Research of Apple Harvesting Robot Based on Least Square Support Vector Machine

Abstract

In apple harvesting robot stereo vision system, fruit recognition based on least squares support vector machine (LS-SVM) and calibration based on binocular vision are proposed, in order to gain the location information of apples including depth. Firstly, vector median filtering, opening and closing operations are employed, then feature vectors, H and S components in HIS color model and shape features, are used as input, LS-SVM is used for apple identification. Finally, corresponding point pixel coordinates in images are used as input, its world coordinates as the output, nonlinear model between input and output is established based on LS-SVM to avoid a large number of complex calculations and obtain apple's spatial location. The results showed that: the running time of this method, apple recognition and camera calibration based on LS-SVM, is short in comparison, and the accuracy rate can reach to 90%.