Sub-field boundary extraction method and device based on unmanned aerial vehicle remote sensing image

Abstract

The invention provides a sub-field boundary extraction method and device based on an unmanned aerial vehicle remote sensing image. The method comprises the steps: acquiring a target area image according to the unmanned aerial vehicle image; performing image segmentation on the target area image to obtain a plurality of image objects; performing target feature extraction on the plurality of image objects, and determining field boundaries according to preset threshold values of target features, wherein the target features are obtained by performing feature optimization based on the separation degree on the multiple features according to a feature space optimization function. According to the method, feature optimization based on the separation degree is carried out on the multiple features according to the feature space optimization function to obtain the target features, the salt-pepper phenomenon generated by a traditional pixel classification method can be avoided, the sub-field boundary extraction precision is improved, and the method is suitable for extraction of sub-field boundary information in the technical field of agricultural remote sensing.

Description

technical field [0001] The invention relates to the field of remote sensing technology, in particular to a method and device for extracting subfield block boundaries based on remote sensing images of drones. Background technique [0002] In recent years, agriculture has developed in the direction of scale, precision and modernization, and a large number of large-scale agricultural management organizations such as family farms and agricultural social service organizations have emerged in various places. For large-scale modern agriculture, the sub-field block boundary is the basic unit of its agricultural production management. Therefore, the sub-field block boundary information is the basic information that must be mastered for the development of large-scale modern agriculture. Modern agricultural field management, agricultural planning and other operations are of great significance. [0003] At present, related technologies are mainly based on medium and high-resolution met...

AI Technical Summary

Problems solved by technology

However, the farmland in some areas is cultivated by small farmers. These farmland plots are often less than 0.1 hectares, and the borderline of the field is generally only about 20cm narrow. For the subfield plots cultivated by small farmers, the mixed pixels are used for extraction based on meter-level satellite images. The phenomenon is very serious, and the boundary extraction of subfield blocks cannot be realized

In order to accurately obtain the boundary information of the subfield block, the traditional field measurement method is generally used, but it is time-consuming, laborious and inefficient

Images