Automatic fruit picking method and device based on visual recognition positioning

Abstract

The invention discloses an automatic fruit picking method and device based on visual recognition positioning. The method comprises the following steps of S1, collecting colorful images; S2, extractingthree RGB single-channel gray level images; S3, extracting single-channel images with obvious color components; S4, preprocessing the images; S5, judging whether a fruit target exists in the images or not; S6, obtaining coordinates of the fruit target in a computer pixel coordinate system; S7, converting the pixel coordinates into coordinates of a world coordinate system; S8, calculating a planemotion amount of a grabbing mechanical claw; S9, controlling the grabbing mechanical claw to move, and enabling the fruit target to be located in the center of the camera imaging plane; S10, controlling the grabbing mechanical claw to move forwards perpendicular to the imaging plane; S11, grabbing the fruit target, and cutting off fruit stems; S12, loosening the grabbing mechanical claw, and enabling fruits to fall into a collecting box. The fruit target is determined through image processing and feature matching, the target is tracked and positioned to accurately position the fruit so as to guide accurate picking, and fruit surface damage is reduced.

Description

technical field [0001] The invention belongs to the technical field of fruit picking, and in particular relates to an automatic fruit picking method and device based on visual recognition and positioning. Background technique [0002] The harvesting of seasonal fruits such as apples needs to be completed in a short period of time. At present, this work is mainly done manually, and labor costs account for a large part of the entire production cost. In order to reduce labor costs, several mechanized fruit-picking schemes have been proposed in the related art, but most of the mechanized solutions cannot accurately determine the position of the fruit when picking, so impacts will be generated during picking and cause fruit surface damage, making harvesting difficult. Products of reduced quality, especially fruits like apples, must avoid bruising of the fruit. Contents of the invention [0003] The object of the present invention is to avoid the deficiencies in the prior art a...

AI Technical Summary

Problems solved by technology

[0002] The harvesting of seasonal fruits such as apples needs to be completed in a short period of time. At present, this work is mainly done manually, and labor costs account for a large part of the entire production cost.

In order to reduce labor costs, several mechanized fruit-picking schemes have been proposed in

Images