A method for extracting rice sheath blight lesions based on imaging hyperspectral analysis

Abstract

The invention discloses a rice sheath blight disease spot extraction method based on imaging hyperspectral analysis. Traditional disease phenotype measurement and investigation mainly depend on manpower, the labor amount is large, and the efficiency is low. The method comprises the following steps: 1, shooting a target crop by using an imaging spectrometer to obtain imaging hyperspectral data; 2,removing the non-plant background in the imaging hyperspectral data obtained in the step 1; 3, classifying rice leaf stems and abnormal areas in the imaging hyperspectral data obtained in the step 2 under the wave band reflectivity of 666 nm and 494 nm; 4, removing non-scab abnormal areas based on scab scanning. The creative image recognition method can recognize the sheath blight disease spots onthe stem, and overcomes the defect that only leaf disease spots can be extracted efficiently in the prior art. According to the method, the scab and the dead leaf in the image can be distinguished, so that relatively high identification precision is achieved.

Description

technical field [0001] The invention belongs to the technical field of agricultural spectrum, and in particular relates to a method for extracting rice sheath blight spots based on imaging hyperspectral analysis. Background technique [0002] As the largest rice producing and consuming country in the world, my country's rice planting area and output account for about 29% and 40% of the national food crops respectively. The issue of rice production is of particular significance to China. With the increasing population, degraded arable land quality, environmental deterioration and shortage of rural labor forces, the growth rate of grain production has slowed down significantly, which seriously threatens my country's food security. Cultivating excellent rice varieties and increasing rice yields have always been important strategic goals in my country. . Rice disease is an important factor affecting rice yield, and rice sheath blight is a major disease that occurs most widely i...

AI Technical Summary

Problems solved by technology

However, there is a lack of methods for extracting phenotypic information of rice sheath blight, which is distributed in stems, leaf sheaths and other parts.

Images