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

Optimization method for improving splicing precision of double-spherical camera and electronic equipment

An optimization method and double spherical technology, applied in the field of image processing, can solve the problems of uneven distribution of pixels, distortion of camera images, and insufficient use of fisheye original pixels in the expanded image, etc., to achieve clear images and eliminate image deviations

Pending Publication Date: 2022-03-11
GUANGDONG STARFIVE TECH LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Generally, the key points of the expanded image of one camera are used as the benchmark, and the key points of the expanded image of the other camera are adjusted for alignment, which results in local distortion of the adjusted camera image.
[0003] The existing technology adopts fusion after unfolding, because fisheye unfolding leads to uneven distribution of pixels in the fisheye image in the unfolded image, so the fusion of the unfolded image does not fully use the original fisheye pixels; Fusion can evenly use fisheye pixels, making the fusion area clearer

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
  • Optimization method for improving splicing precision of double-spherical camera and electronic equipment
  • Optimization method for improving splicing precision of double-spherical camera and electronic equipment
  • Optimization method for improving splicing precision of double-spherical camera and electronic equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0057] This embodiment provides an optimization method for improving the splicing accuracy of a double-spherical camera, including the following steps:

[0058] S1 acquires the original image and extracts the center and radius of the fisheye, performs fisheye distortion correction to obtain a square image with the same length and width;

[0059] S2 maps the left camera image to the right camera, and extracts the feature points of the ROI ring area near the 180-degree overlapping area of ​​the two images;

[0060] S3 numbers the feature points and then pairs them, and performs an alignment operation through perspective transformation, so that the feature points are aligned as a whole;

[0061]S4 performs ring fusion on the processed images, and then performs fusion transition on the left and right images respectively, then expands them, and finally stitches and outputs the result.

[0062] In this embodiment, the images are flipped and aligned before the double fisheye images ...

Embodiment 2

[0066] In terms of specific implementation, this embodiment is an optimization method for improving the splicing accuracy of a double-spherical camera. In this embodiment, the center and radius of the fisheye are extracted from the original image, and then the fisheye distortion is corrected to obtain a square image with the same length and width. Among them, the original right camera image as figure 1 As shown, the center is normalized and the distortion correction is performed as figure 2 shown.

[0067] In this embodiment, the image of the left camera is mapped to the right camera, where the coordinate points of the left image are:

[0068] LX=W / 2+left_R*cos(θL)

[0069] LY=H / 2+left_R*sin(θL)

[0070] In this embodiment, LX, LY are the pixel sub-pixel coordinates of the left image; W, H are the width and height of the left image; left_R is the distance from the left camera pixel to the image center; θL is the distance between the left pixel and the center horn.

[007...

Embodiment 3

[0096] This embodiment provides an electronic device, including a processor and a memory storing execution instructions. When the processor executes the execution instructions stored in the memory, the processor executes an optimization to improve the splicing accuracy of a double spherical camera. method.

[0097] To sum up, before the deployment of the present invention, the alignment is carried out. Firstly, the image of one lens is mapped to the field of view of another camera, and then the ROI of the overlapping part is extracted, and the feature points of the overlapping part of the two fisheye pictures are matched and aligned to avoid After the fisheye is unfolded, the affine transformation alignment is performed, and the alignment of the image after the expansion is easy to cause image distortion. Alignment before deployment can fully eliminate the image deviation caused by the back-to-back installation error of two cameras.

[0098] The present invention performs cir...

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 the technical field of image processing, in particular to an optimization method for improving the splicing precision of a double-spherical-surface camera and electronic equipment, and aims to perform image overturning alignment before unfolding a double-fisheye image and avoid image distortion generated by adopting affine transformation alignment after unfolding the fisheye image. Annular fusion is carried out on the flipped image, so that the flipped image is more uniform than peripheral fusion after expansion, pixel points of the expanded image are not uniform in distribution, fusion weights of left and right images are not uniform in distribution, alignment operation is not needed after expansion, and the fusion effect is better; a parallax compensation mechanism is adopted, so that good alignment can be realized when a certain difference exists between a use distance and a calibration alignment distance to a certain extent. Alignment is carried out before unfolding, image deviation caused by back-to-back installation errors of the two cameras can be fully eliminated, and original pixels can be fully utilized when fisheye image annular region fusion is carried out before unfolding, so that the fused region image is clearer.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to an optimization method and electronic equipment for improving the splicing accuracy of double-spherical cameras. Background technique [0002] The prior art mainly relies on the affine transformation of the expanded image to align and stitch the border. Generally, the key points of the expanded image of one camera are used as the benchmark, and the key points of the expanded image of the other camera are adjusted for alignment, which results in local distortion of the adjusted camera image. [0003] The existing technology adopts fusion after unfolding, because fisheye unfolding leads to uneven distribution of pixels in the fisheye image in the unfolded image, so the fusion of the unfolded image does not fully use the original fisheye pixels; Fusion uses fisheye pixels evenly, making the fused areas clearer. [0004] Therefore, this paper aims to flip and align the dou...

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): G06T3/00G06T5/00G06T7/55
CPCG06T7/55G06T2200/32G06T2207/10028G06T3/14G06T5/80
Inventor 刘刚詹志康
Owner GUANGDONG STARFIVE TECH LTD
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com