Research on apple volumetric calculation based on machine vision
Aiming at the problem of volume measurement in apple grading,a method to find apple volume based on machine vision and integral method is proposed.This method subdivides the apple profile into thin slices and integrates to obtain its volume.The error of the method when the apple pose is tilted is also explored.The vertical tilt angle of the apple was obtained by affine transformation,and the projection transformation was used to correct the posture of the apple tilted in posture.The results show that the relative error between this method and the actual apple volume is less than 2%,the absolute maximum absolute error is not more than 6 cm3,and the detection accuracy is high.When the vertical inclination angle of apples reaches 15°,the absolute absolute error between the method and the actual volume is greater than 6 cm3,and the method fails.The error after posture correction is less than 6 cm3,which proves that posture correction meets the volume measured by this method.The method proposed in this paper can greatly improve the accuracy of apple volume measurement and provide a favorable technical reference for apple grading.
NETL
NSTL
万方数据
