...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Current Science: A Fortnightly Journal of Research >Spectral mixture analysis for subpixel classification of coconut.
【24h】

Spectral mixture analysis for subpixel classification of coconut.

机译：椰子亚像素分类的光谱混合分析。

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 present study was undertaken to test the stability of a spectral mixture modelling method by applying the model to produce land-cover maps of coconut in Kasaragod district, Kerala. Classification results from applying the Spectral Mixture Analysis (SMA) were assessed by comparison with ground-truth data. SMA was performed and evaluated based on Landsat-7 ETM+ (Enhanced Thematic Mapper Plus) data. Landsat-7 ETM+ was available at 30 m resolution with six spectral bands (excluding the panchromatic band and thermal band). The Landsat-7 ETM+ scene used in this study was acquired on 8 August 2000 from path 135, row 21. The scene was a level-2 product and was radiometrically and geometrically corrected (systematic) and resampled to give 25 m resolution. The commercial image processing software, IDRISI32 was used here for data visualization. The procedure used in this study was based on a linear mixture model to derive continuous fields of coconut, road, laterite outcrops, construction, arecanut and cloud. SMA was done on DN values and corresponding radiance values of the satellite imagery. The accuracy of endmember fraction was estimated as the mean of the percentage absolute difference between actual and modelled estimates. The subpixel accuracy achieved for the coconut land-cover was 87% using SMA of DN values, while it was 93% for SMA of radiance values..
机译：通过使用该模型制作喀拉拉邦卡萨拉戈德地区椰子土地覆盖图，本研究旨在测试光谱混合建模方法的稳定性。通过将光谱混合分析（SMA）与地面真实数据进行比较，对分类结果进行了评估。 SMA是根据Landsat-7 ETM +（增强主题映射器增强版）数据执行和评估的。 Landsat-7 ETM +的分辨率为30 m，具有六个光谱带（不包括全色带和热能带）。本研究中使用的Landsat-7 ETM +场景是从2000年8月8日从第135行第21行获取的。该场景是2级产品，经过放射和几何校正（系统化），并重新采样以提供25 m的分辨率。此处使用商业图像处理软件IDRISI32进行数据可视化。本研究中使用的程序基于线性混合模型，以得出椰子，道路，红土露头，建筑，槟榔和云的连续区域。 SMA是根据卫星图像的DN值和相应的辐射值进行的。最终成员分数的准确性估计为实际估计值与模型估计值之间的绝对差值百分比的平均值。使用DN值的SMA，椰子土地覆盖物实现的亚像素精度为87％，而对于辐射值的SMA，则为93％。

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