Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A checkerboard corner detection method and device suitable for low-quality images

A checkerboard and point detection technology, applied in the field of image recognition, can solve the problems of poor anti-noise performance, relatively high image quality requirements, and low accuracy of recognition results, and can solve the problems of high image quality requirements and high robustness. Effect

Inactive Publication Date: 2017-05-10
XIAN UNIV OF POSTS & TELECOMM
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

like figure 1 The checkerboard calibration board is shown, which is the most widely used calibration board in the camera calibration process. Therefore, there are many methods for the corner detection of the checkerboard grid. For example, the more classic methods include the Harris method and the Susan method. etc., the invention patent CN201010105470.6 proposes a method of using grayscale template matching to detect "X" corner points, that is, a checkerboard corner point detection method, but the current method requires pixel-level template matching. The quality requirements are relatively high, figure 2 For the corner recognition results of the Harris method when the image quality is not high, from figure 2 It can be seen that the correct rate of recognition results of this method is very low, and the anti-noise performance is poor.

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 checkerboard corner detection method and device suitable for low-quality images
  • A checkerboard corner detection method and device suitable for low-quality images
  • A checkerboard corner detection method and device suitable for low-quality images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0031] Embodiment 1 of the present invention proposes a checkerboard corner detection method suitable for low-quality images, such as Figure 4 shown, including:

[0032] S11. Obtain a checkerboard image.

[0033] Various common digital image acquisition methods can be used to obtain the checkerboard image, for example, a black and white checkerboard calibration board photographed by a digital camera. figure 1 It is a black and white checkerboard calibration board taken by a digital camera.

[0034] The corner point of the black and white checkerboard calibration board refers to the critical point at the junction of the black and white grids in the checkerboard, and is adjacent to the four black and white grids.

[0035] S12. Perform corner enhancement filtering on the acquired checkerboard image to obtain an enhanced checkerboard image.

[0036] Since the checkerboard image is a black-and-white grid mutation area, in order to accurately extract the corner points, it is nec...

Embodiment 2

[0087] Embodiment 2 of the present invention proposes a checkerboard corner detection method suitable for low-quality images, such as Figure 9 shown, including:

[0088] S21. Obtain a checkerboard image.

[0089] It is the same as S11 in Embodiment 1 and will not be repeated here.

[0090] S22. Perform corner enhancement filtering on the acquired checkerboard image to obtain an enhanced checkerboard image.

[0091] It is the same as S12 in Embodiment 1 and will not be repeated here.

[0092] S23. Perform binarization and dilation and corrosion processing on the enhanced checkerboard image. Obtain the checkerboard image after binarization and dilation and erosion processing.

[0093] Step S23 carries out binarization and expansion and corrosion processing to the enhanced checkerboard image; the specific steps are:

[0094] S231. Set the third threshold of the grayscale image to be RT. If the grayscale value of a certain pixel in the image is greater than RT, assign its va...

Embodiment 3

[0135] Embodiment of the invention three A checkerboard corner detection setup suitable for low-quality images is proposed, such as Figure 10 As shown, it includes: a checkerboard image acquisition module 11 , an enhancement filter module 12 , a binarization and expansion erosion module 13 , a target area determination module 14 and a corner point determination module 15 . in:

[0136] Checkerboard image acquisition module 11: used to acquire the checkerboard image;

[0137] Enhanced filtering module 12: used to perform corner enhancement filtering on the acquired checkerboard image to obtain an enhanced checkerboard image;

[0138] The enhanced filtering module 12 includes: a first filtering module and a second filtering module. in:

[0139] The first filtering module: used for performing corner region enhancement on the acquired checkerboard image through a first filter to obtain a first filtered image.

[0140] The first filter is: assuming that i is the abscissa and...

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 belongs to the field of image identification, and provides a checkerboard pattern corner point detecting method and a checkerboard pattern corner point detecting device. The method comprises the following steps that: checkerboard pattern images are obtained; the obtained checkerboard pattern images are subjected to corner point enhancement filtering to obtain enhanced checkerboard pattern images; located target regions of corner points are determined in the enhanced checkerboard pattern images; and coordinates of the corner points in each target region are determined. The method and the device provided by the invention have the advantages that a method based on polar coordinate shape descriptors and automatic mode identification is adopted for checkerboard pattern corner point detection, and the problems of high requirement on image quality, poor antinoise performance and low corner point detection precision of a conventional corner point detecting method are effectively solved.

Description

technical field [0001] The invention belongs to the field of image recognition, in particular to a checkerboard corner detection method and device thereof. Background technique [0002] Camera calibration is a basic step in the field of computer vision to obtain 3D information from 2D images, and is widely used in 3D reconstruction, visual inspection and monitoring and other fields. The accuracy of camera calibration directly affects the accuracy of subsequent computer vision tasks, and the accuracy of camera calibration depends to a large extent on the image positioning accuracy of the control points of the calibration board. Therefore, improving the image positioning accuracy of the control points of the calibration plate is an important research topic in the field of computer vision. like figure 1 The checkerboard calibration board is shown, which is the most widely used calibration board in the camera calibration process. Therefore, there are many methods for the corne...

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): G06T7/80
Inventor 邓颖娜巩稼民袁立行汤琦孙宇航徐军华王凤利赵德胜乔琳
Owner XIAN UNIV OF POSTS & TELECOMM
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products