CN105809140B - A kind of extracting method and its device of the surface water body information based on Remote Sensing Model - Google Patents
A kind of extracting method and its device of the surface water body information based on Remote Sensing Model Download PDFInfo
- Publication number
- CN105809140B CN105809140B CN201610156982.2A CN201610156982A CN105809140B CN 105809140 B CN105809140 B CN 105809140B CN 201610156982 A CN201610156982 A CN 201610156982A CN 105809140 B CN105809140 B CN 105809140B
- Authority
- CN
- China
- Prior art keywords
- remotely
- remote sensing
- water body
- sensed data
- treated
- 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.)
- Active
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
- G06F2218/02—Preprocessing
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Image Processing (AREA)
Abstract
The extracting method and its device for the surface water body information based on Remote Sensing Model that the embodiment of the invention discloses a kind of, wherein this method comprises: obtaining remote sensing image data；Data prediction is carried out to the remote sensing image data, obtains treated remotely-sensed data；For treated the remotely-sensed data, corresponding threshold value is set；Binary conversion treatment is carried out to treated the remotely-sensed data according to the threshold value, the binaryzation remotely-sensed data that obtains that treated；Surface water body information extraction is carried out according to treated the binaryzation remotely-sensed data.In embodiments of the present invention, Water-Body Information is gradually enhanced, Clean water withdraw information is made to reach higher accuracy rate, faster extraction rate, solves the problems such as background information and extraction accuracy that can not thoroughly inhibit unrelated with water body in the prior art are low, time-consuming.
Description
Technical field
The present invention relates to mentioning for technical field of information processing more particularly to a kind of surface water body information based on Remote Sensing Model
Take method and device thereof.
Background technique
Satellite remote sensing technology is in environmental monitoring, resource investigation, the various fields such as prevent and reduce natural disasters with real-time, accurate and macroscopical
Many advantages, such as play an important role.Utilize the variation of remote sensing technology monitoring water quality, Coastline Changes and flood floods
Natural calamity etc., is widely used.The research of water body, which is be unable to do without, mentions coverage of water, range, distribution, the accurate of boundary line
It takes, this monitors change of water quality, Coastline Changes monitoring, flood floods monitor and hazards entropy is particularly significant.
The 1970s, both at home and abroad just to multispectral sensor-based system (Mu1tispectralSensingSystem,
MSS four wave bands) carry out water body Remote Sensing Study, with the rapid development of optical remote sensing, LandsatTM/ETM+, SPOT,
The lift-off of the sensors sequential transmissions such as MODIS and data it is universal, optical remote sensing Clean water withdraw method is broadly divided into single band method
With multiband method, wherein single band method carries out water body with absorption contrast of other atural objects near infrared band using water body and mentions
It takes, this method increases the confusion with surrounding atural object during being difficult to remove the shade and flood being mixed in water body, so often
It is used in combination with other methods；Multiband method is divided into spectrum-photometric method and band ratio method etc. again, and spectrum-photometric method passes through analysis
The spectral profile feature of water body and non-water body atural object finds out its variation relation and then utilizes expression formula that Clean water withdraw is come out, multiple
Miscellaneous degree is higher.Ratio rule extracts Water-Body Information according to wave spectrum feature of the different land types in different-waveband, and this method calculates
It is simple and quick.Such as it is advantageous for inhibiting vegetation information divided by the simple ratio operation of near infrared band with green light or red spectral band,
Enhance Water-Body Information.But this method can not thoroughly inhibit the background information unrelated with water body.
Normalized ratio type index method is the basis of common Clean water withdraw method.This method is looked in multispectral data
Seek the corresponding most strong reflection wave band of target and most weak reflected waveband, then using the numerical value of most strong reflection wave band as denominator, it is most weak
The numerical value of reflected waveband carries out ratio as molecule, and then data are normalized.Normalized difference water body index
(Normalized Difference Vegetation Water Index, NDWI) is that common use normalized ratio type refers to
The method that number method extracts Water-Body Information.Since the reflection of water body gradually weakens from visible light to middle infrared band, in near-infrared and
Absorbability is most strong within the scope of middle infrared wavelength, almost areflexia, therefore is constituted with the contrast of visible light wave range and near infrared band
NDWI can protrude the Water-Body Information in image.It is generally most strong in the reflectivity of near infrared band additionally, due to vegetation, therefore
The information of vegetation can farthest be inhibited using the ratio of green light band and near infrared band, to reach prominent water body letter
The purpose of breath.
The improved normalized difference water body index (MNDWI) that infrared band replacement near infrared band is constituted in utilization is available
In quick, easy and accurately extract Water-Body Information.Its NDWI index than Mcfeeters has wider application range.
Other than MNDWI is in addition to as NDWI, can be used for the Clean water withdraw of vegetation region, it can be also used for accurately extracting in town-wide
Water-Body Information.And NDWI affects extraction due to containing the noise there are many building information in its extracted Water-Body Information
Precision.It is accordingly difficult to for the water body information within the scope of the built-up areas of cities and towns.
Still it is mingled with many non-Water-Body Informations in the Water-Body Information extracted in many cases, with NDWI, especially exists
Effect is very unsatisfactory in terms of the Clean water withdraw in city in extraction scope.Therefore, it is proposed to improved normalized difference water body index
(MNDWI), the water body in the effect better than NDWI, especially extraction town-wide is largely obtained.But it is higher in landform
The more place of vegetation, still carries non-Water-Body Information secretly, such as massif shade.At the same time, due to the index results calculated,
Artificial threshold value screening is generally required, although process is simple time-consuming, while the process usually contains factor and individual subjective factor: i.e. not
Same people, the threshold value result obtained are different.
Summary of the invention
It is an object of the invention to overcome the deficiencies in the prior art, and the present invention provides a kind of earth's surfaces based on Remote Sensing Model
The extracting method and its device of Water-Body Information, the background information unrelated with water body can not thoroughly be inhibited in the prior art by solving,
And extraction accuracy it is low, time-consuming the problems such as.
To solve the above-mentioned problems, the extraction side for the surface water body information based on Remote Sensing Model that the invention proposes a kind of
Method, which comprises
Obtain remote sensing image data；
Data prediction is carried out to the remote sensing image data, obtains treated remotely-sensed data；
For treated the remotely-sensed data, corresponding threshold value is set；
Binary conversion treatment is carried out to treated the remotely-sensed data according to the threshold value, obtaining that treated, binaryzation is distant
Feel data；
Surface water body information extraction is carried out according to treated the binaryzation remotely-sensed data.
Preferably, described that data prediction is carried out to the remote sensing image data, obtain the step of treated remotely-sensed data
Suddenly, comprising:
Data correction is carried out to the remote sensing image data, the remote sensing image data after being corrected；
Vegetation information normalized is carried out to the remote sensing image data after correction according to normalized differential vegetation index NDVI, is obtained
Treated NDVI remotely-sensed data；
The remote sensing image data after correction is carried out at Water-Body Information normalization according to normalized difference water body index NDWI
Reason obtains treated NDWI remotely-sensed data；
Water-Body Information normalizing is carried out to the remote sensing image data after correction according to amendment normalized difference water body index MNDWI
Change processing, obtains treated MNDWI remotely-sensed data.
Preferably, described the step of Data correction is carried out to the remote sensing image data, comprising:
Data school is carried out to the remote sensing image data according to linear regression radiant correction and FLAASH atmospheric correction mode
Just.
Preferably, described that the remote sensing image data progress vegetation information after correction is returned according to normalized differential vegetation index NDVI
One change processing, the step of obtaining treated NDVI remotely-sensed data, comprising:
Vegetation is carried out to the remote sensing image data after correction according to normalized differential vegetation index NDVI=(NIR-R)/(NIR+R)
Information normalized obtains treated NDVI remotely-sensed data；Wherein, R represents red spectral band, and NIR represents near infrared band.
Preferably, described that water body letter is carried out to the remote sensing image data after correction according to normalized difference water body index NDWI
The step of ceasing normalized, obtaining treated NDWI remotely-sensed data, comprising:
According to normalized difference water body index NDWI=(Green-NIR)/(Green+NIR) to the remote sensing image after correction
Data carry out Water-Body Information normalized, obtain treated NDWI remotely-sensed data；Wherein, Green represents green light band,
NIR represents near infrared band.
Preferably, described that the remote sensing image data after correction is carried out according to amendment normalized difference water body index MNDWI
Water-Body Information normalized, the step of obtaining treated MNDWI remotely-sensed data, comprising:
According to amendment normalized difference water body index MNDWI=(Green-MIR)/(Green+MIR) to distant after correction
Feel image data and carry out Water-Body Information normalized, obtains treated MNDWI remotely-sensed data；Wherein, Green represents green light
Wave band；Infrared band in MIR representative.
Preferably, binary conversion treatment is carried out to treated the remotely-sensed data according to the threshold value, obtains that treated
Binaryzation remotely-sensed data
Correspondingly, the extraction element for the surface water body information based on Remote Sensing Model that the present invention also provides a kind of, described device
Include:
Module is obtained, for obtaining remote sensing image data；
Preprocessing module is obtained for carrying out data prediction to remote sensing image data acquired in the acquisition module
Remotely-sensed data that treated；
Setup module, for corresponding threshold value to be arranged for the remotely-sensed data after handled by the preprocessing module；
Binarization block carries out treated the remotely-sensed data for the threshold value according to set by the setup module
Binary conversion treatment obtains treated binaryzation remotely-sensed data；
Extraction module, for carrying out surface water body information according to the binarization block treated binaryzation remotely-sensed data
It extracts.
Preferably, the preprocessing module includes:
Unit is corrected, for carrying out Data correction to the remote sensing image data, the remote sensing image data after being corrected；
NDVI processing unit, for carrying out vegetation to the remote sensing image data after correction according to normalized differential vegetation index NDVI
Information normalized obtains treated NDVI remotely-sensed data；
NDWI processing unit, for being carried out according to normalized difference water body index NDWI to the remote sensing image data after correction
Water-Body Information normalized obtains treated NDWI remotely-sensed data；
MNDWI processing unit, for according to amendment normalized difference water body index MNDWI to the remote sensing image number after correction
According to Water-Body Information normalized is carried out, treated MNDWI remotely-sensed data is obtained.
Preferably, the NDVI processing unit is used for right according to normalized differential vegetation index NDVI=(NIR-R)/(NIR+R)
Remote sensing image data after correction carries out vegetation information normalized, the NDVI remotely-sensed data that obtains that treated；Wherein, R generation
Table red spectral band, NIR represent near infrared band；
The NDWI processing unit is used for according to normalized difference water body index NDWI=(Green-NIR)/(Green+
NIR Water-Body Information normalized) is carried out to the remote sensing image data after correction, obtains treated NDWI remotely-sensed data；Its
In, Green represents green light band, and NIR represents near infrared band；
The MNDWI processing unit be used for according to amendment normalized difference water body index MNDWI=(Green-MIR)/
(Green+MIR) Water-Body Information normalized is carried out to the remote sensing image data after correction, obtains treated MNDWI remote sensing
Data；Wherein, Green represents green light band；Infrared band in MIR representative.
In embodiments of the present invention, by the way that index is normalized, then passes through threshold value and set, extract water-outlet body letter
Breath, isolates the information of the atural objects such as massif shade, vegetation and building；Further enhanced is carried out to three isolation results to fold
Add, the progressive information for rejecting the atural objects such as massif shade, vegetation and building gradually enhances Water-Body Information, makes Clean water withdraw information
Reach higher accuracy rate, faster extraction rate, the background unrelated with water body can not thoroughly be inhibited in the prior art by solving
The problems such as information and low, time-consuming extraction accuracy.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
Other attached drawings are obtained according to these attached drawings.
Fig. 1 is the flow diagram of the extracting method of the surface water body information based on Remote Sensing Model of the embodiment of the present invention；
Fig. 2 is the flow diagram for carrying out data prediction in the embodiment of the present invention to remote sensing image data；
Fig. 3 a to 3f is the water spectral characteristics of mean curve graph and water spectral value range characteristic pattern of the embodiment of the present invention；
Fig. 4 is the structure composition signal of the extraction element of the surface water body information based on Remote Sensing Model of the embodiment of the present invention
Figure.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Fig. 1 is the flow diagram of the extracting method of the surface water body information based on Remote Sensing Model of the embodiment of the present invention,
As shown in Figure 1, this method comprises:
S1 obtains remote sensing image data；
S2 carries out data prediction to remote sensing image data, obtains treated remotely-sensed data；
S3, for treated, corresponding threshold value is arranged in remotely-sensed data；
S4 carries out binary conversion treatment to treated remotely-sensed data according to threshold value, the binaryzation remote sensing number that obtains that treated
According to；
S5, according to treated, binaryzation remotely-sensed data carries out surface water body information extraction.
In S1, the remote sensing image data of earth's surface is obtained by TM/ETM+ sensor.
Further, as shown in Fig. 2, S2 includes:
S21 carries out Data correction to remote sensing image data, the remote sensing image data after being corrected；
S22 carries out at vegetation information normalization the remote sensing image data after correction according to normalized differential vegetation index NDVI
Reason obtains treated NDVI remotely-sensed data；
S23 carries out Water-Body Information normalizing to the remote sensing image data after correction according to normalized difference water body index NDWI
Change processing, obtains treated NDWI remotely-sensed data；
S24 carries out Water-Body Information to the remote sensing image data after correction according to amendment normalized difference water body index MNDWI
Normalized obtains treated MNDWI remotely-sensed data.
Wherein, S22, S23, S24 can be carried out simultaneously in specific implementation.
In S21, remote sensing image data is counted according to linear regression radiant correction and FLAASH atmospheric correction mode
According to correction.
In S22, according to normalized differential vegetation index NDVI=(NIR-R)/(NIR+R) to the remote sensing image data after correction
Vegetation information normalized is carried out, treated NDVI remotely-sensed data is obtained；Wherein, R represents red spectral band, and NIR represents close
Infrared band.
Normalized differential vegetation index (NDVI) is missed for detecting vegetation growth state, vegetation coverage and eliminating partial radiation
Difference etc..In each band spectrum data of LandSat satellite TM/ETM+ sensor, reflectivity of the near infrared band to vegetation
It is relatively large, and red spectral band is relatively small to the reflectivity of vegetation, therefore by the near-infrared of coordinate points each in remotely-sensed data
Wave band data is subtracted each other with red spectral band data, obtains the vegetation index of the coordinate points.Operation after for convenience, will sit
As molecule, the sum that near-infrared data is added with red spectral band data is calculated the vegetation index of punctuate as molecule,
Obtained coordinate point data will be normalized between 1 and -1, that is, to vegetation index.The formula of NDVI is such as
Under: NDVI=(NIR-R)/(NIR+R)；In formula, R represents red spectral band；NIR represents near infrared band.Remote sensing is obtained after calculating
It include the NDVI remotely-sensed data of each pixel on image.
In S23, according to normalized difference water body index NDWI=(Green-NIR)/(Green+NIR) to correction after
Remote sensing image data carries out Water-Body Information normalized, obtains treated NDWI remotely-sensed data；Wherein, Green represents green
Optical band, NIR represent near infrared band.
Normalized difference water body index (NDWI) is the method for extracting Water-Body Information using normalized ratio type index method.By
It gradually decreases in the reflection of water body from visible light to middle infrared band, is constituted with the contrast of visible light wave range and near infrared band
NDWI can protrude the Water-Body Information in image, generally most strong in the reflectivity of near infrared band additionally, due to vegetation, therefore adopt
It can inhibit to the maximum extent the information of vegetation with the ratio of green light band and near infrared band, to reach prominent Water-Body Information
Purpose.Therefore near-infrared data that the green light band data of coordinate points in remotely-sensed data are subtracted to the coordinate points, obtains
The difference water body index of the coordinate points；Then with the difference water body index of the coordinate points divided by the green light band data of the coordinate points
In addition the sum of near infrared band to be to be normalized, to obtain the normalized difference water body index of the coordinate points.It is public
Formula is as follows: NDWI=(Green-NIR)/(Green+NIR)；In formula, Green represents green light band；NIR represents near-infrared wave
Section.The NDWI remotely-sensed data comprising each pixel on remote sensing images is obtained after calculating.
In S24, according to amendment normalized difference water body index MNDWI=(Green-MIR)/(Green+MIR) to school
Remote sensing image data after just carries out Water-Body Information normalized, the MNDWI remotely-sensed data that obtains that treated；Wherein, Green
Represent green light band；Infrared band in MIR representative.
Amendment normalized difference water body index (MNDWI) be according to the reflectivity of building from near-infrared in it is infrared suddenly
Turn strong, and water body continues the rule to drop in the reflectivity of middle infrared band, and visible light is subtracted middle infrared band, greatly strengthens
Water-Body Information and cut down building information.Compared with NDWI, MNDWI is using the green light band number in remotely-sensed data in coordinate points
According to middle infrared band data are subtracted rather than near-infrared data, then again by the numerical value after subtracting each other divided by green light band data and
The sum of middle infrared band data finally obtains amendment normalized difference water body index MNDWI, formula is such as to realize normalization
Under: MNDWI=(Green-MIR)/(Green+MIR)；In formula, Green represents green light band；Infrared band in MIR representative.Meter
The MNDWI remotely-sensed data comprising all pixels point on remote sensing images is obtained after calculation.
In S4, binaryzation is carried out to NDVI data, NDWI data and MNDWI data respectively, the two-value that obtains that treated
Change remotely-sensed data NDVI+、NDWI-And MNDWI+Data.
Further, S5 includes:
According to treated remotely-sensed data and treated that binaryzation remotely-sensed data obtains water body information Optimized model；
Surface water body information extraction is carried out according to water body information Optimized model.
Present invention method is further described below with reference to Fig. 3 a- Fig. 3 f.Wherein, 3a is water body in lake light
Compose characteristics of mean curve graph；3b is water body in lake spectral region value tag figure；3c is river water spectrum average characteristic curve diagram；
3d is river water spectral region value tag figure；3e is fish pond spectrum average characteristic curve diagram；3f is fish pond spectrum
Value range characteristic pattern.
In specific implementation, used initial data may be from the Landsat plan (LandSat) of U.S. NASA
TM/ETM+ sensor, the spatial resolution of remotely-sensed data are 30 meters, objective area have chosen respectively river, fish pond and lake this
The main water body of three classes.
By the way that the result of artificial judgment pixel vertex type simultaneously is compared with NDVI matrix, NDWI matrix and MNDWI matrix
Compared with and statistics, it can be deduced that for tested separately include lake, river, these three types of fish pond remotely-sensed data in,
Three kinds of exponent datas of the pixel of vegetation, building and water body these three types landforms.It analyzes in these three remotely-sensed datas, three classes landforms
NDVI remotely-sensed data, NDWI remotely-sensed data and MNDWI remotely-sensed data average value and data area, three kinds of remote sensing can be obtained
The spectrum average characteristic curve diagram and spectral region characteristic pattern of three classes landforms in data, as illustrated in figs. 3 a-f.
It is can analyze out according to spectrum average characteristic curve diagram and spectral region characteristic pattern, although in MNDWI remotely-sensed data
The mean value of water body differs larger with the mean value of the non-water body such as vegetation, but also has the MNDWI remote sensing number of fraction part water body
According to identical close with the MNDWI remotely-sensed data of the non-water body such as vegetation, building, it is therefore desirable to distant by NDVI remotely-sensed data and NDWI
Data are felt to remove the non-aqueous body portion in MNDWI remotely-sensed data.Value range characteristic profile in Fig. 3 b, 3d and 3f can
See:
(1) it is 0 when threshold value is arranged in NDVI remotely-sensed data, can be preferably separated out vegetation and non-vegetation.Wherein it is less than threshold value
Part mainly include water body and most of building because water body is relatively high to the reflectivity of visible light；Greater than threshold value portion
Divide mainly includes vegetation, fraction building and fraction water body.
(2) it is 0 when threshold value is arranged in NDWI remotely-sensed data, can preferably separates water-outlet body and non-water body.NDWI remotely-sensed data
In to be less than the part of threshold value mainly include small part water body, most vegetation and most of building；It is big in NDWI remotely-sensed data
Include most of water body, small part building in the part of threshold value.
(3) it is 0 when threshold value is arranged in MNDWI remotely-sensed data, can preferably separates water-outlet body and non-water body.Wherein it is less than threshold value
Part mainly include small part water body, most of building and most vegetation；It mainly include exhausted big portion greater than the part of threshold value
Water distribution component, small part vegetative coverage and small part building.
After being determined threshold value, it is necessary to carry out two to NDVI remotely-sensed data, NDWI remotely-sensed data and MNDWI remotely-sensed data
Value.The binaryzation of data is by the data of each coordinate points in NVDI, NDWI and MNDWI remotely-sensed data according to having determined
Threshold value and certain rule judged, by original data be converted into only include 0 or 1 matrix.The binaryzation of data has
Conducive to the calculation process of next step, become data simply, and data volume reduces, can be effectively reduced operand, promotes fortune
Calculate speed.
After carrying out binaryzation to NDVI remotely-sensed data, NDWI remotely-sensed data and MNDWI remotely-sensed data respectively, NDVI is obtained+、
NDWI-And MNDWI+Data, in which:
NDVI+It is that the part greater than threshold value in NDVI remotely-sensed data is taken 1, the part less than or equal to threshold value takes 0, also
It is to set 1 for vegetation, fraction building and the higher vegetation of water content, sets 0 for water body and most of building.
NDWI-It is that the part for being greater than threshold value in NDWI remotely-sensed data is taken 0, the part less than or equal to threshold value takes 1, that is,
0 is set by most of water body, part building, sets 1 for vegetation and most of building.
MNDWI+It is that the part for being greater than threshold value in MNDWI remotely-sensed data is taken 1, the part less than or equal to threshold value takes 0, also
It is that vegetation and building by water body and very small part is set as 1, sets 0 for most vegetation and building.
The final step of Clean water withdraw operation is carried out after completion binaryzation.By MNDWI+Subtract NDVI+NDWI is subtracted again-, such as
The data that fruit obtains are 1 and are judged as water body, are judged as non-water body if it is less than 1.Formula is as follows:
Water body information Optimized model=MNDWI+-NDVI+-NDWI-
By MNDWI in water body information Optimized model+Subtract NDVI+If, it is meant that MNDWI+The picture that middle numerical value is 1
Vegetarian refreshments is in NDVI+In be also 1, then can be removed, also just eliminate MNDWI+Middle numerical value be 1 be actually vegetation pixel.
NDWI is subtracted again-, it is meant that MNDWI+If the pixel that numerical value is 1 is in NDWI-Also it is 1, then can be removed, also just eliminate
MNDWI+In remaining fraction building.
Water body information Optimized model can preferably solve the problems, such as that NDVI, NDWI, MNDWI method exist, can be preferably
The non-Water-Body Informations such as building, vegetation, massif shade are distinguished on ground, are substantially increased NDVI, NDWI, MNDWI index water body and are mentioned
Take precision.The result shows that: method overall accuracy of the progressive enhancing model than three kinds of routines in two groups of lake, fish pond tests
It improves 13% or more, totality kappa coefficient and improves 0.26 or more, progressive enhancing model is than three kinds in river water test
Conventional method overall accuracy improves 1% or more, totality kappa coefficient and improves 0.02 or more.In addition, water body information
The settable unified segmentation threshold of Optimized model, the full-automation for magnanimity Remote Sensing water body information process provide branch
It holds.
Correspondingly, the embodiment of the present invention also provides a kind of extraction element of surface water body information based on Remote Sensing Model, such as
Shown in Fig. 4, which includes:
Module 1 is obtained, for obtaining remote sensing image data；
Preprocessing module 2, for carrying out data prediction to obtaining remote sensing image data acquired in module 1, at acquisition
Remotely-sensed data after reason；
Setup module 3, for corresponding threshold value to be arranged for the remotely-sensed data after handled by preprocessing module 2；
Binarization block 4, for the threshold value according to set by setup module 3, to treated, remotely-sensed data carries out binaryzation
Processing obtains treated binaryzation remotely-sensed data；
Extraction module 5 is mentioned for carrying out surface water body information according to treated the binaryzation remotely-sensed data of binarization block 4
It takes.
In specific implementation, obtaining module can be TM/ETM+ sensor, for obtaining the remote sensing image data of earth's surface
Further, preprocessing module 2 includes:
Unit is corrected, for carrying out Data correction to remote sensing image data, the remote sensing image data after being corrected；Specifically
Ground carries out Data correction to remote sensing image data according to linear regression radiant correction and FLAASH atmospheric correction mode；
NDVI processing unit, for carrying out vegetation to the remote sensing image data after correction according to normalized differential vegetation index NDVI
Information normalized obtains treated NDVI remotely-sensed data；
NDWI processing unit, for being carried out according to normalized difference water body index NDWI to the remote sensing image data after correction
Water-Body Information normalized obtains treated NDWI remotely-sensed data；
MNDWI processing unit, for according to amendment normalized difference water body index MNDWI to the remote sensing image number after correction
According to Water-Body Information normalized is carried out, treated MNDWI remotely-sensed data is obtained.
In specific implementation, NDVI processing unit is used for according to normalized differential vegetation index NDVI=(NIR-R)/(NIR+R)
Vegetation information normalized is carried out to the remote sensing image data after correction, obtains treated NDVI remotely-sensed data；Wherein, R
Red spectral band is represented, NIR represents near infrared band；
NDWI processing unit is used for right according to normalized difference water body index NDWI=(Green-NIR)/(Green+NIR)
Remote sensing image data after correction carries out Water-Body Information normalized, the NDWI remotely-sensed data that obtains that treated；Wherein,
Green represents green light band, and NIR represents near infrared band；
MNDWI processing unit is used for according to amendment normalized difference water body index MNDWI=(Green-MIR)/(Green+
MIR Water-Body Information normalized) is carried out to the remote sensing image data after correction, obtains treated MNDWI remotely-sensed data；Its
In, Green represents green light band；Infrared band in MIR representative.
Binarization block 4 is further used for carrying out binaryzation to NDVI data, NDWI data and MNDWI data respectively, obtains
To treated binaryzation remotely-sensed data NDVI+、NDWI-And MNDWI+Data.
The function of each functional module can be found at the process in embodiment of the present invention method in the device of the invention embodiment
Reason, which is not described herein again.
In embodiments of the present invention, by the way that index is normalized, then passes through threshold value and set, extract water-outlet body letter
Breath, isolates the information of the atural objects such as massif shade, vegetation and building；Further enhanced is carried out to three isolation results to fold
Add, the progressive information for rejecting the atural objects such as massif shade, vegetation and building gradually enhances Water-Body Information, makes Clean water withdraw information
Reach higher accuracy rate, faster extraction rate, the background unrelated with water body can not thoroughly be inhibited in the prior art by solving
The problems such as information and low, time-consuming extraction accuracy.
Those of ordinary skill in the art will appreciate that all or part of the steps in the various methods of above-described embodiment is can
It is completed with instructing relevant hardware by program, which can be stored in a computer readable storage medium, storage
Medium may include: read-only memory (ROM, Read Only Memory), random access memory (RAM, Random
Access Memory), disk or CD etc..
In addition, be provided for the embodiments of the invention above the surface water body information based on Remote Sensing Model extracting method and
Its device is described in detail, and used herein a specific example illustrates the principle and implementation of the invention,
The above description of the embodiment is only used to help understand the method for the present invention and its core ideas；Meanwhile for the one of this field
As technical staff, according to the thought of the present invention, there will be changes in the specific implementation manner and application range, to sum up institute
It states, the contents of this specification are not to be construed as limiting the invention.
Claims (9)
1. a kind of extracting method of the surface water body information based on Remote Sensing Model, which is characterized in that the described method includes:
Obtain remote sensing image data；
Data prediction is carried out to the remote sensing image data, obtains treated remotely-sensed data；
For treated the remotely-sensed data, corresponding threshold value is set；
Binary conversion treatment is carried out to treated the remotely-sensed data according to the threshold value, the binaryzation remote sensing number that obtains that treated
According to；
Surface water body information extraction is carried out according to treated the binaryzation remotely-sensed data；
Treated according to the binaryzation remotely-sensed data carries out the step of surface water body information extraction and includes:
According to treated remotely-sensed data and treated that binaryzation remotely-sensed data obtains water body information Optimized model；
Surface water body information extraction is carried out according to the water body information Optimized model；
Wherein, the water body information Optimized model formula is as follows:
Water body information Optimized model=MNDWI+—NDVI+—NDWI-；
Wherein, MNDWI+It indicates the part for being greater than threshold value in MNDWI remotely-sensed data taking 1, the part less than or equal to threshold value takes 0；
NDVI+It indicates the part greater than threshold value in NDVI remotely-sensed data taking 1, the part less than or equal to threshold value takes 0；NDWI-Indicating will
Part in NDWI remotely-sensed data greater than threshold value takes 0, and the part less than or equal to threshold value takes 1.
2. the extracting method of the surface water body information based on Remote Sensing Model as described in claim 1, which is characterized in that described right
The step of remote sensing image data carries out data prediction, the remotely-sensed data that obtains that treated, comprising:
Data correction is carried out to the remote sensing image data, the remote sensing image data after being corrected；
Vegetation information normalized is carried out to the remote sensing image data after correction according to normalized differential vegetation index NDVI, at acquisition
NDVI remotely-sensed data after reason；
Water-Body Information normalized is carried out to the remote sensing image data after correction according to normalized difference water body index NDWI, is obtained
Treated NDWI remotely-sensed data；
The remote sensing image data after correction is carried out at Water-Body Information normalization according to amendment normalized difference water body index MNDWI
Reason obtains treated MNDWI remotely-sensed data.
3. the extracting method of the surface water body information based on Remote Sensing Model as claimed in claim 2, which is characterized in that described right
The remote sensing image data carries out the step of Data correction, comprising:
Data correction is carried out to the remote sensing image data according to linear regression radiant correction and FLAASH atmospheric correction mode.
4. the extracting method of the surface water body information based on Remote Sensing Model as claimed in claim 2, which is characterized in that described
Vegetation information normalized is carried out to the remote sensing image data after correction according to normalized differential vegetation index NDVI, treated for acquisition
The step of NDVI remotely-sensed data, comprising:
Vegetation information is carried out to the remote sensing image data after correction according to normalized differential vegetation index NDVI=(NIR-R)/(NIR+R)
Normalized obtains treated NDVI remotely-sensed data；Wherein, R represents red spectral band, and NIR represents near infrared band.
5. the extracting method of the surface water body information based on Remote Sensing Model as claimed in claim 2, which is characterized in that described
Water-Body Information normalized is carried out to the remote sensing image data after correction according to normalized difference water body index NDWI, is handled
The step of rear NDWI remotely-sensed data, comprising:
According to normalized difference water body index NDWI=(Green-NIR)/(Green+NIR) to the remote sensing image data after correction
Water-Body Information normalized is carried out, treated NDWI remotely-sensed data is obtained；Wherein, Green represents green light band, NIR generation
Table near infrared band.
6. the extracting method of the surface water body information based on Remote Sensing Model as claimed in claim 2, which is characterized in that described
Water-Body Information normalized is carried out to the remote sensing image data after correction according to amendment normalized difference water body index MNDWI, is obtained
Treated MNDWI remotely-sensed data the step of, comprising:
According to amendment normalized difference water body index MNDWI=(Green-MIR)/(Green+MIR) to the remote sensing shadow after correction
As data carry out Water-Body Information normalized, treated MNDWI remotely-sensed data is obtained；Wherein, Green represents green light wave
Section；Infrared band in MIR representative.
7. a kind of extraction element of the surface water body information based on Remote Sensing Model, which is characterized in that described device includes:
Module is obtained, for obtaining remote sensing image data；
Preprocessing module is handled for carrying out data prediction to remote sensing image data acquired in the acquisition module
Remotely-sensed data afterwards；
Setup module, for corresponding threshold value to be arranged for the remotely-sensed data after handled by the preprocessing module；
Binarization block carries out two-value to treated the remotely-sensed data for the threshold value according to set by the setup module
Change processing, obtains treated binaryzation remotely-sensed data；
Extraction module is mentioned for carrying out surface water body information according to the binarization block treated binaryzation remotely-sensed data
It takes；
The extraction module is also used to:
According to treated remotely-sensed data and treated that binaryzation remotely-sensed data obtains water body information Optimized model；According to
The water body information Optimized model carries out surface water body information extraction；
Wherein, the water body information Optimized model formula is as follows:
Water body information Optimized model=MNDWI+—NDVI+—NDWI-；
Wherein, MNDWI+It indicates the part for being greater than threshold value in MNDWI remotely-sensed data taking 1, the part less than or equal to threshold value takes 0；
NDVI+It indicates the part greater than threshold value in NDVI remotely-sensed data taking 1, the part less than or equal to threshold value takes 0；NDWI-Indicating will
Part in NDWI remotely-sensed data greater than threshold value takes 0, and the part less than or equal to threshold value takes 1.
8. the extraction element of the surface water body information based on Remote Sensing Model as claimed in claim 7, which is characterized in that described pre-
Processing module includes:
Unit is corrected, for carrying out Data correction to the remote sensing image data, the remote sensing image data after being corrected；
NDVI processing unit, for carrying out vegetation information to the remote sensing image data after correction according to normalized differential vegetation index NDVI
Normalized obtains treated NDVI remotely-sensed data；
NDWI processing unit, for carrying out water body to the remote sensing image data after correction according to normalized difference water body index NDWI
Information normalized obtains treated NDWI remotely-sensed data；
MNDWI processing unit, for according to amendment normalized difference water body index MNDWI to the remote sensing image data after correction into
Row Water-Body Information normalized obtains treated MNDWI remotely-sensed data.
9. the extraction element of the surface water body information based on Remote Sensing Model as claimed in claim 8, which is characterized in that
The NDVI processing unit is used for according to normalized differential vegetation index NDVI=(NIR-R)/(NIR+R) to the remote sensing after correction
Image data carries out vegetation information normalized, obtains treated NDVI remotely-sensed data；Wherein, R represents red spectral band,
NIR represents near infrared band；
The NDWI processing unit is used for right according to normalized difference water body index NDWI=(Green-NIR)/(Green+NIR)
Remote sensing image data after correction carries out Water-Body Information normalized, the NDWI remotely-sensed data that obtains that treated；Wherein,
Green represents green light band, and NIR represents near infrared band；
The MNDWI processing unit is used for according to amendment normalized difference water body index MNDWI=(Green-MIR)/(Green+
MIR Water-Body Information normalized) is carried out to the remote sensing image data after correction, obtains treated MNDWI remotely-sensed data；Its
In, Green represents green light band；Infrared band in MIR representative.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610156982.2A CN105809140B (en) | 2016-03-18 | 2016-03-18 | A kind of extracting method and its device of the surface water body information based on Remote Sensing Model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610156982.2A CN105809140B (en) | 2016-03-18 | 2016-03-18 | A kind of extracting method and its device of the surface water body information based on Remote Sensing Model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105809140A CN105809140A (en) | 2016-07-27 |
| CN105809140B true CN105809140B (en) | 2019-07-05 |
Family
ID=56453370
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610156982.2A Active CN105809140B (en) | 2016-03-18 | 2016-03-18 | A kind of extracting method and its device of the surface water body information based on Remote Sensing Model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105809140B (en) |
Families Citing this family (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107991243B (en) * | 2016-10-27 | 2020-06-19 | 核工业北京地质研究院 | High-altitude area water body extraction method based on aviation hyperspectral remote sensing data |
| CN106778629B (en) * | 2016-12-21 | 2020-07-03 | 中国科学院深圳先进技术研究院 | Greenhouse identification method and device |
| CN106650812B (en) * | 2016-12-27 | 2019-08-06 | 辽宁工程技术大学 | A kind of urban water-body extracting method of satellite remote-sensing image |
| CN108333148B (en) * | 2018-01-11 | 2020-12-01 | 中国科学院遥感与数字地球研究所 | Method and device for identifying black and odorous water body |
| CN108647704B (en) * | 2018-04-20 | 2019-11-22 | 北京英视睿达科技有限公司 | A kind of information acquisition method, device, computer equipment and readable storage medium storing program for executing |
| CN109325973B (en) * | 2018-11-19 | 2020-11-24 | 珠江水利委员会珠江水利科学研究院 | Urban river network area water body atmosphere correction method |
| CN109635765B (en) * | 2018-12-19 | 2023-08-29 | 海南空天信息研究院 | Automatic extraction method for remote sensing information of shallow sea coral reef |
| CN109934095A (en) * | 2019-01-22 | 2019-06-25 | 中交信息技术国家工程实验室有限公司 | A kind of remote sensing images Clean water withdraw method and system based on deep learning |
| CN110208193B (en) * | 2019-05-09 | 2021-11-26 | 航天恒星科技有限公司 | Coral reef integrated monitoring method based on optical remote sensing satellite images |
| CN110399860B (en) * | 2019-08-02 | 2021-04-09 | 吉林高分遥感应用研究院有限公司 | Corn flood monitoring method and system |
| CN110703244B (en) * | 2019-09-05 | 2023-08-04 | 中国科学院遥感与数字地球研究所 | Method and device for identifying urban water body based on remote sensing data |
| CN111626965B (en) * | 2020-06-04 | 2021-03-16 | 成都星时代宇航科技有限公司 | Remote sensing image processing method, device, electronic equipment and storage medium |
| CN111914686B (en) * | 2020-07-15 | 2022-10-18 | 云南电网有限责任公司带电作业分公司 | SAR remote sensing image water area extraction method, device and system based on surrounding area association and pattern recognition |
| CN113433075B (en) * | 2021-05-08 | 2022-06-14 | 中科海慧（天津）科技有限公司 | Simple remote sensing rapid monitoring method for black and odorous water body |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103914692A (en) * | 2014-04-21 | 2014-07-09 | 山东科技大学 | Remote sensing recognition method for surface water systems around coal mine |
| CN105139015A (en) * | 2015-07-24 | 2015-12-09 | 河海大学 | Method for extracting water body from remote sensing image |
| CN105243367A (en) * | 2015-10-12 | 2016-01-13 | 水利部水利信息中心 | Method and device for monitoring scope of water body based on satellite remote sensing data |
-
2016
- 2016-03-18 CN CN201610156982.2A patent/CN105809140B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103914692A (en) * | 2014-04-21 | 2014-07-09 | 山东科技大学 | Remote sensing recognition method for surface water systems around coal mine |
| CN105139015A (en) * | 2015-07-24 | 2015-12-09 | 河海大学 | Method for extracting water body from remote sensing image |
| CN105243367A (en) * | 2015-10-12 | 2016-01-13 | 水利部水利信息中心 | Method and device for monitoring scope of water body based on satellite remote sensing data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105809140A (en) | 2016-07-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105809140B (en) | A kind of extracting method and its device of the surface water body information based on Remote Sensing Model | |
| Yun et al. | Individual tree crown segmentation from airborne LiDAR data using a novel Gaussian filter and energy function minimization-based approach | |
| Lu | The potential and challenge of remote sensing‐based biomass estimation | |
| Hirata et al. | Estimation of aboveground biomass in mangrove forests using high-resolution satellite data | |
| Czerwinski et al. | Mapping forest growth and decline in a temperate mixed forest using temporal trend analysis of Landsat imagery, 1987–2010 | |
| Mack | Landscape as a predictor of wetland condition: an evaluation of the landscape development index (LDI) with a large reference wetland dataset from Ohio | |
| Tornos et al. | Assessment of MODIS spectral indices for determining rice paddy agricultural practices and hydroperiod | |
| Aguiar et al. | Riparian vegetation metrics as tools for guiding ecological restoration in riverscapes | |
| CN106125091A (en) | The city impervious surface Remotely sensed acquisition method that line spectrum solution is mixed | |
| CN105184251B (en) | A kind of recognition methods in the wawter bloom region based on high score No.1 satellite image and device | |
| Shouse et al. | Identification of understory invasive exotic plants with remote sensing in urban forests | |
| Lu et al. | Detection of urban expansion in an urban-rural landscape with multitemporal QuickBird images | |
| Karna | Mapping above ground carbon using worldview satellite image and lidar data in relationship with tree diversity of forests | |
| CN116012723A (en) | Wetland type extraction method and device based on time sequence remote sensing image and electronic equipment | |
| Yuan et al. | Remote detection of ecosystem degradation in the Everglades ridge-slough landscape | |
| Mustafa et al. | RETRACTED: Water surface area detection using remote sensing temporal data processed using MATLAB | |
| CN107121681A (en) | Residential area extraction system based on high score satellite remote sensing date | |
| CN107239886B (en) | GDP density analysis system based on high-resolution satellite remote sensing data | |
| Chen et al. | Mapping center pivot irrigation systems in global arid regions using instance segmentation and analyzing their spatial relationship with freshwater resources | |
| Bernasconi et al. | Automatic extraction of land cover statistics from satellite imagery by deep learning | |
| Beltran-Abaunza | Method development to process hyper-temporal remote sensing (RS) images for change mapping | |
| Liu et al. | Mapping the number of mangrove trees in the Guangdong-Hong Kong-Macao Greater Bay Area | |
| Chen et al. | Rice recognition using multi-temporal and dual polarized synthetic aperture radar images | |
| Singh | Forest structure and biomass in a mixed forest-oil palm landscape in Borneo | |
| Mariz et al. | Fusion of multi‐spectral SPOT‐5 images and very high resolution texture information extracted from digital orthophotos for automatic classification of complex Alpine areas |
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 |