Unlock instant, AI-driven research and patent intelligence for your innovation.

Weed recognition method capable of aiming at green leaf vegetables

An identification method, leafy vegetable technology, applied in the field of weed identification, can solve the problems of lack of targeted research and difficult identification of green leafy vegetables

Inactive Publication Date: 2019-07-05
GUANGXI UNIVERSITY OF TECHNOLOGY
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In the existing weed recognition technology based on machine vision, there is a lack of targeted research on green leafy vegetables, mainly because the leaf color of green leafy vegetables is similar to that of associated weeds and it is difficult to identify

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
  • Weed recognition method capable of aiming at green leaf vegetables
  • Weed recognition method capable of aiming at green leaf vegetables
  • Weed recognition method capable of aiming at green leaf vegetables

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] In order to make the technical means, creative features, goals and effects achieved by the present invention easy to understand, the present invention will be further described below in conjunction with specific embodiments.

[0020] refer to Figure 1-2 , the present embodiment adopts the following technical solutions: a weed identification method for green leafy vegetables, comprising the following steps:

[0021] (1) Through uniform segmentation, select n×m pixel points, and extract the region of interest centered on the pixel point;

[0022] (2) According to the color feature values ​​of the n×m regions of interest, extract the areas with similar color features in the field image, obtain the segmented image, and segment the vegetation area;

[0023] (3) Compare the difference in the area of ​​green vegetation between each segmented image. If there is a large difference in the vegetation area (associated weeds appear, there is a certain color difference), and the ar...

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 weed recognition method capable of aiming at green leaf vegetables. The method comprises the following steps that: (1) through even segmentation, selecting pixels on n*m positions, and taking the pixels as centers to extract regions of interest; (2) according to the color characteristic values of n*m regions of interest, extracting regions with similar color characteristics in a field image, obtaining segmented images, and segmenting vegetation regions; and (3) comparing the area difference of green vegetation regions among segmented images, if the difference (associated weeds occur and a certain color difference is in the presence) of the vegetation regions occurs and the region of interest is green (excluding interferences, including soil background, illumination reflection and the like), judging that associated weeds are in the presence. By use of the method, since the regions of interest are evenly selected, from the perspective of probability, a situationthat the region of interest falls in a weed region can occur on a large probability, and therefore, weed region segmentation is realized.

Description

technical field [0001] The invention relates to a method for identifying weeds, in particular to a method for identifying weeds aimed at green leafy vegetables. Background technique [0002] Green leafy vegetables: mainly refer to vegetables that mainly eat green leaves, such as spinach, rapeseed, lettuce, mustard greens, etc. Weeds may appear in the growth of green leafy vegetables. If you want to use variable spraying herbicides to reduce pesticide residues, you first need to identify whether weeds appear. Aiming at the problem that the leaves of green leafy vegetables and associated weeds are both green and difficult to identify, the present invention proposes to introduce an area of ​​interest to identify the weed area and the vegetable area. [0003] Existing studies on using machine vision to identify weeds lack targeted research on green leafy vegetables, and most of them are analyzed from the location, shape, and spectral characteristics of weeds. Green leafy veget...

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): G01N21/84G06K9/34
CPCG01N21/84G06V10/267
Inventor 胡波方华尚万增
Owner GUANGXI UNIVERSITY OF TECHNOLOGY