CN105809140A - Method and device for extracting surface water body information based on remote sensing model - Google Patents
Method and device for extracting surface water body information based on remote sensing model Download PDFInfo
- Publication number
- CN105809140A CN105809140A CN201610156982.2A CN201610156982A CN105809140A CN 105809140 A CN105809140 A CN 105809140A CN 201610156982 A CN201610156982 A CN 201610156982A CN 105809140 A CN105809140 A CN 105809140A
- Authority
- CN
- China
- Prior art keywords
- remote sensing
- remotely
- water body
- correction
- image data
- 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
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 embodiment of the invention discloses a method and a device for extracting surface water body information based on a remote sensing model. The method comprises the following steps: acquiring remote sensing image data; preprocessing the remote sensing image data to obtain processed remote sensing data; setting a corresponding threshold value for the processed remote sensing data; performing binarization processing on the processed remote sensing data according to the threshold value to obtain processed binarization remote sensing data; and extracting the surface water body information according to the processed binarization remote sensing data. Through adoption of the method and the device, the water body information is enhanced gradually; the water body information extraction accuracy and speed are increased; and the problems of incapability of completely restraining background information which is irrelevant to a water body, low extraction accuracy, high time consumption and the like in the prior art are solved.
Description
Technical field
The present invention relates to technical field of information processing, particularly relate to extracting method and the device thereof of a kind of surface water body information based on Remote Sensing Model.
Background technology
Satellite remote sensing technology plays an important role with the plurality of advantages such as real-time, accurate and macroscopical in environmental monitoring, resource investigation, the various fields such as prevent and reduce natural disasters.Utilize remote sensing technology monitoring water quality change, Coastline Changes and flood floods natural disaster etc., be widely used.The research of water body be unable to do without extracts coverage of water, scope, distribution, the accurate of boundary line, and this is particularly significant to change of water quality monitoring, Coastline Changes monitoring, the monitoring of flood floods and hazards entropy.
20 century 70s start, both at home and abroad just to multispectral sensor-based system (Mu1tispectralSensingSystem, MSS) four wave bands carry out water body Remote Sensing Study, along with developing rapidly of optical remote sensing, LandsatTM/ETM+, SPOT, the lift-off of the sensor sequential transmissions such as MODIS and data universal, optical remote sensing Clean water withdraw method is broadly divided into single band method and multiband method, wherein, single band method utilizes water body and other atural objects absorption contrast near infrared band place to carry out Clean water withdraw, the shade that the method is very difficult to dewater in body to be mixed with, and during flood, increase the confusion with surrounding atural object, so be often combined use with additive method;Multiband method is divided into again spectrum-photometric method and band ratio method etc., and spectrum-photometric method, by the spectral profile feature of analyzing water body with non-water body atural object, is found out its variation relation and then utilizes expression formula Clean water withdraw out, and complexity is higher.Ratio rule is according to different land types wave spectrum feature extraction Water-Body Information in different-waveband, and the method calculates simple and quick.As being advantageous for suppressing vegetation information divided by the simple ratio computing of near infrared band with green glow or red spectral band, strengthen Water-Body Information.But this method cannot thoroughly suppress the background information unrelated with water body.
Normalized ratio type index method is the basis of common Clean water withdraw method.The method is to look for most strong reflection wave band corresponding to target and the most weak reflected waveband in multispectral data, then as molecule, the numerical value of most strong reflection wave band is carried out ratio as the numerical value of denominator, the most weak reflected waveband, then data is normalized.The method that the use normalized ratio type index method that normalization difference water body index (NormalizedDifferenceVegetationWaterIndex, NDWI) is common extracts Water-Body Information.Owing to the reflection of water body weakens gradually from visible ray to middle-infrared band, within the scope of near-infrared and middle infrared wavelength, absorbability is the strongest, and almost without reflection, the NDWI therefore constituted by the contrast of visible light wave range and near infrared band can highlight the Water-Body Information in image.Generally the strongest at the reflectance of near infrared band additionally, due to vegetation, therefore adopt the ratio of green light band and near infrared band can farthest suppress the information of vegetation, thus reaching the purpose of prominent Water-Body Information.
Normalization difference water body index (MNDWI) that middle-infrared band replaces the improvement that near infrared band is constituted is utilized to can be used for quick, easy and extract Water-Body Information exactly.Its NDWI index than Mcfeeters has wider application scope.MNDWI, except the same with NDWI, can be used for beyond the Clean water withdraw of vegetation region, it is also possible to for extracting the Water-Body Information in town-wide accurately.And NDWI is owing to containing the noise of many building informations in its Water-Body Information extracted, have impact on extraction accuracy.It is accordingly difficult to for the water body information within the scope of built-up areas, cities and towns.
Under many circumstances, being still mingled with many non-Water-Body Informations with in the NDWI Water-Body Information extracted, particularly within the scope of extraction, in the Clean water withdraw in city, effect is very undesirable.Therefore, it is proposed to normalization difference water body index (MNDWI) improved, major part obtains the effect better than NDWI, particularly extracts the water body in town-wide.But, in the place that the higher vegetation of landform is more, still carry non-Water-Body Information secretly, such as massif shade.Meanwhile, due to the index results calculated, generally requiring artificial threshold value screening, although process is simple but consuming time, this process usually contains factor and individual subjective factor simultaneously: namely different people, and the threshold value result drawn is different.
Summary of the invention
It is an object of the invention to overcome the deficiencies in the prior art, the invention provides the extracting method of a kind of surface water body information based on Remote Sensing Model and device thereof, solve the background information that cannot thoroughly suppress unrelated with water body in prior art, and the problem such as extraction accuracy is low, consuming time.
In order to solve the problems referred to above, the present invention proposes the extracting method of a kind of surface water body information based on Remote Sensing Model, and described method includes:
Obtain remote sensing image data;
Described remote sensing image data is carried out data prediction, it is thus achieved that the remotely-sensed data after process;
The threshold value of correspondence is set for the remotely-sensed data after described process;
According to described threshold value, the remotely-sensed data after described process is carried out binary conversion treatment, it is thus achieved that the binaryzation remotely-sensed data after process;
Surface water body information retrieval is carried out according to the binaryzation remotely-sensed data after described process.
Preferably, described described remote sensing image data is carried out data prediction, it is thus achieved that the step of the remotely-sensed data after process, including:
Described remote sensing image data is carried out Data correction, it is thus achieved that the remote sensing image data after correction;
According to normalized differential vegetation index NDVI, the remote sensing image data after correction is carried out vegetation information normalized, it is thus achieved that the NDVI remotely-sensed data after process;
According to normalization difference water body index NDWI, the remote sensing image data after correction is carried out Water-Body Information normalized, it is thus achieved that the NDWI remotely-sensed data after process;
According to revising normalization difference water body index MNDWI, the remote sensing image data after correction is carried out Water-Body Information normalized, it is thus achieved that the MNDWI remotely-sensed data after process.
Preferably, the described step that described remote sensing image data is carried out Data correction, including:
According to linear regression radiant correction and FLAASH atmospheric correction mode, described remote sensing image data is carried out Data correction.
Preferably, described according to normalized differential vegetation index NDVI to correction after remote sensing image data carry out vegetation information normalized, it is thus achieved that the step of the NDVI remotely-sensed data after process, including:
According to normalized differential vegetation index NDVI=(NIR-R)/(NIR+R), the remote sensing image data after correction is carried out vegetation information normalized, it is thus achieved that the NDVI remotely-sensed data after process;Wherein, R represents red spectral band, and NIR represents near infrared band.
Preferably, described according to normalization difference water body index NDWI to correction after remote sensing image data carry out Water-Body Information normalized, it is thus achieved that the step of the NDWI remotely-sensed data after process, including:
According to normalization difference water body index NDWI=(Green-NIR)/(Green+NIR), the remote sensing image data after correction is carried out Water-Body Information normalized, it is thus achieved that the NDWI remotely-sensed data after process;Wherein, Green represents green light band, and NIR represents near infrared band.
Preferably, described according to revise normalization difference water body index MNDWI to correction after remote sensing image data carry out Water-Body Information normalized, it is thus achieved that the step of the MNDWI remotely-sensed data after process, including:
According to revising normalization difference water body index MNDWI=(Green-MIR)/(Green+MIR), the remote sensing image data after correction is carried out Water-Body Information normalized, it is thus achieved that the MNDWI remotely-sensed data after process;Wherein, Green represents green light band;MIR represents middle-infrared band.
Preferably, according to described threshold value, the remotely-sensed data after described process is carried out binary conversion treatment, it is thus achieved that the binaryzation remotely-sensed data after process
Correspondingly, the present invention also provides for the extraction element of a kind of surface water body information based on Remote Sensing Model, and described device includes:
Acquisition module, is used for obtaining remote sensing image data;
Pretreatment module, for carrying out data prediction to the remote sensing image data that described acquisition module is acquired, it is thus achieved that the remotely-sensed data after process;
Module is set, corresponding threshold value is set for the remotely-sensed data after handled by described pretreatment module;
Binarization block, for carrying out binary conversion treatment according to the described threshold value arranged set by module to the remotely-sensed data after described process, it is thus achieved that the binaryzation remotely-sensed data after process;
Extraction module, carries out surface water body information retrieval for the binaryzation remotely-sensed data after processing according to described binarization block.
Preferably, described pretreatment module includes:
Correction unit, for carrying out Data correction to described remote sensing image data, it is thus achieved that the remote sensing image data after correction;
NDVI processing unit, for carrying out vegetation information normalized according to normalized differential vegetation index NDVI to the remote sensing image data after correction, it is thus achieved that the NDVI remotely-sensed data after process;
NDWI processing unit, for carrying out Water-Body Information normalized according to normalization difference water body index NDWI to the remote sensing image data after correction, it is thus achieved that the NDWI remotely-sensed data after process;
MNDWI processing unit, for carrying out Water-Body Information normalized according to correction normalization difference water body index MNDWI to the remote sensing image data after correction, it is thus achieved that the MNDWI remotely-sensed data after process.
Preferably, described NDVI processing unit is for carrying out vegetation information normalized according to normalized differential vegetation index NDVI=(NIR-R)/(NIR+R) to the remote sensing image data after correction, it is thus achieved that the NDVI remotely-sensed data after process;Wherein, R represents red spectral band, and NIR represents near infrared band;
Described NDWI processing unit is for carrying out Water-Body Information normalized according to normalization difference water body index NDWI=(Green-NIR)/(Green+NIR) to the remote sensing image data after correction, it is thus achieved that the NDWI remotely-sensed data after process;Wherein, Green represents green light band, and NIR represents near infrared band;
Described MNDWI processing unit is for carrying out Water-Body Information normalized according to correction normalization difference water body index MNDWI=(Green-MIR)/(Green+MIR) to the remote sensing image data after correction, it is thus achieved that the MNDWI remotely-sensed data after process;Wherein, Green represents green light band;MIR represents middle-infrared band.
In embodiments of the present invention, by index is normalized, sets again through threshold value, extract Water-Body Information, isolate the information of the atural objects such as massif shade, vegetation and building;Isolate result to three further and carry out the superposition of enhanced, the information of the atural objects such as progressive rejecting massif shade, vegetation and building, progressively enhance Water-Body Information, Clean water withdraw information is made to reach higher accuracy rate, faster extraction rate, solve the background information that cannot thoroughly suppress unrelated with water body in prior art, and the problem such as extraction accuracy is low, consuming time.
Accompanying drawing explanation
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, the accompanying drawing used required in embodiment or description of the prior art will be briefly described below, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the premise not paying creative work, it is also possible to obtain other accompanying drawing according to these accompanying drawings.
Fig. 1 is the schematic flow sheet 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 schematic flow sheet that remote sensing image data carries out in the embodiment of the present invention data prediction;
Fig. 3 a to 3f is water spectral characteristics of mean curve chart and the water spectral value range characteristic pattern of the embodiment of the present invention;
Fig. 4 is the structure composition schematic diagram of the extraction element of the surface water body information based on Remote Sensing Model of the embodiment of the present invention.
Detailed description of the invention
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is only a part of embodiment of the present invention, rather than whole embodiments.Based on the embodiment in the present invention, the every other embodiment that those of ordinary skill in the art obtain under not making creative work premise, broadly fall into the scope of protection of the invention.
Fig. 1 is the schematic flow sheet of the extracting method of the surface water body information based on Remote Sensing Model of the embodiment of the present invention, as it is shown in figure 1, the method includes:
S1, obtains remote sensing image data;
S2, carries out data prediction to remote sensing image data, it is thus achieved that the remotely-sensed data after process;
S3, arranges the threshold value of correspondence for the remotely-sensed data after processing;
S4, carries out binary conversion treatment according to threshold value to the remotely-sensed data after processing, it is thus achieved that the binaryzation remotely-sensed data after process;
S5, carries out surface water body information retrieval according to the binaryzation remotely-sensed data after processing.
In S1, obtained the remote sensing image data on earth's surface by TM/ETM+ sensor.
Further, as in figure 2 it is shown, S2 includes:
S21, carries out Data correction to remote sensing image data, it is thus achieved that the remote sensing image data after correction;
S22, carries out vegetation information normalized according to normalized differential vegetation index NDVI to the remote sensing image data after correction, it is thus achieved that the NDVI remotely-sensed data after process;
S23, carries out Water-Body Information normalized according to normalization difference water body index NDWI to the remote sensing image data after correction, it is thus achieved that the NDWI remotely-sensed data after process;
S24, carries out Water-Body Information normalized according to revising normalization difference water body index MNDWI to the remote sensing image data after correction, it is thus achieved that the MNDWI remotely-sensed data after process.
Wherein, S22, S23, S24 can carry out in being embodied as simultaneously.
In S21, according to linear regression radiant correction and FLAASH atmospheric correction mode, remote sensing image data is carried out Data correction.
In S22, according to normalized differential vegetation index NDVI=(NIR-R)/(NIR+R), the remote sensing image data after correction is carried out vegetation information normalized, it is thus achieved that the NDVI remotely-sensed data after process;Wherein, R represents red spectral band, and NIR represents near infrared band.
Normalized differential vegetation index (NDVI) is used to detection vegetation growth state, vegetation coverage and elimination partial radiation error etc..In each band spectrum data of LandSat satellite TM/ETM+ sensor, near infrared band is relatively large to the reflectance of vegetation, and red spectral band is relatively small to the reflectance of vegetation, therefore the near-infrared data of coordinate points each in remotely-sensed data and red spectral band data are subtracted each other, obtain the vegetation index of this coordinate points.For the computing after convenience, using the vegetation index of coordinate points as molecule, that near-infrared data is added with red spectral band data and be calculated as molecule, vegetation index between 1 and-1, namely will be normalized by the coordinate points data obtained.The formula of NDVI is as follows: NDVI=(NIR-R)/(NIR+R);In formula, R represents red spectral band;NIR represents near infrared band.The NDVI remotely-sensed data comprising each pixel on remote sensing images is obtained after calculating.
In S23, according to normalization difference water body index NDWI=(Green-NIR)/(Green+NIR), the remote sensing image data after correction is carried out Water-Body Information normalized, it is thus achieved that the NDWI remotely-sensed data after process;Wherein, Green represents green light band, and NIR represents near infrared band.
Normalization difference water body index (NDWI) is the method using normalized ratio type index method to extract Water-Body Information.Owing to the reflection of water body gradually decreases from visible ray to middle-infrared band, the NDWI constituted by the contrast of visible light wave range and near infrared band can highlight the Water-Body Information in image, general the strongest at the reflectance of near infrared band additionally, due to vegetation, therefore the ratio of green light band and near infrared band is adopted can to suppress the information of vegetation to greatest extent, thus reaching the purpose of prominent Water-Body Information.Therefore the green light band data of coordinate points in remotely-sensed data are deducted the near-infrared data of this coordinate points, obtain the difference water body index of this coordinate points;Then with the difference water body index of this coordinate points divided by this coordinate points green light band data plus near infrared band and to be normalized, thus obtaining the normalization difference water body index of this coordinate points.Its formula is as follows: NDWI=(Green-NIR)/(Green+NIR);In formula, Green represents green light band;NIR represents near infrared band.Obtain comprising the NDWI remotely-sensed data of each pixel on remote sensing images after calculating.
In S24, according to revising normalization difference water body index MNDWI=(Green-MIR)/(Green+MIR), the remote sensing image data after correction is carried out Water-Body Information normalized, it is thus achieved that the MNDWI remotely-sensed data after process;Wherein, Green represents green light band;MIR represents middle-infrared band.
Revising normalization difference water body index (MNDWI) is that the reflectance according to building suddenly turns strong from near-infrared to mid-infrared, and water body continues the rule that drops at the reflectance of middle-infrared band, visible ray is subtracted middle-infrared band, greatly strengthen Water-Body Information and cut down building information.Compared with NDWI, MNDWI is that the green light band data used in remotely-sensed data in coordinate points deduct middle-infrared band data but not near-infrared data, then again by the numerical value after subtracting each other divided by green light band data and middle-infrared band data and to realize normalization, finally obtaining correction normalization difference water body index MNDWI, its formula is as follows: MNDWI=(Green-MIR)/(Green+MIR);In formula, Green represents green light band;MIR represents middle-infrared band.Obtain comprising the MNDWI remotely-sensed data of all pixels on remote sensing images after calculating.
In S4, respectively NDVI data, NDWI data and MNDWI data are carried out binaryzation, the binaryzation remotely-sensed data NDVI after being processed+、NDWI-And MNDWI+Data.
Further, S5 includes:
Water body information Optimized model is obtained according to the binaryzation remotely-sensed data after the remotely-sensed data after processing and process;
Surface water body information retrieval is carried out according to water body information Optimized model.
Below in conjunction with Fig. 3 a-Fig. 3 f, embodiment of the present invention method is further described.Wherein, 3a is water body in lake spectrum characteristics of mean curve chart;3b is water body in lake spectral region value tag figure;3c is river water spectrum characteristics of mean curve chart;3d is river water spectral region value tag figure;3e is fish pond spectrum characteristics of mean curve chart;3f is fish pond spectral region value tag figure.
In being embodied as, the initial data used may be from the TM/ETM+ sensor of the Landsat plan (LandSat) of U.S. NASA, the spatial resolution of remotely-sensed data is 30 meters, and objective area have chosen this main water body of three classes of river, fish pond and lake respectively.
By by artificial judgment pixel type and result and NDVI matrix, NDWI matrix and MNDWI matrix compare and add up, can draw for carrying out in the remotely-sensed data comprising lake, river, fish pond these three type respectively tested, three kinds of exponent datas of the pixel of these three classes landforms of vegetation, building and water body.Analyze in these three remotely-sensed data, the meansigma methods of the NDVI remotely-sensed data of three class landforms, NDWI remotely-sensed data and MNDWI remotely-sensed data and scope of data, spectrum characteristics of mean curve chart and the spectral region characteristic pattern of three class landforms in three kinds of remotely-sensed datas can be obtained, as illustrated in figs. 3 a-f.
Can analyze according to spectrum characteristics of mean curve chart and spectral region characteristic pattern, although the average of water body differs bigger with the average of the non-water bodys such as vegetation in MNDWI remotely-sensed data, but the MNDWI remotely-sensed data also having fraction part water body is identical close with the MNDWI remotely-sensed data of the non-water body such as vegetation, building, it is therefore desirable to remove the non-water body part in MNDWI remotely-sensed data by NDVI remotely-sensed data and NDWI remotely-sensed data.Value range characteristic profile in Fig. 3 b, 3d and 3f is visible:
(1) it is 0 when NDVI remotely-sensed data arranges threshold value, vegetation and non-vegetation can be separated out preferably.Wherein mainly include water body and major part building less than the part of threshold value, because water body is of a relatively high to the reflectance of visible ray;Vegetation, fraction building and fraction water body is mainly included more than threshold portion.
(2) it is 0 when NDWI remotely-sensed data arranges threshold value, water body and non-water body can be separated out preferably.NDWI remotely-sensed data mainly includes small part water body, overwhelming majority vegetation and major part building less than the part of threshold value;NDWI remotely-sensed data includes major part water body, small part building more than the part of threshold value.
(3) it is 0 when MNDWI remotely-sensed data arranges threshold value, water body and non-water body can be separated out preferably.Wherein mainly include small part water body, major part building and most vegetation less than the part of threshold value;Overwhelming majority water body, small part vegetative coverage and small part building is mainly included more than the part of threshold value.
After determining threshold value, it is necessary to NDVI remotely-sensed data, NDWI remotely-sensed data and MNDWI remotely-sensed data are carried out binaryzation.The binaryzation of data be by the data of each coordinate points in NVDI, NDWI and MNDWI remotely-sensed data according to it has been determined that threshold value and certain rule judge, original data are converted into the matrix only comprising 0 or 1.The binaryzation of data is conducive to next step calculation process, makes data become simple, and data volume reduces, it is possible to effectively reduce operand, improving operational speed.
After respectively NDVI remotely-sensed data, NDWI remotely-sensed data and MNDWI remotely-sensed data being carried out binaryzation, obtain NDVI+、NDWI-And MNDWI+Data, wherein:
NDVI+It is that the part more than threshold value in NDVI remotely-sensed data is taken 1, takes 0 less than or equal to the part of threshold value, namely vegetation higher to vegetation, fraction building and water content is set to 1, water body is set to 0 with major part building.
NDWI-It is that part more than threshold value in NDWI remotely-sensed data is taken 0, takes 1 less than or equal to the part of threshold value, namely major part water body, part building are set to 0, vegetation is set to 1 with major part building.
MNDWI+It is that part more than threshold value in MNDWI remotely-sensed data is taken 1, takes 0 less than or equal to the part of threshold value, namely the vegetation of water body and very small part and building are set to 1, overwhelming majority vegetation and building are set to 0.
The final step of Clean water withdraw computing is carried out after completing binaryzation.By MNDWI+Deduct NDVI+Deduct NDWI again-If the data obtained are 1, are judged as water body, it is judged as non-water body if less than 1.Formula is as follows:
Water body information Optimized model=MNDWI+-NDVI+-NDWI-
By MNDWI in water body information Optimized model+Deduct NDVI+If, it is meant that MNDWI+Middle numerical value is that the pixel of 1 is at NDVI+In be also 1, then can be removed, also just eliminate MNDWI+Middle numerical value is the pixel that reality is vegetation of 1.Deduct NDWI again-, it is meant that MNDWI+If the pixel that numerical value is 1 is at NDWI-Also it is 1, then can be removed, also just eliminate MNDWI+In remaining fraction building.
Water body information Optimized model can solve NDVI, NDWI, MNDWI method Problems existing preferably, can distinguish the non-Water-Body Informations such as building, vegetation, massif shade preferably, substantially increase NDVI, NDWI, MNDWI index Clean water withdraw precision.Result shows: in lake, fish pond two groups test, the progressive enhancing model method overall accuracy conventional than three kinds improves more than 13%, overall kappa coefficient improves more than 0.26, and the method overall accuracy that progressive enhancing model is more conventional than three kinds in river water test improves more than 1%, overall kappa coefficient improves more than 0.02.It addition, water body information Optimized model can arrange unified segmentation threshold, the full-automatic offer for magnanimity Remote Sensing water body information process is supported.
Correspondingly, the embodiment of the present invention also provides for the extraction element of a kind of surface water body information based on Remote Sensing Model, and as shown in Figure 4, this device includes:
Acquisition module 1, is used for obtaining remote sensing image data;
Pretreatment module 2, for carrying out data prediction to the remote sensing image data that acquisition module 1 is acquired, it is thus achieved that the remotely-sensed data after process;
Module 3 is set, corresponding threshold value is set for the remotely-sensed data after handled by pretreatment module 2;
Binarization block 4, for carrying out binary conversion treatment according to the threshold value arranged set by module 3 to the remotely-sensed data after processing, it is thus achieved that the binaryzation remotely-sensed data after process;
Extraction module 5, carries out surface water body information retrieval for the binaryzation remotely-sensed data after processing according to binarization block 4.
In being embodied as, acquisition module can be TM/ETM+ sensor, for obtaining the remote sensing image data on earth's surface
Further, pretreatment module 2 includes:
Correction unit, for carrying out Data correction to remote sensing image data, it is thus achieved that the remote sensing image data after correction;Specifically, according to linear regression radiant correction and FLAASH atmospheric correction mode, remote sensing image data is carried out Data correction;
NDVI processing unit, for carrying out vegetation information normalized according to normalized differential vegetation index NDVI to the remote sensing image data after correction, it is thus achieved that the NDVI remotely-sensed data after process;
NDWI processing unit, for carrying out Water-Body Information normalized according to normalization difference water body index NDWI to the remote sensing image data after correction, it is thus achieved that the NDWI remotely-sensed data after process;
MNDWI processing unit, for carrying out Water-Body Information normalized according to correction normalization difference water body index MNDWI to the remote sensing image data after correction, it is thus achieved that the MNDWI remotely-sensed data after process.
In being embodied as, NDVI processing unit is for carrying out vegetation information normalized according to normalized differential vegetation index NDVI=(NIR-R)/(NIR+R) to the remote sensing image data after correction, it is thus achieved that the NDVI remotely-sensed data after process;Wherein, R represents red spectral band, and NIR represents near infrared band;
NDWI processing unit is for carrying out Water-Body Information normalized according to normalization difference water body index NDWI=(Green-NIR)/(Green+NIR) to the remote sensing image data after correction, it is thus achieved that the NDWI remotely-sensed data after process;Wherein, Green represents green light band, and NIR represents near infrared band;
MNDWI processing unit is for carrying out Water-Body Information normalized according to correction normalization difference water body index MNDWI=(Green-MIR)/(Green+MIR) to the remote sensing image data after correction, it is thus achieved that the MNDWI remotely-sensed data after process;Wherein, Green represents green light band;MIR represents middle-infrared band.
Binarization block 4 is further used for respectively NDVI data, NDWI data and MNDWI data being carried out binaryzation, the binaryzation remotely-sensed data NDVI after being processed+、NDWI-And MNDWI+Data.
In assembly of the invention embodiment, the function of each functional module referring to the flow processing in the inventive method embodiment, can repeat no more here.
In embodiments of the present invention, by index is normalized, sets again through threshold value, extract Water-Body Information, isolate the information of the atural objects such as massif shade, vegetation and building;Isolate result to three further and carry out the superposition of enhanced, the information of the atural objects such as progressive rejecting massif shade, vegetation and building, progressively enhance Water-Body Information, Clean water withdraw information is made to reach higher accuracy rate, faster extraction rate, solve the background information that cannot thoroughly suppress unrelated with water body in prior art, and the problem such as extraction accuracy is low, consuming time.
One of ordinary skill in the art will appreciate that all or part of step in the various methods of above-described embodiment can be by the hardware that program carrys out instruction relevant and completes, this program can be stored in a computer-readable recording medium, storage medium may include that read only memory (ROM, ReadOnlyMemory), random access memory (RAM, RandomAccessMemory), disk or CD etc..
Additionally, extracting method and the device thereof of the surface water body information based on the Remote Sensing Model above embodiment of the present invention provided are described in detail, principles of the invention and embodiment are set forth by specific case used herein, and the explanation of above example is only intended to help to understand method and the core concept thereof of the present invention;Simultaneously for one of ordinary skill in the art, according to the thought of the present invention, all will change in specific embodiments and applications, in sum, this specification content should not be construed as limitation of the present invention.
Claims (10)
1. the extracting method based on the surface water body information of Remote Sensing Model, it is characterised in that described method includes:
Obtain remote sensing image data;
Described remote sensing image data is carried out data prediction, it is thus achieved that the remotely-sensed data after process;
The threshold value of correspondence is set for the remotely-sensed data after described process;
According to described threshold value, the remotely-sensed data after described process is carried out binary conversion treatment, it is thus achieved that the binaryzation remotely-sensed data after process;
Surface water body information retrieval is carried out according to the binaryzation remotely-sensed data after described process.
2. the extracting method of the surface water body information based on Remote Sensing Model as claimed in claim 1, it is characterised in that described described remote sensing image data is carried out data prediction, it is thus achieved that the step of the remotely-sensed data after process, including:
Described remote sensing image data is carried out Data correction, it is thus achieved that the remote sensing image data after correction;
According to normalized differential vegetation index NDVI, the remote sensing image data after correction is carried out vegetation information normalized, it is thus achieved that the NDVI remotely-sensed data after process;
According to normalization difference water body index NDWI, the remote sensing image data after correction is carried out Water-Body Information normalized, it is thus achieved that the NDWI remotely-sensed data after process;
According to revising normalization difference water body index MNDWI, the remote sensing image data after correction is carried out Water-Body Information normalized, it is thus achieved that the MNDWI remotely-sensed data after process.
3. the extracting method of the surface water body information based on Remote Sensing Model as claimed in claim 2, it is characterised in that the described step that described remote sensing image data is carried out Data correction, including:
According to linear regression radiant correction and FLAASH atmospheric correction mode, described remote sensing image data is carried out Data correction.
4. the extracting method of the surface water body information based on Remote Sensing Model as claimed in claim 2, it is characterized in that, described according to normalized differential vegetation index NDVI to correction after remote sensing image data carry out vegetation information normalized, it is thus achieved that the step of the NDVI remotely-sensed data after process, including:
According to normalized differential vegetation index NDVI=(NIR-R)/(NIR+R), the remote sensing image data after correction is carried out vegetation information normalized, it is thus achieved that the NDVI remotely-sensed data after process;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, it is characterized in that, described according to normalization difference water body index NDWI to correction after remote sensing image data carry out Water-Body Information normalized, it is thus achieved that the step of the NDWI remotely-sensed data after process, including:
According to normalization difference water body index NDWI=(Green-NIR)/(Green+NIR), the remote sensing image data after correction is carried out Water-Body Information normalized, it is thus achieved that the NDWI remotely-sensed data after process;Wherein, Green represents green light band, and NIR represents near infrared band.
6. the extracting method of the surface water body information based on Remote Sensing Model as claimed in claim 2, it is characterized in that, described according to revise normalization difference water body index MNDWI to correction after remote sensing image data carry out Water-Body Information normalized, the step of the MNDWI remotely-sensed data after acquisition process, including:
According to revising normalization difference water body index MNDWI=(Green-MIR)/(Green+MIR), the remote sensing image data after correction is carried out Water-Body Information normalized, it is thus achieved that the MNDWI remotely-sensed data after process;Wherein, Green represents green light band;MIR represents middle-infrared band.
7. the extracting method of the surface water body information based on Remote Sensing Model as claimed in claim 1, it is characterised in that described carry out the step of surface water body information retrieval according to the binaryzation remotely-sensed data after described process and include:
Water body information Optimized model is obtained according to the binaryzation remotely-sensed data after the remotely-sensed data after processing and process;
Surface water body information retrieval is carried out according to described water body information Optimized model.
8. the extraction element based on the surface water body information of Remote Sensing Model, it is characterised in that described device includes:
Acquisition module, is used for obtaining remote sensing image data;
Pretreatment module, for carrying out data prediction to the remote sensing image data that described acquisition module is acquired, it is thus achieved that the remotely-sensed data after process;
Module is set, corresponding threshold value is set for the remotely-sensed data after handled by described pretreatment module;
Binarization block, for carrying out binary conversion treatment according to the described threshold value arranged set by module to the remotely-sensed data after described process, it is thus achieved that the binaryzation remotely-sensed data after process;
Extraction module, carries out surface water body information retrieval for the binaryzation remotely-sensed data after processing according to described binarization block.
9. the extraction element of the surface water body information based on Remote Sensing Model as claimed in claim 8, it is characterised in that described pretreatment module includes:
Correction unit, for carrying out Data correction to described remote sensing image data, it is thus achieved that the remote sensing image data after correction;
NDVI processing unit, for carrying out vegetation information normalized according to normalized differential vegetation index NDVI to the remote sensing image data after correction, it is thus achieved that the NDVI remotely-sensed data after process;
NDWI processing unit, for carrying out Water-Body Information normalized according to normalization difference water body index NDWI to the remote sensing image data after correction, it is thus achieved that the NDWI remotely-sensed data after process;
MNDWI processing unit, for carrying out Water-Body Information normalized according to correction normalization difference water body index MNDWI to the remote sensing image data after correction, it is thus achieved that the MNDWI remotely-sensed data after process.
10. the extraction element of the surface water body information based on Remote Sensing Model as claimed in claim 9, it is characterised in that
Described NDVI processing unit is for carrying out vegetation information normalized according to normalized differential vegetation index NDVI=(NIR-R)/(NIR+R) to the remote sensing image data after correction, it is thus achieved that the NDVI remotely-sensed data after process;Wherein, R represents red spectral band, and NIR represents near infrared band;
Described NDWI processing unit is for carrying out Water-Body Information normalized according to normalization difference water body index NDWI=(Green-NIR)/(Green+NIR) to the remote sensing image data after correction, it is thus achieved that the NDWI remotely-sensed data after process;Wherein, Green represents green light band, and NIR represents near infrared band;
Described MNDWI processing unit is for carrying out Water-Body Information normalized according to correction normalization difference water body index MNDWI=(Green-MIR)/(Green+MIR) to the remote sensing image data after correction, it is thus achieved that the MNDWI remotely-sensed data after process;Wherein, Green represents green light band;MIR represents middle-infrared band.
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 true CN105809140A (en) | 2016-07-27 |
CN105809140B 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) |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106650812A (en) * | 2016-12-27 | 2017-05-10 | 辽宁工程技术大学 | City water body extraction method for satellite remote sensing image |
CN106778629A (en) * | 2016-12-21 | 2017-05-31 | 中国科学院深圳先进技术研究院 | Greenhouse recognition methods and device |
CN107991243A (en) * | 2016-10-27 | 2018-05-04 | 核工业北京地质研究院 | A kind of high altitude localities Clean water withdraw method based on Airborne Hyperspectral remotely-sensed data |
CN108333148A (en) * | 2018-01-11 | 2018-07-27 | 中国科学院遥感与数字地球研究所 | A kind of recognition methods of black and odorous water and device |
CN108647704A (en) * | 2018-04-20 | 2018-10-12 | 北京英视睿达科技有限公司 | The information acquisition method and device merged with related coefficient based on NDBI |
CN109325973A (en) * | 2018-11-19 | 2019-02-12 | 珠江水利委员会珠江水利科学研究院 | A kind of city river network water body atmospheric correction method |
CN109635765A (en) * | 2018-12-19 | 2019-04-16 | 三亚中科遥感研究所 | A kind of shallow sea coral reef remote sensing information extraction method |
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 |
CN110208193A (en) * | 2019-05-09 | 2019-09-06 | 航天恒星科技有限公司 | A kind of coral reef integration monitoring method based on Optical remote satellite image |
CN110399860A (en) * | 2019-08-02 | 2019-11-01 | 吉林高分遥感应用研究院有限公司 | A kind of corn damage caused by waterlogging monitoring method and system |
CN110703244A (en) * | 2019-09-05 | 2020-01-17 | 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 |
CN111626965A (en) * | 2020-06-04 | 2020-09-04 | 成都星时代宇航科技有限公司 | Remote sensing image processing method, device, electronic equipment and storage medium |
CN111914686A (en) * | 2020-07-15 | 2020-11-10 | 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 |
CN112507763A (en) * | 2019-09-16 | 2021-03-16 | 中科星图股份有限公司 | Water body extraction method and system based on multi-source multi-spectral remote sensing image and readable storage medium |
CN113433075A (en) * | 2021-05-08 | 2021-09-24 | 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 |
Cited By (23)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107991243A (en) * | 2016-10-27 | 2018-05-04 | 核工业北京地质研究院 | A kind of high altitude localities Clean water withdraw method based on Airborne Hyperspectral remotely-sensed data |
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 |
CN106778629A (en) * | 2016-12-21 | 2017-05-31 | 中国科学院深圳先进技术研究院 | Greenhouse recognition methods and device |
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 |
CN106650812A (en) * | 2016-12-27 | 2017-05-10 | 辽宁工程技术大学 | City water body extraction method for satellite remote sensing image |
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 |
CN108333148A (en) * | 2018-01-11 | 2018-07-27 | 中国科学院遥感与数字地球研究所 | A kind of recognition methods of black and odorous water and device |
CN108647704A (en) * | 2018-04-20 | 2018-10-12 | 北京英视睿达科技有限公司 | The information acquisition method and device merged with related coefficient based on NDBI |
CN109325973A (en) * | 2018-11-19 | 2019-02-12 | 珠江水利委员会珠江水利科学研究院 | A kind of city river network water body atmospheric correction method |
CN109635765A (en) * | 2018-12-19 | 2019-04-16 | 三亚中科遥感研究所 | A kind of shallow sea coral reef remote sensing information extraction 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 |
CN110208193A (en) * | 2019-05-09 | 2019-09-06 | 航天恒星科技有限公司 | A kind of coral reef integration monitoring method based on Optical remote satellite image |
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 |
CN110399860A (en) * | 2019-08-02 | 2019-11-01 | 吉林高分遥感应用研究院有限公司 | A kind of corn damage caused by waterlogging 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 |
CN110703244A (en) * | 2019-09-05 | 2020-01-17 | 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 |
CN112507763A (en) * | 2019-09-16 | 2021-03-16 | 中科星图股份有限公司 | Water body extraction method and system based on multi-source multi-spectral remote sensing image and readable storage medium |
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 |
CN111626965A (en) * | 2020-06-04 | 2020-09-04 | 成都星时代宇航科技有限公司 | Remote sensing image processing method, device, electronic equipment and storage medium |
CN111914686A (en) * | 2020-07-15 | 2020-11-10 | 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 |
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 |
CN113433075A (en) * | 2021-05-08 | 2021-09-24 | 中科海慧(天津)科技有限公司 | Simple remote sensing rapid monitoring method for black and odorous water body |
Also Published As
Publication number | Publication date |
---|---|
CN105809140B (en) | 2019-07-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105809140A (en) | Method and device for extracting surface water body information based on remote sensing model | |
CN111274865B (en) | Remote sensing image cloud detection method and device based on full convolution neural network | |
CN103400151B (en) | The optical remote sensing image of integration and GIS autoregistration and Clean water withdraw method | |
Haibo et al. | Water body extraction methods study based on RS and GIS | |
CN111062368B (en) | City update region monitoring method based on Landsat time sequence remote sensing image | |
Lu et al. | Detection of urban expansion in an urban-rural landscape with multitemporal QuickBird images | |
CN109410228A (en) | Internal wave of ocean detection algorithm based on Method Based on Multi-Scale Mathematical Morphology Fusion Features | |
CN112699756B (en) | Hyperspectral image-based tea origin identification method and system | |
CN115439759B (en) | Method and device for extracting vegetation in remote sensing image, electronic equipment and medium | |
CN105184251B (en) | A kind of recognition methods in the wawter bloom region based on high score No.1 satellite image and device | |
CN106650812A (en) | City water body extraction method for satellite remote sensing image | |
CN110458201A (en) | A kind of remote sensing image object-oriented classification method and sorter | |
CN103745453A (en) | Town information extraction method based on Google Earth remote sensing image | |
CN106778629A (en) | Greenhouse recognition methods and device | |
CN116630225B (en) | Method and device for identifying underwater foundation damage of railway bridge and processing equipment | |
CN112507763A (en) | Water body extraction method and system based on multi-source multi-spectral remote sensing image and readable storage medium | |
CN113780307A (en) | Method for extracting blue-green space information with maximum regional year | |
Xue et al. | An automatic shadow detection method for high-resolution remote sensing imagery based on polynomial fitting | |
CN111882573A (en) | Cultivated land plot extraction method and system based on high-resolution image data | |
Duan et al. | An index-based shadow extraction approach on high-resolution images | |
Luo et al. | New deep learning method for efficient extraction of small water from remote sensing images | |
Fan et al. | Estimating the aquatic-plant area on a pond surface using a hue-saturation-component combination and an improved Otsu method | |
Mustafa et al. | RETRACTED: Water surface area detection using remote sensing temporal data processed using MATLAB | |
Feng et al. | S2EFT: Spectral-spatial-elevation fusion transformer for hyperspectral image and LiDAR classification | |
Lu et al. | Breast cancer mitotic cell detection using cascade convolutional neural network with U-Net |
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 |