Study on the Method of Matched Splice Grafting for Melon Seedlings Based on Visual Image

Abstract

Due to the cutting mechanism of the existing grafting machine, it cannot adjust the cutting angle in real time, resulting in low fitting precision on the cutting surfaces between the rootstocks and scion seedlings and, thus, seriously affecting the survival rate and quality of the grafting seedlings. In this paper, a kind of splice grafting method based on visual image is proposed, aiming at maximizing the joint rate between cutting surfaces of rootstocks and scion seedlings and realizing precise cutting and grafting of grafting machine. After analysis, we determined that melon rootstock seedlings have a structure of pith cavity inside, and the solid structure from the top of the pith cavity to the left and right base points of a growing point forms the important area of a cutting surface. In order to obtain the geometric model of the cutting surfaces of the seedlings, a visual image analysis system was established to identify, analyze, and model the pith cavity structure inside the rootstock seedling, as well as the external morphological characteristics, and the ultimate cutting angle of the rootstock seedling and cutting surface parameters were determined. By measuring the length of minor axis of scion seedlings in order to achieve the maximum joint rate, the optimal cutting angle of the rootstocks and scion seedlings was determined. Then grafting and seedling cultivation tests were carried out. The test results showed that the range of ultimate cutting angle on rootstock seedlings (Cucurbita moschata) was 18.21 ± 1.92°; the cutting angles of the rootstock (Cucurbita moschata) and scion seedlings (watermelon) were 22° and 19.68°, respectively; the cutting surface length of the two was 4.96 mm; and the cutting surface thickness of the rootstock was 0.13 mm, all of which could satisfy the technological requirements of the matched splice grafting of melons. The research results can serve as a reference for the design in vision-guided precision cutting and real-time grafting operation on grafting robots.