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

A Deformation Parameter Bundle Adjustment Method and Image Stitching Method for Image Dataset

An image data set and image stitching technology, applied in the field of image processing, can solve problems such as low calculation efficiency and poor calculation convergence, and achieve the effects of increasing calculation speed, reducing the scale of problems, and enhancing parallel computing capabilities

Active Publication Date: 2020-12-08
HUAZHONG UNIV OF SCI & TECH
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention provides a deformation parameter bundle adjustment method and an image splicing method of an image data set, which are used to solve the problem that the existing deformation parameter bundle adjustment method for large-scale image splicing is caused by joint adjustment of the deformation parameters of all images at the same time. The technical problems of poor calculation convergence and low calculation efficiency

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
  • A Deformation Parameter Bundle Adjustment Method and Image Stitching Method for Image Dataset
  • A Deformation Parameter Bundle Adjustment Method and Image Stitching Method for Image Dataset
  • A Deformation Parameter Bundle Adjustment Method and Image Stitching Method for Image Dataset

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0040] A deformation parameter bundle adjustment method 100 in image stitching, such as figure 1 shown, including:

[0041] Step 110, based on the image data set to be spliced, an image matching relationship diagram is established;

[0042] Step 120, segmenting the image matching relationship graph to obtain multiple sub-matching relationship graphs, wherein there are some identical nodes between every two adjacent sub-matching relationship graphs, and each node represents an image;

[0043] Step 130: Using the alternate direction multiplier method, based on the constraint conditions, iteratively optimize the deformation parameters of the image sub-datasets corresponding to each sub-matching relationship diagram in parallel, and complete the deformation parameter bundle adjustment of the image data set, wherein the constraint conditions make The corresponding deformation parameters of the same image in different sub-matching relationship graphs are equal.

[0044]The method ...

Embodiment 2

[0090] An image mosaic method 200, such as image 3 shown, including:

[0091] Step 210, using the deformation parameter bundle adjustment method of any image data set in the first embodiment to realize the optimal adjustment of the deformation parameters of each image;

[0092] Step 220, based on the optimized and adjusted deformation parameters of each image, project each image to a reference coordinate system;

[0093] Step 230, merging all the images in the reference coordinate system to complete image stitching.

Embodiment 3

[0095] A storage medium, in which instructions are stored, and when the computer reads the instructions, the computer is made to execute the deformation parameter bundle adjustment method for an image data set described in any one of the above-mentioned embodiments and / or the method described in the second embodiment An image stitching method described above.

[0096] The relevant technical solutions are the same as those in Embodiment 1, and will not be repeated here.

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 deformation parameter cluster adjustment method of an image data set and an image splicing method, and the deformation parameter cluster adjustment method comprises: buildingan image matching relation graph based on a to-be-spliced image data set; segmenting the image matching relation diagram to obtain a plurality of sub-matching relation diagrams, every two adjacent sub-matching relation diagrams having a part of same nodes, and each node representing an image; and performing iterative optimization on the deformation parameters of the image sub-data sets corresponding to the sub-matching relational graphs in parallel by adopting an alternating direction multiplier method on the basis of constraint conditions to complete the cluster adjustment of the deformationparameters of the image data sets, and the corresponding deformation parameters of the same image in different sub-matching relational graphs being equal by the constraint conditions. According to the method, the global cluster adjustment problem is decomposed, the images are grouped, a global optimal solution is achieved through an alternating direction multiplier method, grouping optimization and binding adjustment, and the method is low in calculation complexity, high in efficiency and high in convergence.

Description

technical field [0001] The invention belongs to the technical field of image processing, in particular to a deformation parameter bundle adjustment method of an image data set and an image splicing method. Background technique [0002] A core problem in panoramic image stitching technology is to solve the deformation parameters of each image, and the quality of the deformation parameters directly determines the quality of the stitched image. The homography matrix between the two images can be obtained by means of feature point matching, etc., and the homography matrix describes the projection mapping relationship between the two images. The deformation parameters of each image can be estimated through the homography matrix. However, the homography matrix only considers the projective mapping relationship between the two images, and errors will inevitably be introduced in the process of calculating the homography matrix, resulting in the fact that the deformation parameters ...

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 Patents(China)
IPC IPC(8): G06T3/40G06T5/50
CPCG06T3/4038G06T5/50G06T2207/20221
Inventor 颜露新吴锐夫钟胜陈立群王广雅
Owner HUAZHONG UNIV OF SCI & 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