Cultivated land recognition method in satellite image and computing device

A computing device, comprising:

• at least one processor;
• and
• a storage device storing one or more programs which when executed by the at least one processor, causes the at least one processor to:
• segment a satellite image of the Earth into a plurality of standard images;
• recognize cultivated land area in each of the standard images using a cultivated land recognition model to obtain a plurality of first images;
• detect edges of ground level entities in each of the standard images using an edge detection model to obtain a plurality of second images;
• merge each of the first images and a corresponding one of the second images to obtain a plurality of third images;
• and
• obtain cultivated land images by segmenting each of the third images using a watershed segmentation algorithm.

A non-transitory storage medium having stored thereon instructions that, when executed by a processor of a computing device, causes the computing device to perform a cultivated land recognition method in a satellite image, the method comprising:

• segmenting a satellite image of the Earth into a plurality of standard images;
• recognizing cultivated land area in each of the standard images using a cultivated land recognition model to obtain a. plurality of first images;
• detecting edges of ground level entities in each of the standard images using an edge detection model to obtain a plurality of second images;
• merging each of the first images and a corresponding one of the second images to obtain a plurality of third images;
• and
• obtaining cultivated land images by segmenting each of the third images using a watershed segmentation algorithm.