Close-range image splicing method based on long-strip-shaped checkerboard calibration board

An image stitching and checkerboard technology, which is applied to the details of image stitching, graphic image conversion, image enhancement, etc. Insensitive, universal, and scalable

Active Publication Date: 2019-12-13
上海黑塞智能科技有限公司
View PDF4 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005]In special application scenarios, such as close-range images with low information entropy, it is difficult to extract robust feature points due to inconspicuous features, which leads to the failure of traditional image stitching 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
  • Close-range image splicing method based on long-strip-shaped checkerboard calibration board
  • Close-range image splicing method based on long-strip-shaped checkerboard calibration board
  • Close-range image splicing method based on long-strip-shaped checkerboard calibration board

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0073] In order to verify the splicing method of the present invention, the installation method is adopted in the embodiment, and the calibration plate is installed in the shooting picture, and a total of 6 pictures are taken to ensure that adjacent pictures overlap at least one group of concentric circles.

[0074] Such as Figure 5(a)-5(b) It is the local image of each stage with serial number 1 actually measured by the method of the embodiment of the present invention. The positioning mark of the local image of each stage with this serial number is 5, and the relevant information of the stitching parameters is: stitching has occurred, and the effective area of ​​stitching is 840×560, corresponding to perspective transformation The matrix (with two decimal places) is:

[0075]

[0076] Such as Figure 6(a)-6(b) It is the local image of each stage with serial number 2 actually measured by the method of the embodiment of the present invention. The positioning mark of the l...

Embodiment 2

[0098] The image preprocessing process is as follows Figure 12 shown. Firstly, grayscale processing is performed on the original image to obtain a grayscale image to improve image processing efficiency. Then check the corners of the checkerboard on the grayscale image to obtain the pixel coordinates of the corners of the checkerboard to prepare for image projection transformation. Finally, the perspective projection transformation is carried out, and the front view correction is carried out to obtain the front view image.

[0099] After preprocessing the image of the checkerboard, the crack image is processed according to the same processing parameters, and finally the front view image is obtained, such as Figure 13 shown.

Embodiment 3

[0101] The principle of the image geometric positioning algorithm in the present invention is a coding registration algorithm, and the images can be registered according to the coding rules of the calibration board, and the present invention proposes a "coding registration" algorithm accordingly. The code registration algorithm divides the crack image into multiple regions according to the concentric circle codes that come with the calibration plate. For adjacent images, the regions with the same code are overlapping regions. Based on this, the images can be registered, such as Figure 14 shown.

[0102] The checkerboard coding calibration board adopts the middle concentric circles for coding, and the coding of the concentric circles depends on the number of concentric circles, and the order along the movement direction is "5-4-3-2-5-4-3-2-···" . According to this, the overlap of one concentric circle encoding is satisfied during shooting, and the registration can be performe...

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 close-range image splicing method based on a long-strip-shaped checkerboard calibration plate, and the method comprises the following steps: 1, enabling the long-strip-shaped checkerboard calibration plate to be spliced with an image of a to-be-spliced region through a covering method or an installation method, and obtaining a to-be-spliced original image; 2, performingfront-view correction on the to-be-spliced original image by adopting an image front-view correction algorithm to obtain a front-view sequence image; 3, geometrically positioning the to-be-spliced original image by adopting an image geometric positioning algorithm to obtain a splicing parameter of each image; and 4, splicing all the front-view sequence images by utilizing the splicing parameters of each image to obtain a final complete front-view spliced image. Compared with the prior art, the method has the advantages of wide applicability, high expandability, high execution efficiency and the like.

Description

technical field [0001] The invention relates to the technical field of image mosaic, in particular to a method for mosaicing close-up images based on elongated checkerboard marking plates. Background technique [0002] Image stitching is one of the important issues in the field of image processing. The stitching algorithm for conventional images is relatively mature, but in some special environments, the traditional stitching algorithm may fail, such as common large-scale infrastructure (buildings, bridges, tunnels, etc.), Its characteristic is that the surface size of the structure is large, so a series of images need to be taken, and the information entropy of the surface image is low, so the image characteristics are poor, and it is difficult to shoot frontally, so it is difficult to obtain a complete frontal surface panorama. [0003] Image stitching generally first extracts and matches features, then calculates the homography matrix, performs image registration, and the...

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): G06T3/40G06T5/00G06T7/33G06T7/80G06T9/00
CPCG06T3/4038G06T5/006G06T7/33G06T7/80G06T9/00G06T2200/32
Inventor 潘玥董一庆王达磊徐聿升
Owner 上海黑塞智能科技有限公司
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