• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Journal of Applied Remote Sensing >Learning or assessment of classification algorithms relying on biased ground truth data: what interest?
【24h】

Learning or assessment of classification algorithms relying on biased ground truth data: what interest?

机译：学习或评估依赖于偏见的地面真理数据的分类算法：什么感兴趣？

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

The use of ground truth (GT) data in the learning and/or assessment of classification algorithms is essential. Using a biased or simplified GT attached to a remote sensing image to partition does not allow a rigorous explanation of the physical phenomena reflected by such images. Unfortunately, this scientific problem is not always treated carefully and is generally neglected in the relevant literature. Furthermore, the impacts of obtained classification results for decision-making are negative. This is inconsistent when considering investments in both the development of sophisticated sensors and the design of objective classification algorithms. Any GT must be validated according to a rigorous protocol before utilization, which is unfortunately not always the case. The evidence of this problem is provided, using two popular hyperspectral images (Indian Pine and Pavia University) that misleadingly are frequently used without care by the remote sensing community since the associated GTs are not accurate. The heterogeneity of the spectral signatures of some GT classes was proven using a semisupervised and an unsupervised classification method. Through this critical analysis, we propose a general framework for a minimum objective assessment and validation of the GT accuracy, before exploiting them in a classification method. (C) The Authors. Published by SPIE under a Creative Commons Attribution 4.0 Unported License.
机译：在学习和/或分类算法的学习和/或评估中使用地面真理（GT）数据至关重要。使用附加到遥感图像的偏置或简化的GT到分区不允许对这些图像反映的物理现象进行严格的解释。不幸的是，这种科学问题并不总是仔细对待，并且在相关文献中通常被忽视。此外，所获得的分类结果对决策的影响是消极的。这在考虑在复杂传感器的发展和客观分类算法的设计中考虑投资时不一致。必须根据利用前的严格方案验证任何GT，遗憾的是并非总是如此。提供了这个问题的证据，使用了两个受欢迎的高光谱图像（印度松树和帕维亚大学），由于相关的GTS不准确，遥感社区经常被误导地使用而不会受到误导。使用半质化和无监督的分类方法证明了一些GT类的光谱签名的异质性。通过这一批判性分析，在以分类方法利用它们之前，我们提出了一个最低目标评估和验证GT准确性的一般框架。 （c）作者。由SPIE出版，根据创意公约归因于4.0未受平许可。

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