Poa pratensis variety identification method based on hyper-spectral image

Abstract

The invention discloses a Poa pratensis variety identification method based on a hyper-spectral image. The method comprises the following steps of: 1, placing Poa pratensis samples which are prepared in a hyper-spectral imaging device, and acquiring the hyper-spectral image; 2, extracting the information of the hyper-spectral image, which comprises spectral information and / or external characteristic information; 3, calculating total difference between different Poa pratensis varieties at different wave bands according to the spectral information which is extracted; 4, establishing a function model for determining different varieties of Poa pratensis according to the total difference at each wave band or according to the total difference and the external characteristic information; and 5, determining the samples according to the function model which is established in the step 4 to identify different varieties of Poa pratensis. The method provided by the invention is easy and convenient to operate, and has large technical advantages. The acquired information is accurate and reliable, and batch quick identification can be performed.

Description

Technical field [0001] The invention relates to the field of infrared spectrum identification, in particular to a method for identifying Poa pratensis varieties based on hyperspectral images. Background technique [0002] Bluegrass is an excellent cold-season turf grass. It is widely planted in Europe, America and northern my country, and is widely used in urban green spaces, garden greening, and sports fields. According to incomplete statistics, there are currently more than 70 varieties of Kentucky bluegrass cultivated. Since different varieties have different growth and development characteristics, and their adaptability to the environment are also different, it is extremely important to select suitable varieties for production. However, the use of variety names on the market is very confusing. Some illegal seed sellers, in pursuit of economic benefits, change the variety names at will from time to time, causing consumers to suffer losses. Finding a fast and accurate method ...

AI Technical Summary

Problems solved by technology

However, there are serious defects in the morphological recognition method. This method is limited to those grass species with significant characteristics in appearance. The purpose of identification is achieved by observing traits such as leaf color, leaf width, and blade angle. However, these traits may vary due to There are variations due to different regions and conservation management; on the other hand, there are many varieties with extremely small differences in appearance, which are difficult to distinguish by conventional morphological recognition methods

In addition, the genetic identification method is also an effective method to identify turf varieties, but this method has a complicated analysis process and a long analysis period, and is not suitable for rapid identification of samples in batches, so it is very inconvenient to use

Images