Supercharge Your Innovation With Domain-Expert AI Agents!

Hedge nursery stock pruning and centering method based on binocular vision

A binocular vision and hedgerow technology, applied in the field of hedgerow centering, can solve the problems of time-consuming and labor-consuming, low centering accuracy, and high requirements for operator proficiency, so as to improve the level of intelligence, improve operating efficiency, and accurately The effect of rate guarantee

Active Publication Date: 2021-03-26
GUANGXI UNIV
View PDF9 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

There are two main disadvantages of this technology. One is that the process of aligning the position of the manipulator with the hedge is completely dependent on manual labor, and the alignment is mainly performed by human eyes through video. The degree requirements are relatively high; the second is that due to the non-complete symmetry of the hedge, it is easy to cause low alignment accuracy
Therefore, the hedge trimming efficiency is difficult to improve and the trimming quality is difficult to guarantee

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
  • Hedge nursery stock pruning and centering method based on binocular vision
  • Hedge nursery stock pruning and centering method based on binocular vision
  • Hedge nursery stock pruning and centering method based on binocular vision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0032] Please see attached figure 1 , a method for trimming and centering hedge seedlings based on binocular vision, comprising the following steps:

[0033] Step 1, the binocular camera acquires the hedge image and generates a point cloud

[0034] Such as figure 2 As shown, the binocular vision camera 2 is installed on the base of the manipulator, which can scan the hedge and other objects in the surrounding environment to obtain RGB images from different angles, and then calculate the disparity map of the left and right images based on the SGBM algorithm. relationship, calculate the depth value z of each pixel point, and further calculate the x, y coordinates of each spatial point, and then the spatial point cloud can be obtained.

[0035] Step two, use the convolutional neural network to complete the target recognition of the hedgerow.

[0036] The invention adopts the MASK-RCNN target detection network to detect the hedgerow target; the hedgerow point cloud can be more...

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 relates to the technical field of hedge centering of hedge trimmers, in particular to a hedge nursery stock trimming centering method based on binocular vision, which comprises the following steps: S1, acquiring RGB images of hedges at different angles, and generating a point cloud through a parallax principle; S2, carrying out the recognition and segmentation of the hedge image through employing a target detection network, and obtaining the contour line of a hedge in the image; S3, filtering outliers by counting and judging the distance between each query point and the neighborhood point set, and removing point cloud outliers; S4, performing clustering filtering through the DBSCAN to remove clustered invalid point cloud sets; and S5, fitting the hedgerow point cloud, and obtaining a canopy model of the corresponding shape of the hedgerow through a certain number of iterations. According to the method, the hedge images at different angles are obtained and converted into the point cloud data, the shape category and geometric parameters of the hedge can be obtained through data processing of the images and the point cloud, the centering accuracy is high, and the operation efficiency is greatly improved.

Description

technical field [0001] The invention relates to the technical field of hedge centering of a hedge trimmer, in particular to a method for trimming and centering hedge seedlings based on binocular vision. Background technique [0002] In recent years, with the continuous development of China's economy and the advancement of urbanization, the market capacity and boundaries of urban landscaping construction have continued to expand, ushering in new opportunities for development. But what follows is the maintenance of urban greening. At present, many research institutions in China have conducted a certain degree of research on hedge trimmers. For example, Xi'an University of Technology has disclosed a green belt trimming system and its trimming method based on laser cutting. The application number is: CN201910151378.4, which can effectively reduce the Working noise, but because the laser beam can only cut planes, the application scenarios are relatively limited; Guangxi Universi...

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): G06T7/66G06T7/13G06T7/593G06K9/62A01G7/06
CPCG06T7/66G06T7/13G06T7/593A01G7/06G06T2207/10012G06T2207/10028G06T2207/20081G06T2207/20084G06F18/2321G06F18/2433
Inventor 蒙艳玫武豪赵秦川许恩永韦锦张婷婷董振唐治宏张腾
Owner GUANGXI UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More