首页> 外文会议>The 28th International Symposium on Remote Sensing of Environment, Mar 27-31, 2000, Cape Town, South Africa >Land Cover Classification by Artificial Neural Networks using Spaceborne Imagery and Ancillary Information
【24h】

Land Cover Classification by Artificial Neural Networks using Spaceborne Imagery and Ancillary Information

机译:利用星空图像和辅助信息的人工神经网络进行土地覆盖分类

获取原文
获取原文并翻译 | 示例

摘要

The computerised generation of land cover inventories by using remotely sensed data is an arduous task, especially when spectrally complex and heterogeneous environments are involved. In such areas the use of other sources of information becomes a necessity. This paper focuses on the use of ancillary information with a non-parametric classification approach based on artificial neural networks (ANN's). The ancillary data set comprises pedological, climatological, demographical and topographical features. The value of the spectral and ancillary features to characterise the complex savanna area of Kara (northern Togo) is quantitatively demonstrated.
机译:使用遥感数据以计算机方式生成土地覆盖物清单是一项艰巨的任务,尤其是在涉及光谱复杂且异构的环境时。在这样的地区,必须使用其他信息来源。本文着重于通过基于人工神经网络(ANN)的非参数分类方法对辅助信息进行使用。辅助数据集包括教育学,气候学,人口统计学和地形学特征。定量证明了表征卡拉(北多哥)复杂稀树草原地区的光谱和辅助特征的价值。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号