一种倒伏玉米遥感提取方法与装置

本发明涉及一种倒伏玉米遥感提取方法与装置。本发明创造性的提出了采用绿波段纹理均值(B2_Mean)可区分倒伏与非倒伏玉米,并通过构建DVIG-B区分倒伏玉米与水稻,创建了结合光谱和纹理的倒伏玉米提取决策树模型,所述方法不需提前获取玉米种植区域范围,可直接使用模型对经预处理后的影像提取倒伏玉米,所用数据不需要复杂的多光谱波段,仅需含有蓝、绿、红、近红外四个波段的影像数据即可提取倒伏玉米,实现快速准确监测玉米倒伏状况。 The invention relates to a lodging corn remote sensing extraction method and device. Accor...

Full description

Saved in:
Bibliographic Details
Format Patent
LanguageChinese
Published 06.12.2024
Subjects
Online AccessGet full text

Cover

More Information
Summary:本发明涉及一种倒伏玉米遥感提取方法与装置。本发明创造性的提出了采用绿波段纹理均值(B2_Mean)可区分倒伏与非倒伏玉米,并通过构建DVIG-B区分倒伏玉米与水稻,创建了结合光谱和纹理的倒伏玉米提取决策树模型,所述方法不需提前获取玉米种植区域范围,可直接使用模型对经预处理后的影像提取倒伏玉米,所用数据不需要复杂的多光谱波段,仅需含有蓝、绿、红、近红外四个波段的影像数据即可提取倒伏玉米,实现快速准确监测玉米倒伏状况。 The invention relates to a lodging corn remote sensing extraction method and device. According to the method, the green band texture mean value (B2Mean) is creatively adopted to distinguish the lodging corn and the non-lodging corn, the DVIG-B is constructed to distinguish the lodging corn and the rice, the lodging corn extraction decision-making tree model combining the spectrum and the texture is created, the corn planting area range does not need to be obtained in advance, and the method is simple and convenient to operate. The lodging corn can be extracted from the preprocessed image by directly using the model, the used data does not need complex multispectral bands, the lodging corn can be extracted only by image data containing blue, green, red and near-infrared bands, and the lodging condition o
Bibliography:Application Number: CN202011441317