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

Binocular camera image suture line splicing method and system based on regional feature registration

A technology of binocular camera and area feature

Active Publication Date: 2020-06-05
WUHAN UNIV
View PDF8 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Aiming at the deficiencies of the prior art, the present invention provides a binocular camera image suture line stitching method based on regional feature registration to solve the problem of excessive inspection in image stitching, and stitching is performed after grid deformation registration Line optimization, which can effectively avoid artificial ghosting of spliced ​​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
  • Binocular camera image suture line splicing method and system based on regional feature registration
  • Binocular camera image suture line splicing method and system based on regional feature registration
  • Binocular camera image suture line splicing method and system based on regional feature registration

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] The present invention is mainly based on image region feature registration, and considering the spatial similarity on both sides of the suture line, proposes a binocular camera image stitching method and system based on region feature registration. This method fully considers the influence of different image features and constraints on the quality of stitching results, and weighs the above factors through an image grid transformation model. The results obtained by the invention are more scientific and more accurate.

[0041] The method provided by the invention can use computer software technology to realize the process. see figure 1 , a binocular camera image suture stitching method based on regional feature registration proposed in the embodiment, taking binocular cameras arranged left and right as an example to describe the process of the present invention in detail, as follows:

[0042] Step 1, for the input image I 0 and I1 (i.e. images from left and right persp...

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 provides a binocular camera image suture line splicing method and system based on regional feature registration. The method comprises the steps: inputted left and right visual angle images are subjected to feature extraction and matching, and extraction of feature points and geometric structure features of a local region of the image is included; the image is divided into grids, an image grid transformation model is constructed by using a matching result, and grid vertexes are optimized to minimize the total error so as to realize image registration; an optimal suture line is solved for the registered image overlapping region, so that the pixel difference between the two sides of the suture line is minimum; and exposure compensation is carried out on the overlapping regions on the two sides of the suture line, and splicing along the suture line is carried out to obtain a spliced image. According to the method, grid deformation is adopted, the overlapping region of the twoimages is registered as much as possible, then the optimal suture line is solved in the overlapping region, the obtained suture line can bypass the foreground with large parallax, and therefore ghosting is prevented from being generated in the place with large parallax during image fusion.

Description

technical field [0001] The invention belongs to the field of image splicing processing, and in particular relates to a technical scheme of a binocular camera image stitching method based on regional feature registration. Background technique [0002] Image mosaic technology is a technology that spatially registers a group of images that overlap with each other, and forms a complete, high-definition new image of a wide-view scene containing information about each image sequence after resampling and fusion. Image stitching is an important research direction in the field of digital image processing. It has wide application value in photogrammetry, computer vision, remote sensing image analysis, computer graphics and other fields. Important research topics in the field of space exploration, seabed survey, medicine, meteorology, geological survey, military, video compression and transmission, video indexing and retrieval, 3D reconstruction of objects, military reconnaissance and ...

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): G06T3/40G06T7/33
CPCG06T3/4038G06T7/33G06T2207/10004
Inventor 何楚李勇超汪悦恺林明远
Owner WUHAN 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