Fusion method of sar image and visible light image based on variational multi-scale decomposition
A multi-scale decomposition and image fusion technology, which is applied in the field of image processing, can solve the problems of loss of important geometric structure and texture information, and fusion image is affected by noise, etc., to achieve the effect of reducing influence and clear structure
Active Publication Date: 2019-03-26
XIDIAN UNIV
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] The purpose of the present invention is to propose a method for fusion of SAR images and visible light images based on variational multi-scale decomposition to solve the problem of severe noise in the fused image due to the influence of SAR image speckle noise in the fusion of SAR images and visible light images in the prior art. , Loss of important geometric structure and texture information
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0030] The present invention will be further described below in conjunction with accompanying drawing:
[0031] refer to figure 1 , the implementation steps of the present invention are as follows:
[0032] Step 1: Input two images, one of which is a SAR image f A , and the other is a visible light image f B .
[0033] The two input images are SAR image and visible light image acquired in the same scene.
[0034] Step 2: Perform variational multi-scale image decomposition on the input SAR image to obtain three components of the SAR image.
[0035] 2a) For an input SAR image f A , given the initial scale λ=0.0005, solve the following energy functional:
[0036]
[0037] in, Represents the structural components of the input SAR image at scale λ, Indicates the texture component of the input SAR image at the scale λ, λ indicates the scale parameter, arginf( ) indicates the corresponding independent variable value when the likelihood function reaches the maximum value,...
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
Login to View More Abstract
The invention discloses a variation multi-scale decomposing based SAR image and visible light image integration method with the aim to solve the serious noise problem caused by the speckle noise of an SAR image when the SAR image is integrated with a visible light image. The method is performed through the following steps: inputting the SAR image and the visible light image; Conducting variation multi-scale decomposing to the two images so as to obtain their structure components and texture components; integrating the structure components of the two images based on a curve wave transformation and combination strategy; integrating the texture components of the two images with a partial energy combination strategy; adding together the integrated structure component and the integrated texture component to form an integrated image. Compared to the prior art, the integrated structure and detailed information become clearer, and can effectively suppress the impact of speckle noise on the integrated image, making the method able to improve image processing and target detecting and identifying.
Description
technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a fusion method of a synthetic aperture radar SAR image and a visible light image, which can be used in various military and civilian image processing systems. Background technique [0002] With the rapid development of aerospace technology, in the field of remote sensing detection, the single visible light remote sensing mode has gradually developed into a multi-sensor remote sensing mode. Especially in recent years, SAR remote sensing images have attracted more and more attention. System, SAR is very sensitive to the geometric characteristics of the target, which is often reflected in the image as a very dark or bright point or area, while visible light is more sensitive to the physical and chemical properties of the target, and the image mainly reflects the outline and spectral information. The fusion of SAR images and visible light images can make full u...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06T5/50
CPCG06T5/50G06T2207/10044G06T2207/20221
Inventor 吴艳李思宇樊建伟杨傲张洋王超
Owner XIDIAN UNIV