• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences >GENERALIZED KNOWLEDGE DISTILLATION FOR MULTI-SENSOR REMOTE SENSING CLASSIFICATION: AN APPLICATION TO LAND COVER MAPPING
【24h】

GENERALIZED KNOWLEDGE DISTILLATION FOR MULTI-SENSOR REMOTE SENSING CLASSIFICATION: AN APPLICATION TO LAND COVER MAPPING

机译：多传感器遥感分类的广义知识蒸馏：陆地覆盖映射的应用

获取原文
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Due to the proliferation of Earth Observation programmes, information at different spatial, spectral and temporal resolution is collected by means of various sensors (optical, radar, hyperspectral, LiDAR, etc.). Despite such abundance of information, it is not always possible to obtain a complete coverage of the same area (especially for large ones) from all the different sensors due to: (i) atmospheric conditions and/or (ii) acquisition cost. In this context of data (or modalities) misalignment, only part of the area under consideration could be covered by the different sensors (modalities). Unfortunately, standard machine learning approaches commonly employed in operational Earth monitoring systems require consistency between training and test data (i.e., they need to match the same information schema). Such a constraint limits the use of additional fruitful information, i.e., information coming from a particular sensor that may be available at training but not at test time. Recently, a framework able to manage such information misalignment between training and test information is proposed under the name of Generalized Knowledge Distillation (GKD). With the aim to provide a proof of concept of GKD in the context of multi-source Earth Observation analysis, here we provide a Generalized Knowledge Distillation framework for land use land cover mapping involving radar (Sentinel-1) and optical (Sentinel-2) satellite image time series data (SITS). Considering that part of the optical information may not be available due to bad atmospheric conditions, we make the assumption that radar SITS are always available (at both training and test time) while optical SITS are only accessible when the model is learnt (i.e., it is considered as privileged information). Evaluations are carried out on a real-world study area in the southwest of France, namely Dordogne, considering a mapping task involving seven different land use land cover classes. Experimental results underline how the additional (privileged) information ameliorates the results of the radar based classification with a main gain on the agricultural classes.
机译：由于地球观测程序的增殖，通过各种传感器（光学，雷达，高光谱，激光雷达等，收集不同空间，光谱和时间分辨率的信息。尽管提供了如此丰富的信息，但由于：（i）大气条件和/或（ii）收购成本，并不总能从所有不同传感器中获得相同区域（特别是大型的区域）的完整覆盖范围。在数据（或方式）未对准的情况下，所考虑的区域的只有部分可以由不同的传感器（方式）涵盖。遗憾的是，在运营地球监测系统中通常采用的标准机器学习方法需要训练和测试数据之间的一致性（即，他们需要匹配相同的信息模式）。这种约束限制了额外的富有成果信息的使用，即来自特定传感器的信息，这些传感器可以在训练中可用但不在测试时间。最近，在广义知识蒸馏（GKD）的名称，提出了一种能够管理训练和测试信息之间的这种信息的框架。旨在在多源地球观察分析的背景下提供GKD概念证明，在这里，我们为涉及雷达（Sentinel-1）和光学（Sentinel-2）的陆地使用陆地覆盖映射提供了广义知识蒸馏框架卫星图像时间序列数据（坐）。考虑到由于大气条件不好，可能无法使用的光学信息，假设雷达均始终可用（训练和测试时间），而在学习模型时仅可访问光学坐姿（即，它被视为特权信息）。考虑到涉及七种不同土地覆盖课程的绘制任务，在法国西南部的真实研究区域进行了评估，即Dordogne。实验结果强调了附加（特权）信息如何改善基于雷达的分类结果，并在农业课程上获得主要增益。

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