Vision-based intelligent table top size detection method and system

A size detection and table top technology, applied in the field of image processing, can solve problems such as limited anti-interference ability, and achieve the effect of strong anti-interference ability

Pending Publication Date: 2022-08-05
杭州景吾智能科技有限公司
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But the invention has limited anti-interference ability

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
  • Vision-based intelligent table top size detection method and system
  • Vision-based intelligent table top size detection method and system
  • Vision-based intelligent table top size detection method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0116] According to a visual-based intelligent table size detection method provided by the present invention, such as Figure 1-Figure 3 shown, including:

[0117] Step S1: collecting the pose of the robot's photographing point;

[0118] Specifically, in the step S1:

[0119] Teach the robot one or more camera points, navigate the robot to the robot working point in front of the table, make the Z-axis of the robot perpendicular to the ground, and the X-axis point to the front table, switch the robot to the teaching mode, and convert the real-time image captured by the camera Open;

[0120] Drag the end of the robotic arm of the robot to different poses, so that the cameras on the end of the robotic arm point to the preset positions respectively. According to the size of the table, select the number of poses m, and monitor the real-time image of the camera to ensure the adjacent poses. In this case, the image of the camera has overlapping areas above the preset value, and th...

Embodiment 2

[0167] Embodiment 2 is a preferred example of Embodiment 1, in order to describe the present invention in more detail.

[0168] Those skilled in the art can understand the method for detecting the size of a smart countertop based on vision provided by the present invention as a specific embodiment of the system for detecting the size of a smart countertop based on vision, that is, the system for detecting the size of the smart countertop based on vision. This can be achieved by executing the flow of steps of the method.

[0169] A system for visual-based intelligent countertop size detection provided according to the present invention includes:

[0170] Module M1: collect the pose of the robot's photographing point;

[0171] Specifically, in the module M1:

[0172] Teach the robot one or more camera points, navigate the robot to the robot working point in front of the table, make the Z-axis of the robot perpendicular to the ground, and the X-axis point to the front table, sw...

Embodiment 3

[0220] Embodiment 3 is a preferred example of Embodiment 1, in order to describe the present invention in more detail.

[0221] This system consists of a mobile chassis, a robotic arm, and a depth camera, such as figure 1 shown.

[0222] The method includes the following steps:

[0223] Step 1: Determine the pose of multiple camera points of the robot;

[0224] Step 2: Online 3D reconstruction of the countertop;

[0225] Step 3: Identify the corner points of the table based on the table model;

[0226] Wherein, step 1 includes the following steps:

[0227] Step 1.1: Teach the robot multiple camera points;

[0228] First, navigate the robot to the robot working point in front of the table. At this time, the Z-axis of the robot is perpendicular to the ground, and the X-axis points to the front table. And switch the robot to teaching mode, and open the real-time image captured by the camera at the same time.

[0229] Then drag the end of the robotic arm of the robot to dif...

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 provides a vision-based intelligent table top size detection method and system. The vision-based intelligent table top size detection method comprises the following steps: S1, acquiring a posture of a photographing point of a robot; s2, collecting point cloud data according to a set pose, converting the point cloud data into a robot coordinate system, and combining the point cloud data into a complete point cloud; and S3, carrying out size identification based on the model of the complete point cloud. According to the invention, the cleaning robot can identify angular points of table tops in various hotel rooms; the method can be applied to identification of different types of table tops by simply configuring parameters; according to the method, table tops with uniform room types and different sizes can be quickly copied; the anti-interference capability is strong, and the change of light and texture on the table surface does not influence the identification of the table surface.

Description

technical field [0001] The present invention relates to the field of image processing, and in particular, to a method and system for detecting the size of an intelligent countertop based on vision. Background technique [0002] Hotel rooms require a lot of cleaning every day. However, as the problem of the aging population becomes more and more serious, the labor force willing or able to do hotel cleaning will become less and less, and the cost will become higher and higher. Using robots to replace human labor and cleaning hotels will become the future development direction. An important part of the cleaning of the hotel is the cleaning of the bathroom. The bathrooms of different room types are slightly different in size and style. It is necessary for the robot to be able to identify the cleanable range of the bathroom in real time. Among them, for the cleaning of the countertop of the basin, the robot needs to accurately identify the three-dimensional space coordinates of ...

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): A47L11/40
CPCA47L11/4002A47L11/4011
Inventor 夏子涛郭涛
Owner 杭州景吾智能科技有限公司
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