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

Robust binocular stereo image stitching method

A binocular stereo image stitching technology, applied in image enhancement, image analysis, image data processing, etc., can solve the problems of stitching images, ghost images, blurred stitching results, etc., achieve accurate stitching, reduce ghosting, and achieve seamlessness stitching effect

Active Publication Date: 2018-08-31
SHENZHEN INST OF FUTURE MEDIA TECH +1
View PDF8 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In reality, the scene has depth information, and only two-dimensional transformation cannot stitch images well, which will cause problems such as blurring or even ghosting in the stitching results due to misregistration between images

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
  • Robust binocular stereo image stitching method
  • Robust binocular stereo image stitching method
  • Robust binocular stereo image stitching method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] The present invention will be further described below with reference to the accompanying drawings and in combination with preferred embodiments.

[0042] like figure 1 As shown, the preferred embodiment of the present invention proposes a robust binocular stereo image stitching method, comprising the following steps:

[0043] S1: Use a binocular camera to collect two sets of images, where each set of images includes the left view captured by the left camera and the right view captured by the right camera, and calculate the distance between the left and right views of each set of images disparity map;

[0044] Specifically, the two groups of images collected are denoted as I 1 and I 2 , where the first set of images I 1 Including the first left view captured by the left camera and the first right view captured by the right camera The second set of images I 2 Including the second left view captured by the left camera and the second right view captured by the righ...

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 discloses a robust binocular stereo image stitching method. The method comprises: a binocular camera is used for collecting two groups of images and a disparity map between a left view and a right view of each group of images is calculated respectively; feature points of each group of images are extracted and the feature points are described; GMS feature point matching is carried outon the feature points of each group of images and error matching is screened out to obtain accurate feature point pair set; according to the disparity maps and the feature point pair set, a new feature constraint condition is set to obtain homography transformation enabling the feature constraint condition to be optimized, global transformation is carried out on the second group of images by using the homography transformation, and local shape retaining transformation is carried out on a non-overlapped region, relative to the first group of images, of the second group of images; and the leftviews and the right views after transformation are fused respectively to obtain a spliced left view and a spliced right view, and then synthesis is carried out to obtain a final space diagram. Therefore, seamless splicing is realized; and the algorithm has certain robustness.

Description

technical field [0001] The invention relates to the fields of computer vision technology and image processing, in particular to a robust binocular stereo image stitching method. Background technique [0002] Image stitching technology is widely used and plays an important role in medical treatment, aerospace, entertainment live broadcasting, etc., enriching people's lives; especially with the development of VR and AR, people are no longer satisfied with the images taken by existing camera perspectives , the pursuit of higher resolution and even high-quality images of 360-degree panoramas brings challenges to traditional monocular image stitching technology. The traditional monocular image stitching technology uses the perspective transformation between images to transform the images into a unified coordinate system for fusion, which is a two-dimensional plane transformation. In reality, the scene has depth information, and only two-dimensional transformation cannot stitch i...

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): G06T3/40G06T7/33
CPCG06T3/4038G06T7/33G06T2207/10012
Inventor 王好谦周雅玲王兴政方璐戴琼海
Owner SHENZHEN INST OF FUTURE MEDIA TECH
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