Nondestructive measurement method for biomass in whole growth period of soybeans

Abstract

The embodiment of the invention provides a soybean whole growth period biomass nondestructive measurement method and a processor. The method comprises the steps that N soybean images of each plant of soybean in each growth period are obtained, N is a natural number, the N soybean images comprise side views and top views of the soybeans, the soybean images are input into a plant segmentation model, the characteristics of each soybean image are extracted through the plant segmentation model, and for each plant of soybean, the characteristics of each soybean image are extracted; and taking the features of the side view and the features of the top view as image feature values of the soybeans, screening all image feature values of each soybean plant to obtain an optimal feature subset of each soybean plant, and inputting the image feature values in the optimal feature subset of each soybean plant into a prediction model to obtain a prediction result of each soybean plant. And predicting the biomass of each soybean plant through the prediction model.

Description

technical field [0001] The invention belongs to the field of agricultural automation, and in particular relates to a non-destructive measurement method and processor for soybean biomass in the whole growth period. Background technique [0002] Soybean is an important economic crop in my country. Rapid and accurate monitoring of soybean growth information is of great significance for the implementation of refined management and yield prediction during soybean growth. The accumulation of aboveground biomass dynamically reflects the growth status of soybeans, and is closely related to the growth rate, health status, light energy utilization efficiency, yield and quality of soybeans. In the prior art, through the traditional manual measurement method, the soybean plants must be destructively sampled in the field and then brought back to the laboratory for analysis. The whole process is time-consuming, laborious, and has low accuracy and cannot continuously measure the entire gr...

AI Technical Summary

Problems solved by technology

In the prior art, through the traditional manual measurement method, the soybean plants must be destructively sampled in the field and then brought back to the laboratory for analysis. The whole process is time-consuming, laborious, and has low accuracy and cannot continuously measure the entire growth period of soybeans. sex observation

Images