Rapid registration and fusion method for infrared and visible light images

A technology of infrared image and fusion method, which is applied in the field of image processing, can solve the problems of the influence of visible light work effect and low imaging resolution, and achieve the effect of improving speed and solving real-time problems

Pending Publication Date: 2020-12-08
NANCHANG HANGKONG UNIVERSITY
View PDF6 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Among them, in the field of target detection and tracking, visible light is mainly used. Visible light images can provide details and texture information of the target, but under the condition of low visibility, the working effect of visible light will be greatly affected; and the imaging mechanism of infrared is different from that of visible light imaging. , which can effectively image thermal targets under conditions of low visibility, but it is not sensitive to scene brightness changes, and the imaging resolution is low

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
  • Rapid registration and fusion method for infrared and visible light images
  • Rapid registration and fusion method for infrared and visible light images
  • Rapid registration and fusion method for infrared and visible light images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] The present invention will be further described below in conjunction with drawings and embodiments. see Figures 1 to 3d .

[0032] A rapid registration and fusion method of infrared and visible light images, the experimental process is described below:

[0033] 1) Select an open natural scene 3 area with a depth greater than 100 meters and obvious object features;

[0034] 2) Use the infrared sensor 1 and the visible light sensor 2 to simultaneously collect images of the same scene 3 (such as figure 1 shown), respectively extract 32 groups of feature points, and align the feature points (u, v) of the infrared image with the feature points (x, y) of the visible light image one by one to form a feature point set; the natural scene 3 Visible images such as Figure 2a , the infrared image of the natural scene 3 is as Figure 2b , where visible light sensor 2 uses BASLER’s ACE1920-155UC image collector, with an image size of 1920*1200, and infrared sensor 1 uses a V3-1...

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 quick registration and fusion method for infrared and visible light images, which comprises the following steps of: simultaneously acquiring images of a same scene by utilizing an infrared sensor and a visible light sensor, and solving a homography matrix converted between an infrared image plane coordinate system and a visible light image plane coordinate system by adopting singular value decomposition; taking the visible light image as a reference image, and obtaining an infrared image registered with the reference image through homography transformation; and carrying out image fusion on the reference image and the registered infrared image by adopting an adaptive weight pixel point superposition method. Aiming at fusion of infrared and visible light heterologous sensor images, advantage complementation is realized, and the problems that visible light image features are difficult to extract and register under the condition of weak visible light are solved; and meanwhile, on the basis of ensuring certain fusion precision, the image fusion speed is greatly improved, and the real-time problem in practical application is solved.

Description

technical field [0001] The invention relates to an image processing method, which is an image fusion based on fast image registration based on homography transformation and pixel point superposition based on adaptive weight, in particular to a fast registration and fusion method of infrared and visible light images. Background technique [0002] Image fusion is to fuse two or more images of the same scene according to a specific algorithm, so that the information contained in the fused single image is more comprehensive, and it is more suitable for human visual understanding and computer detection, classification, recognition and other tasks. At present, image fusion technology has been widely used in many fields, including remote sensing image analysis and processing, computer vision, unmanned driving, medical image processing, and target detection and tracking. Among them, in the field of target detection and tracking, visible light is mainly used. Visible light images can...

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): G06T7/33G06T5/50
CPCG06T7/337G06T5/50G06T2207/10048G06T2207/20004G06T2207/20221
Inventor 陈震卢锋张聪炫张弛江少锋危水根
Owner NANCHANG HANGKONG UNIVERSITY
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