A Robust Recognition Method for AR Code Marked on Cylinder

An identification method and AR code technology, applied in the field of AR code identification, can solve the problem of low AR code recognition rate and other problems

Active Publication Date: 2019-04-02
SHIJIAZHUANG TIEDAO UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0010] The purpose of the present invention is to provide a robust identification method for AR codes marked on cylinders, to solve the problem of low recognition rate of such AR codes in traditional identification methods

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
  • A Robust Recognition Method for AR Code Marked on Cylinder
  • A Robust Recognition Method for AR Code Marked on Cylinder
  • A Robust Recognition Method for AR Code Marked on Cylinder

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0108] Such as figure 1 As shown, taking a classic AR code with an object to be identified on a certain cylinder and a data bit of 5×5 as an example, the robust identification method of the present invention includes the following steps:

[0109] 1. Improve the coding structure of the AR code by adding positioning flags in the AR code. The specific method is:

[0110] 1-1. Add a row of positioning flags with one data bit on the upper edge of the 5×5 AR code data area, and add a column of positioning flags with one data bit on the left side of the AR code data area. The row positioning flags and columns The positioning flags form an overlapping flag in the upper left corner, thereby forming a 6×6 resolution area.

[0111]1-2. Add a row positioning identifier of 101010 to the row positioning flag from left to right, add a column positioning identifier of 101010 to the column positioning flag from top to bottom, and overlap the identifier in the flag at the upper left corner If...

Embodiment 2

[0156] This embodiment is a robust identification of classic AR codes, and the specific method includes the following steps:

[0157] 1. Collect the AR code marked on the cylinder (see figure 1 ), get AR code area image I 0 .

[0158] 2. For AR code area image I 0 Perform adaptive threshold segmentation and morphological filtering to obtain the filtered binarized image I 1 (see image 3 ).

[0159] 3. Detection and filtering of binarized image I 1 After excluding the non-four vertices, non-convex quadrilateral contours and too small contours in the image, the contours that only contain the AR code area are obtained, and the pixels in the area other than the contours that only contain the AR code area are filled as representatives" 0" pure black, make a mask layer (see Figure 4 ), and then the AR code area image I 0 Copy it into the mask layer to get a binarized image I containing only the AR code area 2 (see Figure 5 ). The four vertices of the AR code area outlin...

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 method for robust recognition of an AR code marked on a cylinder, comprising the following steps: binarizing the AR code image, extracting the contour of the AR code binarized image, and extracting the AR code area in the contour The image is straightened; the arc distortion detection and rotation are performed on the squared AR code area, so that the concave arc side faces upward, and the concave arc side is straightened; the convex arc side is straightened by using the local adaptive compression algorithm to obtain An AR code area with a rectangular outline; non-linear scribing recognition for the AR code area. The invention solves the problems that some traditional recognition methods have low recognition accuracy rate of AR codes and cannot correctly recognize AR codes when arc distortion occurs, and improves the robustness of AR code recognition.

Description

technical field [0001] The invention relates to a method for identifying an AR code, in particular to a method for robustly identifying an AR code marked on a cylinder. Background technique [0002] Augmented reality assisted maintenance technology superimposes virtual prompt information on the real scene, provides users with intuitive and flexible operation prompts in complex equipment maintenance, and can provide accurate and real-time maintenance assistance for users who are not familiar with complex equipment inspection and maintenance. It is of great significance to shorten the maintenance cycle of equipment, improve maintenance efficiency and reduce costs. [0003] The identification methods applied to augmented reality auxiliary maintenance systems generally include identification based on markers and identification based on natural features, and AR codes are typical markers applied to augmented reality systems, and have been widely used at present. However, due to t...

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 Patents(China)
IPC IPC(8): G06K9/20
CPCG06V10/23G06V30/10
Inventor 王伟明孙一杰杨萌何亚轩张勇闫德立靳邵云佀明华
Owner SHIJIAZHUANG TIEDAO UNIV
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