CN106548465A - A kind of Enhancement Method of multi-spectrum remote sensing image - Google Patents
A kind of Enhancement Method of multi-spectrum remote sensing image Download PDFInfo
- Publication number
- CN106548465A CN106548465A CN201611058623.XA CN201611058623A CN106548465A CN 106548465 A CN106548465 A CN 106548465A CN 201611058623 A CN201611058623 A CN 201611058623A CN 106548465 A CN106548465 A CN 106548465A
- Authority
- CN
- China
- Prior art keywords
- remote sensing
- sensing image
- band
- pixel
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 19
- 238000001228 spectrum Methods 0.000 title claims abstract description 16
- 230000002708 enhancing effect Effects 0.000 claims abstract description 8
- 230000006978 adaptation Effects 0.000 claims abstract description 6
- 239000000284 extract Substances 0.000 claims abstract description 3
- VMXUWOKSQNHOCA-UKTHLTGXSA-N ranitidine Chemical compound [O-][N+](=O)\C=C(/NC)NCCSCC1=CC=C(CN(C)C)O1 VMXUWOKSQNHOCA-UKTHLTGXSA-N 0.000 abstract description 3
- 230000000007 visual effect Effects 0.000 abstract description 3
- 238000002203 pretreatment Methods 0.000 abstract description 2
- 239000013589 supplement Substances 0.000 abstract description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10032—Satellite or aerial image; Remote sensing
- G06T2207/10036—Multispectral image; Hyperspectral image
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The present invention relates to a kind of remote sensing image process field, specifically a kind of Enhancement Method of multi-spectrum remote sensing image.Comprise the steps:Step 1, extracts each wave band of input remote sensing image;Step 2, carries out the self-adaptive processing of local contrast respectively to each wave band, obtains local contrast self-adaptive processing result;Step 3, carries out global white balance self-adaptive processing respectively to the result of step 2, obtains global white balance self adaptation result;Step 4, merges to the result in step 3, obtains the enhancing result of multi-spectrum remote sensing image.Used as the pre-treatment step of multi-spectrum remote sensing image, the present invention can strengthen the discrimination of various atural objects, improve the accuracy rate and efficiency of algorithm of remote sensing image target recognition, while can also be used as a kind of visual effective supplement of remote sensing image.
Description
Technical field
The present invention relates to a kind of remote sensing image process field, specifically a kind of Enhancement Method of multi-spectrum remote sensing image.
Background technology
The imaging process of remote sensing image is affected by several factors, such as satellite velocities change, the phase of electromagnetic wave and air
Interaction, random noise etc., actual image intensity value are not fully the reflections of atural object radiant electromagnetic energy size, are caused
The distortion and distortion of image.When remote sensing image is analyzed, in order to improve the visual effect of remote sensing image and enable analyst easy
Picture material is definitely recognized, needs to carry out pretreatment.Wherein image enhaucament is a kind of common processing method.Image enhaucament is just
It is that some features in image are emphasized, is allowed to more suitable eye-observation or machine processing.Remote sensing image enhancing technology is main
It is divided into two big class, a class is Space domain, i.e., the method for calculation process being carried out to the grey scale pixel value of image in the plane of delineation;
Another kind of is frequency domain method, and refer to carries out certain process in the frequency domain of image to image.Contain in multi-spectrum remote sensing image
There is a larger quantity of information, and human eye identifying and distinguishing between ability and can reach more than the Radix Achyranthis Bidentatae of gray scale resolving ability to color,
So the enhancing of multi-spectrum remote sensing image has very important effect to obtaining more information.Although directly using to gray scale
The Enhancement Method of figure can strengthen the detail luminance in image, but obtain the tone in result and be possible to completely nonsensical, this
Be because all there occurs change to each component of the same pixel of correspondence in enhancing figure, their relative value with originally not
Together, so as to causing the large change of artwork color.
The content of the invention
The invention provides a kind of Enhancement Method of multi-spectrum remote sensing image, using multi-spectrum remote sensing image as data source,
Processed in terms of local and the overall situation two respectively, shadow can be retained to greatest extent on the premise of image enhaucament is realized
The effective information of picture, the amount of calculation of method are little, and adaptive ability is strong, output result reliability.
By the technical scheme that adopts of target for realizing the present invention it is:Method is comprised the following steps:
Step 1:Extract each wave band { Band of input remote sensing image image1,Band2,…,Bandn, n is remote sensing image
The wave band sum of image;
Step 2:To each wave band { Band1,Band2,…,BandnLocal contrast self-adaptive processing is carried out respectively, obtain office
Portion contrast self-adaptive processing result { LC1,LC2,…,LCn};
Step 3:To { the LC in step 21,LC2,…,LCnBe respectively processed, obtain global white balance self adaptation result
{GW1,GW2,…,GWn};
Step 4:To the global white balance self adaptation result { GW in step 31,GW2,…,GWnMerged, obtain multispectral distant
The enhancing result of sense image.
The self-adaptive processing of described local contrast is calculated by below equation:
In formula 1, x and y is pixel, and Θ is the space comprising image all pixels point x, Θ x be not comprising pixel x
Θ, | | x-y | | are that the Euclidean distance between pixel x and y, I (x) and I (y) are respectively the gray value of pixel x and y, value
Scope be [0,255], TαK () is slope function, k=I (x)-I (y), TαK the span of () is [- 1,1], for amplifying difference
The big pixel of different little pixel and diminution difference.Abs () is the function that takes absolute value, as abs (α)≤1, Tα(k)=α k;When
During abs (α) >=1, Tα(k)=min { max { α k, -1 }, 1 };When α tends to infinity, T∞K () is sign function.
Described global white balance self-adaptive processing is calculated by below equation:
In formula 2, min represents and minimizes that max represents maximizing.
The invention has the beneficial effects as follows:As the pre-treatment step of multi-spectrum remote sensing image, various atural objects can be strengthened
Discrimination, improves the accuracy rate and efficiency of algorithm of remote sensing image target recognition, while can also be visual as remote sensing image
A kind of effective supplement.
Description of the drawings
Fig. 1 is the overall process flow figure of the present invention.
Specific embodiment
Describe the specific embodiment of the present invention below in conjunction with the accompanying drawings in detail.
In step 101, be input into pending multi-spectrum remote sensing image image be comprising R, tetra- wave bands of G, B, NIR
Quickbird remote sensing images, spatial resolution are 2.4 meters.
In step 102,4 wave bands { R, G, B, NIR } of input remote sensing image image are extracted respectively.
In step 103, local contrast is carried out respectively to 4 wave bands { R, G, B, NIR } in step 102 using below equation
The self-adaptive processing of degree:
Wherein, x and y are pixel, and Θ is the space comprising image all pixels point x, Θ x be not comprising pixel x
Θ, | | x-y | | are that the Euclidean distance between pixel x and y, I (x) and I (y) are respectively the gray value of pixel x and y, value
Scope be [0,255], TαK () is slope function, k=I (x)-I (y), TαK the span of () is [- 1,1], for amplifying difference
The big pixel of different little pixel and diminution difference.Abs () is the function that takes absolute value, as abs (α)≤1, Tα(k)=α k;When
During abs (α) >=1, Tα(k)=min { max { α k, -1 }, 1 }, when α tends to infinity, T∞K () is sign function.
Obtain the self-adaptive processing result { LC of local contrastR,LCG,LCB,LCNIR}。
In step 104, using below equation to the output result { LC in step 103R,LCG2,LCB,LCNIRCarry out respectively
Global white balance self-adaptive processing:
Wherein, min represents and minimizes that max represents maximizing.
Global white balance self-adaptive processing result { GW is obtained using above-mentioned formulaR,GWG,GWB3,GWNIR}。
In step 105, to the output result { GW in step 104R,GWG,GWB3,GWNIRMerged, obtain multispectral
The enhancing result of remote sensing image.
In step 106, the enhancing result of multi-spectrum remote sensing image is exported.
Claims (3)
1. a kind of Enhancement Method of multi-spectrum remote sensing image, it is characterised in that comprise the following steps:
Step 1:Extract each wave band { Band of input remote sensing image image1,Band2,…,Bandn, n is remote sensing image
The wave band sum of image;
Step 2:To each wave band { Band1,Band2,…,BandnLocal contrast self-adaptive processing is carried out respectively, obtain office
Portion contrast self-adaptive processing result { LC1,LC2,…,LCn};
Step 3:To { the LC in step 21,LC2,…,LCnBe respectively processed, obtain global white balance self adaptation result { GW1,
GW2,…,GWn};
Step 4:To the global white balance self adaptation result { GW in step 31,GW2,…,GWnMerged, obtain multispectral distant
The enhancing result of sense image.
2. the Enhancement Method of a kind of multi-spectrum remote sensing image according to claim 1, it is characterised in that local contrast
Self-adaptive processing is calculated by below equation:
In formula 1, x and y is pixel, and Θ is the space comprising image all pixels point x, Θ x be not comprising pixel x
Θ, | | x-y | | are that the Euclidean distance between pixel x and y, I (x) and I (y) are respectively the gray value of pixel x and y, value
Scope be [0,255], TαK () is slope function, k=I (x)-I (y), TαK the span of () is [- 1,1], for amplifying difference
The big pixel of different little pixel and diminution difference;Abs () is the function that takes absolute value, as abs (α)≤1, Tα(k)=α k;When
During abs (α) >=1, Tα(k)=min { max { α k, -1 }, 1 }, when α tends to infinity, T∞K () is sign function.
3. the Enhancement Method of a kind of multi-spectrum remote sensing image according to claim 1, it is characterised in that global white balance from
At adaptation, reason below equation is calculated:
Wherein, min represents and minimizes that max represents maximizing.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611058623.XA CN106548465A (en) | 2016-11-25 | 2016-11-25 | A kind of Enhancement Method of multi-spectrum remote sensing image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611058623.XA CN106548465A (en) | 2016-11-25 | 2016-11-25 | A kind of Enhancement Method of multi-spectrum remote sensing image |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106548465A true CN106548465A (en) | 2017-03-29 |
Family
ID=58395969
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611058623.XA Pending CN106548465A (en) | 2016-11-25 | 2016-11-25 | A kind of Enhancement Method of multi-spectrum remote sensing image |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106548465A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114821376A (en) * | 2022-06-27 | 2022-07-29 | 中咨数据有限公司 | Unmanned aerial vehicle image geological disaster automatic extraction method based on deep learning |
GB2621645A (en) * | 2022-06-27 | 2024-02-21 | Checc Data Co Ltd | Deep learning based method for automatic geological disaster extraction from unmanned aerial vehicle image |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101951523A (en) * | 2010-09-21 | 2011-01-19 | 北京工业大学 | Adaptive colour image processing method and system |
CN102222221A (en) * | 2011-07-01 | 2011-10-19 | 哈尔滨工程大学 | Target detection method based on multispectral image filtering output statistical distribution regularity |
CN103363962A (en) * | 2013-07-23 | 2013-10-23 | 中国科学院遥感与数字地球研究所 | Remote sensing evaluation method of lake water reserves based on multispectral images |
CN103903014A (en) * | 2014-04-17 | 2014-07-02 | 西安煤航卫星数据应用有限公司 | Desertification interpretation method based on satellite remote sensing technology |
CN104899836A (en) * | 2015-05-06 | 2015-09-09 | 南京第五十五所技术开发有限公司 | Foggy image enhancing device and method based on near infrared multispectral imaging |
-
2016
- 2016-11-25 CN CN201611058623.XA patent/CN106548465A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101951523A (en) * | 2010-09-21 | 2011-01-19 | 北京工业大学 | Adaptive colour image processing method and system |
CN102222221A (en) * | 2011-07-01 | 2011-10-19 | 哈尔滨工程大学 | Target detection method based on multispectral image filtering output statistical distribution regularity |
CN103363962A (en) * | 2013-07-23 | 2013-10-23 | 中国科学院遥感与数字地球研究所 | Remote sensing evaluation method of lake water reserves based on multispectral images |
CN103903014A (en) * | 2014-04-17 | 2014-07-02 | 西安煤航卫星数据应用有限公司 | Desertification interpretation method based on satellite remote sensing technology |
CN104899836A (en) * | 2015-05-06 | 2015-09-09 | 南京第五十五所技术开发有限公司 | Foggy image enhancing device and method based on near infrared multispectral imaging |
Non-Patent Citations (2)
Title |
---|
张明 等: "基于金字塔分解的自动色彩均衡算法", 《计算机工程》 * |
张红涛 等: "基于多光谱图像融合技术的麦粒图像增强方法研究", 《华北水利电大学学报(自然科学版)》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114821376A (en) * | 2022-06-27 | 2022-07-29 | 中咨数据有限公司 | Unmanned aerial vehicle image geological disaster automatic extraction method based on deep learning |
CN114821376B (en) * | 2022-06-27 | 2022-09-20 | 中咨数据有限公司 | Unmanned aerial vehicle image geological disaster automatic extraction method based on deep learning |
WO2024000927A1 (en) * | 2022-06-27 | 2024-01-04 | 中咨数据有限公司 | Deep learning based method for automatic geological disaster extraction from unmanned aerial vehicle image |
GB2621645A (en) * | 2022-06-27 | 2024-02-21 | Checc Data Co Ltd | Deep learning based method for automatic geological disaster extraction from unmanned aerial vehicle image |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Wong et al. | Histogram equalization and optimal profile compression based approach for colour image enhancement | |
CN108090888B (en) | Fusion detection method of infrared image and visible light image based on visual attention model | |
Kong et al. | Color image enhancement using brightness preserving dynamic histogram equalization | |
Gorai et al. | Hue-preserving color image enhancement using particle swarm optimization | |
US10325338B2 (en) | Information embedding device, information detecting device, information embedding method, and information detecting method | |
CN108765347A (en) | A kind of color enhancement method of suitable remote sensing image | |
US11182912B2 (en) | Image registering method and apparatus | |
CN107358184A (en) | The extracting method and extraction element of document word | |
Xu et al. | FPGA-based low-visibility enhancement accelerator for video sequence by adaptive histogram equalization with dynamic clip-threshold | |
CN110298796A (en) | Based on the enhancement method of low-illumination image for improving Retinex and Logarithmic image processing | |
CN106548465A (en) | A kind of Enhancement Method of multi-spectrum remote sensing image | |
CN108550124B (en) | Illumination compensation and image enhancement method based on bionic spiral | |
Román et al. | Image color contrast enhancement using multiscale morphology | |
CN108198163A (en) | A kind of PAN and multi-spectral image interfusion method based on discrete cosine transform | |
CN116452447A (en) | Low-illumination high-definition image processing method | |
CN106446909A (en) | Chinese food image feature extraction method | |
Tribak et al. | Remote solar panels identification based on patterns localization | |
Li et al. | Contrast enhancement algorithm for outdoor infrared images based on local gradient-grayscale statistical feature | |
Fan et al. | Infrared image enhancement based on saliency weight with adaptive threshold | |
CN108229487B (en) | Significance detection method combining space domain and frequency domain | |
CN111191518A (en) | Double-spectrum target detection frame coordinate synchronization and mask layer drawing method | |
Yin | The method to capture the form of opera performance based on machine vision | |
CN108364261A (en) | A kind of TV-Retinex single-frame images defogging methods of gradient guiding | |
CN109146795A (en) | The image pre-processing method of the reconstruction of hologram | |
Liu et al. | Method of traffic signs segmentation based on color-standardization |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170329 |
|
WD01 | Invention patent application deemed withdrawn after publication |