首页> 外文会议>Asian conference on remote sensing;ACRS >LAND COVER CHANGE DETECTION USING POLSAR IMAGE
【24h】

LAND COVER CHANGE DETECTION USING POLSAR IMAGE

机译:使用POLSAR图像进行土地覆盖变化检测

获取原文

摘要

In this paper, a change detection scheme for Polarimetric Synthetic Aperture Radar (PolSAR) images using Normalize Difference Ratio (NDR) is proposed. The NDR change map is compared with change maps obtained using traditional Difference Image (DI), Mean Ratio Detector (MRD) and Log Ratio Detector (LRD) operators. The amplitude information of (HH, HV) and the elements of the coherency matrix (T3) from both the dates are used to generate the change image. Supervised threshold segmentation is used to extract a binary mask for change detection. ALOS-1-PALSAR dual pol L-band images acquired on two different dates are used for this study. The proposed change detection technique is also compared with supervised post classification technique. The result demonstrates that the proposed NDR operator produce much higher detection rate than traditional difference, ratio operators and post classification technique.
机译:提出了一种利用归一化差比(NDR)对极化合成孔径雷达(PolSAR)图像进行变化检测的方案。将NDR变化图与使用传统差值图像(DI),平均比率检测器(MRD)和对数比率检测器(LRD)运算符获得的变化图进行比较。来自两个日期的(HH,HV)振幅信息和相关矩阵(T3)的元素用于生成变化图像。监督阈值分割用于提取二进制掩码以进行更改检测。本研究使用在两个不同日期获取的ALOS-1-PALSAR双极化L波段图像。提议的变更检测技术也与监督后分类技术进行了比较。结果表明,提出的NDR算子产生的检测率比传统的差值,比率算子和后分类技术要高得多。

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