Method for judging maturity of soybeans in harvesting period based on remote sensing of unmanned aerial vehicle

Abstract

Disclosed is a method for judging maturity of soybeans in a harvesting period based on remote sensing of an unmanned aerial vehicle. A vegetation index of the soybean maturity period is calculated by utilizing multispectral data, a soybean maturity characterization method is established by utilizing a natural breakpoint grading algorithm and combining the vegetation index, and soybean maturity grades are divided; spectral reflectivity, color feature and texture feature parameters of the soybeans are extracted in the image, and feature screening is performed on feature difference comparative analysis; and a soybean maturity grade discrimination model of a support vector machine learning algorithm is established in combination with the soybean maturity grade. The soybean maturity can be accurately judged by combining unmanned aerial vehicle multispectrum with a machine learning technology, so that judgment of the soybean maturity in a breeding plan is facilitated, determination of the optimal harvest time of soybeans is facilitated, the soybean harvest loss is reduced, and the soybean yield is indirectly increased.

Description

technical field [0001] The invention belongs to a method for judging the maturity of soybeans by using spectral image features, in particular to a method for judging the maturity of soybeans in the harvest period based on remote sensing of an unmanned aerial vehicle. Background technique [0002] Soybean is an important oil crop in my country and is also the main source of plant protein, with a large planting area. For soybean breeding programs, the results of yield measurement are used as a decision to select and promote the development of new varieties, and judgment of maturity is an important decision before yield measurement, especially the judgment of maturity. Harvesting at a reasonable and accurate harvesting time can effectively prevent the harvest loss caused by too early or too late harvesting, and also prolong the storage period of soybeans, objectively ensuring the yield and quality of soybeans. In China, soybeans are often harvested by a combine harvester. The ...

AI Technical Summary

Problems solved by technology

At present, the maturity evaluation of soybeans before harvest mainly depends on the subjective observation and evaluation of experts with naked eyes or manual harvesting and threshing, and the moisture content is measured by the grain moisture meter to judge whether it has reached the harvest time. This method has the problems of time-consuming, laborious and large errors.

Images