CN106815874B - A kind of interactive more image color method for visualizing of high spectrum image - Google Patents
A kind of interactive more image color method for visualizing of high spectrum image Download PDFInfo
- Publication number
- CN106815874B CN106815874B CN201611121980.6A CN201611121980A CN106815874B CN 106815874 B CN106815874 B CN 106815874B CN 201611121980 A CN201611121980 A CN 201611121980A CN 106815874 B CN106815874 B CN 106815874B
- Authority
- CN
- China
- Prior art keywords
- image
- interactive
- information
- color
- display
- 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.)
- Expired - Fee Related
Links
- 238000000034 method Methods 0.000 title claims abstract description 74
- 230000002452 interceptive effect Effects 0.000 title claims abstract description 33
- 238000001228 spectrum Methods 0.000 title claims abstract description 23
- 238000010586 diagram Methods 0.000 claims abstract description 9
- 238000010606 normalization Methods 0.000 claims abstract description 6
- 238000012545 processing Methods 0.000 claims abstract description 6
- 230000000694 effects Effects 0.000 claims description 6
- 238000012986 modification Methods 0.000 claims description 3
- 230000004048 modification Effects 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 2
- 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 16
- 241001466077 Salina Species 0.000 description 10
- 238000012800 visualization Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 7
- 230000008859 change Effects 0.000 description 6
- 230000004913 activation Effects 0.000 description 5
- 230000002146 bilateral effect Effects 0.000 description 5
- 238000001914 filtration Methods 0.000 description 5
- 230000009467 reduction Effects 0.000 description 5
- 238000007794 visualization technique Methods 0.000 description 5
- 238000002474 experimental method Methods 0.000 description 4
- 210000002837 heart atrium Anatomy 0.000 description 4
- 238000002156 mixing Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 230000004927 fusion Effects 0.000 description 3
- 230000003595 spectral effect Effects 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 230000006835 compression Effects 0.000 description 2
- 238000007906 compression Methods 0.000 description 2
- 230000005484 gravity Effects 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000000155 melt Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J3/00—Spectrometry; Spectrophotometry; Monochromators; Measuring colours
- G01J3/28—Investigating the spectrum
- G01J3/2823—Imaging spectrometer
Landscapes
- Physics & Mathematics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- General Physics & Mathematics (AREA)
- Processing Or Creating Images (AREA)
Abstract
A kind of interactive more image color method for visualizing of high spectrum image, it is characterised in that: steps are as follows: step 1, information sifting；Step 2, node diagram sequence；Step 3, interactive adjusting triple channel information；Step 4 shows that by the processing such as normalization or image enhancement, the triple channel for being used separately as color space carries out display and obtains output image three obtained in step 3 gray level image in color space.Interactive interface of the present invention is convenient for user's operation；More information can be stated, and different types of information can be combined and be shown；It can be used for high spectrum image, the image information of other classifications can also be shown, adjust integral color as needed；It can more easily determine best output image, certain atural object or classification can be highlighted.
Description
Technical field
The invention belongs to remote sensing information process technical field, especially a kind of color display method of high spectrum image.
Background technique
Since imaging spectrometer comes out, high spectrum image (Hyperspectral Imagery, HSI) is more and more extensive
Ground is applied to military affairs, agricultural, ocean, environment etc., and corresponding visualization technique is also by the day of researchers at home and abroad
Benefit concern.High spectrum image can not be directly displayed in the color space of only triple channel due to a large amount of wave band.
For this purpose, to show that high spectrum image, Existing methods are all to be transformed to lower dimensional space first in image space, these methods
Have, waveband selection, PCA dimensionality reduction, Band fusion etc..Conventional visualization method is all directly to utilize these transform methods by original height
Spectrum picture is converted into three wave bands, and three channels for being then assigned to color space respectively are shown, or by different type
Information is respectively displayed in multiple independent images.
However, for the high spectrum image with high information quantity, to make visualization result include more comprehensively information, such as
Atural object spatial information, atural object classification information, object spectrum information, target information, marginal information, texture information etc., generally require
It is stated by the image more than three width.However the information belonged to originally in same data is independently shown in multiple image
In, and the processing complexity that observer will be will increase.Therefore, for the data with labyrinth, multi-modality images are expressed
It becomes more and more important.Meanwhile how information integration as much as possible in HSI to be shown at the same interface, it has also become
Nowadays urgent problem to be solved.In addition, in limited display space, if visualization technique can not only provide fix information
Image show, additionally it is possible to provided according to the interactive operation of user and different information selected to be indicated, even image is dynamic
The expression of state variation, then user can also greatly improve the reception of information and the degree of understanding.
CAI etc. proposes a kind of multilayer based on character-driven point (FEATURE-DRIVEN) suitable for high-spectral data
Method for visualizing, this method are mixed false color image of the character-driven image after mixed from solution according to different transparencies
It closes, solves the problems, such as that spatial information can not express simultaneously with spectral information in HSI visual image.But this method is still deposited
The expression of spatial information can be influenced to some extent in some shortcomings, such as character-driven figure layer, and picture material also shows more
Confusion, and there are redundancies between information expressed by each figure layer used in this method, in addition, this method is only in image
Local region, which is amplified to when carrying out solving mixed as a unit to a certain degree or by more pixels, to be just suitable for showing character-driven figure
Layer, otherwise character-driven layer will lose it and show meaning.
KOVESI etc. is arranged and is proposed series of interactive multi-modality images display methods, such as triangle nature difference side
Case；Four linearity mixed methods；More image annular hybrid plans；The dynamic range compression algorithm and more images that phase is kept
Mixed method etc..These methods are all mixed and are shown to multi-modality images information using interactive approach, and achieve compared with
Good effect of visualization.But there is also some problems for these methods, are such as unable to fully utilize color channel information, Yi Jidou
It can not be suitable for the mass data etc. of high spectrum image, in addition, between these methods, and which kind of method can not be proved to some
The display of data possesses optimal display effect.
Summary of the invention
The purpose of the present invention is to provide a kind of suitable for high-spectral data and is satisfied with multi-modality images requirement
The interactive more image color method for visualizing of high spectrum image.The present invention can export color image, and root in same interface
Adjusting according to user to cursor statically or dynamically shows more useful informations in high spectrum image.Through the invention, make
User can change output image according to their own needs in visualization process, this enables this Interactive Visualization method
It is enough that purposive information excavating is carried out to high spectrum image.In addition, present invention is equally applicable to the visualization of other more images,
Such as multispectral image, anisotropic filter exports image, different focusedimages, isospace region different time image, isospace area
The image etc. that domain different sensors obtain.
A kind of interactive more image color method for visualizing of high spectrum image, steps are as follows:
Step 1, information sifting.
By data processing or hand picking method, the useful image for display for meeting user's requirement is selected, this
A little iamge descriptions are the gray level image of several same space scales.
Step 2, node diagram sequence.
By the gray level image filtered out in step 1 according to image correlation size order, it is arranged in section equidistant on annulus
Point on.
Step 3, interactive adjusting triple channel information.
System will automatically select display methods according to the number of predetermined point.It can be according to the needs of users during display
Increase and decrease or modification predetermined point, meanwhile, display methods changes also with predetermined number of points purpose and accordingly changes.It is carried out when to predetermined point
When modification, the sequence of node diagram can also be adjusted simultaneously, to reach better display effect.Finally, three gray level images obtained
By three channels output to be shown in color space.
Step 4 is shown in color space.
Three gray level images obtained in step 3 are used separately as color space by normalization or image enhancement processing
Triple channel carries out display and obtains output image.
Compared with the prior art, the invention has the following advantages:
1, interactive interface is convenient for user's operation；
2, more information can be stated, and different types of information can be combined and be shown；
3, this method can be not only used for high spectrum image, can also show to the image information of other classifications, such as more
Spectrum picture, anisotropic filter output image, different focusedimages, isospace region different time image etc., and to other
When the image information of classification is shown, it can also be used to comparison and comparison between image；
4, it is easier to determine that special atural object, the different atural object color of variation tendency can more protrude not by modified-image
Same atural object classification, meanwhile, the features that can not be shown under certain mixing wave bands will preferably be shown in other combinations, this
Integral color can also be adjusted as needed outside；
5, observer can more easily determine by changing cursor position and most preferably export image, meanwhile, it is used in the image
It is relatively easy to determine with mixed image and its mixed coefficint；
6, it is the method for visualizing that can highlight certain atural object or classification.
Detailed description of the invention
Fig. 1 is process simplified schematic diagram of the invention；
Fig. 2 is the choosing method schematic diagram that image is exported when cursor is fallen within outside unit circle；
Fig. 3 is three kinds of display strategies；
Wherein, 3 points of (a) determines method, and (b) two o'clock determines method, (c) a little determines method；
Fig. 4 is interactive interface schematic diagram；
Fig. 5 is PCA color image；
Fig. 6 is the ranking results of useful image Image1-Image6 after sorted；
Fig. 7 is the visualization result in the presence of no predetermined point；
Fig. 8 is visualization result when there are a predetermined point；
Fig. 9 is visualization result when there are two predetermined points；
Figure 10 is the ranking results of the useful image Image1-Image6 of Salinas area image after sorted；
Wherein, (A) spectral weighting and, (B)-(D) PCA, the part (E) atural object solution is mixed as a result, (F)-(H) bilateral filtering merges
As a result, (I) certain category classification result；
Figure 11 is that 3 points of the multi-modality images of Salinas area image data determine that Faxian shows result.
Specific embodiment
More detailed description is made to the present invention with reference to the accompanying drawing.
The interactive more image color method for visualizing of a kind of high spectrum image of the present invention, using interactive means to EO-1 hyperion
Data carry out purposive display, and here is detailed implementation process:
Step 1: information sifting.
In the high-spectral data containing bulk information, n width gray level image is selected, these images are to indicate as complete as possible
The interested information of whole user.It is denoted as Image 1, Image 2 ... Image n, wherein 3≤n≤10 respectively.Work as node
This method is still feasible when number n > 10, but output image effect may degenerate with increasing for number of nodes.But for
Currently used most of images, even the high spectrum image containing bulk information, the information of the overwhelming majority can also lead to
The image crossed within 10 width is indicated, therefore already can satisfy current application needs as n≤10.And as n≤3,
Conventional color method for visualizing can show, and at this time and can not make full use of the advantage of this method, therefore may be selected relatively simple
Conventional visualization method shown.
The image of screening can using only wave band extraction, Data Dimensionality Reduction, information fusion, classification, solution are the methods of mixed will be former high
Tie up high-spectral data dimensionality reduction to as a result, the result using different disposal method can also be integrated.For example, the image for node can
It is used in mixed way first three principal component of PCA, the supervision message of three wave bands and certain classification that bilateral filtering is fused into.
Step 2: node diagram sorts.
The node location that the useful image filtered out need to be placed in interactive interface in a certain order becomes corresponding section
Point image.The sort method of node image can be by user's unrestricted choice, such as auto-sequencing and User- defined Node figure sequence.Automatically
Sort method can be arranged according to the correlation of image, for example, the higher two images of correlation in annulus at a distance of it is remoter,
It is close etc..In addition, user can also adjust at any time the sequence of node image in interactive visual.
Step 3, the interactive adjusting triple channel information.
Extracting method is as follows:
(1) in interactive interface, predetermined point is set.
(2) other points are determined.
Situation is 1.: when cursor point is upper or when circle is outer in circle, output image is shown as cursor point representated by the circle above mapping point
Gray level image.
The cursor being activated exports result by changing the position change of point P.Fall in outside the circle in interactive areas when cursor or
When on circle, output image is and cursor gray level image made of nearest two o'clock linear hybrid, determination method such as Fig. 2 institute
Show.The point A that point is mapped on round O is formed by Image 2 and 3 linear hybrid of Image, and mixed coefficint a, b meets following formula respectively
A+b=1 (1)
A:b=β: α (2)
Wherein α and β is respectively the angle of radius where radius OA and another two images.It is image normalized representated by A point
It is afterwards output image, exporting image at this time is gray level image.
Situation is 2.: when cursor point is in circle, output image is three channel color images.Three channel information determination side at this time
Method need to first determine whether the quantity of predetermined point, be divided into following three kinds according to predetermined number of points purpose difference later, determine method such as Fig. 3
It is shown.
1. 3 points determine method.
In the presence of no predetermined point, P point determines one using P point as center of gravity, and O is the isosceles inscribed triangle of circumscribed circle
ABC.After three image normalized [5a] that the Atria vertex determines, i.e., as the triple channel value of RGB color space
It is shown.Determine that Atria point is sat shown in calibration method such as Fig. 3 (a) simultaneously according to cursor point P position.Known unit justifies O
Radius is that the polar coordinates of 1, P point are (θ, ρ), and P point is triangle ABC center of gravity, then according to triangle core property
Again because AP=1- ρ meets following formula line segment OD length can be obtained:
It can thus be concluded that Atria vertex polar coordinates are respectively as follows:
Wherein α=arccos (OD), and all angular ranges are all [0,2 π] in calculating process.When P point is located at unit circle
When the center of circle, P point angular coordinate can be by the cursor previous moment P that moves0Angular coordinate determine.
Triangular apex position can be acquired by formula (4), image in this position is by two waves similar on annulus
Section linearity mixes, and mixed method also uses method shown in Fig. 3.Assuming that one of triangular apex falls within point A, that is, exist
On circular arc between image1 and image4, then the image of A point is formed by image1 and image4 linear hybrid, mixed stocker
Number a, b meet formula (1) and formula (2) respectively.
2. two o'clock determines method.
In the presence of having a predetermined point, such as Fig. 3 (b), P point has determined a string vertical with radius where P point, and hangs down
Foot is P, and two intersection points and default fixed point of string and circle constitute a triangle, and image representated by this 3 points determines can
Depending on changing output image when display.B point and C point polar coordinates may be expressed as: known to Fig. 3 (b)
Wherein α=arccos ρ, angular range are all converted to [0,2 π].The image mixing method of three points is all Fig. 4 institute
Show.
3. a little determining method.
When, there are two in the presence of predetermined point, cursor P need to only determine a point on circle again.Therefore, such as Fig. 3
(c) shown in, which can be set as crossing intersection point of the radius of P point on circle, i.e. point C inside circle O.It later, respectively should by determining
Point finds out three width blending images by formula (1) and formula (2) with other two predetermined point, this three width image will be used to visualize aobvious
Show.
(3) output image (single channel gray level image/Three Channel Color image) is determined.
Combine three channel informations of the known predetermined point together as output image to aobvious via determining mixed image
Show.
Step 4 is described as follows in color space display methods:
The single band determined through above-mentioned steps or three band images are with the figure that will be used in color space obtain output
Picture.The present invention carries out visualization display in RGB color space.By before the step of obtain three width single band images, this three
Width image is needed before RGB color space is shown by normalization.It is colored that three width images after normalization form a width
Image, this width color image can be used as output image or user also and the methods of image enhancement can be selected to image progress
Optimization.The present invention enhances color image with simplest brightness and contrast variation.
The interactive interface that the present invention exports is as shown in figure 4, left side circle indicates interactive interface, right side display output image.
Interactive interface is made of the unit circle that a radius is 1, is equidistantly arranged a group node on circular boundary, in Fig. 4, open circles
Indicate node, the image of each node corresponding a width ' selection ', the interior solid dot of circle represents cursor position, and Grey Point represents on circle
Predetermined point.
Before cursor activation, output image is shown as the gray level image image 1 after normalization.Mouse is clicked in interactive interface
After mark, cursor activation, the at this time change of cursor position will directly affect the variation of output image.When the cursor of activation falls within circle
When internal, it will appear corresponding triangle in circle in interactive process, image represented by the Atria vertex is
Export three channels of image.When the cursor of activation falls within display image area, export what image was kept using phase at this time
Dynamic range compression algorithm.And when cursor falls within other regions, it exports to be shown as single-channel two waveband blending image.
After interactive interface activation, right side output image will correspondingly change cursor according to the movement of cursor position.This
When, user can be according to the variation tendency adjustment cursor position of output image to reach more preferably output effect.If without pre-
Image data is set, the rough idea of the rough observation experiment data of method is determined using 3 points, finding best output image terminates
Operation, or determine one to two default fixed points, and then determine method using two o'clock or a little determine that method is further displayed.In advance
Set point can also be adjusted according to circumstances at any time in practical applications.
In order to illustrate effectiveness of the invention, three groups of HSI are tested altogether, respectively state of Indiana agricultural atural object
(Indiana Pines), not Fitow area image (Moffet) and Salinas area image (Salinas).Three groups of data are all
Overcorrect and removal strong noise wave band, pseudo color image shows that result difference is as shown in Figure 4 after PCA dimensionality reduction.This five groups
Data all will be used to verify the validity of proposed method under matlab platform.
1. several single mode images
For the validity of verification method, selection PCA method Fitow area picture number to state of Indiana agricultural atural object and not
According to dimensionality reduction is carried out, retain the first six main component, as the useful image to export.This experiment will be higher according to correlation
Two images are ranked up useful image at a distance of remoter, the useful image of two groups of data acquisitions and its ranking results such as Fig. 6 institute
Show, is followed successively by Image 1-Image 6 from (f) of (a)-Fig. 6 of Fig. 6.After information sifting and node image sequence, respectively
Visualization display is interacted to four groups of data.
Above data is applied in method of the invention, obtained display result is as shown in fig. 7, wherein right side is defeated
Image out, left side are interactive interface, and hollow dots represent node image, and solid dot is cursor, three tops of inscribe triangle in circle
The position of point determines the hybrid mode of three channel images, and these images are subsequently used for RGB color space and are shown.When
After node image determines, cursor position will determine the output image of the system, and result can carry out free tune to it by user
Section.As shown in Figure 8 and Figure 9.
2. multi-modality images
Filter information process is not only capable of handling former HSI using a kind of processing method, but can combine a variety of
Data processed result shows former data information.In the experiment of this section, PCA will be used simultaneously, will be classified, and solution is mixed, bilateral
The data processed result of filtering fusion and all wave band weighted sums shows Salinas area image (Salinas).
Figure 10 is the node image that Salinas area image (Salinas) is obtained through information sifting, is respectively from (a)-(i)
Image 1-Image 9.Figure 10 determines the visual of method using 3 points for Salinas area image (Salinas) multiple types image
Change result.As it can be seen that the information for exporting image expression will generate variation when cursor position difference.For example, when the three of cursor control
When angular one of vertex is close to Image 5 or Image9, output image can highlight respective classes, pass through at this time
The different mixed proportion of mixed image is adjusted, the degree for highlighting classification is also different.When cursor is close to bilateral filtering image
When Image 6-Image 8, the boundary information for exporting image is then relatively sharp.Meanwhile it can be seen from figure 11 that in output image
The color of each atural object also changes in the variation with cursor position.
In Figure 10, (a) spectral weighting and, (b)-(d) PCA, (e) atural object solution in part is mixed as a result, (f)-(h) bilateral filtering melts
It closes as a result, (i) certain category classification result.
Through experiment as can be seen that the present invention can carry out purposive information excavating, interaction to HSI according to the needs of users
Interface can state more information convenient for user's operation, and can combine and show to different types of information, and the present invention not only may be used
To be used for high spectrum image, the image information of other classifications can also be shown, such as multispectral image, anisotropic filter output
Image, different focusedimages, isospace region different time image, the image etc. that isospace region different sensors obtain.And
When the image information to other classifications is shown, it can also be used to comparison and comparison between image.More held by modified-image
Easily determine atural object；The different atural object color of variation tendency can more protrude different atural object classifications.Meanwhile in certain mixed recharges
The lower feature that can not be shown of section will preferably be shown in other combinations；It additionally can according to need adjustment integral color.
Observer can more easily determine best output image by change cursor position, meanwhile, to mixed figure in the image
Picture and its mixed coefficint are relatively easy to determine.The present invention is a kind of method for visualizing that can highlight certain atural object or classification.
Claims (2)
1. a kind of interactive more image color method for visualizing of high spectrum image, it is characterised in that: steps are as follows: step 1, letter
Breath screening selects the useful image for display for meeting user's requirement by data processing or hand picking method, these
Iamge description is the gray level image of several same space scales；Step 2, node diagram sequence, the gray scale that will be filtered out in step 1
Image is arranged on node equidistant on annulus according to image correlation size order；Step 3, interactive adjusting triple channel letter
Breath, system will automatically select display methods according to the number of predetermined point, can increase and decrease according to the needs of users during display
Or modification predetermined point, meanwhile, display methods changes also with predetermined number of points purpose and accordingly changes, and modifies when to predetermined point
When, the sequence of node diagram can also be adjusted simultaneously, to reach better display effect, finally, three gray level images obtained will be used
With the three channels output shown in color space；Step 4 shows in color space, three obtained in step 3 grayscale image
As by normalization or image enhancement processing, the triple channel for being used separately as color space carries out display and obtains output image.
2. the interactive more image color method for visualizing of a kind of high spectrum image according to claim 1, it is characterised in that:
The extracting method of the interactive adjusting triple channel information of step 3 is as follows:
(1) in interactive interface, predetermined point is set；
(2) other points are determined；
(3) output image, single channel gray level image/Three Channel Color image are determined；
Combine three channel informations of the known predetermined point together as output image to show via determining mixed image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611121980.6A CN106815874B (en) | 2016-12-08 | 2016-12-08 | A kind of interactive more image color method for visualizing of high spectrum image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611121980.6A CN106815874B (en) | 2016-12-08 | 2016-12-08 | A kind of interactive more image color method for visualizing of high spectrum image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106815874A CN106815874A (en) | 2017-06-09 |
| CN106815874B true CN106815874B (en) | 2019-05-24 |
Family
ID=59106991
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611121980.6A Expired - Fee Related CN106815874B (en) | 2016-12-08 | 2016-12-08 | A kind of interactive more image color method for visualizing of high spectrum image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106815874B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102411782A (en) * | 2011-11-01 | 2012-04-11 | 哈尔滨工程大学 | Three layer color visualization method of hyperspectral remote sensing image |
| CN102779353A (en) * | 2012-05-31 | 2012-11-14 | 哈尔滨工程大学 | High-spectrum color visualization method with distance maintaining property |
| CN102945546A (en) * | 2012-10-19 | 2013-02-27 | 哈尔滨工程大学 | Visualization method capable of sparsely representing hyperspectral image |
-
2016
- 2016-12-08 CN CN201611121980.6A patent/CN106815874B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102411782A (en) * | 2011-11-01 | 2012-04-11 | 哈尔滨工程大学 | Three layer color visualization method of hyperspectral remote sensing image |
| CN102779353A (en) * | 2012-05-31 | 2012-11-14 | 哈尔滨工程大学 | High-spectrum color visualization method with distance maintaining property |
| CN102945546A (en) * | 2012-10-19 | 2013-02-27 | 哈尔滨工程大学 | Visualization method capable of sparsely representing hyperspectral image |
Non-Patent Citations (3)
| Title |
|---|
| Cai S.et al.Hyperspectral Imagery Visualization Using Double Layers.《IEEE Transactions on Geoscience and Remote Sensing》.2007, |
| Kovesi P..Phase Preserving Tone Mapping ofNon-Photographic High Dynamic Range Images.《Proceedings Digital Image Computing:Techniques and Applications,Crawley,Australia》.2012, |
| 高光谱图像的同步彩色动态显示;刘丹凤等;《哈尔滨工程大学学报》;20140630;全文 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106815874A (en) | 2017-06-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| McGarigal | FRAGSTATS help | |
| Yan et al. | Comparison of pixel‐based and object‐oriented image classification approaches—a case study in a coal fire area, Wuda, Inner Mongolia, China | |
| Gao et al. | A comparison of the performance of pixel-based and object-based classifications over images with various spatial resolutions | |
| Herold et al. | Object-oriented mapping and analysis of urban land use/cover using IKONOS data | |
| Mallinis et al. | Object-based classification using Quickbird imagery for delineating forest vegetation polygons in a Mediterranean test site | |
| De Kok et al. | Object based classification and applications in the Alpine forest environment | |
| CN111625608B (en) | Method and system for generating electronic map according to remote sensing image based on GAN model | |
| US7822224B2 (en) | Terrain map summary elements | |
| Peng et al. | Object-based change detection from satellite imagery by segmentation optimization and multi-features fusion | |
| CN106875481A (en) | A kind of preparation method of three-dimensional visualization remote sensing image Surface classification model | |
| Alexakis et al. | Integrated use of satellite remote sensing, GIS, and ground spectroscopy techniques for monitoring olive oil mill waste disposal areas on the island of Crete, Greece | |
| Warner | Hyperspherical direction cosine change vector analysis | |
| Lizarazo et al. | Fuzzy image segmentation for urban land-cover classification | |
| CN106815874B (en) | A kind of interactive more image color method for visualizing of high spectrum image | |
| Zou et al. | Object based image analysis combining high spatial resolution imagery and laser point clouds for urban land cover | |
| Zhang et al. | Automatic classification of fine-scale mountain vegetation based on mountain altitudinal belt | |
| Zhang et al. | Urban UAV images semantic segmentation based on fully convolutional networks with digital surface models | |
| JP6334281B2 (en) | Forest phase analysis apparatus, forest phase analysis method and program | |
| Kressler et al. | Object-oriented classification of orthophotos to support update of spatial databases | |
| Hamandawana et al. | The use of step‐wise density slicing in classifying high‐resolution panchromatic photographs | |
| Kux et al. | Object-oriented analysis of high-resolution satellite images for intra-urban land cover classification: Case study in São José Dos Campos, São Paulo State, Brazil | |
| Boukir et al. | Improving remote sensing multiple classification by data and ensemble selection | |
| CN108053406A (en) | Ground mulching drafting method and device based on multiple-spatial resolution remote sensing image | |
| Galli et al. | Hyperspectral Data Classification by Object-Oriented Approach for The Management of Urban Landscape | |
| Lawrence | Early detection of Heacleum Mantegazzianum (Giant Hogweed) based on leaf spectral characteristics from UAV images SVM and OBIA Techniques |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20190524 Termination date: 20201208 |