Automatic sorting system and method for stacked objects in container

An automatic sorting system and object technology, which is applied in sorting and other directions, can solve the problems of difficult to realize the suction of objects at different heights, achieve strong anti-environmental interference ability, and solve time-consuming and labor-intensive effects

Pending Publication Date: 2021-12-03
XI'AN UNIVERSITY OF ARCHITECTURE AND TECHNOLOGY
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to overcome the shortcomings of the existing material sorting robots in the above-mentioned prior art that it is difficult...

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
  • Automatic sorting system and method for stacked objects in container
  • Automatic sorting system and method for stacked objects in container
  • Automatic sorting system and method for stacked objects in container

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0045] An automatic sorting system for stacked objects in a container, comprising:

[0046] An image acquisition module, configured to acquire image information of objects piled up in the container;

[0047]The control unit includes an image information processing module and a positioning module. The image information processing module interacts with the image acquisition module to process the acquired image information to obtain training samples, and then perform instance segmentation on the training samples to obtain the maximum The upper object image and the bounding box of the image; the positioning module interacts with the image information processing module, and based on the uppermost object image of the stacked objects in the container, after calculation, the pixel coordinates of the suction point of the object to be sucked and the position of the object to be sucked when being sucked are obtained. The rotation angle and the distance relationship between the object to ...

Embodiment 2

[0051] A method for automatic sorting of accumulated objects in a container, comprising the following steps:

[0052] Step 1) collecting image information of objects piled up in the container, processing the obtained image information to obtain training samples, performing instance segmentation on the training samples, and obtaining the top object image of the piled objects and the bounding box of the image;

[0053] Step 2) Based on the topmost object image of the stacked objects in the container, the pixel coordinates of the suction point of the object to be sucked are obtained after calculation;

[0054] Step 3) Based on the topmost object image of the stacked objects in the container, calculate the rotation angle of the object to be sucked in the stacked objects when sucking;

[0055] Step 4) Obtain the distance relationship between the object to be picked up and the target position based on the topmost object image of the stacked objects in the container, and convert the ...

Embodiment 3

[0058] A method for automatic sorting of accumulated objects in a container, comprising the following steps:

[0059] Step 1) collecting image information of objects piled up in the container, processing the obtained image information to obtain training samples, performing instance segmentation on the training samples, and obtaining the top object image of the piled objects and the bounding box of the image;

[0060] The training samples are labeled well-preserved object pictures;

[0061] The instance segmentation process is:

[0062] Build an instance segmentation network based on training samples;

[0063] Send the newly collected image of the piled-up object in the container to the instance segmentation network to obtain the segmented uppermost object image and the bounding box of the image.

[0064] Step 2) Based on the topmost object image of the stacked objects in the container, the pixel coordinates of the suction point of the object to be sucked are obtained after 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 discloses an automatic sorting system and method for stacked objects in a container, and belongs to the technical field of artificial intelligence and robotics. The automatic sorting system comprises an image collecting module, a control unit and a visual robot, and the control unit comprises an image information processing module and a positioning module. The automatic sorting method comprises the steps that collected images are processed through a stacked object recognizing and positioning algorithm to acquire position information of a to-be-sucked object; and the obtained position information of the to-be-sucked object is sent to the visual robot, and the visual robot sucks the to-be-sucked object. The concept of intelligent automation of the robot is fully embodied, the visual robot can autonomously and intelligently recognize the object located on the uppermost part in the container and suck the object, and automatic sorting of the object is achieved. The visual robot replaces human eyes to recognize and position objects in the container, and a magnetic induction actuator below a mechanical arm replaces human hands to sort the objects in a real environment. The automatic sorting system is high in environmental interference resistance and suitable for various working environments.

Description

technical field [0001] The invention belongs to the field of artificial intelligence and robot technology, and relates to an automatic sorting system and method for objects accumulated in a container. Background technique [0002] Automation refers to the automatic operation or operation of machines or devices according to prescribed procedures or instructions without human intervention, and the simulation of human intelligence activities. Automation technology is widely used in industry, agriculture, national defense, transportation and other aspects. Automation technology can not only liberate people from boring and heavy physical labor, but also prevent people from working in high-risk environments. Therefore, promoting industrial intelligent automation has become an important task at present. [0003] The current material sorting robot has been able to sort and grab target objects on a plane, and put the target objects on the conveyor belt, or grab and place the target ...

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): B07C5/342B07C5/36
CPCB07C5/3422B07C5/361B07C5/362B07C2501/0063
Inventor 徐胜军李康平韩九强孟月波刘光辉
Owner XI'AN UNIVERSITY OF ARCHITECTURE AND TECHNOLOGY
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