Planting structure classification method and device

The invention relates to a planting structure classification method and device. The method mainly comprises the following steps: preprocessing remote sensing data; that is to say, the planting structure index of the remote sensing data is extracted. And adding the determined planting structure index into original remote sensing image data, fusing and labeling images of multiple wave bands to serveas a training set, training the constructed network model, preprocessing remote sensing images to be classified, and inputting the preprocessed remote sensing images to the trained network model to classify the planting structure. By increasing the spatial resolution and spectral richness of the images for training, parameters in subsequent network model training are determined, and the remote sensing images to be tested are accurately classified. 本发明涉及一种种植结构的分类方法及装置，其主要是通过对遥感数据进行预处理，也即通过对遥感数据进行种植结构指数的提取，将确定的种植结构指数加入到原始遥感图像数据中，并对多个波段的影像进行融合，标注后作为训练集，对构建的网络模型进行训练，并将待分类的遥感图像经过预处理后输入到训练好的网络模型进行种植结构的分类。本发明通过增加训练用影像的空间分辨率