Hyperspectral image denoising method and device and storage medium
A hyperspectral image and variance technology, applied in the field of image processing, can solve problems such as accurate identification of unfavorable image targets, and achieve the effects of reducing impact, improving accuracy, and eliminating stripe noise.
Pending Publication Date: 2020-12-08
WUYI UNIV
View PDF0 Cites 3 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
It can be seen that band noise brings great challenges to the application of hyperspectral images, which is not conducive to the accurate identification of image targets. Therefore, effective removal of band noise is the premise and basis for the good application of hyperspectral 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
[0036] The embodiments of the present invention will be further described below in conjunction with the accompanying drawings.
[0037] Such as figure 1 As shown, the denoising method of a hyperspectral image according to an embodiment of the present invention includes the following steps:
[0038] Step S100: Obtain the pixel points on the hyperspectral image, determine the gray value, the column mean value and the column variance of each column according to the pixel points, and form a column mean value distribution map of all column mean values;
[0039] Step S200: Obtain all the extreme points in the column mean value distribution graph, and determine the corresponding extreme points whose steepness value is less than the steepness threshold according to the steepness value at the extreme point, and generate the first extreme value set; the second An extremum set includes several first extremums;
[0040] Step S300: Obtain two adjacent first extremums whose relative dista...
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 hyperspectral image denoising method and device and a storage medium, and the method comprises the following steps: obtaining pixel points on a hyperspectral image, and forming a column mean value distribution diagram; obtaining all extreme points in the column mean value distribution diagram, determining the corresponding extreme points of which the gradient values are smaller than a gradient threshold, and generating a first extreme value set; obtaining an adjacent first extreme value of which the relative distance is smaller than a distance threshold value, and removing first extreme values with smaller values from the first extreme value set according to the adjacent first extreme value to generate a second extreme value set; classifying the hyperspectral image according to the second extreme value to obtain a noise column and a non-noise column; performing smooth filtering processing on the pixel points on the noise column and the non-noise column to obtain a filtering mean value and a filtering variance of each column; and checking the hyperspectral image to obtain a denoised image. According to the method, the hyperspectral image can be denoised, the influence of strip noise on the hyperspectral image is reduced, and the recognition accuracy of the hyperspectral image is improved.
Description
technical field [0001] The invention relates to the field of image processing, in particular to a hyperspectral image denoising method, device and storage medium. Background technique [0002] In the process of acquiring hyperspectral images, they are generally polluted by band noise. These band noises are not exactly the same in hyperspectral images of different bands. There will be fewer bands in the image, and the width and scattering intensity of the bands are not fixed. It can be seen that band noise brings great challenges to the application of hyperspectral images, which is not conducive to the accurate recognition of image targets. Therefore, effective removal of band noise is the premise and basis for the good application of hyperspectral images. Contents of the invention [0003] The present invention aims to solve at least one of the technical problems existing in the prior art. To this end, the present invention proposes a hyperspectral image denoising method...
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 Applications(China)
IPC IPC(8): G06T5/00
CPCG06T2207/10036G06T2207/20032G06T5/70Y02A40/10
Inventor 冯华李伟科梁明健邓辅秦黄永深
Owner WUYI UNIV