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

Three-dimensional image splicing method

A stereo image, left and right image technology, applied in the field of image processing and stereo vision, can solve the problems of shape distortion, not fully considering the consistency of stereo image parallax, artifacts, etc., to achieve the effect of enhancing clarity and depth perception

Active Publication Date: 2019-08-09
TIANJIN UNIV
View PDF4 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006]The methods in the prior art usually use 2D image stitching technology to process stereoscopic images, and do not fully consider the parallax consistency of stereoscopic images; existing methods usually use single-stage deformation The alignment stitching method lacks the optimized alignment stitching process of multi-stage deformation, which can easily cause shape distortion and cause artifacts

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
  • Three-dimensional image splicing method
  • Three-dimensional image splicing method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0037] The embodiment of the present invention proposes a stereo image stitching method, see figure 1 , the method consists of three models: the disparity minimization homography model is used to pre-align the left and right images and reduce the vertical disparity; the multi-constraint deformation model further aligns the left and right images, and at the same time introduces the initial disparity map to maintain the consistency of the stereo image disparity; the disparity Consistent seam selection and fusion models are used to determine the optimal seam and perform stereo image stitching, the best implementation is as follows:

[0038] 1. Pre-alignment based on parallax minimization homography model

[0039] Consider that the vertical disparity of stereo images can be controlled by feature points in spatial coordinates. Therefore, the vertical disparity of the pre-aligned object left and right images can be constrained by minimizing the y-coordinate difference between featu...

Embodiment 2

[0071] The scheme in embodiment 1 is carried out feasibility verification below, see the following description for details:

[0072] Table 1 shows the average vertical parallax comparison results of stereoscopic image stitching results. The comparison algorithms include: APAP and CSPS, where APAP is a planar image stitching algorithm, and CSPS is a stereoscopic image stitching algorithm. The smaller the average vertical parallax, the higher the 3D visual experience. It can be seen from Table 1 that the average vertical disparity value of the embodiment of the present invention is smaller than that of the APAP algorithm, which proves the effectiveness of the disparity constraint in stereoscopic image stitching. Furthermore, the CSPS algorithm performs worse than the embodiments of the present invention in maintaining disparity consistency. Mainly due to the shape distortion of the CSPS algorithm, it is easy to produce vertical parallax. It can be seen from Table 1 that benefi...

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, which comprises the following steps of: inputting a left three-dimensional image and a right three-dimensional image, pre-aligning the left three-dimensional image and the right three-dimensional image through parallax minimization of homography, and reducing vertical parallax; further aligning the left image and the right image through multi-constraint deformation, and introducing an initial disparity map to keep the disparity consistency of the three-dimensional image; and determining an optimal joint based on joint selectionand fusion with consistent parallax, and carrying out three-dimensional image splicing. According to the method, optimization and alignment of multi-stage deformation are carried out on the stereoscopic images, and parallax information of the stereoscopic images is combined, so that accurate splicing of the stereoscopic images is realized, visual distortion is avoided, and parallax consistency ofthe stereoscopic images is kept.

Description

technical field [0001] The invention relates to the technical fields of image processing and stereo vision, in particular to a method for splicing stereo images. Background technique [0002] In recent years, with the development of multimedia and display technology, stereoscopic image processing has become a hot topic. In addition, as an important and effective scene expression of virtual reality technology, stereoscopic images become an important part of creating interactive virtual scenes. Currently, in order to obtain stereo images with larger scenes, mainstream methods focus on stitching a series of left and right images captured by high-resolution binocular cameras. However, the inconsistency of object positions in left and right images easily causes visual fatigue and affects stereo perception. Therefore, how to ensure that the stereoscopic image has a reasonable parallax range and less visual distortion, and how to enhance the depth and clarity of the obtained ster...

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): G06T3/40
CPCG06T3/4038G06T2207/10012
Inventor 雷建军范晓婷侯春萍徐立莹杨博兰祝新鑫
Owner TIANJIN UNIV
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