Rootstock leaf expansion direction identification method based on image processing

A technology of leaf development direction and recognition method, which is applied in the field of image recognition, can solve problems such as labor-intensive, inaccurate cutting angles, and low survival rate, and achieve the effect of reducing grafting costs and improving survival rate

Inactive Publication Date: 2022-07-05
合肥佳富特机器人科技有限责任公司
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] The purpose of the present invention is to provide a rootstock leaf development direction recognition method based on image processing, through the projection length of the leaf development in the image information by shooting and analyzing the digital image information in the rotation process, and establish the positional relationshi

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Rootstock leaf expansion direction identification method based on image processing
  • Rootstock leaf expansion direction identification method based on image processing
  • Rootstock leaf expansion direction identification method based on image processing

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0064] like figure 2 As shown, rotate the rootstock to be cut, and take photos of cotyledons at different angles. During the process of rotating and shooting, the rotation angle of the rootstock is controlled by the system, and it rotates 15 degrees each time; There is a projection line segment in this visual projection surface, and the line where this projection line segment is located is the zero-angle line;

[0065] Select pictures with the best effect from different angles, and then perform binarization processing after graying the best cotyledon photos from different angles; When the background pixel value of the actual cotyledon map is greater than the cotyledon pixel value, it is used to subtract the corresponding pixels from the template cotyledon map and the actual cotyledon map; Remove the corresponding pixels of the template cotyledon map; when the subtracted value is less than 0, assign the value to 0; calculate the pixel sum after the subtraction operation of ea...

Embodiment 2

[0072] like image 3 As shown, manually place the rootstock 6 that needs to be grafted into the mechanical clamp 1, when the rootstock sensors on both sides of the mechanical clamp 1 detect that there is a rootstock in the mechanical clamp 1, after the controller controls the mechanical clamp 1 to clamp the rootstock, the controller controls the mechanical arm 1, the rootstock is moved between the image acquisition device 3 and the projection plate 4;

[0073] The light source in the image acquisition device 3 enables the shadow of the rootstock to fall on the projection board, and the light source is adjusted repeatedly so that the shadow of the rootstock is positioned accurately on the projection board and the shadow is clear;

[0074] The rotating device in the mechanical clamp 1 is rotated, and the stock is controlled to rotate by 15° each time, so as to provide images of different angles; according to Example 1, after the image processing is completed, the initial angle o...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a stock leaf expansion direction identification method based on image processing, and relates to the technical field of image identification. The method comprises the following steps: S1, rotating a rootstock, and taking cotyledon photos at different angles; s2, recording an angle value of rotating the rootstock each time; s3, obtaining the projection length of the cotyledon of the stock in the image observation direction; and S4, establishing a calculation formula, and solving to obtain the leaf expansion direction of the stock. According to the method, the projection length of leaf expansion in image information is analyzed through shooting of digital image information in the rotating process, the position relation between the projection length and the rotating angle is established to calculate the initial angle, the rootstock is rotated to the position needing to be cut according to the leaf expansion angle, the rootstock is automatically rotated to the optimal cutting position, and the cutting efficiency is improved. The survival rate of the grafted rootstock is improved and the grafting cost is reduced.

Description

technical field [0001] The invention belongs to the technical field of image recognition, and in particular relates to a method for recognizing rootstock leaf spreading direction based on image processing. Background technique [0002] At present, the feeding module has two modes: automatic feeding and manual feeding. [0003] The current equipment of the fully automatic feeding method uses the finished manipulator to feed the rootstock and the ear seedlings respectively. The disadvantage is that the action speed of the finished manipulator is currently slow, which cannot meet the requirements of grafting speed. Secondly, the cost of the finished manipulator used is too high. [0004] The manual feeding method has advantages and disadvantages in terms of convenience and adaptability of seedlings. [0005] The Korean equipment needs to be manually fed into the gap between the two ear seedlings. There are positioning requirements for feeding, and the operator cannot leave the...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): A01G2/32A01G2/35
CPCA01G2/32A01G2/35Y02A40/10
Inventor 林茂先陈宏江蔡奎
Owner 合肥佳富特机器人科技有限责任公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap