Visual identification method and device for single-category unstacking, equipment and medium

A category and preset template technology, applied in image data processing, instruments, image feedback, etc., can solve problems such as poor image quality, position and size deviation of deep learning recognition, etc.

Pending Publication Date: 2020-10-23
SEIZET TECH SHEN ZHEN CO LTD
View PDF10 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of the above defects or improvement needs of the prior art, the present invention proposes a visual recognition method, device, equipment and medium for single-category unstacking, thereby solving the problem that

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
  • Visual identification method and device for single-category unstacking, equipment and medium
  • Visual identification method and device for single-category unstacking, equipment and medium
  • Visual identification method and device for single-category unstacking, equipment and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0052] Such as figure 2 Shown is a schematic flowchart of a visual recognition method for single-category depalletizing provided by an embodiment of the present invention. figure 2 The method shown includes the following steps:

[0053] S1: After filtering and downsampling the original 3D point cloud of the object to be destacked, the target point cloud is obtained;

[0054] S2: Perform boundary extraction on the target point cloud to obtain a boundary point cloud, where only contour points are included in the boundary point cloud;

[0055] S3: Perform 3D matching between the preset template point cloud and the boundary point cloud, and segment the contour point clouds of each workpiece that match the preset template point cloud from the boundary point cloud, wherein the preset template point cloud is the object to be unstacked Consistent contour point cloud of each workpiece type in ;

[0056] In the embodiment of the present invention, step S3 may be implemented in the ...

Embodiment 2

[0080] Such as image 3 Shown is a schematic flowchart of another visual recognition method for single-category depalletizing provided by an embodiment of the present invention, which includes the following steps:

[0081] (1) Obtain the original 3D point cloud of the object to be unstacked, and set the original 3D point cloud of the object to be unstacked as P0;

[0082] In the embodiment of the present invention, the original 3D point cloud of the object to be destacked can be acquired through a 3D camera.

[0083] (2) Preliminary filtering is carried out to the original 3D point cloud P0 of the object to be unstacked in step (1), to obtain the filtered point cloud P1;

[0084] In the embodiment of the present invention, the PassThrough channel filter can be used to filter the original 3D point cloud P0 of the object to be unstacked in step (1), and other filtering methods can also be selected, which are not uniquely limited in the embodiment of the present invention.

[0...

Embodiment 3

[0106] Such as Figure 10 Shown is a schematic structural diagram of a visual recognition device for single-category depalletizing provided by an embodiment of the present invention, including:

[0107] The preprocessing module 101 is used to obtain the target point cloud after filtering and downsampling the original 3D point cloud of the object to be destacked;

[0108] Contour extraction module 102, is used for carrying out boundary extraction to target point cloud, obtains boundary point cloud, wherein, only includes contour point in the boundary point cloud;

[0109] The matching module 103 is used to carry out 3D matching with the preset template point cloud and the boundary point cloud, and segment each workpiece contour point cloud matching with the preset template point cloud from the boundary point cloud, wherein the preset template point cloud is the same as Contour point clouds of the same type of workpieces in the object to be depalletized;

[0110] The pose acqu...

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 visual identification method and device for single-category unstacking, equipment and a medium, and belongs to the field of machine vision, and the visual identification method comprises the steps: carrying out the filtering and down-sampling of an original 3D point cloud of a to-be-unstacked object, and obtaining a target point cloud; performing boundary extraction on the target point cloud to obtain boundary point cloud, wherein the boundary point cloud only comprises contour points; performing 3D matching on a preset template point cloud and the boundary point cloud, and segmenting out each workpiece contour point cloud matched with the preset template point cloud from the boundary point cloud, the preset template point cloud being a contour point cloud consistent with each workpiece type in the to-be-unstacked object; and obtaining workpiece poses corresponding to the workpiece contour point clouds obtained through matching, and performing unstacking according to height information in the workpiece poses. According to the visual identification method, 3D contour matching is carried out on the filtered workpiece point cloud and template point cloud of which the boundaries are extracted, so that the interference of a large amount of plane point clouds is reduced, and the matching precision is improved, and the calculation speed is increased.

Description

technical field [0001] The invention belongs to the field of machine vision, and more specifically relates to a visual recognition method, device, equipment and medium for unstacking of single items. Background technique [0002] In the field of industrial manufacturing and logistics, the traditional depalletizing system is realized based on deep learning image recognition and segmentation. The economic cost is high, and there are certain recognition errors. It is difficult to achieve accurate grasping and cannot adapt to the accuracy requirements for subsequent processing Scenes. In the palletizing scenario corresponding to depalletizing, high space utilization is required, the gap between adjacent items is small, and some even require close fit, which also requires depalletizing to have the ability to identify and divide items with small gaps. With the promotion of industrial-grade 3D cameras and the rise of 3D vision algorithms, the depalletizing system based on 3D visio...

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): G06T7/73G06T1/00
CPCG06T7/74G06T1/0014G06T2207/10028G06T2207/30164
Inventor 李城旭高磊
Owner SEIZET TECH SHEN ZHEN CO LTD
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