Non-repetitive multispectral/hyperspectral remote sensing image color uniformizing method based on FCM clustering matching and Wallis filtering

A hyperspectral remote sensing and image technology, applied in the field of multi/hyperspectral remote sensing image color equalization, can solve the problems of only focusing on color equalization processing and poor image effect, and achieve the effect of improving image effect, suppressing noise, and enhancing image contrast.

Active Publication Date: 2020-09-25
HARBIN INST OF TECH
View PDF9 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to solve the problem that the existing method only pays attention to the uniform color processing between remote sensing images with overlapping areas, and does not involve color uniformity between images without overlapping areas, resulting in poor image effects, and proposes Unweighted multi / hyperspectral remote sensing image color uniform method based on FCM cluster matching + Wallis filter

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
  • Non-repetitive multispectral/hyperspectral remote sensing image color uniformizing method based on FCM clustering matching and Wallis filtering
  • Non-repetitive multispectral/hyperspectral remote sensing image color uniformizing method based on FCM clustering matching and Wallis filtering
  • Non-repetitive multispectral/hyperspectral remote sensing image color uniformizing method based on FCM clustering matching and Wallis filtering

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0029] Embodiment 1: Combining figure 2 Describe this embodiment, the specific process of this embodiment based on FCM cluster matching+Wallis filtering without multiple / hyperspectral remote sensing image color leveling method is as follows:

[0030] In order to solve this problem, the present invention is based on the FCM clustering algorithm and the Wallis filtering algorithm, from the perspective of using FCM clustering to solve the dilemma of the no-heavy area, fully utilizes the information richness of the reference image, and performs color-leveling processing on the to-be-leveled image. . The purpose of the present invention is to keep the overall tone of the multi / hyperspectral remote sensing image of the non-heavy area after processing consistent, the brightness of the whole image is uniform, and the contrast ratio is suitable, so as to achieve a good effect of enhancing the visual sense of the image, and satisfy the needs of researchers and researchers. Based on th...

specific Embodiment approach 2

[0041] Embodiment 2: The difference between this embodiment and Embodiment 1 is that in the second step, the information amount and the ground of the mth group of grayscale images X1, X2, X3, . . . , Xα, . The richness of the objects (type of objects) is selected, and the reference image is selected as the reference (the image whose reference value Q is the maximum value); the specific process is as follows:

[0042] Step 21. Information entropy represents the amount of information contained in the mth group of grayscale images of the same band X1, X2, X3,..., Xα,..., Xn;

[0043] For the mth group of grayscale images X1, X2, X3, ..., Xα, ..., Xn of the same band, it is considered that each image of the mth group of grayscale images of the same band X1, X2, X3, ..., Xα, ..., Xn The gray values ​​are independent samples, and the proportion of each gray value in a single image (one of the mth group of gray images of the same band X1, X2, X3, ..., Xα, ..., Xn) is p = { p 1 , p ...

specific Embodiment approach 3

[0053] Embodiment 3: This embodiment is different from Embodiment 1 or 2 in that: in the step 3, the FCM clustering is performed on the image to be leveled Xd and the reference image Xe respectively, which essentially uses the same feature between the two images. The sub-image block is used as an overlapping area for color leveling processing (two images are required as a group, one of which is the image to be leveled, and the other is the reference image obtained in step 2. The color leveling result image processed by the algorithm It can also be used as a new reference image) to obtain the result after FCM clustering;

[0054] Determine the selected ambiguity index, the maximum number of iterations, the distance determination standard and the number of categories according to the size of the image and the category of ground objects, and reflect and appropriately improve the algorithm;

[0055] The specific process is:

[0056] Define an evaluation function J m , the member...

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 non-repetition multispectral / hyperspectral remote sensing image color uniformizing method based on FCM clustering matching and Wallis filtering, and relates to a multispectral / hyperspectral remote sensing image color uniformizing method. The objective of the invention is to solve the problem of poor effect of an obtained image due to the fact that color uniformization between images without overlapping regions is not involved in an existing method. The method comprises the following steps: 1, carrying out band-dividing processing on a multi-spectral / hyperspectral remote sensing image; 2, selecting a reference image as a reference; 3, obtaining a result after clustering; 4, performing category matching; 5, obtaining various types of data after local color uniformization processing; 6, synthesizing a new to-be-homogenized image; 7, carrying out the histogram matching, and carrying out the color uniformization; 8, repeatedly executing the steps 3-7 by taking theimage subjected to the color uniformization processing as a reference image until all grayscale images in the same waveband are subjected to color uniformization processing, and splicing the images; 9, repeating the steps 2 to 8 to obtain all spliced images, and synthesizing a new multispectral / hyperspectral remote sensing image. The method is applied to the field of image color uniformization.

Description

technical field [0001] The invention relates to a method for leveling color of multi / hyperspectral remote sensing image images. Background technique [0002] At present, the development direction of remote sensing technology includes many aspects, mainly the comprehensive application of multi-spectral, multi-angle, multi-temporal, multi-platform, and multi-sensor fusion. However, no matter what means or methods are used to obtain remote sensing data, there will be some external factors such as sensor factors, human factors and weather conditions, etc., which make it impossible to directly and widely use the obtained remote sensing images. These images require Researchers have undergone certain processing and correction, such as image geometry or radiation correction, image color leveling, etc. Only after such post-processing can images be applied to various fields. The color leveling process of the image requires researchers to make unremitting efforts for a long time, so t...

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): G06T5/40G06T7/90
CPCG06T5/40G06T7/90G06T2207/10024G06T2207/10032G06T2207/20024
Inventor 高国明俞雪雷谷延锋
Owner HARBIN INST OF TECH
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