Crop identification method and computing device

A computing device comprising:

• a storage device;
• at least one processor;
• and
• the storage device storing one or more programs, which when executed by the at least one processor, cause the at least one processor to perform operations comprising:
• acquiring multi-temporal sample remote sensing images labeled with first planting blocks of a specific crop;
• calculating a normalized difference vegetation index (NDVI) value of each pixel in the sample remote sensing images to obtain NDVI data of the sample remote sensing images;
• reducing noise of the NDVI data of the sample remote sensing images to obtain de-noised NDVI data of the sample remote sensing images;
• fitting a first multivariate Gaussian model based on the de-noised NDVI data of the sample remote sensing images;
• acquiring multi-temporal target remote sensing images;
• calculating an NDVI value of each pixel in the target remote sensing images;
• constructing an NDVI time series of each pixel in the target remote sensing images according to the NDVI value of each pixel in the target remote sensing images;
• inputting the NDVI time series of each pixel in the target remote sensing images to the first multivariate Gaussian model to obtain a likelihood value of each pixel in the remote sensing images;
• and
• determining second planting blocks of the specific crop in the target remote sensing images according to the likelihood value of each pixel in the remote sensing images.

A non-transitory storage medium having stored thereon instructions that, when executed by a computing device of a computing device, causes the computing device to perform a crop identification method, the method comprising:

• acquiring multi-temporal sample remote sensing images labeled with first planting blocks of a specific crop;
• calculating a normalized difference vegetation index (NDVI) value of each pixel in the sample remote sensing images to obtain NDVI data of the sample remote sensing images;
• reducing noise of the NDVI data of the sample remote sensing images to obtain de-noised NDVI data of the sample remote sensing images;
• fitting a first multivariate Gaussian model based on the de-noised NDVI data of the sample remote sensing images;
• acquiring multi-temporal target remote sensing images;
• calculating an NDVI value of each pixel in the target remote sensing images;
• constructing an NDVI time series of each pixel in the target remote sensing images according to the NDVI value of each pixel in the target remote sensing images;
• inputting the NDVI time series of each pixel in the target remote sensing images to the first multivariate Gaussian model to obtain a likelihood value of each pixel in the remote sensing images;
• and
• determining second planting blocks of the specific crop in the target remote sensing images according to the likelihood value of each pixel in the remote sensing images.