CN106056044A - Hyperspectral image emissivity spectrum extraction method based on end-member abundance inversion - Google Patents

Hyperspectral image emissivity spectrum extraction method based on end-member abundance inversion Download PDF

Info

Publication number
CN106056044A
CN106056044A CN201610340061.1A CN201610340061A CN106056044A CN 106056044 A CN106056044 A CN 106056044A CN 201610340061 A CN201610340061 A CN 201610340061A CN 106056044 A CN106056044 A CN 106056044A
Authority
CN
China
Prior art keywords
image
high spectrum
emissivity
pixel
curve
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.)
Granted
Application number
CN201610340061.1A
Other languages
Chinese (zh)
Other versions
CN106056044B (en
Inventor
刘畅
李军伟
王广平
何茜
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Institute of Environmental Features
Original Assignee
Beijing Institute of Environmental Features
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Institute of Environmental Features filed Critical Beijing Institute of Environmental Features
Priority to CN201610340061.1A priority Critical patent/CN106056044B/en
Publication of CN106056044A publication Critical patent/CN106056044A/en
Application granted granted Critical
Publication of CN106056044B publication Critical patent/CN106056044B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
    • G06F2218/08—Feature extraction
    • G06F2218/10—Feature extraction by analysing the shape of a waveform, e.g. extracting parameters relating to peaks

Abstract

The invention provides a hyperspectral image emissivity spectrum extraction method based on end-member abundance inversion, comprising: first, performing mixed pixel decomposition operation on a whole infrared hyperspectral image to obtain pure end-members in the image and the abundance value corresponding to each end-member, and to furthermore obtain the radiance spectral curve of each pixel point in the image; performing curvilinear integral on an interested target radiance spectrum in a set temperature threshold range; estimating the absolute black body temperature stimulated by an infrared hyperspectral emissivity curve; and furthermore obtaining an emissivity spectral curve. For extraction of an interested target radiance curve, the hyperspectral image emissivity spectrum extraction method considers mixed pixel influence, obtains a target real radiance curve through end-member extraction and abundance inversion, improves radiance curve extraction precision, and furthermore improves emissivity curve extraction precision.

Description

A kind of high spectrum image emissivity spectra extracting method based on end member abundance inverting
Technical field
The invention belongs to infrared high spectrum target property and target identification technology field, be specifically related to a kind of rich based on end member The high spectrum image emissivity spectra extracting method of degree inverting.
Background technology
Infrared high spectrum remote sensing is the new technique that recent decades grows up.In infrared high spectrum remote sensing, primary work Work is inverting temperature and emissivity.Emissivity is to characterize the object physical quantity to ambient radiation ability size, object emission Rate spectrum is relevant with its composition and structure, therefore, in many applications, can be identified by the shape of emissivity spectra curve Object.And the extraction of emissivity spectra feature have to carry out the separation (TES) of temperature and emissivity to infrared high spectrum image.
Temperature and emissivity separation method generally refer to utilize a phase of infrared high spectrum to ask for temperature and emissivity Wave spectrum.The key problem of the method is: in the case of emissivity is totally unknown, and the observation of N number of wave band has N number of data, but Also having N number of unknown number accordingly, add target temperature the unknown, just have N+1 unknown number, this is a underdetermined equation the most all the time Problem.In order to solve this underdetermined equation, it is necessary to introduce extra condition.This extra condition is typically backs Certain priori of spectral shape, according to the difference of Prior Knowledge Constraints condition, the most just determines different algorithm types.Temperature The solution procedure of degree and emissivity separation algorithm is exactly the process of emissivity spectra feature extraction.Common method has: envelope Method；Reference channel method (REF)；Emissivity normalization method (NEM)；α residual basis (ADE) etc..
Ground object emission spectrum signal acquired in infrared high spectrum imaging instrument records in units of pixel.Due to The restriction of sensor spatial resolution and the complexity of background so that high spectrum image generally exists mixed pixel.As The applied researcies such as fruit carries out mixed pixel to classify as pure pixel, target detection and identification, result has the biggest error.This Just infrared high spectrum Decomposition of Mixed Pixels problem is made to become the important and key link that infrared high modal data processes.Mixed Closing pixel analysis needs the work that carries out to be exactly inside pixel, is end member by Decomposition of Mixed Pixels and obtains its shared ratio Example, makes graphical analysis enter sub-pixed mapping rank.
Traditional emissivity extraction algorithm, when carrying out interesting target spoke brightness curve and extracting, is generally used in image The method of straight access point is carried out.Owing to generally there is mixed pixel in infrared high spectrum image, that is at this moment extracted is interested Target spoke brightness curve is probably a mixed pixel, if using true as this target of this mixed pixel spoke luminance spectral Real spectrum proceeds subsequent transmission rate spectrum and extracts operation, will necessarily introduce certain error in result.
Summary of the invention
The purpose of the present invention is: the defect existed for above-mentioned prior art, proposes a kind of based on end member abundance inverting High spectrum image emissivity spectra extracting method, solve infrared high spectrum image is carried out when temperature separates with emissivity introduce The problem of mixed pixel, has obtained target true spoke brightness curve by Endmember extraction and abundance inverting, improves spoke brightness bent Line drawing precision, and then the extraction accuracy of emissivity curve is improved.
A kind of based on end member abundance inverting the high spectrum image emissivity spectra extracting method that the present invention provides, it improves Part is, method comprises the steps:
1) view picture infrared high spectrum image is carried out Decomposition of Mixed Pixels, obtain the end member of infrared high spectrum image and each end The Abundances that unit is corresponding；
2) interesting target is determined；
3) according to described pure end member and described Abundances, extract described interesting target, obtain infrared high spectrum image In the spoke luminance spectral curve of each pixel point；
4) design temperature threshold range；
5) the spoke luminance spectral curve march line integral to described interesting target；
6) the absolute black body temperature of infrared high spectrum emissivity curve simulation is estimated according to integral area；
7) obtain emissivity spectra curve, and be normalized.
Preferably, step 1) Decomposition of Mixed Pixels includes Endmember extraction step and abundance inversion step, wherein:
Endmember extraction step uses infrared high spectrum end member extraction method based on extended mathematical morphology to extract；
Abundance inversion step uses linear solution mixing method to carry out abundance inverting.
More preferably, Endmember extraction step includes:
1. read in infrared high spectrum original image, utilize the least structure element Kmin, to target EO-1 hyperion in structural element Each pixel of image carries out expansion based on barycenter in neighborhood and corrosion calculates, find the purest pixel d (x, y, w) and (x, y w), and calculate now corresponding MEI value to mix the most serious pixel e；
MEI represents morphology eccentricity index, is defined as:
MEI (x, y, and w)=dist (d (x, y, w), e (x, y, w)), w=1,2 ..., n
Wherein, dist represents the distance between 2, d (x, y, w) pixel the purest in expression image, e (x, y, w) table Show the pixel that mixing is the most serious；
2. it is continuously increased the size of structural element, repeats step step 1., until it reaches max architecture element Kmax；Instead Calculate MEI value again and note down, each MEI value corresponding for identical pixel being averaged, obtains final MEI image；
3. carry out threshold decision, using obtained MEI image gray value a little be averaged as the threshold value set, In MEI image, the pixel more than this threshold value will be marked as Pure pixel；
4. the end member image finally obtained is carried out image segmentation and region growing completes automatically selecting of end member；
5. utilize linear solution mixing method to carry out linear spectral separation and obtain end member abundance figure.
More preferably, calculation procedure 3) expression formula of spoke luminance spectral curve of described each pixel point is:
x i = Σ j = 1 m α i j e j = Eα i
Wherein, ejRepresent each end member in image, αijRepresenting each end member proportion in the picture, E represents end member matrix, αiRepresent abundance matrix.
More preferably, calculation procedure 6) expression formula of described absolute black body temperature is:
T M = T 1 + ( L V - L 1 L 2 - L 1 ) ( T 2 - T 1 )
Wherein: T1,T2For the initial temperature threshold set；L1,L2It is respectively T1,T2Corresponding black matrix spoke brightness；LVFor this Curve of spectrum integration.
More preferably, calculation procedure 7) expression formula of described emissivity spectra curve is:
Bυ,T=2hc2υ3(echυ/kT-1)-1
Wherein: c is the light velocity；H is planck constant, h=6.6262 × 10-34J·S；K is Boltzmann constant, k= 1.3806×10-23J/K。
More preferably, step 7) expression formula that is normalized emissivity spectra curve is:
B υ , T ′ = B υ , T M A X ( B υ , T ) .
The present invention, by setting up a kind of high spectrum image emissivity spectra extraction algorithm based on end member abundance inverting, solves Infrared high spectrum image carries out introducing when temperature separates with emissivity the problem of mixed pixel, is carrying out interesting target spoke When brightness curve extracts, it is contemplated that the impact of mixed pixel, obtain the true spoke of target by Endmember extraction and abundance inverting bright Write music line, improve spoke brightness curve extraction accuracy, and then the extraction accuracy of emissivity curve is improved, for high accuracy Emissivity spectra provide strong support.
Accompanying drawing explanation
Fig. 1 is the stream of the high spectrum image emissivity spectra extraction algorithm based on end member abundance inverting of the embodiment of the present invention Cheng Tu；
Fig. 2 is the infrared high spectrum end member extraction method flow chart based on extended mathematical morphology of the embodiment of the present invention.
Detailed description of the invention
For making the purpose of the present invention, technical scheme and advantage clearer, referring to the drawings the present invention is entered one Step describes in detail.However, it is necessary to explanation, the many details listed in description are only used to make reader to the present invention's One or more aspects have a thorough explanation, can also realize these sides of the present invention even without these specific details Face.
Restriction and the complexity of background due to sensor spatial resolution so that high spectrum image generally exists Mixed pixel.If mixed pixel is carried out classifying as pure pixel, the applied research such as target detection and identification, result has very Big error.
A kind of based on end member abundance inverting the high spectrum image emissivity spectra extracting method that the present invention proposes, flow chart As it is shown in figure 1, specifically comprise the following steps that
1) view picture infrared high spectrum image is carried out Decomposition of Mixed Pixels, walk including Endmember extraction step and abundance inverting Then obtain the Abundances that the end member (i.e. Pure pixel) of infrared high spectrum image is corresponding with each end member suddenly,；
Concrete employing infrared high spectrum end member extraction method based on extended mathematical morphology carries out end member in the present invention Extract, then utilize linear solution mixing method to carry out abundance inverting, as in figure 2 it is shown, specifically comprise the following steps that
1. read in infrared high spectrum original image, utilize the least structure element Kmin, to target EO-1 hyperion in structural element Each pixel of image carries out expansion based on barycenter and erosion operation in neighborhood, find the purest pixel d (x, y, w) and (x, y w), and calculate now corresponding MEI value to mix the most serious pixel e.Wherein, MEI represents morphology eccentricity index, It is defined as:
MEI (x, y, and w)=dist (d (x, y, w), e (x, y, w)), w=1,2 ..., n
Wherein, dist represents the distance between 2, d (x, y, w) pixel the purest in expression image, e (x, y, w) table Show the pixel that mixing is the most serious.
2. it is continuously increased the size of structural element, repeats the step of step 1, until it reaches max architecture element Kmax.Simultaneously Repeatedly calculate MEI value and note down, each MEI value corresponding for identical pixel being averaged, obtains final MEI image.
3. carry out threshold decision, using obtained MEI image gray value a little be averaged as the threshold value set, In MEI image, the pixel more than this threshold value will be marked as end member.
4. the end member image finally given is carried out image segmentation and region growing completes automatically selecting of end member.
5. utilize linear solution mixing method to carry out linear spectral separation and obtain end member abundance figure.
2) interesting target is determined；
3) according to described end member and described Abundances, extract described interesting target, obtain in infrared high spectrum image every The spoke luminance spectral curve of 1 pixel point.The expression formula of spoke luminance spectral curve is:
x i = Σ j = 1 m α i j e j = Eα i
Wherein, ejRepresent each end member in image, αijRepresenting each end member proportion in the picture, E represents end member matrix, αiRepresent abundance matrix.
4) design temperature threshold range；
5) the spoke luminance spectral curve march line integral to described interesting target；
6) the absolute black body temperature of infrared high spectrum emissivity curve simulation, its expression formula is estimated according to integral area For:
T M = T 1 + ( L V - L 1 L 2 - L 1 ) ( T 2 - T 1 )
Wherein: T1,T2For the initial temperature threshold set；L1,L2It is respectively T1,T2Corresponding black matrix spoke brightness；LVFor this Curve of spectrum integration.
7) obtain emissivity spectra curve, and be normalized.Wherein:
Utilize Planck law, it is thus achieved that on image, the simulation absolute black body temperature spoke brightness of this point changes with wave number (ν) Spectral emissivity curve:
Bυ,T=2hc2υ3(echυ/kT-1)-1
In above-mentioned expression formula: c is the light velocity；H is planck constant, h=6.6262 × 10-34J·S；K is that Boltzmann is normal Number, k=1.3806 × 10-23J/K。
The expression formula being normalized emissivity spectra curve is:
B υ , T ′ = B υ , T M A X ( B υ , T ) .
The above is only the preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art For Yuan, under the premise without departing from the principles of the invention, it is also possible to make some improvements and modifications, these improvements and modifications also should It is considered as protection scope of the present invention.

Claims (7)

1. a high spectrum image emissivity spectra extracting method based on end member abundance inverting, it is characterised in that described method Comprise the steps:
1) view picture infrared high spectrum image is carried out Decomposition of Mixed Pixels, obtain the end member of infrared high spectrum image and each end member pair The Abundances answered；
2) interesting target is determined；
3) according to described pure end member and described Abundances, extract described interesting target, obtain in infrared high spectrum image every The spoke luminance spectral curve of 1 pixel point；
4) design temperature threshold range；
5) the spoke luminance spectral curve march line integral to described interesting target；
6) the absolute black body temperature of infrared high spectrum emissivity curve simulation is estimated according to integral area；
7) obtain emissivity spectra curve, and be normalized.
2. high spectrum image emissivity spectra extracting method as claimed in claim 1, it is characterised in that step 1) mixed pixel Decompose and include Endmember extraction step and abundance inversion step, wherein:
Endmember extraction step uses infrared high spectrum end member extraction method based on extended mathematical morphology to extract；
Abundance inversion step uses linear solution mixing method to carry out abundance inverting.
3. high spectrum image emissivity spectra extracting method as claimed in claim 2, it is characterised in that described Endmember extraction walks Suddenly include:
1. read in infrared high spectrum original image, utilize the least structure element Kmin, to target high spectrum image in structural element Each pixel in neighborhood, carry out expansion based on barycenter and corrosion calculates, find the purest pixel d (x, y, w) and mixing (x, y w), and calculate now corresponding MEI value to the most serious pixel e；
MEI represents morphology eccentricity index, is defined as:
MEI (x, y, and w)=dist (d (x, y, w), e (x, y, w)), w=1,2 ..., n
Wherein, dist represents the distance between 2, and (x, y, w) pixel the purest in expression image, (x, y w) represent mixed to e to d Close the most serious pixel；
2. it is continuously increased the size of structural element, repeats step step 1., until it reaches max architecture element Kmax；Repeatedly count Calculate MEI value and note down, each MEI value corresponding for identical pixel being averaged, obtains final MEI image；
3. carry out threshold decision, using obtained MEI image gray value a little be averaged as the threshold value set, MEI schemes In Xiang, the pixel more than this threshold value will be marked as Pure pixel；
4. the end member image finally obtained is carried out image segmentation and region growing completes automatically selecting of end member；
5. utilize linear solution mixing method to carry out linear spectral separation and obtain end member abundance figure.
4. high spectrum image emissivity spectra extracting method as claimed in claim 1, it is characterised in that calculation procedure 3) described The expression formula of the spoke luminance spectral curve of each pixel point is:
x i = Σ j = 1 m α i j e j = Eα i
Wherein, ejRepresent each end member in image, αijRepresenting each end member proportion in the picture, E represents end member matrix, αiTable Show abundance matrix.
5. high spectrum image emissivity spectra extracting method as claimed in claim 1, it is characterised in that calculation procedure 6) described The expression formula of absolute black body temperature is:
T M = T 1 + ( L V - L 1 L 2 - L 1 ) ( T 2 - T 1 )
Wherein: T1,T2For the initial temperature threshold set；L1,L2It is respectively T1,T2Corresponding black matrix spoke brightness；LVSet a song to music for this light Line integral.
6. high spectrum image emissivity spectra extracting method as claimed in claim 1, it is characterised in that calculation procedure 7) described The expression formula of emissivity spectra curve is:
Bυ,T=2hc2υ3(echυ/kT-1)-1
Wherein: c is the light velocity；H is planck constant, h=6.6262 × 10-34J·S；K is Boltzmann constant, k=1.3806 ×10-23J/K。
7. high spectrum image emissivity spectra extracting method as claimed in claim 1, it is characterised in that step 7) to emissivity The expression formula that the curve of spectrum is normalized is:
B υ , T ′ = B υ , T M A X ( B υ , T ) .
CN201610340061.1A 2016-05-19 2016-05-19 A kind of high spectrum image emissivity spectra extracting method based on end member abundance inverting Active CN106056044B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610340061.1A CN106056044B (en) 2016-05-19 2016-05-19 A kind of high spectrum image emissivity spectra extracting method based on end member abundance inverting

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610340061.1A CN106056044B (en) 2016-05-19 2016-05-19 A kind of high spectrum image emissivity spectra extracting method based on end member abundance inverting

Publications (2)

Publication Number Publication Date
CN106056044A true CN106056044A (en) 2016-10-26
CN106056044B CN106056044B (en) 2019-03-29

Family

ID=57177292

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610340061.1A Active CN106056044B (en) 2016-05-19 2016-05-19 A kind of high spectrum image emissivity spectra extracting method based on end member abundance inverting

Country Status (1)

Country Link
CN (1) CN106056044B (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106595873A (en) * 2017-01-03 2017-04-26 哈尔滨工业大学 Subpixel temperature retrieval method based on long-wave infrared atmospheric bottom-layer radiation and visible light band linear mixed model
CN107274387A (en) * 2017-05-19 2017-10-20 西安电子科技大学 The end member extraction method of target in hyperspectral remotely sensed image based on Evolutionary multiobjective optimization
CN109696406A (en) * 2018-11-29 2019-04-30 北京航空航天大学 A kind of menology high spectrum image shadow region solution mixing method based on compound end member
CN110428454A (en) * 2019-08-13 2019-11-08 电子科技大学中山学院 Hyperspectral unmixing method and device, electronic equipment and storage medium

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090144350A1 (en) * 2007-09-28 2009-06-04 Chein-I Chang Maximum simplex volume criterion-based endmember extraction algorithms
CN101887012A (en) * 2010-06-28 2010-11-17 中国国土资源航空物探遥感中心 Spectral reflectance peak decomposition based quantitative inversion method of hyperspectral remote sensing mineral content
CN102194099A (en) * 2010-02-17 2011-09-21 波音公司 Advanced background estimation technique and circuit for a hyper-spectral target detection method
CN103325096A (en) * 2013-06-25 2013-09-25 中国科学院遥感与数字地球研究所 Method for reconstructing wide hyperspectral image based on fusion of multispectral/hyperspectral images

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090144350A1 (en) * 2007-09-28 2009-06-04 Chein-I Chang Maximum simplex volume criterion-based endmember extraction algorithms
CN102194099A (en) * 2010-02-17 2011-09-21 波音公司 Advanced background estimation technique and circuit for a hyper-spectral target detection method
CN101887012A (en) * 2010-06-28 2010-11-17 中国国土资源航空物探遥感中心 Spectral reflectance peak decomposition based quantitative inversion method of hyperspectral remote sensing mineral content
CN103325096A (en) * 2013-06-25 2013-09-25 中国科学院遥感与数字地球研究所 Method for reconstructing wide hyperspectral image based on fusion of multispectral/hyperspectral images

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
刘汉湖，等.: "高光谱遥感岩矿端元提取与分析方法研究", 《岩石矿物学杂志》 *
赵利民，等.: "基于能量平衡与端元合成技术的地表热辐射场景动态模拟", 《中国科学》 *

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106595873A (en) * 2017-01-03 2017-04-26 哈尔滨工业大学 Subpixel temperature retrieval method based on long-wave infrared atmospheric bottom-layer radiation and visible light band linear mixed model
CN106595873B (en) * 2017-01-03 2019-03-29 哈尔滨工业大学 Sub-pixed mapping temperature retrieval method based on LONG WAVE INFRARED surface air radiation and visible light wave range linear mixed model
CN107274387A (en) * 2017-05-19 2017-10-20 西安电子科技大学 The end member extraction method of target in hyperspectral remotely sensed image based on Evolutionary multiobjective optimization
CN107274387B (en) * 2017-05-19 2019-09-06 西安电子科技大学 The end member extraction method of target in hyperspectral remotely sensed image based on Evolutionary multiobjective optimization
CN109696406A (en) * 2018-11-29 2019-04-30 北京航空航天大学 A kind of menology high spectrum image shadow region solution mixing method based on compound end member
CN109696406B (en) * 2018-11-29 2020-10-02 北京航空航天大学 Moon table hyperspectral image shadow region unmixing method based on composite end member
CN110428454A (en) * 2019-08-13 2019-11-08 电子科技大学中山学院 Hyperspectral unmixing method and device, electronic equipment and storage medium
CN110428454B (en) * 2019-08-13 2022-02-25 电子科技大学中山学院 Hyperspectral unmixing method and device, electronic equipment and storage medium

Also Published As

Publication number Publication date
CN106056044B (en) 2019-03-29

Similar Documents

Publication Publication Date Title
CN109949278A (en) Hyperspectral abnormity detection method based on confrontation autoencoder network
CN106056044A (en) Hyperspectral image emissivity spectrum extraction method based on end-member abundance inversion
CN111007039B (en) Automatic extraction method and system for sub-pixel level water body of medium-low resolution remote sensing image
CN104966085A (en) Remote sensing image region-of-interest detection method based on multi-significant-feature fusion
JPS63118889A (en) Change detection system by picture
CN109977834B (en) Method and device for segmenting human hand and interactive object from depth image
CN101958000A (en) Face image-picture generating method based on sparse representation
CN107392211B (en) Salient target detection method based on visual sparse cognition
CN110097499B (en) Single-frame image super-resolution reconstruction method based on spectrum mixing kernel Gaussian process regression
CN109696406B (en) Moon table hyperspectral image shadow region unmixing method based on composite end member
CN106846377A (en) A kind of target tracking algorism extracted based on color attribute and active features
CN111222576B (en) High-resolution remote sensing image classification method
CN106204596B (en) Panchromatic waveband remote sensing image cloud detection method based on Gaussian fitting function and fuzzy mixed estimation
CN113095218A (en) Hyperspectral image target detection algorithm
CN109815825B (en) Hyperspectral abnormal target detection method based on similarity constrained convex-nonnegative matrix decomposition
CN108280486A (en) A kind of high spectrum image solution mixing method based on end member cluster
CN107832793A (en) The sorting technique and system of a kind of high spectrum image
Shi et al. Hyperspectral target detection using a bilinear sparse binary hypothesis model
Zeng et al. U-net-based multispectral image generation from an rgb image
CN115620132A (en) Unsupervised comparative learning ice lake extraction method
CN108985307A (en) A kind of Clean water withdraw method and system based on remote sensing image
CN109190506A (en) It is a kind of based on core is sparse and the EO-1 hyperion object detection method of space constraint
Vollmer et al. Simultaneous multi-band detection of low surface brightness galaxies with Markovian modeling
Sigurdsson et al. Total variation and ℓ q based hyperspectral unmixing for feature extraction and classification
CN110992390B (en) Hyperspectral image mixed pixel decomposition method

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant