Scholarlink

Accurate crop classification with synthetic aperture radar (SAR) data is a significant area of research and translating into practice from local to regional scale crop inventory mapping. With the growing accessibility to abundant data sources from both current and upcoming dual-polarimetric SAR missions, the capability to generate precise crop maps is set to enhance substantially. The geometric and dielectric properties of targets highly influence radar backscatter. Especially for agricultural crops, which exhibit dynamic changes in target properties and physiological structure throughout their phenology, discriminating between crops using SAR data remains a significant challenge. This study utilizes a Convolutional Neural Networks (CNN) classifier (with two variants to intrinsically capture temporal and spatial information) for discriminating winter wheat and barley crops. Dual-polarimetric SAR data acquired over the AgriSAR2006 site in Germany was used for the study. The performance evaluation of the 3D-CNN model revealed robust accuracy across different polarimetric modes.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Assessing Multi-mode Temporal PolSAR Data for Winter Wheat and Barley Discrimination Using Convolutional Neural Networks

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Debanjan Chowdhury,
  • Sagar Kumar,
  • Swarnendu Sekhar Ghosh,
  • Dipankar Mandal

摘要

Accurate crop classification with synthetic aperture radar (SAR) data is a significant area of research and translating into practice from local to regional scale crop inventory mapping. With the growing accessibility to abundant data sources from both current and upcoming dual-polarimetric SAR missions, the capability to generate precise crop maps is set to enhance substantially. The geometric and dielectric properties of targets highly influence radar backscatter. Especially for agricultural crops, which exhibit dynamic changes in target properties and physiological structure throughout their phenology, discriminating between crops using SAR data remains a significant challenge. This study utilizes a Convolutional Neural Networks (CNN) classifier (with two variants to intrinsically capture temporal and spatial information) for discriminating winter wheat and barley crops. Dual-polarimetric SAR data acquired over the AgriSAR2006 site in Germany was used for the study. The performance evaluation of the 3D-CNN model revealed robust accuracy across different polarimetric modes.