Multi-algorithm 2D-VMD embedded fusion method of infrared polarization and intensity images based on complementary relationship
A 2D-VMD, infrared polarization technology, used in image enhancement, image data processing, computing and other directions, can solve the problems of fusion image brightness, contour, edge and detail fusion image distortion, to avoid information mutual interference, high definition , Improve the effect of fusion performance
Active Publication Date: 2018-01-26
ZHONGBEI UNIV
View PDF2 Cites 12 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] In order to solve the problem that the existing multi-algorithm embedded fusion of infrared polarization and light intensity images is difficult to complete the difference characteristics such as brightness, contour, edge and detail between fusion images and easily cause fusion image distortion, a method based on complementary relationship is proposed. Multi-algorithm 2D-VMD embedded fusion method for infrared polarization and light intensity images
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
[0037] refer to figure 1 flow chart for figure 2 and image 3 The shown infrared polarization and light intensity images are the research object and the experiment is carried out.
[0038] A multi-algorithm 2D-VMD embedded fusion method for infrared polarization and light intensity images based on a complementary relationship, comprising the following steps:
[0039] S1: Select energy weighted, PCA, MSGT, NSST, NSCT and DWCT commonly used fusion algorithms to fuse infrared polarization and light intensity images; respectively calculate the difference between the fusion image and infrared polarization image and infrared light intensity image; use the gray average and The local standard deviation describes the brightness features and contour features of DI and I respectively; the edge features and detail features of DP and P are described by Canny operator and local energy Laplacian operator, the process is as follows:
[0040] S11: Use energy weighting, PCA, MSGT, NSST, NSC...
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 belongs to the field of fusion of infrared images, and in particular to a multi-algorithm 2D-VMD embedded fusion method of infrared polarization and intensity images based on a complementary relationship. The method includes the following steps: firstly, separately extracting the brightness and profile features of the differential chart between a fusion image and an infrared polarization image and also the brightness and the profile features of a infrared intensity image by using the gray average and the local standard deviation, separately extracting the edge and detail featuresof the differential chart between the fusion image and the infrared light intensity image and also the edge and detail features of the infrared polarization image by using a Canny operator and an energy laplace operator; secondly, establishing the indexes for evaluating algorithm fusion performances based on feature similarities; then, based on the indexes for evaluating fusion performances of different algorithms, determining the complementary relationship among the different algorithms; then, based on the features of infrared polarization and intensity images, determining the order for performing embedding among MSGT and NSST, acquiring a high-frequency feature fusion image; and eventually, integrating a low-frequency feature fusion image and the high-frequency fusion image by using the2D-VMD, and obtaining a final fusion image. According to the invention, the method herein is applied to and is not limited to the field of infrared image fusion.
Description
technical field [0001] The invention belongs to the field of infrared image fusion, and specifically relates to a multi-algorithm 2D-VMD embedded fusion method for infrared polarization and light intensity images based on a complementary relationship. Background technique [0002] Infrared polarization and light intensity image fusion can enrich information such as the shape, size, brightness, details and position of the target, and significantly improve the detection rate and target recognition accuracy of the infrared imaging detection system. According to the difference characteristics between infrared polarization and light intensity images, researchers have proposed different fusion algorithms. The fusion performance of different fusion algorithms is different, and each has advantages and disadvantages. However, the difference between infrared polarization and light intensity images has many types and complex changes. , making it difficult for a single fusion algorithm ...
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 IPC IPC(8): G06T5/50
Inventor 杨风暴吉琳娜孙豫峰张雷王建萍王肖霞刘哲
Owner ZHONGBEI UNIV