Crop disease and pest identification method and system based on hyperspectral remote sensing image

The invention provides a crop disease and pest identification method and system based on a hyperspectral remote sensing image, and the method comprises the steps: extracting images of a near-infrared band, a red band and a neighborhood band in the hyperspectral remote sensing image to obtain a first image and a second image, and obtaining a third image according to the first image and the second image, segmenting the third image to obtain at least one planting area of the crop; obtaining a spectrum characteristic curve of a crop growth stage, and reducing the number of spectrum channel images of the hyperspectral remote sensing image according to the curve so as to obtain a dimension-reduced spectrum remote sensing image of the planting area; and inputting the dimension-reduced spectral remote sensing image of the planting area into the trained deep learning model to obtain a planting area pest and disease identification result. The number of channels in the hyperspectral remote sensing image is effectively r