Rice yield prediction method based on visual analysis

Abstract

The invention discloses a rice yield prediction method based on visual analysis, and the method comprises the following steps: S1, collecting a video of a paddy field through employing an unmanned plane, recognizing the crop types in the video, and determining a rice growth image; s2, identifying the ear length and the ear number of rice in the rice growth image in sequence; and S3, determining the rice yield of the rice field according to the ear length, ear number and color of the rice. According to the method, the rice image is acquired through the unmanned aerial vehicle, the regression model and the rice yield prediction model are sequentially established, so that rice yield prediction is performed, the influence of rice color, ear length and ear number on the yield is fully considered, the influence of shriveled rice grains and rice inclination on rice yield prediction is eliminated, and the accuracy of a prediction result is ensured.

Description

technical field [0001] The invention belongs to the technical field of crop yield prediction, and in particular relates to a method for predicting rice yield based on visual analysis. Background technique [0002] The crop yield forecast has very important reference value for the formulation of the agricultural product purchase plan, and the crop yield forecast is the yield measured in advance by certain methods before the crops are harvested. At present, the prediction models for grain production are generally divided into three categories: time series models and artificial neural network models and regression models. Each model has its advantages and disadvantages. Among them, the neural network has better comprehensive performance, but there is a problem of high computational complexity. The current yield prediction method based on the neural network model has large limitations and slow prediction speed due to high computational complexity. Contents of the invention ...

AI Technical Summary

Problems solved by technology

Each model has its advantages and disadvantages. Among them, the neural network has better comprehensive performance, but there is a problem of large computational complexity.

The current yield prediction method based on the neural network model has large limitations and slow prediction speed due to high computational complexity.

Images