CN107271367A - A kind of identifying water boy method and device - Google Patents
A kind of identifying water boy method and device Download PDFInfo
- Publication number
- CN107271367A CN107271367A CN201710313128.7A CN201710313128A CN107271367A CN 107271367 A CN107271367 A CN 107271367A CN 201710313128 A CN201710313128 A CN 201710313128A CN 107271367 A CN107271367 A CN 107271367A
- Authority
- CN
- China
- Prior art keywords
- water body
- mrow
- identified
- msub
- unit
- 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
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N2021/1793—Remote sensing
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention provides a kind of identifying water boy method and device.This method includes：The water body probabilistic image of multispectral image to be identified is obtained according to the standard water body curve of spectrum；The water body probabilistic image is divided into multiple units to be identified；Object function is constructed for fitness value according to the water body probability for treating each pixel in unit to be identified；Solution is iterated to the object function, the water body of the unit to be identified when obtaining the fitness value maximum is distributed, to carry out identifying water boy to the unit to be identified.The embodiment of the present invention only extracts the information relevant with water body, and non-Water-Body Information is pressed, therefore specific aim is stronger；All spectral band information are considered simultaneously, the reproducibility to Water-Body Information is stronger, there is higher information utilization than water body index (only considering special spectrum wave band), realize and accurate identifying water boy is carried out to a wide range of region.
Description
Technical field
The present invention relates to technical field of remote sensing image processing, and in particular to a kind of identifying water boy method and device.
Background technology
Inland Water drawing is research inland water circulation, especially studies the premise of inland freshwater system.Although internal water
Shared area is smaller (2%~3%) at the earth's surface, but it supports the animal in the whole world 10% and nearly 35% vertebra dynamic
Thing, is played an important role in terms of bio-diversity and ecosystem function is maintained.However, the bio-diversity of internal water is just
Declining rapidly, the ecosystem the most in imminent danger may be turned into the world.Inland water resource is recognized as in global carbon
In play an important role.Developing rapidly for remote sensing technology is observed there is provided possible on a large scale for Inland Water.Since last century
Since the US Terrestrial landsat Landsat transmittings seventies, the satellite remote sensing images data of relevant earth's surface monitoring increase sharply.
The initial identifying water boy method based on visual interpretation is difficult to meet big model because cost of labor is high, expend time length etc.
Enclose the requirement in the fields such as monitoring, the assessment of disaster instantaneity.
The existing identifying water boy classification precision based on supervised classification study is higher, but requires input sample point, sample
This precision is influenceed by priori, and the selection of sample point also has very big workload.Supervised classification charts for zonule
Have no problem, if region is excessive, data volume rises sharply, supervised classification precision can produce larger mistake because of the problem typical of sample
Difference.
Although the existing identifying water boy method based on unsupervised classification study is less by manual intervention, it will can not classify
As a result corresponded with type of ground objects, and far away from supervised classification in terms of stability, nicety of grading.
The content of the invention
The embodiment of the present invention provides a kind of identifying water boy method and device, for solving how to carry out standard to a wide range of region
The problem of true identifying water boy.
The embodiments of the invention provide a kind of identifying water boy method, including：
The water body probabilistic image of multispectral image to be identified is obtained according to the standard water body curve of spectrum；
The water body probabilistic image is divided into multiple units to be identified；
Object function is constructed for fitness value according to the water body probability for treating each pixel in unit to be identified；
Solution, the water of the unit to be identified when the acquisition fitness value is maximum are iterated to the object function
Body is distributed, to carry out identifying water boy to the unit to be identified.
Alternatively, the water body probabilistic image that multispectral image to be identified is obtained according to the standard water body curve of spectrum,
Including：
The curve of spectrum and the standard water spectral respectively to each pixel in the multispectral image to be identified
Curve is normalized；
Obtain the curve of spectrum and standard water body of each pixel in the multispectral image to be identified after normalized
The similarity of the curve of spectrum；
The water body probability of each pixel according to being obtained the similarity of each pixel.
Alternatively, the formula of the object function is as follows：
Wherein, T represents fitness value；c1For constant, the weight of water body part, c are represented2For constant, non-aqueous body portion is represented
Weight, c3For constant, the weight of neighborhood part is represented；Pw,kRepresent that k-th of pixel is the general of water body in the unit to be identified
Rate, Pnw,kRepresent in the unit to be identified the probability that k-th of pixel is non-water body；Represent the unit to be identified
The minimum value of distance between middle each two pixel.
Alternatively, it is described to be iterated solution to the object function, including：
Solution is iterated to the object function using discrete particle cluster algorithm.
The embodiment of the present invention provides a kind of identifying water boy device, including：
Water body probabilistic image acquiring unit, for obtaining multispectral image to be identified according to the standard water body curve of spectrum
Water body probabilistic image；
Image division unit, for the water body probabilistic image to be divided into multiple units to be identified；
Objective function unit, for treating the water body probability of each pixel in unit to be identified for adapting to according to
Angle value constructs object function；
Identifying water boy unit, for being iterated solution to the object function, when the acquisition fitness value is maximum
The water body distribution of the unit to be identified, to carry out identifying water boy to the unit to be identified.
Alternatively, the water body probabilistic image acquiring unit includes：
Normalized module, for respectively to the curve of spectrum of each pixel in the multispectral image to be identified
It is normalized with the standard water body curve of spectrum；
Similarity acquisition module, for obtaining each pixel in the multispectral image to be identified after normalized
The similarity of the curve of spectrum and the standard water body curve of spectrum；
Water body probability acquisition module, the water body for obtaining each pixel according to the similarity of each pixel is general
Rate.
Alternatively, the formula of the object function is as follows：
Wherein, T represents fitness value；c1For constant, the weight of water body part, c are represented2For constant, non-aqueous body portion is represented
Weight, c3For constant, the weight of neighborhood part is represented；Pw,kRepresent that k-th of pixel is the general of water body in the unit to be identified
Rate, Pnw,kRepresent in the unit to be identified the probability that k-th of pixel is non-water body；Represent the unit to be identified
The minimum value of distance between middle each two pixel.
Alternatively, the identifying water boy unit is further used for：
Solution is iterated to the object function using discrete particle cluster algorithm.
The embodiment of the present invention provides a kind of electronic equipment, including：Processor, memory and bus；Wherein,
Processor and memory complete mutual communication by bus；
Processor is used to call the programmed instruction in memory, to perform above-mentioned identifying water boy method.
The embodiment of the present invention provides a kind of non-transient computer readable storage medium storing program for executing, the non-transient computer readable storage
Medium storing computer is instructed, and the computer instruction makes the computer perform above-mentioned identifying water boy method.
Identifying water boy method and device provided in an embodiment of the present invention, multiple waits to know by the way that water body probabilistic image is divided into
Other unit, it is considered to the space connectivity of water body object in unit to be identified, it is final to obtain the two-value point for representing water body and non-water body
Class image.The information relevant with water body is only extracted, non-Water-Body Information is pressed, therefore specific aim is stronger；Consider simultaneously all
Spectral band information, the reproducibility to Water-Body Information is stronger, has than water body index (only considering special spectrum wave band) higher
Information utilization, realize and accurate identifying water boy carried out to a wide range of region, to prevent and reduce natural disasters, climate change, Eco-hydrological
The fields such as process provide support.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
There is the accompanying drawing used required in technology description to be briefly described, it should be apparent that, drawings in the following description are the present invention
Some embodiments, for those of ordinary skill in the art, on the premise of not paying creative work, can also basis
These accompanying drawings obtain other accompanying drawings.
Fig. 1 is the schematic flow sheet of the identifying water boy method of one embodiment of the invention；
Fig. 2 is the structural representation of the identifying water boy device of one embodiment of the invention；
Fig. 3 is the entity structure schematic diagram of the electronic equipment of one embodiment of the invention.
Embodiment
To make the purpose, technical scheme and advantage of the embodiment of the present invention clearer, below in conjunction with the embodiment of the present invention
In accompanying drawing, clear, complete description is carried out to the technical scheme in the embodiment of the present invention, it is clear that described embodiment is
A part of embodiment of the present invention, rather than whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art
The every other embodiment obtained under the premise of creative work is not made, belongs to the scope of protection of the invention.
Fig. 1 is the schematic flow sheet of the method for one embodiment of the invention.As shown in figure 1, the method for the embodiment includes：
S11：The water body probabilistic image of multispectral image to be identified is obtained according to the standard water body curve of spectrum；
It should be noted that the standard spectral curves in the embodiment of the present invention are obtained from typical water body, ripple is represented
The long corresponding relation with reflectivity.In actual applications, Landsat8OLI multispectral images can be used, it would however also be possible to employ other
Multispectral curve, the invention is not limited in this regard.
Water body probability refers to similar between the standard water body curve of spectrum and the curve of spectrum of pixel in multispectral image
Degree.The spectrum of pixel and the similarity of standard spectrum are higher, and probable value is bigger, and the pixel is more likely to be water body.
S12：The water body probabilistic image is divided into multiple units to be identified；
It should be noted that earth's surface is a continuous surface, water body distribution also shows as geographic continuity.In order to characterize
This continuity, water body probabilistic image is divided into multiple units to be identified, the size of each unit to be identified for rows rows and
Cols is arranged.For example, rows and cols all values are 4, then, in 4 × 4 unit to be identified of totally 16 pixels, each pixel
Whether it is that water depends on surrounding other 15 pixels.
S13：Object function is constructed for fitness value according to the water body probability for treating each pixel in unit to be identified；
It should be noted that the embodiment of the present invention constructs object function for fitness value.
S14：Solution is iterated to the object function, the unit to be identified during the fitness value maximum is obtained
Water body distribution, to carry out identifying water boy to the unit to be identified；
It should be noted that multispectral image to be identified includes multiple processing units to be identified, (unit number is depended on
Rows and cols size, rows needs not be equal to cols), each unit to be identified can regard an assorting process as.At this
In assorting process, whether some pixel is optimum results of the water body depending on object function.Assorting process is an iterative process, when
When fitness value reaches maximum, optimal classification result, iteration ends are represented.
Identifying water boy method provided in an embodiment of the present invention, by the way that water body probabilistic image is divided into multiple lists to be identified
Member, it is considered to the space connectivity of water body object in unit to be identified, it is final to obtain the two-value classification chart for representing water body and non-water body
Picture.The information relevant with water body is only extracted, non-Water-Body Information is pressed, therefore specific aim is stronger；Consider all spectrum simultaneously
Band class information, the reproducibility to Water-Body Information is stronger, has higher letter than water body index (only considering special spectrum wave band)
Cease utilization rate, realize and accurate identifying water boy is carried out to a wide range of region, to prevent and reduce natural disasters, climate change, Eco-hydrological Processes
Support is provided Deng field.
In a kind of optional embodiment of the embodiment of the present invention, described obtained according to the standard water body curve of spectrum waits to know
The water body probabilistic image of other multispectral image, including：
The curve of spectrum and the standard water spectral respectively to each pixel in the multispectral image to be identified
Curve is normalized；
Obtain the curve of spectrum and standard water body of each pixel in the multispectral image to be identified after normalized
The similarity of the curve of spectrum；
The water body probability of each pixel according to being obtained the similarity of each pixel.
Specifically, it is vectorialWithStandard water body is represented respectively
The curve of spectrum of pixel in the curve of spectrum and multispectral image, b is wave band number.In order to protrude the relative mistake between different-waveband
Different, spectral vector can be normalized by formula (1)：
δ is representedOrFunction MIN () represents ordered series of numbers { w1, w2..., wbOr { O1, O2..., ObMinimum value, letter
Number MAX () then represents maximum.Describe, will hereafter use for convenienceWithRepresentWith
Similarity can be characterized with cosine similarity (formula (3)) and Distance conformability degree (formula (4)), therefore water body probability
It can be calculated with formula (2).
Water body probability PwSpan be [0,1], correspondingly, non-water body probability is：
Pnw=1-Pw (5)
Specifically, the formula of the object function is as follows：
Wherein, T represents fitness value；c1For constant, the weight of water body part, c are represented2For constant, non-aqueous body portion is represented
Weight, c3For constant, the weight of neighborhood part is represented；Pw,kRepresent that k-th of pixel is the general of water body in the unit to be identified
Rate, Pnw,kRepresent in the unit to be identified the probability that k-th of pixel is non-water body；Represent the unit to be identified
The minimum value of distance between middle each two pixel.
In order to improve to the multifarious sensitiveness of earth's surface, (it is shown in Table the embodiments of the invention provide 4 kinds of weighted value Setting patterns
1), wherein μ is the probability average in unit to be identified (rows × cols), and σ is the standard deviation in the unit.
H patterns represent the earth's surface to be likely to be the water body or non-water body of homogeneity, because average is larger, standard deviation compared with
It is small.In such a mode, by setting c1More than c2To protrude Water-Body Information.
M-mode represents that the earth's surface is likely to be heterogeneous non-water body, because standard deviation is larger.In this mode, due to other
Object spectrum is more similar to water spectral, it is difficult to water body be made a distinction with non-water body, so c1、c2And c3Value it is equal.
L mode reflects recognition capability of the algorithm to small water-body (such as network of waterways), and it is further segmented as LL and LH two
The pattern of kind.Difference between both patterns depends on average, and similitude depends on standard deviation.Higher standard deviation means different
Matter, represents to be likely to be the mixed pixel of water body and non-water body.When average is relatively low (such as LL patterns), it may be possible to tiny tributary.
In this mode, c1Compare c2It is much bigger, to emphasize small water-body information from large area land.Meanwhile, by increasing c3Value
To reflect the connectivity between small water-body (such as network of waterways).When average is higher (such as LH patterns), it may be possible to land and water boundary area.
Under this pattern, c1It is set to smaller, but still compares c2Greatly, because enough in land and water boundary area water body, it is not necessary to undue strong
Adjust.
The weighted value Setting pattern of table 1.
Further, it is described to be iterated solution to the object function, including：
Solution is iterated to the object function using discrete particle cluster algorithm.
If it should be noted that water body probabilistic image is divided into n units to be identified, object function solution procedure
It will be repeated n times.The solution procedure only to a pending unit is described below, the solution procedure of other units to be identified
It is identical with this.
The unit to be identified that given size is D=rows × cols, its feasible solution is { x1, x2..., xD, by formula (7)
Provide.
Regard each feasible solution as particle that a dimension is N.Each particle has position x, speed v and fitness value
T.Position x is calculated by formula (7), and fitness value T is calculated by formula (6), and speed v is calculated by formula (8).In iteration each time
In, position x will update according to formula (8)~(12).
I refers to i-th of particle, and d refers to d-th of dimension, and k refers to kth time iteration, and w refers to inertia weight.In discrete particle
In group's algorithm, w is defined by formula (11).wmaxIt is normally provided as 0.95, wminIt is normally provided as 0.4.kmax=2.05, r1,
r2All it is to obey [0,1] equally distributed random number with R.Different particles, r1,r2Value is different；And R is relevant with iterations,
In each iteration, R value is identical.pidIt is the history optimal solution of i-th of particle, pgdIt is the global optimum of all particles
Solution.vmaxAnd vminIt is maximum and minimum value that speed allows.If do not limited, particle would be possible to beyond feasible zone (i.e.
[0,1]).In this algorithm, vmax=1, vmin=0.L () is logical function (Logistic Function), and formula is shown in definition
(12)。
Therefore, in each unit to be identified, the solution procedure of object function is：
(1) I particle is created at random, and dimension is D, such as matrix X (formula (13)).X is a 0-1 matrix.It is random to create phase
The rate matrices V answered, is shown in formula (14).
(2) for X every a line, pixel is divided into water body and the class of non-water body two.X is calculated per a line according to formula (6)
Fitness value T.Because history value is not present in first time iteration, therefore history optimal solution is exactly X.Globally optimal solution is exactly history
That corresponding a line of maximum T values in optimal solution.
(3) new speed V is calculated according to formula (8) and (9), and X is updated according to formula (10).
(4) fitness value Ts of the X per a line is calculated.To every a line, the T values of current iteration and the T of last iteration are respectively compared
Value.Larger corresponding that row X of T values is set to history optimal solution.
(5) if k is equal to kmax, continue next step；Otherwise, return to (3).
(6) global optimum retained is exactly the final classification results of the basic computational ele- ment.Jump to next meter
Unit is calculated, continues above step.
For the technique effect of the identifying water boy method of verifying the embodiment of the present invention, 8 experimental points are selected in the whole world, are covered
The vast climatic province in temperate zone, the torrid zone and frigid zone, is related to turbid water body, rich in humus water body, salt lake, urban water-body, river of gathering
The various water bodies types such as net.In the verification accepted standard water spectral curve for 0.1153,0.0942,0.0779,
0.0715,0.0324,0.0055,0.0031 } (Landsat 8OLI sensors, wavelength gradually increases).
As a result show, the algorithm can reach the level of supervised classification in stability and precision aspect, meanwhile, it is capable to as non-
Supervised classification has less manual intervention, and flexibility and automaticity are greatly improved.
Fig. 2 is the structural representation of the identifying water boy device of one embodiment of the invention.As shown in Fig. 2 the present invention is implemented
The device of example, which includes water body probabilistic image acquiring unit 21, image division unit 22, objective function unit 23 and water body, to be known
Other unit 24, specifically：
Water body probabilistic image acquiring unit 21, for obtaining multispectral image to be identified according to the standard water body curve of spectrum
Water body probabilistic image；
Image division unit 22, for the water body probabilistic image to be divided into multiple units to be identified；
Objective function unit 23, for treating the water body probability of each pixel in unit to be identified for suitable according to
Angle value is answered to construct object function；
Identifying water boy unit 24, for being iterated solution to the object function, when obtaining the fitness value maximum
The unit to be identified water body distribution, to carry out identifying water boy to the unit to be identified.
Identifying water boy device provided in an embodiment of the present invention, by the way that water body probabilistic image is divided into multiple lists to be identified
Member, it is considered to the space connectivity of water body object in unit to be identified, it is final to obtain the two-value classification chart for representing water body and non-water body
Picture.The information relevant with water body is only extracted, non-Water-Body Information is pressed, therefore specific aim is stronger；Consider all spectrum simultaneously
Band class information, the reproducibility to Water-Body Information is stronger, has higher letter than water body index (only considering special spectrum wave band)
Cease utilization rate, realize and accurate identifying water boy is carried out to a wide range of region, to prevent and reduce natural disasters, climate change, Eco-hydrological Processes
Support is provided Deng field.
In a kind of optional embodiment of the embodiment of the present invention, water body probabilistic image acquiring unit 21 includes：
Normalized module, for respectively to the curve of spectrum of each pixel in the multispectral image to be identified
It is normalized with the standard water body curve of spectrum；
Similarity acquisition module, for obtaining each pixel in the multispectral image to be identified after normalized
The similarity of the curve of spectrum and the standard water body curve of spectrum；
Water body probability acquisition module, the water body for obtaining each pixel according to the similarity of each pixel is general
Rate.
Specifically, the formula of the object function is as follows：
Wherein, T represents fitness value；c1For constant, the weight of water body part, c are represented2For constant, non-aqueous body portion is represented
Weight, c3For constant, the weight of neighborhood part is represented；Pw,kRepresent that k-th of pixel is the general of water body in the unit to be identified
Rate, Pnw,kRepresent in the unit to be identified the probability that k-th of pixel is non-water body；Represent the unit to be identified
The minimum value of distance between middle each two pixel.
Identifying water boy unit 24 is further used for：
Solution is iterated to the object function using discrete particle cluster algorithm.
The identifying water boy device of the embodiment of the present invention can be used for performing above method embodiment, its principle and technique effect
Similar, here is omitted.
Fig. 3 is the entity structure schematic diagram of the electronic equipment of one embodiment of the invention.
Reference picture 3, electronic equipment includes：Processor (processor) 31, memory (memory) 32 and bus 33；Its
In,
Processor 31 and memory 32 complete mutual communication by bus 33；
Processor 31 is used to call the programmed instruction in memory 32, to perform the side that above-mentioned each method embodiment is provided
Method.
In addition, the logical order in above-mentioned memory 32 can be realized by the form of SFU software functional unit and is used as solely
Vertical production marketing in use, can be stored in a computer read/write memory medium.Understood based on such, this hair
The part or the part of the technical scheme that bright technical scheme substantially contributes to prior art in other words can be with soft
The form of part product is embodied, and the computer software product is stored in a storage medium, including some instructions are to make
Obtain a computer equipment (can be personal computer, server, or network equipment etc.) and perform each embodiment of the invention
The all or part of step of methods described.And foregoing storage medium includes：USB flash disk, mobile hard disk, read-only storage (ROM,
Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disc or CD etc. it is various
Can be with the medium of store program codes.
The present embodiment provides a kind of computer program product, and the computer program product includes being stored in non-transient calculating
Computer program on machine readable storage medium storing program for executing, the computer program includes programmed instruction, when described program instruction is calculated
When machine is performed, computer is able to carry out the identifying water boy method that above-mentioned each method embodiment is provided.
The present embodiment provides a kind of non-transient computer readable storage medium storing program for executing, the non-transient computer readable storage medium storing program for executing
Computer instruction is stored, the computer instruction makes the computer perform the identifying water boy that above-mentioned each method embodiment is provided
Method.
Identifying water boy method and device provided in an embodiment of the present invention, multiple waits to know by the way that water body probabilistic image is divided into
Other unit, it is considered to the space connectivity of water body object in unit to be identified, it is final to obtain the two-value point for representing water body and non-water body
Class image.The information relevant with water body is only extracted, non-Water-Body Information is pressed, therefore specific aim is stronger；Consider simultaneously all
Spectral band information, the reproducibility to Water-Body Information is stronger, has than water body index (only considering special spectrum wave band) higher
Information utilization, realize and accurate identifying water boy carried out to a wide range of region, to prevent and reduce natural disasters, climate change, Eco-hydrological
The fields such as process provide support.
It should be understood by those skilled in the art that, embodiments of the invention can be provided as method, system or computer program
Product.Therefore, the present invention can be using the reality in terms of complete hardware embodiment, complete software embodiment or combination software and hardware
Apply the form of example.Moreover, the present invention can be used in one or more computers for wherein including computer usable program code
The computer program production that usable storage medium is implemented on (including but is not limited to magnetic disk storage, CD-ROM, optical memory etc.)
The form of product.
The present invention is the flow with reference to method according to embodiments of the present invention, equipment (system) and computer program product
Figure and/or block diagram are described.It should be understood that can be by every first-class in computer program instructions implementation process figure and/or block diagram
Journey and/or the flow in square frame and flow chart and/or block diagram and/or the combination of square frame.These computer programs can be provided
The processor of all-purpose computer, special-purpose computer, Embedded Processor or other programmable data processing devices is instructed to produce
A raw machine so that produced by the instruction of computer or the computing device of other programmable data processing devices for real
The device for the function of being specified in present one flow of flow chart or one square frame of multiple flows and/or block diagram or multiple square frames.
It should be noted that term " comprising ", "comprising" or its any other variant are intended to the bag of nonexcludability
Contain, so that process, method, article or equipment including a series of key elements are not only including those key elements, but also including
Other key elements being not expressly set out, or also include for this process, method, article or the intrinsic key element of equipment.
In the absence of more restrictions, the key element limited by sentence "including a ...", it is not excluded that including the key element
Process, method, article or equipment in also there is other identical element.
In the specification of the present invention, numerous specific details are set forth.Although it is understood that, embodiments of the invention can
To be put into practice in the case of these no details.In some instances, known method, structure and skill is not been shown in detail
Art, so as not to obscure the understanding of this description.Similarly, it will be appreciated that disclose in order to simplify the present invention and helps to understand respectively
One or more of individual inventive aspect, above in the description of the exemplary embodiment of the present invention, each of the invention is special
Levy and be grouped together into sometimes in single embodiment, figure or descriptions thereof.However, should not be by the method solution of the disclosure
Release and be intended in reflection is following：I.e. the present invention for required protection requirement is than the feature that is expressly recited in each claim more
Many features.More precisely, as the following claims reflect, inventive aspect is to be less than single reality disclosed above
Apply all features of example.Therefore, it then follows thus claims of embodiment are expressly incorporated in the embodiment,
Wherein each claim is in itself as the separate embodiments of the present invention.
Above example is merely to illustrate technical scheme, rather than its limitations；Although with reference to the foregoing embodiments
The present invention is described in detail, it will be understood by those within the art that：It still can be to foregoing each implementation
Technical scheme described in example is modified, or carries out equivalent substitution to which part technical characteristic；And these are changed or replaced
Change, the essence of appropriate technical solution is departed from the spirit and scope of various embodiments of the present invention technical scheme.
Claims (10)
1. a kind of identifying water boy method, it is characterised in that including：
The water body probabilistic image of multispectral image to be identified is obtained according to the standard water body curve of spectrum；
The water body probabilistic image is divided into multiple units to be identified；
Object function is constructed for fitness value according to the water body probability for treating each pixel in unit to be identified；
Solution is iterated to the object function, the water body of the unit to be identified when obtaining the fitness value maximum divides
Cloth, to carry out identifying water boy to the unit to be identified.
2. according to the method described in claim 1, it is characterised in that described to obtain to be identified according to the standard water body curve of spectrum
The water body probabilistic image of multispectral image, including：
The curve of spectrum and the standard water body curve of spectrum respectively to each pixel in the multispectral image to be identified
It is normalized；
Obtain the curve of spectrum and standard water spectral of each pixel in the multispectral image to be identified after normalized
The similarity of curve；
The water body probability of each pixel according to being obtained the similarity of each pixel.
3. according to the method described in claim 1, it is characterised in that the formula of the object function is as follows：
<mrow>
<mi>max</mi>
<mi> </mi>
<mi>T</mi>
<mo>=</mo>
<msub>
<mi>c</mi>
<mn>1</mn>
</msub>
<mo>&CenterDot;</mo>
<msubsup>
<mi>&Sigma;</mi>
<mrow>
<mi>k</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mrow>
<mi>r</mi>
<mi>o</mi>
<mi>w</mi>
<mi>s</mi>
<mo>&times;</mo>
<mi>c</mi>
<mi>o</mi>
<mi>l</mi>
<mi>s</mi>
</mrow>
</msubsup>
<msub>
<mi>P</mi>
<mrow>
<mi>w</mi>
<mo>,</mo>
<mi>k</mi>
</mrow>
</msub>
<mo>+</mo>
<msub>
<mi>c</mi>
<mn>2</mn>
</msub>
<mo>&CenterDot;</mo>
<msubsup>
<mi>&Sigma;</mi>
<mrow>
<mi>k</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mrow>
<mi>r</mi>
<mi>o</mi>
<mi>w</mi>
<mi>s</mi>
<mo>&times;</mo>
<mi>c</mi>
<mi>o</mi>
<mi>l</mi>
<mi>s</mi>
</mrow>
</msubsup>
<msub>
<mi>P</mi>
<mrow>
<mi>n</mi>
<mi>w</mi>
<mo>,</mo>
<mi>k</mi>
</mrow>
</msub>
<mo>-</mo>
<msub>
<mi>c</mi>
<mn>3</mn>
</msub>
<mo>&CenterDot;</mo>
<mfrac>
<msub>
<mover>
<mi>D</mi>
<mo>&OverBar;</mo>
</mover>
<mrow>
<mi>n</mi>
<mi>e</mi>
<mi>a</mi>
<mi>r</mi>
<mi>e</mi>
<mi>s</mi>
<mi>t</mi>
</mrow>
</msub>
<msqrt>
<mrow>
<msup>
<mi>rows</mi>
<mn>2</mn>
</msup>
<mo>+</mo>
<msup>
<mi>cols</mi>
<mn>2</mn>
</msup>
</mrow>
</msqrt>
</mfrac>
</mrow>
Wherein, T represents fitness value；c1For constant, the weight of water body part, c are represented2For constant, the power of non-aqueous body portion is represented
Weight, c3For constant, the weight of neighborhood part is represented；Pw,kThe probability that k-th of pixel is water body is represented in the unit to be identified,
Pnw,kRepresent in the unit to be identified the probability that k-th of pixel is non-water body；Represent in the unit to be identified
The minimum value of distance between each two pixel.
4. according to the method described in claim 1, it is characterised in that described to be iterated solution to the object function, including：
Solution is iterated to the object function using discrete particle cluster algorithm.
5. a kind of identifying water boy device, it is characterised in that including：
Water body probabilistic image acquiring unit, the water body for obtaining multispectral image to be identified according to the standard water body curve of spectrum
Probabilistic image；
Image division unit, for the water body probabilistic image to be divided into multiple units to be identified；
Objective function unit, for treating that the water body probability of each pixel in unit to be identified is directed to fitness value according to
Construct object function；
Identifying water boy unit, it is described when the acquisition fitness value is maximum for being iterated solution to the object function
The water body distribution of unit to be identified, to carry out identifying water boy to the unit to be identified.
6. device according to claim 5, it is characterised in that the water body probabilistic image acquiring unit includes：
Normalized module, for the curve of spectrum respectively to each pixel in the multispectral image to be identified and institute
The standard water body curve of spectrum is stated to be normalized；
Similarity acquisition module, the spectrum for obtaining each pixel in the multispectral image to be identified after normalized
The similarity of curve and the standard water body curve of spectrum；
Water body probability acquisition module, the water body probability for obtaining each pixel according to the similarity of each pixel.
7. device according to claim 5, it is characterised in that the formula of the object function is as follows：
<mrow>
<mi>max</mi>
<mi> </mi>
<mi>T</mi>
<mo>=</mo>
<msub>
<mi>c</mi>
<mn>1</mn>
</msub>
<mo>&CenterDot;</mo>
<msubsup>
<mi>&Sigma;</mi>
<mrow>
<mi>k</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mrow>
<mi>r</mi>
<mi>o</mi>
<mi>w</mi>
<mi>s</mi>
<mo>&times;</mo>
<mi>c</mi>
<mi>o</mi>
<mi>l</mi>
<mi>s</mi>
</mrow>
</msubsup>
<msub>
<mi>P</mi>
<mrow>
<mi>w</mi>
<mo>,</mo>
<mi>k</mi>
</mrow>
</msub>
<mo>+</mo>
<msub>
<mi>c</mi>
<mn>2</mn>
</msub>
<mo>&CenterDot;</mo>
<msubsup>
<mi>&Sigma;</mi>
<mrow>
<mi>k</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mrow>
<mi>r</mi>
<mi>o</mi>
<mi>w</mi>
<mi>s</mi>
<mo>&times;</mo>
<mi>c</mi>
<mi>o</mi>
<mi>l</mi>
<mi>s</mi>
</mrow>
</msubsup>
<msub>
<mi>P</mi>
<mrow>
<mi>n</mi>
<mi>w</mi>
<mo>,</mo>
<mi>k</mi>
</mrow>
</msub>
<mo>-</mo>
<msub>
<mi>c</mi>
<mn>3</mn>
</msub>
<mo>&CenterDot;</mo>
<mfrac>
<msub>
<mover>
<mi>D</mi>
<mo>&OverBar;</mo>
</mover>
<mrow>
<mi>n</mi>
<mi>e</mi>
<mi>a</mi>
<mi>r</mi>
<mi>e</mi>
<mi>s</mi>
<mi>t</mi>
</mrow>
</msub>
<msqrt>
<mrow>
<msup>
<mi>rows</mi>
<mn>2</mn>
</msup>
<mo>+</mo>
<msup>
<mi>cols</mi>
<mn>2</mn>
</msup>
</mrow>
</msqrt>
</mfrac>
</mrow>
1
Wherein, T represents fitness value；c1For constant, the weight of water body part, c are represented2For constant, the power of non-aqueous body portion is represented
Weight, c3For constant, the weight of neighborhood part is represented；Pw,kThe probability that k-th of pixel is water body is represented in the unit to be identified,
Pnw,kRepresent in the unit to be identified the probability that k-th of pixel is non-water body；Represent in the unit to be identified
The minimum value of distance between each two pixel.
8. device according to claim 5, it is characterised in that the identifying water boy unit is further used for：
Solution is iterated to the object function using discrete particle cluster algorithm.
9. a kind of electronic equipment, it is characterised in that including：Processor, memory and bus；Wherein,
Processor and memory complete mutual communication by bus；
Processor is used to call the programmed instruction in memory, and the identifying water boy side described in any one of 1-4 is required with perform claim
Method.
10. a kind of non-transient computer readable storage medium storing program for executing, the non-transient computer readable storage medium storing program for executing storage computer refers to
Order, the computer instruction makes the computer perform claim require the identifying water boy method described in any one of 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710313128.7A CN107271367B (en) | 2017-05-05 | 2017-05-05 | A kind of identifying water boy method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710313128.7A CN107271367B (en) | 2017-05-05 | 2017-05-05 | A kind of identifying water boy method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107271367A true CN107271367A (en) | 2017-10-20 |
| CN107271367B CN107271367B (en) | 2019-06-28 |
Family
ID=60073835
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710313128.7A Active CN107271367B (en) | 2017-05-05 | 2017-05-05 | A kind of identifying water boy method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107271367B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109472294A (en) * | 2018-10-15 | 2019-03-15 | 广州地理研究所 | A kind of recognition methods of urban water-body, device, storage medium and equipment |
| CN109886067A (en) * | 2018-12-17 | 2019-06-14 | 北京师范大学 | Wetland is damaged remote sensing recognition method and device |
| CN110517575A (en) * | 2019-08-21 | 2019-11-29 | 华北水利水电大学 | A kind of surface water body drafting method and device |
| CN111753647A (en) * | 2020-05-11 | 2020-10-09 | 广东无限阵列科技有限公司 | Automatic identification method and device for livestock breeding shed and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101900687A (en) * | 2010-07-06 | 2010-12-01 | 重庆大学 | Method for monitoring and early warning water bloom in small water area based on image processing |
| CN102073879A (en) * | 2010-12-02 | 2011-05-25 | 南京大学 | Method for identifying characteristic land categories of ocean remote sensing images of coast on basis of semi-supervised learning |
| CN102855494A (en) * | 2012-08-20 | 2013-01-02 | 中国测绘科学研究院 | Method and device for extracting water body of satellite remote sensing image |
| US20130286377A1 (en) * | 2012-04-27 | 2013-10-31 | SATOP GmbH | Using Multispectral Satellite Data to Determine Littoral Water Depths Despite Varying Water Turbidity |
| CN103400151A (en) * | 2013-08-16 | 2013-11-20 | 武汉大学 | Optical remote-sensing image, GIS automatic registration and water body extraction integrated method |
| CN104463166A (en) * | 2014-11-13 | 2015-03-25 | 环境保护部卫星环境应用中心 | Extraction method and system for target water body |
| CN105631903A (en) * | 2015-12-24 | 2016-06-01 | 河海大学 | Remote sensing image water extraction method and device based on RGBW characteristic space diagram cutting algorithm |
-
2017
- 2017-05-05 CN CN201710313128.7A patent/CN107271367B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101900687A (en) * | 2010-07-06 | 2010-12-01 | 重庆大学 | Method for monitoring and early warning water bloom in small water area based on image processing |
| CN102073879A (en) * | 2010-12-02 | 2011-05-25 | 南京大学 | Method for identifying characteristic land categories of ocean remote sensing images of coast on basis of semi-supervised learning |
| US20130286377A1 (en) * | 2012-04-27 | 2013-10-31 | SATOP GmbH | Using Multispectral Satellite Data to Determine Littoral Water Depths Despite Varying Water Turbidity |
| CN102855494A (en) * | 2012-08-20 | 2013-01-02 | 中国测绘科学研究院 | Method and device for extracting water body of satellite remote sensing image |
| CN103400151A (en) * | 2013-08-16 | 2013-11-20 | 武汉大学 | Optical remote-sensing image, GIS automatic registration and water body extraction integrated method |
| CN104463166A (en) * | 2014-11-13 | 2015-03-25 | 环境保护部卫星环境应用中心 | Extraction method and system for target water body |
| CN105631903A (en) * | 2015-12-24 | 2016-06-01 | 河海大学 | Remote sensing image water extraction method and device based on RGBW characteristic space diagram cutting algorithm |
Non-Patent Citations (2)
| Title |
|---|
| 于晓宁: ""基于高分辨率遥感影像的水体信息提取方法研究"", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 蒋卫国 等: ""基于HPSO和FCM的多光谱遥感图像湿地分类"", 《光谱学与光谱分析》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109472294A (en) * | 2018-10-15 | 2019-03-15 | 广州地理研究所 | A kind of recognition methods of urban water-body, device, storage medium and equipment |
| CN109886067A (en) * | 2018-12-17 | 2019-06-14 | 北京师范大学 | Wetland is damaged remote sensing recognition method and device |
| CN109886067B (en) * | 2018-12-17 | 2021-05-14 | 北京师范大学 | Wetland damage remote sensing identification method and device |
| CN110517575A (en) * | 2019-08-21 | 2019-11-29 | 华北水利水电大学 | A kind of surface water body drafting method and device |
| CN111753647A (en) * | 2020-05-11 | 2020-10-09 | 广东无限阵列科技有限公司 | Automatic identification method and device for livestock breeding shed and storage medium |
| CN111753647B (en) * | 2020-05-11 | 2021-01-29 | 广东无限阵列科技有限公司 | Automatic identification method and device for livestock breeding shed and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107271367B (en) | 2019-06-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wan et al. | A small-patched convolutional neural network for mangrove mapping at species level using high-resolution remote-sensing image | |
| Xia et al. | Cloud/shadow segmentation based on global attention feature fusion residual network for remote sensing imagery | |
| CN109446889B (en) | Object tracking method and device based on twin matching network | |
| Storie et al. | Deep learning neural networks for land use land cover mapping | |
| CN103413151B (en) | Hyperspectral image classification method based on figure canonical low-rank representation Dimensionality Reduction | |
| CN107918776B (en) | Land planning method and system based on machine vision and electronic equipment | |
| CN107271367B (en) | A kind of identifying water boy method and device | |
| Yu et al. | NestNet: A multiscale convolutional neural network for remote sensing image change detection | |
| CN112084923B (en) | Remote sensing image semantic segmentation method, storage medium and computing device | |
| Dixit et al. | Dilated-ResUnet: A novel deep learning architecture for building extraction from medium resolution multi-spectral satellite imagery | |
| Mboga et al. | Fully convolutional networks for land cover classification from historical panchromatic aerial photographs | |
| Jeon et al. | Semantic segmentation of seagrass habitat from drone imagery based on deep learning: A comparative study | |
| CN110689043A (en) | Vehicle fine granularity identification method and device based on multiple attention mechanism | |
| Li et al. | A comparison of deep learning methods for airborne lidar point clouds classification | |
| CN110059677A (en) | Digital table recognition methods and equipment based on deep learning | |
| Tao et al. | MSNet: Multispectral semantic segmentation network for remote sensing images | |
| CN106845417B (en) | Based on feature poolization and the high-resolution remote sensing image classification method except normalization expression | |
| Leinonen et al. | Unsupervised classification of snowflake images using a generative adversarial network and K-medoids classification | |
| Clark et al. | Optimised U-Net for land use–land cover classification using aerial photography | |
| Candare et al. | Mapping of high value crops through an object-based SVM model using lidar data and orthophoto in Agusan del Norte Philippines | |
| Alam et al. | Identification of empty land based on google earth using convolutional neural network algorithm | |
| Arezki et al. | AQUAZONE: a spatial decision support system for aquatic zone management | |
| Sarra et al. | Semantic segmentation of remote sensing images using u-net and its variants: Conference new technologies of information and communication (ntic 2022) | |
| Vongkusolkit | Physics-Informed Weakly Supervised Learning for Near Real-Time Flood Mapping | |
| Poonkuntran et al. | Efficient Classification of Satellite Image with Hybrid Approach Using CNN-CA |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |