Grape stem accurate identification method based on deep learning post optimization

Abstract

The invention provides a grape stem accurate identification method based on deep learning post optimization. The grape stem accurate identification method comprises the steps: 1, collecting and marking a grape stem picture; 2, identifying the marked grape fruit stem picture through a deep learning model Mask R-CNN to obtain a pre-identified grape fruit stem area; 3, according to the pre-recognizedgrape stem area, obtaining grape stem contour coordinates and grape stem area coordinates; 4, obtaining H, S and V channel values of the grape stem contour and H, S and V channel values of the grapestem area; 5, respectively calculating an H channel average value, an S channel average value and a V channel average value of the grape stem area; 6, selecting the grape stem contour as a seed point,and carrying out regional growth according to a regional growth criterion based on the seed point. The method can achieve the recognition of the grape stems in a natural environment, and solves a problem that the grape stems are difficult to recognize under a natural orchard scene because of the change and shielding of light.

Description

technical field [0001] The invention relates to the technical field of fruit picking, in particular to a method for accurately identifying grape stems based on deep learning and post-optimization. Background technique [0002] Grapes have extremely high nutritional and economic value. They are not only rich in essential amino acids and vitamins for human beings, but also well-known in the field of winemaking. With the advancement of technology and the increase of labor costs, intelligent picking of grapes by picking robots in the future is essential. There are two main ways for the picking robot to pick: 1. Pulling type, this method is suitable for fruits whose stems will not be affected by the fruit itself, such as apples or kiwis; 2. Grasp and cut type, this method is suitable for Fruits with soft skin and thick fruit stalks whose freshness will be affected if the fruit stalks fall off, such as grapes. Therefore, the grape picking robot must identify the grape stems and ...

AI Technical Summary

Problems solved by technology

[0004] In order to overcome the problem that traditional grape picking robots rely on color threshold segmentation to identify grape stems, which is not suitable for complex natural environments, the present invention provides an accurate identification method for grape stems based on deep learning optimization, and its specific technical scheme as follows:

Images