Identification method of corns for seed on the basis of high resolution remote sensing data texture analysis

Abstract

The invention provides an identification method of corns for seed on the basis of high resolution remote sensing data texture analysis. The method comprises the following steps of: obtaining the moderate-resolution remote sensing image of a corn in a whole growth period and the high-resolution remote sensing image of the corn in a tasseling stage in a target detection zone; preprocessing the remote sensing images; according to the enhanced vegetation index of the preprocessed moderate-resolution remote sensing image in the growth period, identifying all corn fields in the target detection region; and extracting the texture information of all corn fields in the preprocessed high-resolution remote sensing image in the tasseling stage, and identifying the corn fields of the corns for seed in all corn fields. The non-artificial distinguishing of the corns for seed and corns which are planted in lands for growing field crops is realized, the identification method has an accurate, quick and reliable identification result, the corn fields of the corns for seed can be effectively monitored so as to effectively forbid illegal seed production behaviors including secret breeding, excessive manufacture and the like which aim at corns, and the order of a corn planting industry is guaranteed.

Description

technical field [0001] The invention relates to a remote sensing image processing technology applied to agriculture, in particular to a seed corn identification method based on texture analysis of high-resolution remote sensing data. Background technique [0002] To ensure food security, we must first ensure the safety of food seeds. Under the background that corn has become the largest food crop in my country, strengthening the construction of corn seed production base has become the top priority of agricultural production. In 2012, my country's hybrid corn seed production area reached 4.1 million mu, and about 900 million kilograms of hybrid corn seeds are needed for annual production. Accurately grasping the seed production area and yield of hybrid corn and rice and other crops is the basis for ensuring the safety of seed supply; especially in In the corn field, it is even more important to distinguish the seed corn from the field corn, and the method of identifying crops...

AI Technical Summary

Problems solved by technology

In 2012, my country's hybrid corn seed production area reached 4.1 million mu, and about 900 million kilograms of hybrid corn seeds are needed for annual production. Accurately grasping the seed production area and yield of hybrid corn and rice and other crops is the basis for ensuring the safety of seed supply; especially in In the corn field, it is even more important to distinguish the seed corn from the field corn, and the method of identifying crops is usually a single-phase spectral classification method, although it can better identify a part of the country's land use status. land type, but it is impossible to distinguish between seed maize and field maize with similar phenological characteristics and similar biomass

[0003] At present, the most commonly used methods for identifying seed production corn are manual investigation and level-by-level reporting, which has low efficiency, high labor costs and poor timeliness; at the same time, it is difficult for this conventional method to monitor illegal seed production activities such as private multiplication of corn in a timely manner. Seriously disrupted the order of the industry, and could not guarantee the accuracy of seed corn identification

Images