CN112597939B - Surface water body classification extraction method, system, equipment and computer storage medium - Google Patents
Surface water body classification extraction method, system, equipment and computer storage medium Download PDFInfo
- Publication number
- CN112597939B CN112597939B CN202011594310.2A CN202011594310A CN112597939B CN 112597939 B CN112597939 B CN 112597939B CN 202011594310 A CN202011594310 A CN 202011594310A CN 112597939 B CN112597939 B CN 112597939B
- Authority
- CN
- China
- Prior art keywords
- spectrum
- ground object
- value
- classified
- surface water
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 239000002352 surface water Substances 0.000 title claims abstract description 76
- 238000000605 extraction Methods 0.000 title claims abstract description 51
- 238000001228 spectrum Methods 0.000 claims description 162
- 238000012545 processing Methods 0.000 claims description 21
- 238000000034 method Methods 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 11
- 230000003595 spectral effect Effects 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims description 4
- 230000001788 irregular Effects 0.000 claims description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 abstract description 27
- 239000000284 extract Substances 0.000 abstract description 5
- 238000007635 classification algorithm Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 238000012216 screening Methods 0.000 description 4
- 238000003809 water extraction Methods 0.000 description 4
- 230000007547 defect Effects 0.000 description 3
- 206010061274 Malocclusion Diseases 0.000 description 2
- 238000003491 array Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 230000005764 inhibitory process Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 238000002310 reflectometry Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/182—Network patterns, e.g. roads or rivers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a surface water body classification extraction method, a system, equipment and a computer storage medium, wherein the surface water body classification extraction method comprises the following steps: classifying all pixels in the remote sensing image related to the surface water body into a feature space; the characteristic space is composed of a plurality of characteristic wave bands; selecting pixels positioned at corner points in the feature space as ground object samples, and forming a ground object sample library; classifying the pixels to be classified according to the ground object samples to obtain ground surface classification results; and extracting the surface water body from the surface classification result. The surface water body classification extraction method, the system, the equipment and the computer storage medium can rapidly and automatically extract large-area water bodies, have certain identification on the water bodies in different states, and can well inhibit the influence of background ground features.
Description
Technical Field
The invention belongs to the technical field of remote sensing image classification, relates to an extraction method and system, and particularly relates to an earth surface water body classification extraction method, system, equipment and a computer storage medium.
Background
The rapid and automatic extraction of large surface waters using remote sensing images is a very important and challenging task. Recently, the free optical data of the sentinel No. 2 issued by the European air office provides a new opportunity for large-area water extraction. However, the precise extraction of water bodies in different states and different scales from the sentinel No. 2 image, and the inhibition of the influence of background features are also an open problem to be solved. Existing water extraction algorithms can be divided into the following three categories:
1. water body index. The water index is a simple but widely used method for water mapping. In general, the water body index is to make use of the difference of the spectral reflectivities of the water body in the green light wave band and the near infrared wave band to highlight the water body and weaken Beijing fifth. Common water indices include Normalized Differential Water Index (NDWI), modified NDWI (MNDWI), automatic Water Extraction Index (AWEI), and the like. The water index is a simple, rapid and effective algorithm for extracting the water in the remote sensing image in a large area, but most indexes usually act on specific wave bands, for example MNDWI needs participation of short wave infrared wave bands, AWEI is designed for Landsat 8OLI data, and large-area popularization of the water index is limited.
2. Unsupervised classification. The non-supervision classification algorithm classifies the image pixels into several categories defined in advance through a clustering algorithm. The non-supervision classification algorithm does not need training samples, is easy to implement in practical application, but needs a user to determine the types of the ground features to be classified of the images in advance, and has certain requirements on the specialization of the user.
3. And (5) supervising the classification. The supervised classification algorithm needs to train samples to adjust parameters of the classifier so as to classify the whole image. The support vector machine SVM and the random forest RF are widely applied water supervision classification algorithms.
In the field of water classification and extraction, the supervision classification algorithm has higher precision and robustness. However, the following two major problems remain in the use process of the supervised classification algorithm: (1) Selecting a proper sample consumes a great deal of manpower and material resources, and the quality of the sample can directly influence the extraction result of the water body; (2) Traditional supervised classification classifiers, such as SVM and RF, are directed to the absolute spectral reflectance of features. However, it is difficult for a conventional supervised classifier like SVM, RF to extract water bodies of different states simultaneously and to suppress interference of background features.
Therefore, how to provide a method, a system, a device and a computer storage medium for classifying and extracting surface water bodies to solve the defects that the prior art is difficult to extract water bodies in different states and simultaneously inhibit the interference of background ground features and the like is a technical problem to be solved urgently by those skilled in the art.
Disclosure of Invention
In view of the above-mentioned drawbacks of the prior art, an object of the present invention is to provide a method, a system, a device and a computer storage medium for classification and extraction of surface water bodies, which are used for solving the problem that it is difficult to extract water bodies in different states while suppressing interference of background ground objects in the prior art.
To achieve the above and other related objects, an aspect of the present invention provides a method for classifying and extracting a surface water body, including: classifying all pixels in the remote sensing image related to the surface water body into a feature space; the characteristic space is composed of a plurality of characteristic wave bands; selecting pixels positioned at corner points in the feature space as ground object samples, and forming a ground object sample library; classifying the pixels to be classified according to the ground object samples to obtain ground surface classification results; and extracting the surface water body from the surface classification result.
In an embodiment of the present invention, the plurality of characteristic bands includes tan (blue band spectrum value-green band spectrum value), tan (blue band spectrum value-red band spectrum value), tan (blue band spectrum value-near infrared band spectrum value), tan (green band spectrum value-red band spectrum value), tan (green band spectrum value-near infrared band spectrum value), and tan (red band spectrum value-near infrared band spectrum value).
In an embodiment of the invention, the pixels of different corner points belong to different ground object categories.
In an embodiment of the present invention, the step of classifying the pixels to be classified according to the ground object sample to obtain a ground surface classification result includes: calculating the spectrum similarity between the pixel to be classified and the ground object sample; wherein the spectrum similarity between the pixel to be classified and the ground object sample is represented by a spectrum angle between the spectrum of the pixel to be classified and the spectrum of the ground object sample.
In an embodiment of the present invention, a calculation formula of a spectrum angle between a spectrum of a pixel to be classified and a spectrum of a ground object sample is:wherein X is i The spectrum of the ith pixel is represented, i=1, 2,3, …, N and N represent the total number of pixels to be classified in the remote sensing image, Y j The spectrum of the j-th class of ground object sample is represented, M represents the total number of ground object categories in the ground object sample library, and alpha represents the spectrum X of the pixels to be classified i Spectrum Y of sample with ground object j The spectral angle between them.
In an embodiment of the present invention, the step of classifying the pixels to be classified according to the ground object sample to obtain a ground surface classification result further includes: calculating a correlation coefficient between the spectrum of the pixel to be classified and the spectrum of the ground object sample, and if the correlation coefficient is larger than 0, adopting a spectrum angle between the spectrum of the pixel to be classified and the spectrum of the ground object sample as a classification basis for classifying the pixel to be classified, and calculating a cosine value of the spectrum angle; if the correlation coefficient is smaller than or equal to 0, amplifying the spectrum angle, and calculating the cosine value of the amplified spectrum angle; when the cosine value of the spectrum angle or the cosine value of the amplified spectrum angle is smaller than a preset threshold value, the similarity between the pixel to be classified and the ground object sample is high; and when the cosine value of the spectrum angle amplified by the cosine value of the spectrum angle is larger than or equal to a preset threshold value, the similarity between the pixel to be classified and the ground object sample is low.
In one embodiment of the present invention, the step of extracting the surface water body from the surface classification result includes: and carrying out binarization processing on the surface classification result, and extracting surface water from the surface result after the binarization processing.
In another aspect, the present invention provides a surface water classification extraction system comprising: the classifying module is used for classifying all pixels in the remote sensing image related to the surface water body into a characteristic space; the characteristic space is composed of a plurality of characteristic wave bands; the sample selection module is used for selecting pixels positioned at corner points in the feature space as ground object samples and forming a ground object sample library; the classification module is used for classifying the pixels to be classified according to the ground object samples so as to obtain ground surface classification results; and the extraction module is used for extracting the surface water body from the surface classification result.
In yet another aspect, the present invention provides a computer storage medium having stored thereon a computer program which when executed by a processor implements the surface water classification extraction method.
In a final aspect, the invention provides a surface water body classification extraction apparatus comprising: a processor and a memory;
the memory is configured to store a computer program, and the processor is configured to execute the computer program stored by the memory to cause the surface water body classification extraction device to perform the surface water body classification extraction method.
As described above, the surface water body classification extraction method, system, equipment and computer storage medium of the invention have the following beneficial effects:
the surface water body classification extraction method, the system, the equipment and the computer storage medium can rapidly and automatically extract large-area water bodies, have certain identification on the water bodies in different states, and can well inhibit the influence of background ground features.
Drawings
Fig. 1 is a schematic flow chart of an embodiment of the surface water classification extraction method according to the present invention.
Fig. 2 is a schematic flow chart of S13 in the surface water body classification and extraction method according to the present invention.
Fig. 3 is a schematic structural diagram of an surface water classification extraction system according to an embodiment of the invention.
Description of element reference numerals
3. Surface water body classification extraction system
31. Classification module
32. Sample selection module
33. Classification module
34. Extraction module
S11 to S14 steps
S131 to S134 steps
Detailed Description
Other advantages and effects of the present invention will become apparent to those skilled in the art from the following disclosure, which describes the embodiments of the present invention with reference to specific examples. The invention may be practiced or carried out in other embodiments that depart from the specific details, and the details of the present description may be modified or varied from the spirit and scope of the present invention. It should be noted that the following embodiments and features in the embodiments may be combined with each other without conflict.
It should be noted that the illustrations provided in the following embodiments merely illustrate the basic concept of the present invention by way of illustration, and only the components related to the present invention are shown in the drawings and are not drawn according to the number, shape and size of the components in actual implementation, and the form, number and proportion of the components in actual implementation may be arbitrarily changed, and the layout of the components may be more complicated.
Example 1
The embodiment provides a surface water body classification extraction method, which comprises the following steps:
classifying all pixels in the remote sensing image related to the surface water body into a feature space; the characteristic space is composed of a plurality of characteristic wave bands;
selecting pixels positioned at corner points in the feature space as ground object samples, and forming a ground object sample library;
classifying the pixels to be classified according to the ground object samples to obtain ground surface classification results;
and extracting the surface water body from the surface classification result.
The surface water body classification extraction method provided in this embodiment will be described in detail with reference to the drawings. Referring to fig. 1, a flow chart of an embodiment of a surface water classification extraction method is shown. As shown in fig. 1, the surface water body classification extraction method specifically includes the following steps:
s11, classifying all pixels in the remote sensing image related to the surface water body into a feature space. In this embodiment, the remote sensing image related to the surface water body includes optical data with resolution of 10 meters of 4-band sentinel number 2.
The feature space is composed of a plurality of feature bands.
Specifically, the plurality of characteristic bands include TAN (blue band spectrum value-green band spectrum value), TAN (blue band spectrum value-red band spectrum value), TAN (blue band spectrum value-near infrared band spectrum value), TAN (green band spectrum value-red band spectrum value), TAN (green band spectrum value-near infrared band spectrum value), and TAN (red band spectrum value-near infrared band spectrum value), that is, the characteristic space is a tangent space (TAN space) formed by tangent values between every two of 6 bands. The tangent function can carry out nonlinear stretching on the basis of the original pixel value, so that the difference between the same ground species can be reduced and the difference between different ground species can be enlarged.
S12, selecting pixels positioned at corner points in the feature space as ground object samples, and forming a ground object sample library.
The specific detailed steps of sample extraction are: and aiming at the convex polygon formed by all the pixel scattered points in the new feature space, manually judging pixels belonging to the corner points of the convex polygon, wherein the pixels at different corner points belong to different ground object categories. And for the pixels of different types selected for the first time manually, the pixels are corresponding to the original image according to the positions of the pixels in the image, and the selection is performed again. The principle of screening is as follows: sample pixels of the selected different corner points should be classified into different categories, and the sample pixels should be located in a portion of the category that is relatively uniform, pure, and free of mixed pixels. And screening the pixels selected for the first time according to the principle, and forming a final sample library after removing the pixels which do not accord with the principle.
In this embodiment, after the pixel points to be classified in the image are unfolded in the feature space, it may be found that the pixel scattered points represent irregular convex polygon features, which illustrates the effectiveness of feature space construction. Based on the feature space and the convex geometric theory of sample selection, selecting pixels of the feature space at corner points as surface samples, wherein the pixels of different corner points belong to different ground object categories.
S13, classifying the pixels to be classified according to the ground object samples to obtain ground surface classification results.
Referring to fig. 2, a flow chart of S13 is shown. As shown in fig. 2, the S13 includes:
s131, calculating the spectrum similarity between the pixel to be classified and the ground object sample; wherein the spectrum similarity between the pixel to be classified and the ground object sample is represented by a spectrum angle between the spectrum of the pixel to be classified and the spectrum of the ground object sample.
In this embodiment, a calculation formula of a spectrum angle between a spectrum of a pixel to be classified and a spectrum of a ground object sample is:
wherein X is i The spectrum of the ith pixel is represented, i=1, 2,3, …, N and N represent the total number of pixels to be classified in the remote sensing image, Y j The spectrum of the j-th class of ground object sample is represented, M represents the total number of ground object categories in the ground object sample library, and alpha represents the spectrum X of the pixels to be classified i Spectrum Y of sample with ground object j The spectral angle between them.
S132, calculating a correlation coefficient between the spectrum of the pixel to be classified and the spectrum of the ground object sample, and judging whether the correlation coefficient is larger than 0; if yes, executing S133; if not, S134 is performed. The angle is usually calculated to be between 0 deg. -90 deg., which means that the above-mentioned spectral angle algorithm cannot identify the negative correlation of the spectrum. However, such defects are very limited in surface water extraction processes, and in complex urban environments, some artificial features have spectral characteristics that are diametrically opposed to those of surface water bodies, so that traditional spectral angle classification would classify these artificial features as also being in the body of water. Therefore, the method introduces the judgment of the pearson correlation coefficient between the spectrum of the pixel to be classified and the spectrum of the ground object sample on the basis of spectrum angle classification, and can identify the negative correlation relationship between the pixel to be classified and the sample by calculating the pearson correlation coefficient between the image pixel and the spectrum of the sample so as to avoid the occurrence of the wrong division phenomenon to the greatest extent.
S133, if the correlation coefficient is greater than 0, adopting a spectrum angle between the spectrum of the pixel to be classified and the spectrum of the ground object sample as a classification basis for classifying the pixel to be classified, and calculating a cosine value of the spectrum angle.
And S134, if the correlation coefficient is smaller than or equal to 0, amplifying the spectrum angle, and calculating the cosine value of the amplified spectrum angle. In practical applications, the spectral angle can be amplified by a factor of 100, i.e., α×100.
When the cosine value of the spectrum angle or the cosine value of the amplified spectrum angle is smaller than a preset threshold value, the similarity between the pixel to be classified and the ground object sample is high, and the pixel to be classified is classified under the category of the ground object sample;
and when the cosine value of the spectrum angle amplified by the cosine value of the spectrum angle is larger than or equal to a preset threshold value, the similarity between the pixel to be classified and the ground object sample is low.
S14, extracting the surface water body from the surface classification result.
Specifically, the surface classification result is subjected to binarization processing, and surface water is extracted from the surface result after the binarization processing.
The surface water body classification extraction method can rapidly and automatically extract large-area water bodies, has a certain identification property on water bodies in different states, and can well inhibit the influence of background ground features.
The present embodiment also provides a computer storage medium (also referred to as a computer-readable storage medium) on which a computer program is stored, which when executed by a processor, implements the above-described surface water body classification extraction method.
One of ordinary skill in the art will appreciate that the computer-readable storage medium is: all or part of the steps for implementing the method embodiments described above may be performed by computer program related hardware. The aforementioned computer program may be stored in a computer readable storage medium. The program, when executed, performs steps including the method embodiments described above; and the aforementioned storage medium includes: various media that can store program code, such as ROM, RAM, magnetic or optical disks.
Example two
The embodiment provides a surface water body classification extraction system, which comprises:
the classifying module is used for classifying all pixels in the remote sensing image related to the surface water body into a characteristic space; the characteristic space is composed of a plurality of characteristic wave bands;
the sample selection module is used for selecting pixels positioned at corner points in the feature space as ground object samples and forming a ground object sample library;
the classification module is used for classifying the pixels to be classified according to the ground object samples so as to obtain ground surface classification results;
and the extraction module is used for extracting the surface water body from the surface classification result.
The surface water body classification extraction system provided by the present embodiment will be described in detail below with reference to the drawings. Referring to fig. 3, a schematic diagram of a surface water classification extraction system according to an embodiment is shown. As shown in fig. 3, the surface water classification extraction system 3 includes a classification module 31, a sample selection module 32, a classification module 33, and an extraction module 34.
The classifying module 31 is configured to classify all pixels in the remote sensing image related to the surface water body into a feature space. In this embodiment, the remote sensing image related to the surface water body includes optical data with resolution of 10 meters of 4-band sentinel number 2.
The feature space is composed of a plurality of feature bands.
Specifically, the plurality of characteristic bands include TAN (blue band spectrum value-green band spectrum value), TAN (blue band spectrum value-red band spectrum value), TAN (blue band spectrum value-near infrared band spectrum value), TAN (green band spectrum value-red band spectrum value), TAN (green band spectrum value-near infrared band spectrum value), and TAN (red band spectrum value-near infrared band spectrum value), that is, the characteristic space is a tangent space (TAN space) formed by tangent values between every two of 6 bands. The tangent function can carry out nonlinear stretching on the basis of the original pixel value, so that the difference between the same ground species can be reduced and the difference between different ground species can be enlarged.
The sample selection module 32 is configured to select a pixel located at a corner in the feature space as a ground object sample, and form a ground object sample library.
Specifically: the sample selection module 32 manually judges pixels belonging to corner points of the convex polygon aiming at the convex polygon formed by all pixel scattering points in the new feature space, and pixels at different corner points are classified into different ground object categories. And for the pixels of different types selected for the first time manually, the pixels are corresponding to the original image according to the positions of the pixels in the image, and the selection is performed again. The principle of screening is as follows: sample pixels of the selected different corner points should be classified into different categories, and the sample pixels should be located in a portion of the category that is relatively uniform, pure, and free of mixed pixels. And screening the pixels selected for the first time according to the principle, and forming a final sample library after removing the pixels which do not accord with the principle.
In this embodiment, after the pixel points to be classified in the image are unfolded in the feature space, it may be found that the pixel scattered points represent irregular convex polygon features, which illustrates the effectiveness of feature space construction. Based on the feature space and the convex geometric theory of sample selection, selecting pixels of the feature space at corner points as surface samples, wherein the pixels of different corner points belong to different ground object categories.
The classification module 33 is configured to classify the pixels to be classified according to the feature sample, so as to obtain a surface classification result.
Specifically, the classification module 33 calculates the spectrum similarity between the pixels to be classified and the ground object sample; calculating a correlation coefficient between the spectrum of the pixel to be classified and the spectrum of the ground object sample, and judging whether the correlation coefficient is larger than 0; if yes, adopting a spectrum angle between the spectrum of the pixel to be classified and the spectrum of the ground object sample as a classification basis for classifying the pixel to be classified, and calculating a cosine value of the spectrum angle; if not, amplifying the spectrum angle, and calculating the cosine value of the amplified spectrum angle. When the cosine value of the spectrum angle or the cosine value of the amplified spectrum angle is smaller than a preset threshold value, the similarity between the pixel to be classified and the ground object sample is high, and the pixel to be classified is classified under the category of the ground object sample; and when the cosine value of the spectrum angle amplified by the cosine value of the spectrum angle is larger than or equal to a preset threshold value, the similarity between the pixel to be classified and the ground object sample is low.
Wherein the spectrum similarity between the pixel to be classified and the ground object sample is represented by a spectrum angle between the spectrum of the pixel to be classified and the spectrum of the ground object sample.
In this embodiment, a calculation formula of a spectrum angle between a spectrum of a pixel to be classified and a spectrum of a ground object sample is:
wherein X is i The spectrum of the ith pixel is represented, i=1, 2,3, …, N and N represent the total number of pixels to be classified in the remote sensing image, Y j The spectrum of the j-th class of ground object sample is represented, M represents the total number of ground object categories in the ground object sample library, and alpha represents the spectrum X of the pixels to be classified i Spectrum Y of sample with ground object j The spectral angle between them.
In practical applications, the classification module 33 may amplify the spectrum angle by 100 times, i.e., α×100.
The extraction module 34 is configured to extract a body of surface water from the surface classification result.
Specifically, the extraction module 34 performs binarization processing on the surface classification result, and extracts the surface water body from the surface result after the binarization processing.
It should be noted that, it should be understood that the division of the modules of the above system is merely a division of a logic function, and may be fully or partially integrated into a physical entity or may be physically separated. The modules can be realized in a form of calling the processing element through software, can be realized in a form of hardware, can be realized in a form of calling the processing element through part of the modules, and can be realized in a form of hardware. For example: the x module may be a processing element which is independently set up, or may be implemented in a chip integrated in the system. The x module may be stored in the memory of the system in the form of program codes, and the functions of the x module may be called and executed by a certain processing element of the system. The implementation of the other modules is similar. All or part of the modules can be integrated together or can be implemented independently. The processing element described herein may be an integrated circuit having signal processing capabilities. In implementation, each step of the above method or each module above may be implemented by an integrated logic circuit of hardware in a processor element or an instruction in a software form. The above modules may be one or more integrated circuits configured to implement the above methods, for example: one or more application specific integrated circuits (Application Specific Integrated Circuit, ASIC for short), one or more microprocessors (Digital Singnal Processor, DSP for short), one or more field programmable gate arrays (Field Programmable Gate Array, FPGA for short), and the like. When a module is implemented in the form of a processing element scheduler code, the processing element may be a general-purpose processor, such as a central processing unit (Central Processing Unit, CPU) or other processor that may invoke the program code. These modules may be integrated together and implemented in the form of a System-on-a-chip (SOC) for short.
Example III
The embodiment provides a surface water body classification draws equipment, includes: a processor, memory, transceiver, communication interface, or/and system bus; the memory and the communication interface are connected with the processor and the transceiver through the system bus and complete the communication among each other, the memory is used for storing computer programs, the communication interface is used for communicating with other equipment, and the processor and the transceiver are used for running the computer programs so that the surface water body classification extraction equipment can execute the steps of the surface water body classification extraction method.
The system bus mentioned above may be a peripheral component interconnect standard (Peripheral Component Interconnect, PCI) bus or an extended industry standard architecture (Extended Industry Standard Architecture, EISA) bus, or the like. The system bus may be classified into an address bus, a data bus, a control bus, and the like. For ease of illustration, the figures are shown with only one bold line, but not with only one bus or one type of bus. The communication interface is used for realizing communication between the database access device and other devices (such as a client, a read-write library and a read-only library). The memory may comprise random access memory (Random Access Memory, RAM) and may also comprise non-volatile memory (non-volatile memory), such as at least one disk memory.
The processor may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU for short), a network processor (Network Processor, NP for short), etc.; but also digital signal processors (Digital Signal Processing, DSP for short), application specific integrated circuits (Application Specific Integrated Circuit, ASIC for short), field programmable gate arrays (Field Programmable Gate Array, FPGA for short) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.
The protection scope of the surface water body classification extraction method is not limited to the execution sequence of the steps listed in the embodiment, and all the schemes of step increase and decrease and step replacement in the prior art according to the principles of the invention are included in the protection scope of the invention.
The invention also provides a surface water body classifying and extracting system which can realize the surface water body classifying and extracting method, but the realizing device of the surface water body classifying and extracting method comprises but is not limited to the structure of the surface water body classifying and extracting system listed in the embodiment, and all structural deformation and replacement of the prior art according to the principle of the invention are included in the protection scope of the invention.
In summary, the surface water body classification extraction method, system, equipment and computer storage medium can rapidly and automatically extract large-area water bodies, have certain identification on water bodies in different states, and can well inhibit the influence of background ground features. The invention effectively overcomes various defects in the prior art and has high industrial utilization value.
The above embodiments are merely illustrative of the principles of the present invention and its effectiveness, and are not intended to limit the invention. Modifications and variations may be made to the above-described embodiments by those skilled in the art without departing from the spirit and scope of the invention. Accordingly, it is intended that all equivalent modifications and variations of the invention be covered by the claims, which are within the ordinary skill of the art, be within the spirit and scope of the present disclosure.
Claims (8)
1. A method for classifying and extracting surface water, which is characterized by comprising the following steps:
classifying all pixels in the remote sensing image related to the surface water body into a feature space; the characteristic space is composed of a plurality of characteristic wave bands;
selecting pixels positioned at corner points in the feature space as ground object samples, and forming a ground object sample library;
classifying the pixels to be classified according to the ground object samples to obtain ground surface classification results;
extracting an earth surface water body from the earth surface classification result;
the plurality of characteristic bands include tan (blue band spectrum value-green band spectrum value), tan (blue band spectrum value-red band spectrum value), tan (blue band spectrum value-near infrared band spectrum value), tan (green band spectrum value-red band spectrum value), tan (green band spectrum value-near infrared band spectrum value), and tan (red band spectrum value-near infrared band spectrum value);
the ground object sample selection step comprises the following steps: after pixel points to be classified in the remote sensing image are unfolded in the feature space, finding out that the pixel points present irregular convex polygon features, and explaining the effectiveness of feature space construction; based on the feature space and the convex geometry theory of sample selection, selecting pixels of the feature space at corner points as surface samples, wherein pixels of different corner points belong to different ground object categories.
2. The method according to claim 1, wherein the step of classifying the pixels to be classified according to the ground object samples to obtain the ground surface classification result comprises:
calculating the spectrum similarity between the pixel to be classified and the ground object sample; wherein the spectrum similarity between the pixel to be classified and the ground object sample is represented by a spectrum angle between the spectrum of the pixel to be classified and the spectrum of the ground object sample.
3. The surface water body classification extraction method according to claim 2, wherein a calculation formula of a spectrum angle between a spectrum of a pixel to be classified and a spectrum of a ground object sample is:
wherein X is i The spectrum of the ith pixel is represented, i=1, 2,3, …, N and N represent the total number of pixels to be classified in the remote sensing image, Y j The spectrum of the j-th class of ground object sample is represented, M represents the total number of ground object categories in the ground object sample library, and alpha represents the spectrum X of the pixels to be classified i Spectrum Y of sample with ground object j The spectral angle between them.
4. The method according to claim 3, wherein the step of classifying the pixels to be classified according to the ground object samples to obtain the ground surface classification result further comprises:
calculating a correlation coefficient between the spectrum of the pixel to be classified and the spectrum of the ground object sample, and if the correlation coefficient is larger than 0, adopting a spectrum angle between the spectrum of the pixel to be classified and the spectrum of the ground object sample as a classification basis for classifying the pixel to be classified, and calculating a cosine value of the spectrum angle; if the correlation coefficient is smaller than or equal to 0, amplifying the spectrum angle, and calculating the cosine value of the amplified spectrum angle;
when the cosine value of the spectrum angle or the cosine value of the amplified spectrum angle is smaller than a preset threshold value, the similarity between the pixel to be classified and the ground object sample is high;
and when the cosine value of the spectrum angle amplified by the cosine value of the spectrum angle is larger than or equal to a preset threshold value, the similarity between the pixel to be classified and the ground object sample is low.
5. The method of surface water classification extraction according to claim 4, wherein the step of extracting surface water from the surface classification result comprises:
and carrying out binarization processing on the surface classification result, and extracting surface water from the surface result after the binarization processing.
6. A surface water body classification extraction system, comprising:
the classifying module is used for classifying all pixels in the remote sensing image related to the surface water body into a characteristic space; the characteristic space is composed of a plurality of characteristic wave bands;
the sample selection module is used for selecting pixels positioned at corner points in the feature space as ground object samples and forming a ground object sample library;
the classification module is used for classifying the pixels to be classified according to the ground object samples so as to obtain ground surface classification results;
the extraction module is used for extracting the surface water body from the surface classification result;
the plurality of characteristic bands include tan (blue band spectrum value-green band spectrum value), tan (blue band spectrum value-red band spectrum value), tan (blue band spectrum value-near infrared band spectrum value), tan (green band spectrum value-red band spectrum value), tan (green band spectrum value-near infrared band spectrum value), and tan (red band spectrum value-near infrared band spectrum value);
the ground object sample selection step comprises the following steps: after pixel points to be classified in the remote sensing image are unfolded in the feature space, finding out that the pixel points present irregular convex polygon features, and explaining the effectiveness of feature space construction; based on the feature space and the convex geometry theory of sample selection, selecting pixels of the feature space at corner points as surface samples, wherein pixels of different corner points belong to different ground object categories.
7. A computer storage medium having stored thereon a computer program, which when executed by a processor implements the surface water classification extraction method of any of claims 1 to 5.
8. An apparatus for classifying and extracting a body of surface water, comprising: a processor and a memory;
the memory is configured to store a computer program, and the processor is configured to execute the computer program stored in the memory, to cause the surface water body classification extraction device to perform the surface water body classification extraction method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011594310.2A CN112597939B (en) | 2020-12-29 | 2020-12-29 | Surface water body classification extraction method, system, equipment and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011594310.2A CN112597939B (en) | 2020-12-29 | 2020-12-29 | Surface water body classification extraction method, system, equipment and computer storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112597939A CN112597939A (en) | 2021-04-02 |
| CN112597939B true CN112597939B (en) | 2023-11-07 |
Family
ID=75204120
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011594310.2A Active CN112597939B (en) | 2020-12-29 | 2020-12-29 | Surface water body classification extraction method, system, equipment and computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112597939B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102609918A (en) * | 2012-02-15 | 2012-07-25 | 国家海洋局第二海洋研究所 | Image characteristic registration based geometrical fine correction method for aviation multispectral remote sensing image |
| CN102620655A (en) * | 2012-04-16 | 2012-08-01 | 中国科学院光电技术研究所 | Method for measuring size of light spot |
| CN104408277A (en) * | 2014-09-28 | 2015-03-11 | 沈阳大学 | Method for predicting, preventing and controlling earth surface residual movement and deformation caused by newly-built building in mine lot |
| WO2017006314A1 (en) * | 2015-07-05 | 2017-01-12 | THE WHOLLYSEE.Ltd. | Optical identification and characterization system and tagss |
| CN106950177A (en) * | 2016-11-16 | 2017-07-14 | 中国科学院遥感与数字地球研究所 | A kind of Clean water withdraw method of the satellite remote-sensing images of GF 4 |
| CN107507202A (en) * | 2017-09-28 | 2017-12-22 | 武汉大学 | A kind of vegetation rotary island towards high-resolution remote sensing image automates extracting method |
| CN107655574A (en) * | 2017-08-23 | 2018-02-02 | 中国科学院光电研究院 | The method and system of sequential thermal infrared remote sensing surface temperature/emissivity Simultaneous Inversion |
| CN109598202A (en) * | 2018-11-05 | 2019-04-09 | 中国科学院遥感与数字地球研究所 | A kind of object-based satellite image multi objective built-up areas extraction method |
| CN110992273A (en) * | 2019-11-04 | 2020-04-10 | 中国科学院西安光学精密机械研究所 | Self-similarity constrained hyperspectral image unmixing method |
| CN111024618A (en) * | 2019-11-25 | 2020-04-17 | 广州丰泽源水利科技有限公司 | Water quality health monitoring method and device based on remote sensing image and storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090214114A1 (en) * | 2008-02-19 | 2009-08-27 | Diascan Ab | Pixel classification in image analysis |
-
2020
- 2020-12-29 CN CN202011594310.2A patent/CN112597939B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102609918A (en) * | 2012-02-15 | 2012-07-25 | 国家海洋局第二海洋研究所 | Image characteristic registration based geometrical fine correction method for aviation multispectral remote sensing image |
| CN102620655A (en) * | 2012-04-16 | 2012-08-01 | 中国科学院光电技术研究所 | Method for measuring size of light spot |
| CN104408277A (en) * | 2014-09-28 | 2015-03-11 | 沈阳大学 | Method for predicting, preventing and controlling earth surface residual movement and deformation caused by newly-built building in mine lot |
| WO2017006314A1 (en) * | 2015-07-05 | 2017-01-12 | THE WHOLLYSEE.Ltd. | Optical identification and characterization system and tagss |
| CN106950177A (en) * | 2016-11-16 | 2017-07-14 | 中国科学院遥感与数字地球研究所 | A kind of Clean water withdraw method of the satellite remote-sensing images of GF 4 |
| CN107655574A (en) * | 2017-08-23 | 2018-02-02 | 中国科学院光电研究院 | The method and system of sequential thermal infrared remote sensing surface temperature/emissivity Simultaneous Inversion |
| CN107507202A (en) * | 2017-09-28 | 2017-12-22 | 武汉大学 | A kind of vegetation rotary island towards high-resolution remote sensing image automates extracting method |
| CN109598202A (en) * | 2018-11-05 | 2019-04-09 | 中国科学院遥感与数字地球研究所 | A kind of object-based satellite image multi objective built-up areas extraction method |
| CN110992273A (en) * | 2019-11-04 | 2020-04-10 | 中国科学院西安光学精密机械研究所 | Self-similarity constrained hyperspectral image unmixing method |
| CN111024618A (en) * | 2019-11-25 | 2020-04-17 | 广州丰泽源水利科技有限公司 | Water quality health monitoring method and device based on remote sensing image and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| Mapping of urban typical land covers GaoFen-5 data: linear spectral unmixing based on a novel spectral analysis technique;Hui Huang 等;《Proceedings Of SPIE》;第11763卷;1176381-1至1176381-8 * |
| 一种改进光谱角匹配的水体信息提取方法;张伟 等;《测绘通报》(第10期);34-38 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112597939A (en) | 2021-04-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111292305B (en) | Improved YOLO-V3 metal processing surface defect detection method | |
| CN109492593B (en) | Hyperspectral image classification method based on principal component analysis network and space coordinates | |
| CN110378313B (en) | Cell cluster identification method and device and electronic equipment | |
| Salau et al. | Vehicle plate number localization using a modified GrabCut algorithm | |
| Valliammal et al. | Plant leaf segmentation using non linear K means clustering | |
| CN107633503A (en) | The image processing method of stalk is remained in a kind of automatic detection grain | |
| US20120213440A1 (en) | Systems and Methods for Automatically Identifying Shadows in Images | |
| Safdar et al. | Intelligent microscopic approach for identification and recognition of citrus deformities | |
| CN106778814B (en) | Method for removing SAR image spots based on projection spectral clustering algorithm | |
| US20140304271A1 (en) | Method To Identify An Object And A System For Doing The Same | |
| CN113221881B (en) | Multi-level smart phone screen defect detection method | |
| Öztürk et al. | Comparison of HOG, MSER, SIFT, FAST, LBP and CANNY features for cell detection in histopathological images | |
| Sharma et al. | An object-based shadow detection method for building delineation in high-resolution satellite images | |
| Tosta et al. | Computational method for unsupervised segmentation of lymphoma histological images based on fuzzy 3-partition entropy and genetic algorithm | |
| CN116310471A (en) | Hyperspectral image classification method | |
| CN108960246B (en) | Binarization processing device and method for image recognition | |
| Agarwal et al. | Machine learning approach for the classification of wheat grains | |
| CN114822781A (en) | Medical image desensitization method based on examination images | |
| CN112926592B (en) | Trademark retrieval method and device based on improved Fast algorithm | |
| Azevedo Tosta et al. | Evaluation of statistical and Haralick texture features for lymphoma histological images classification | |
| Nguyen et al. | Using contextual information to classify nuclei in histology images | |
| Panigrahi et al. | Evaluations of fractal geometry and invariant moments for shape classification of corn germplasm | |
| CN112597939B (en) | Surface water body classification extraction method, system, equipment and computer storage medium | |
| Bejnordi et al. | Novel chromatin texture features for the classification of pap smears | |
| CN112070116B (en) | Automatic artistic drawing classification system and method based on support vector machine |
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 |