源源
-
安徽省地震局，合肥 230031
- Author(s):
-
YU Shuyuan; LUO Jiaji; YANG Yuanyuan
-
Anhui Earthquake Agency，Hefei 230031，China
-
- 关键词:
-
面向对象; 高分辨率影像; 城市建筑物; 影像分割
- Keywords:
-
Object-oriented; High-resolution image; Urban buildings; Image segmentation
- DOI:
-
10.13512/j.hndz.2019.02.005
- 文献标志码:
-
A
- 摘要:
-
以安庆市区的高分一号影像为信息源，结合地震应急基础统计数据资料，重点研究基于CART决策树的面向对象分类对研究区的建筑物进行分类提取，分类的总体精度和Kappa系数分别为83.9%和0.821。结果表明：基于CART决策树面向对象分类方法对研究区高分一号影像进行建筑物提取，分类精度较好，可作为地震应急基础数据库更新辅助手段之一。
- Abstract:
-
Based on the high-score No. 1 image of Anqing city and the basic statistical data of earthquake emergency，the object-oriented classification based on CART decision tree is studied to extract the buildings in the study area. The overall accuracy and Kappa coefficient of the classification are 83.9% and 0.821，respectively. Results show that the object-oriented classification method based on CART decision tree can extract buildings from the high-score No. 1 image in the study area，and the classification accuracy is good. It can be used as one of the auxiliary means for updating the basic database of earthquake emergency response.
更新日期/Last Update:
2019-07-04