The rice canopy density prediction model research based on SVM

Abstract

This paper mainly researched the basic principle of support vector machine based on Gaussian kernel function. Aiming at the defects of existing Gaussian kernel function of support vector machine, particle swarm optimization algorithm was used to optimize the penalty factor and Gaussian radial parameters to improve the generalization prediction ability of the support vector machine. Moreover, based on the support vector machine and particle swarm optimization, the rice canopy density prediction model and correlation analysis experiment were established using the rice canopy image data. The experiment shows that the absolute error and relative error of the rice canopy density prediction model based on support vector machine and particle swarm optimization can meet the requirements of real-time control of the feed amount of the combined harvest under normal and back light conditions.