Image splicing method and device

A technology of image stitching and splicing images, which is applied in the field of image processing, can solve problems such as low registration accuracy and poor stitching quality, and achieve the effects of improving quality, ensuring computing efficiency, and fast and accurate image registration

Inactive Publication Date: 2020-04-28
UNIV OF SCI & TECH BEIJING +1
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is to provide an image splicing method and a splicing device to solve the problems existing in the prior art for image registration and splicing based on the low-level features extracted by the SURF algorithm, resulting in low registration accuracy and poor splicing quality. bad question

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
  • Image splicing method and device
  • Image splicing method and device
  • Image splicing method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] Such as figure 1 As shown, the image stitching method provided by the embodiment of the present invention includes:

[0047] S101, acquiring the image to be spliced ​​and a reference image;

[0048] S102, respectively performing feature point detection on the image to be spliced ​​and the reference image and calculating an accelerated robust feature (SURF);

[0049] S103, for the image to be spliced ​​and the reference image, center each detected feature point, select a feature image block of a preset size, and extract a convolutional neural network (Convolutional NeuralNetworks, CNN) feature according to the selected feature image block, Fuse the obtained accelerated robust features and convolutional neural network features to generate the features of the image to be spliced ​​and the features of the reference image;

[0050] S104, calculating the matching degree between the features of the fused image to be stitched and the features of the reference image, performin...

Embodiment 2

[0083] The present invention also provides a specific embodiment of an image stitching device. Since the image stitching device provided by the present invention corresponds to the specific embodiment of the aforementioned image stitching method, the image stitching device can execute the process steps in the specific embodiment of the above method To achieve the purpose of the present invention, therefore, the explanations in the specific implementation of the image stitching method above are also applicable to the specific implementation of the image stitching device provided by the present invention, and will not be repeated in the following specific implementations of the present invention.

[0084] Such as figure 2 As shown, the embodiment of the present invention also provides an image stitching device, including:

[0085] Obtaining module 11, is used for obtaining image to be spliced ​​and reference image;

[0086] The detection module 12 is used to perform feature po...

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 an image splicing method and an image splicing device, which can realize rapid and accurate image registration and splicing. The method comprises the steps of obtaining a to-be-spliced image and a reference image; carrying out feature point detection on the to-be-spliced image and the reference image and calculating acceleration robust features; aiming at the to-be-spliced image and the reference image, taking each detected feature point as a center, selecting feature image blocks with a preset size, extracting convolutional neural network features according to the selected feature image blocks, fusing the obtained acceleration robust features and the convolutional neural network features, and generating features of the to-be-spliced image and features of the reference image; calculating the matching degree between the features of the fused to-be-spliced image and the features of the reference image, and carrying out the transformation matrix estimation, therebyachieving the registration of the to-be-spliced image and the reference image; and fusing the registered to-be-spliced image and the reference image to obtain a complete spliced image. The invention relates to the field of image processing.

Description

technical field [0001] The invention relates to the field of image processing, in particular to an image splicing method and splicing device. Background technique [0002] Image stitching refers to the technology of combining two or several images of the same scene with overlapping parts to generate a seamless panorama or high-resolution image, which is a research hotspot in the field of image processing. Image mosaic technology is widely used in remote sensing technology, virtual reality, military monitoring and other fields. How to accurately extract feature points and realize image registration is a key issue to improve the quality of image stitching, which has important research significance. [0003] The Speed ​​Up Robust Features (SURF) algorithm is a commonly used feature extraction algorithm at present. Compared with other algorithms, its operation speed is greatly improved, but the extracted feature points are less, and only some low-level features are used. infor...

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): G06T3/40G06N3/04G06N3/08
CPCG06T3/4038G06N3/08G06N3/045
Inventor 林福宏杨惠萱周成成陆月明许海涛安建伟
Owner UNIV OF SCI & TECH BEIJING
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