Crop classification and identification method and device and electronic equipment

Abstract

The invention provides a crop classification and identification method and device and electronic equipment, and relates to the technical field of image processing, and the method comprises the steps:obtaining a to-be-classified agricultural remote sensing image, and the geographic position and monthly average temperature data of each pixel in the to-be-classified agricultural remote sensing image; processing the to-be-classified agricultural remote sensing image to obtain target data of each pixel in the to-be-classified agricultural remote sensing image; and processing the geographic position of each pixel, the monthly average temperature data and the target data by using a target classification model to obtain distribution data of target crops in the to-be-classified agricultural remotesensing image. According to the method, the self-learning capability of a neural network model is utilized; the target classification model learns the characteristics of various crops; the method hasthe capability of classifying and identifying the crops in the agricultural remote sensing image to be classified according to the surface reflectance of the pixel, the normalized vegetation index, the enhanced vegetation index, the geographic position and the monthly average temperature data, and the accuracy of the distribution data of the target crops obtained through classification and identification is high.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a crop classification recognition method, device and electronic equipment. Background technique [0002] With the rapid development of satellite technology, many methods of classifying and identifying crops using remote sensing images have emerged. The implementation of traditional remote sensing classification methods for crops requires the use of high-resolution remote sensing images, and further use of the spectral characteristics and spatial characteristics of different crops. Texture features are used to classify and identify crops, but because green vegetation has many commonalities in the spectrum, it is often difficult to distinguish different types of crop vegetation using the above classification methods, and then crop classification and recognition errors occur. [0003] To sum up, the crop classification and recognition methods in the prior art have the techn...

AI Technical Summary

Problems solved by technology

[0002] With the rapid development of satellite technology, there are many methods for classifying and identifying crops using remote sensing images. The implementation of traditional remote sensing classification methods for crops requires the use of high-resolution remote sensing images, and further use of the spectral characteristics and spatial characteristics of different crops. Texture features are used to classify and identify crops, but because green vegetation has many commonalities in the spectrum, it is often difficult to distinguish different types of crop vegetation using the above classification methods, and then crop classification and recognition errors occur.

[0003] In summary, there is a technical problem of low accuracy in the crop classification and recognition methods in the prior art

Images