• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Living planet symposium >PATCH-BASED IMAGE CLASSIFICATION FOR SENTINEL-1 AND SENTINEL-2 EARTH OBSERVATION IMAGE DATA PRODUCTS
【24h】

PATCH-BASED IMAGE CLASSIFICATION FOR SENTINEL-1 AND SENTINEL-2 EARTH OBSERVATION IMAGE DATA PRODUCTS

机译：Sentinel-1和Sentinel-2接地观察图像数据产品的补丁的图像分类

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

摘要

In an era where the satellite image collections are in a continuous growth, Earth Observation (EO) image annotation and classification is becoming an important component of data exploitation. In this paper we present how feature extraction methods such as Gabor (G) and Weber Local Descriptor (WLD) are performing in a patchbased approach in the frame of Sentinel-1 and Sentinel-2 image data analysis. Having the goal to develop an application capable to join feature extraction and classification algorithms, in our assessment, we performed supervised support vector machines (SVM) and k-Nearest Neighbors (k-NN) classifications to extract a few generic classes from synthetic aperture radar (SAR), multispectral (MSI) and data fusion (DFI) images. The result of this study is intended to establish the optimum number of classes that can be found in the Sentinel-1 and Sentinel-2 images when using patch based image classification techniques. Also another important objective of this paper is to determine the best patch sizes suitable for this classification type in order to return best results for Sentinel-1 and Sentinel-2 EO images.
机译：在卫星图像收集在持续增长的时代，地球观测（EO）图像注释和分类正在成为数据剥削的重要组成部分。在本文中，我们介绍了特征提取方法，如Gabor（G）和Weber本地描述符（WLD）在Sentinel-1和Sentinel-2图像数据分析的帧中以补丁帧的方法执行。实现了开发一个能够加入功能提取和分类算法的应用程序，在我们的评估中，我们对我们进行了监督支持向量机（SVM）和K-Neard邻居（K-NN）分类，以从合成孔径雷达中提取几个通用类（SAR），多光谱（MSI）和数据融合（DFI）图像。该研究的结果旨在建立当使用基于贴片的图像分类技术时在Sentinel-1和Sentinel-2图像中可以找到的最佳类型。此文的另一个重要目标是确定适合该分类类型的最佳补丁尺寸，以便为Sentinel-1和Sentinel-2 EO图像返回最佳结果。

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