Three-dimensional image splicing method for eliminating motion ghosting

A technology for stereoscopic images and moving objects, which is applied in image enhancement, image analysis, image data processing and other directions to achieve the effect of reducing ghosting, eliminating motion ghosting, and stitching accurately

Pending Publication Date: 2019-03-19
SHENZHEN GRADUATE SCHOOL TSINGHUA UNIV
View PDF4 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For the stitching of stereoscopic images with moving objects, it is necessary to improve the stitching accuracy while removing motion ghosts as much as possible to reduce the corresponding distort

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
  • Three-dimensional image splicing method for eliminating motion ghosting
  • Three-dimensional image splicing method for eliminating motion ghosting
  • Three-dimensional image splicing method for eliminating motion ghosting

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] The present invention will be further described below with reference to the accompanying drawings and in combination with preferred embodiments.

[0040] Such as figure 1 , a preferred embodiment of the present invention proposes a stereoscopic image stitching method for eliminating motion ghosting, comprising the following steps:

[0041] 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 disparity map of the left and right views between each set of images;

[0042] Specifically, the two groups of images collected are denoted as I 1 and I 2 , where each group of images includes the left view captured by the left camera ( and ) and the right view captured by the right camera ( and ), and calculate the disparity maps of the left and right views in each group of images, denoted as D 1 and D 2 .

[0043] S2: Use ...

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 three-dimensional image splicing method for eliminating motion ghosting, which comprises the following steps of: acquiring two groups of images by adopting a binocular camera, and respectively calculating the view difference of the two groups of images; extracting feature points of each group of images, describing and matching the feature points, and then screening out wrong matching to obtain an accurate feature point pair set; setting a new feature constraint condition according to the view difference and the feature point pair set, and performing global transformation on the second group of images by adopting the obtained homography transformation which optimizes the feature constraint condition; determining an overlapping region of the first group of images and the transformed second group of images, finding out a moving object of the overlapping region, and designing a weighted fusion coefficient according to the relative position of the moving object andthe virtual splicing line; and respectively fusing and splicing the left view and the right view, and synthesizing the spliced left view and right view to obtain a final stereo image. According to the stereo image splicing method provided by the invention, high-quality splicing is realized for the stereo image containing the moving object.

Description

technical field [0001] The invention relates to the fields of computer vision technology and image processing, in particular to a stereoscopic image splicing method for eliminating motion ghosting. Background technique [0002] Image stitching technology is widely used and plays an important role in education, medical care, aerospace, entertainment live broadcasting, etc., greatly enriching people's lives. Especially with the development of VR, AR and gigapixels, people are no longer satisfied with images with limited viewing angles, and begin to pursue high-quality wide-angle images with higher resolution and even 360-degree panoramas; Stitching technology presents new challenges. For stereoscopic image stitching, not only the registration and blurring and ghosting problems in traditional monocular image stitching must be considered, but also high-quality stitching images with stereoscopic effects need to be obtained based on the parallax (depth) information of stereoscopi...

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
CPCG06T3/4038G06T7/337G06T2207/20221G06T2207/10012
Inventor 王好谦周雅玲张永兵戴琼海
Owner SHENZHEN GRADUATE SCHOOL TSINGHUA 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

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