A visible light-infrared image registration method based on salient region features and edge degree

A technology of regional features and infrared images, applied in the field of visible light-infrared image registration, which can solve the problems of poor registration accuracy and low similarity.

Active Publication Date: 2017-02-22
NORTHWESTERN POLYTECHNICAL UNIV
View PDF2 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] In order to overcome the disadvantages of poor registration accuracy caused by the low feature similarity between images extracted by existing visible light-in

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 visible light-infrared image registration method based on salient region features and edge degree
  • A visible light-infrared image registration method based on salient region features and edge degree
  • A visible light-infrared image registration method based on salient region features and edge degree

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0094] The specific steps of the visible light-infrared image registration method based on the salient area feature and edge degree of the present invention are as follows:

[0095] 1. Salient region detection based on improved local contrast.

[0096] First, use a graph-based image segmentation algorithm to divide the input image into several regions, and calculate the color histogram of each region, then the region r k The significance value S(r k ) is calculated as formula (1).

[0097]

[0098] In the formula, ω(r i ) is the area r i weight, D r (r k ,r i ) is the area r k and r i The color distance metric between , and its calculation method is shown in formula (2).

[0099]

[0100] In the formula, f(c k,i ) is the i-th color c k,i in the kth region r k The probability of appearing in all colors of , the probability density function is the normalized color histogram. D(c 1,i ,c 2,j ) is color c 1,i and color c 2,j The Lab space color distance. Sin...

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 visible light-infrared image registration method based on salient region features and edge degree, and is to solve the technical problem of poor registration precision due to low similarity of image features extracted through an existing visible light-infrared image registration method. The technical scheme is characterized by extracting a salient region from an image pair to be registered through a significant region detection method based on adaptive local contrast; describing shape features of the salient region by utilizing a Zernike rotation invariant moment to ensure translation, gray level, scale and rotation invariance of the utilized features; through RANSAC, obtaining a homonymy point pair and carrying out estimation to obtain initial transform parameters; and finally, carrying out optimization on the initial transform parameters by utilizing a three-dimensional joint histogram constructed based on edge degree to obtain a final result. The method improves image registration precision through salient region and edge degree features, the similarity of which are higher, between heterogeneous source images, and invariance of the Zernike moment.

Description

technical field [0001] The invention relates to a visible light-infrared image registration method, in particular to a visible light-infrared image registration method based on salient area features and edge degrees. Background technique [0002] Multi-source image registration technology refers to preprocessing two or more image data obtained by different types of sensors for the same scene, from different times and from different angles, and using certain algorithms and models to compare their complementarity. The process of combining information or advantage information and transforming it into the same coordinate system. [0003] The demand for multi-source fusion technology that can more comprehensively and truly reflect the essential information and characteristics of things is increasing by selectively organically combining the data in multi-source images. Multi-source image registration provides a unified spatial reference for multi-source images and is the basis fo...

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): G06T7/30
CPCG06T2207/10048
Inventor 张艳宁陈妍佳张秀伟黄梅娇李飞符志鹏
Owner NORTHWESTERN POLYTECHNICAL UNIV
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