Unlock instant, AI-driven research and patent intelligence for your innovation.

Image matching method based on LFGC network and compression excitation module

A matching method and network model technology, applied in the field of image matching, can solve problems such as complex and diverse types of image point sets and difficult images

Active Publication Date: 2021-02-23
CHINA UNIV OF GEOSCIENCES (WUHAN)
View PDF5 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In addition, in the actual application process, the number of image point sets to be matched is often large and complex, and it is very difficult to design a unified general algorithm to solve all image matching problems.

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 matching method based on LFGC network and compression excitation module
  • Image matching method based on LFGC network and compression excitation module
  • Image matching method based on LFGC network and compression excitation module

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0063] In order to have a clearer understanding of the technical features, purposes and effects of the present invention, the specific implementation manners of the present invention will now be described in detail with reference to the accompanying drawings.

[0064] The embodiment of the present invention provides an image matching method based on LFGC network and compressed excitation module.

[0065] Please refer to figure 1 , figure 1 It is a flowchart of an image matching method based on an LFGC network and a compression excitation module in an embodiment of the present invention, and the method includes the following steps:

[0066] S1, acquire images, and in the images, a part is used as a training set, a part is used as a verification set, and the remaining part is used as a test set; wherein, the images include: outdoor data sets St.Peters and Reichstag and indoor data sets Brown; St The .Peters and Brown datasets contain 2506 and 841 image pairs respectively, and ...

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 matching method based on an LFGC network and a compression excitation module. The method comprises the steps: obtaining an image, enabling one part of the image to serve as a training set, enabling the other part of the image to serve as a verification set, and enabling the remaining part to serve as a test set; integrating the compression excitation module into anLFGC network, and constructing a network model for image matching; training the network model for image matching by using images as a training set to obtain a trained network model for image matching;and matching a to-be-matched image by using the trained network model for image matching to obtain a matching result of the to-be-matched image. According to the method, global information can be used for selectively emphasizing the characteristics of rich information, useless characteristics are inhibited, and the characterization capability of the network is improved.

Description

technical field [0001] The invention relates to the field of image matching, in particular to an image matching method based on an LFGC network and a compression excitation module. Background technique [0002] Establishing a set of reliable matching relationships between two sets of image points is a basic task in computer vision. Sensing image processing) and other aspects have made this task attract the attention of researchers. Judging from the existing research results, image matching usually adopts a two-step method, that is, the initial matching is first established and then the wrong matching (outlier points) is eliminated. The process of establishing initial matching is usually to match some local feature descriptors, such as SIFT and LIFT. However, some mis-matches are usually unavoidable in the initial matching due to issues such as keypoint positioning errors, limitations of local descriptors, and viewing angle changes. In order to solve this problem, research...

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): G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/22G06F18/29G06F18/214
Inventor 陈珺顾越罗林波龚文平王永涛宋俊磊
Owner CHINA UNIV OF GEOSCIENCES (WUHAN)