Agricultural cropland mapping using black-and-white aerial photography, Object-Based Image Analysis and Random Forests
详细信息 查看全文
- 作者：M.F.A. Vogels ; m.f.a.vogels@uu.nl" class="auth_mail" title="E-mail the corresponding author ; S.M. de Jong ; G. Sterk ; E.A. Addink
- 关键词：Agricultural cropland expansion ; Land-use change ; Black-and-white (historical) aerial photography ; GEOBIA ; Random Forests
- 刊名：International Journal of Applied Earth Observation and Geoinformation
- 出版年：2017
- 出版时间：February 2017
- 年：2017
- 卷：54
- 期：Complete
- 页码：114-123
- 全文大小：5413 K
文摘
- titem" id="list_list0005">
Cropland acreage mapping by means of a semi-automated machine-learning application on B&W photography.
GEOBIA and a Random Forest classification proved able to classify cropland on B&W photography with an accuracy of 90–96%.
This mapping method enables the assessment of cropland expansion over large regions for the pre-satellite era.