Check patentability & draft patents in minutes with Patsnap Eureka AI!

Typesetting system and method based on visual tracking robot

A visual tracking and visual system technology, applied in the field of visual tracking, can solve the problems of inability to distinguish complex component products, inability to accurately judge and obtain component products, etc., to improve clarity, eliminate errors, and ensure accuracy and effectiveness. Effect

Pending Publication Date: 2021-12-17
GUANGDONG SANSHUI INST OF HEFEI UNIV OF TECH +1
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the process of industrial component production and packaging, this patent cannot effectively distinguish a variety of mixed complex component products on the conveyor belt, and cannot accurately judge and obtain component products that need to be sorted and placed in an orderly manner

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
  • Typesetting system and method based on visual tracking robot
  • Typesetting system and method based on visual tracking robot
  • Typesetting system and method based on visual tracking robot

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0031]A typesetting system based on a visual tracking robot, which includes a conveyor belt 1 , a visual system 2 , an image processing and analysis system 3 , a control system 4 and an adjustment system 5 .

[0032] according to figure 1 In a specific embodiment shown, a vision system 2 capable of capturing images of at least a partial area of ​​the conveyor belt 1 and an adjustment system 5 capable of grabbing target objects on the belt body are sequentially provided above the conveyor belt 1 along its driving direction. . The transmission belt 1 is used to transport scattered target objects, so that the vision system 2 can acquire image information containing the target objects. The image processing and analysis system 3 can perform image processing and analysis according to the image information transmitted by the vision system 2 , thereby accurately analyzing and calculating the position, attitude and other information of the target object, and transmitting the analysis ...

Embodiment 2

[0081] This embodiment is a further improvement on Embodiment 1, and repeated content will not be repeated here.

[0082] Preferably, when the vision system 2 collects images of the conveyor belt, it needs to adjust the focus according to the resolution and definition of the actually collected images. Preferably, the active depth focusing method based on the digital image, the focusing scheme and key steps such as Figure 6 Shown:

[0083] The system is controlled by an industrial computer, using a frame grabber to capture images and then send them to the system's central processing unit. The image clarity evaluation link determines the image clarity and sends corresponding instructions to the control drive unit, and monitors the execution results of the corresponding link through an industrial computer. The main operations are as follows:

[0084] (1) System initialization, start auto focus;

[0085] (2) The image acquisition system acquires the target image;

[0086] (3...

Embodiment 3

[0089] This embodiment is a further improvement on Embodiment 1, and repeated content will not be repeated here.

[0090] The present application also relates to a typesetting method based on a visual robot. When the typesetting method screens the region of interest in the image, the super-resolution reconstruction operation of the scene image includes:

[0091] Sub-aperture image sequence acquisition: The image sequence acquisition process is to extract and rearrange the sub-pixels at the same position covered by all microlenses in the camera. Preferably, in the case of obtaining the orthogonally arranged macropixels and the original camera image, the darker edge position of the image in the sub-aperture image sequence is removed as noise, thereby effectively improving the accuracy of the algorithm.

[0092] Super-resolution reconstruction: Using the high-precision point spread function obtained in the previous steps as prior knowledge and accurate color vector information as c...

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 a typesetting system and method based on a visual tracking robot, the typesetting system at least comprises a conveyor belt (1) and a visual system (2), the visual system (2) can selectively acquire an image containing a target object on the conveyor belt (1), and transmits the image to an image processing and analyzing system (3); the image processing and analyzing system (3) can identify and segment the received image so as to obtain image information only containing a target object; when the image processing and analyzing system (3) obtains a high-resolution image through super-resolution reconstruction of a scene image, the image processing and analyzing system (3) completes resolution image gray scale segmentation in a super-pixel segmentation mode, and the image processing and analyzing system (3) calculates a threshold value according to the segmented image. And the segmentation of the region of interest containing the target object image is completed in a threshold segmentation mode.

Description

technical field [0001] The invention relates to the technical field of visual tracking, in particular to a typesetting system and method based on a visual tracking robot. Background technique [0002] Most of the sorting work in industrial production is completed by teaching and programming of industrial robots. This method often puts forward higher requirements for peripheral auxiliary equipment and increases production costs [1]. Scholars from Harbin Institute of Technology carried out work based on the sorting robot system of machine vision, conducted theoretical research and experimental verification, and successfully solved the problems of visual image recognition, target tracking and grasping and sorting control strategies of SCARA robots. Scholars from South China University of Technology designed a dual-vision sorting and tracking system based on industrial computers and embedded systems, using embedded technology to effectively improve the computing efficiency of th...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/73G06T7/136G06T7/11G06T7/90G06T3/40G06N3/04G06N3/08
CPCG06T7/75G06T7/136G06T7/11G06T3/4053G06T7/90G06N3/04G06N3/084G06N3/086
Inventor 杨国宇朱家诚吴天星吴焱明李铭锋
Owner GUANGDONG SANSHUI INST OF HEFEI UNIV OF TECH
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

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com