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

Visible light and infrared image registration method for equalization second-order gradient histogram descriptor

A second-order gradient, infrared image technology, applied in image enhancement, image analysis, image data processing and other directions, can solve the problems of dependence, can not fundamentally solve the problems and difficulties of multi-source image registration, and achieve high practicability , to achieve the effect of convenience and a wide range of scenes

Pending Publication Date: 2022-04-12
NO 709 RES INST OF CHINA SHIPBUILDING IND CORP
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method is actually a compromise method for the difficult multi-source image registration problem. It cannot fundamentally solve the problem of multi-source image registration and relies on the effect of the key region extraction algorithm.

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
  • Visible light and infrared image registration method for equalization second-order gradient histogram descriptor
  • Visible light and infrared image registration method for equalization second-order gradient histogram descriptor
  • Visible light and infrared image registration method for equalization second-order gradient histogram descriptor

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0054] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0055] Most of the current feature matching methods are aimed at homogeneous images, and the design purpose of feature descriptors is generally to accurately describe the pixel information characteristics of local areas of images, such as SIFT, SURF, ORB feature extraction and description methods. The application of these methods to the registration and alignment problem of homogeneous images is now relatively mature. However, there are non-linear differences in grayscale information between heterogeneous images, so the feature description operators generated by reflecting local areas of images at ...

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 visible light and infrared image registration method for a balanced second-order gradient histogram descriptor, and belongs to the field of multi-source image registration, and the method comprises the steps: carrying out the DoG feature detection of visible light and infrared images, and obtaining the position information and scale information of image spot features; first-order gradient amplitudes and arguments of the visible light image and the infrared image in a multi-scale space are calculated, denoising and contrast-limited adaptive histogram equalization processing are carried out on the first-order gradient amplitude of the infrared image, and then second-order gradients are obtained for the processed first-order gradient amplitude of the infrared image and the first-order gradient amplitude of the visible light image; using an SIFT or GLOH histogram statistical feature description method to solve feature descriptors of second-order gradient generation feature points of the infrared and visible light images, and finally calculating an image geometric transformation model parameter H through the matched feature points. According to the method, the function of sub-pixel alignment of the infrared and visible light images can be automatically achieved, the algorithm is intelligent, implementation is convenient, and the application range is wide.

Description

technical field [0001] The invention belongs to the field of multi-source image registration, and in particular relates to a registration method of visible light and infrared images based on feature point matching, specifically a visible light and infrared image based on a limited contrast adaptive equalization second-order gradient histogram descriptor registration method. Background technique [0002] On the basis of the development of information sensors and the development of computer hardware and software, and the actual needs of machines to perceive complex environments, multi-source information fusion technology is becoming more and more important. In the field of computer vision and image processing, the fusion of multi-source image or video data from various sensors can obtain more environmental visual information, which is more conducive to subsequent data analysis operations and robustness to shooting environment changes. Multi-source images are also called multi...

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): G06T5/00G06T5/40G06T7/33G06V10/50G06V10/46G06V10/74G06V10/77G06K9/62
Inventor 闫石
Owner NO 709 RES INST OF CHINA SHIPBUILDING IND CORP
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