Region division method and device, computer equipment and storage medium

Abstract

The invention provides a region division method and device, computer equipment and a storage medium, and the method comprises the steps: determining a classification threshold value of a standard deviation set of an interferometric synthetic aperture radar (InSAR) amplitude diagram sequence through an Otsu method; dividing the pixel points corresponding to the standard deviation set into a stable point class and a non-stable point class according to the classification threshold; expanding the unstable point class through a region growing algorithm to obtain a growing region; and performing hole filling and small region elimination on the growth region to generate an unstable region. In the technical scheme provided by the invention, the standard deviation is used as a physical quantitative index for measuring the scattering stability, the classification threshold is automatically determined based on the standard deviation through an Otsu method, and automatic division of the pixel points is realized according to the classification threshold, so that subjective threshold setting is avoided, the reasonability of the classification threshold is improved, and the accuracy of the classification threshold is improved. Rapid processing of large-scale multi-temporal InSAR data can be met, and the region division efficiency is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of InSAR analysis, and particularly relates to a region division method and device, computer equipment and a storage medium. BACKGROUND

[0002] Interferometric Synthetic Aperture Radar (InSAR) is a remote sensing technology that uses the phase difference (interferometric phase) between two or more radar images acquired from the same or similar orbits to measure ground deformation, elevation or surface features. InSAR images usually include an amplitude map (reflecting the echo intensity) and a phase map (reflecting the radar wave propagation distance and phase).

[0003] InSAR technology has been widely used in ground deformation monitoring, but its accuracy and reliability are highly dependent on the selection of stable points. In traditional InSAR data processing, the identification of stable points and the removal of non-stable regions (such as water bodies and densely vegetated areas) often require manual experience or complex auxiliary data. In particular, water bodies have extremely unstable scattering characteristics, which can easily lead to decorrelation in InSAR interferograms, introduce noise and seriously interfere with subsequent deformation analysis. In related technologies, external water mask data is often relied on, or semi-automatic processing is performed through complex filtering and threshold setting. These methods generally have problems such as reliance on external data, low automation level, or subjective threshold setting, and are difficult to meet the needs of large-scale and automated InSAR data processing. SUMMARY

[0004] In view of the above problems, the embodiments of the present application provide a region division method, device, computer equipment and storage medium to solve the problem that the prior art relies on external data, has low automation level, or has subjective threshold setting, and is difficult to meet the needs of large-scale and automated InSAR data processing.

[0005] In a first aspect, the embodiments of the present application provide a region division method, which comprises: determining a classification threshold of a standard deviation set of an InSAR amplitude map sequence by Otsu method; dividing pixel points corresponding to the standard deviation set into a stable point class and a non-stable point class according to the classification threshold; extending the non-stable point class by a region growing algorithm to obtain a growing region; performing hole filling and small region removal on the growing region to generate a non-stable region.

[0006] In a possible implementation, the classification threshold of the standard deviation set of the InSAR amplitude image sequence is determined by the Otsu method, including: standard deviation calculation is performed on all amplitude values of each pixel point in the InSAR amplitude image sequence to obtain a standard deviation set; quantizing the standard deviation set into multiple intervals to determine the probability of each interval; calculating the class probability, class mean and overall mean of the stable point class and the non-stable point class based on the probability of each interval; calculating the inter-class variance according to the class probability, the class mean and the overall mean; traversing the boundary values of the multiple intervals to select a boundary value with the minimum inter-class variance as the classification threshold.

[0007] In a possible implementation, the non-stable point is expanded by the region growing algorithm to obtain a growing region, including: judging whether the neighborhood pixels of each non-stable point satisfy a tolerance condition; if it is judged that the neighborhood pixels satisfy the tolerance condition, the neighborhood pixels are divided into a non-stable point class; if it is judged that the neighborhood pixels do not satisfy the tolerance condition, the neighborhood pixels are divided into a stable point class; continuing to perform the step of judging whether the neighborhood pixels of each non-stable point satisfy the tolerance condition until all neighborhood pixels of each non-stable point are traversed, and the region formed by the non-stable point class is taken as a growing region.

[0008] In a possible implementation, the tolerance condition is that the absolute value of the difference between the standard deviation of the neighborhood pixels and the standard deviation of the non-stable point is less than or equal to a preset tolerance.

[0009] In a possible implementation, the growing region is filled with holes and small regions are removed to generate a non-stable region, including: respectively taking each pixel point in the growing region as a center point of a convolution kernel, and dividing all pixel points in the convolution kernel into a non-stable point class.

[0010] In a possible implementation, the growing region is one or more, and the growing region is filled with holes and small regions are removed to generate a non-stable region, including: when there are multiple growing regions, the number of pixel points of each growing region is counted respectively; judging whether the number of pixel points of the growing region is less than a preset number threshold; if it is judged that the number of pixel points of the growing region is less than the number threshold, the growing region is deleted. If it is judged that the number of pixel points of the growth region is greater than or equal to the number threshold, the growth region is reserved. The non-stable region is formed according to all the reserved growth regions.

[0011] In a second aspect, an embodiment of the present application provides a region division device, and the device comprises: A determination module is configured to determine a classification threshold of a standard deviation set of an InSAR amplitude image sequence by using the Otsu method. A division module is configured to divide pixel points corresponding to the standard deviation set into a stable point class and a non-stable point class according to the classification threshold. A growth module is configured to expand the non-stable point class by using a region growing algorithm to obtain a growth region. A generation module is configured to perform hole filling and small region elimination on the growth region to generate a non-stable region.

[0012] In a possible implementation, the determination module comprises: A first calculation submodule is configured to calculate standard deviations of all amplitude values of each pixel point in the InSAR amplitude image sequence to obtain a standard deviation set. A determination submodule is configured to quantize the standard deviation set into multiple intervals and determine a probability of each interval. A second calculation submodule is configured to calculate class probabilities, class mean values and overall mean values of the stable point class and the non-stable point class respectively based on the probability of each interval. A third calculation submodule is configured to calculate an inter-class variance according to the class probability, the class mean value and the overall mean value. A selection submodule is configured to traverse boundary values of the multiple intervals and select a boundary value with the minimum inter-class variance as a classification threshold.

[0013] In a third aspect, an embodiment of the present application provides a computer device, which comprises one or more processors, a memory and one or more computer programs, wherein the one or more computer programs are stored in the memory, and the one or more computer programs comprise instructions, which, when executed by the computer device, cause the computer device to perform the region division method in the first aspect or any possible implementation manner of the first aspect.

[0014] In a fourth aspect, an embodiment of the present application provides a computer readable storage medium, which comprises a stored program, wherein the program controls a device where the computer readable storage medium is located to perform the region division method in the first aspect or any possible implementation manner of the first aspect when the program is running.

[0015] In the technical scheme provided by the embodiment of the present application, the standard deviation is taken as a physical quantitative index for measuring scattering stability, the classification threshold is automatically determined based on the standard deviation by using the Otsu method, and the pixel points are automatically divided according to the classification threshold, so that subjective threshold setting is avoided, the rationality of the classification threshold is improved, and the regional division efficiency is improved. BRIEF DESCRIPTION OF DRAWINGS

[0016] Figure 1 A flowchart of a regional division method provided by the embodiment of the present application.

[0017] Figure 2 A flowchart of determining a classification threshold in a regional division method provided by the embodiment of the present application.

[0018] Figure 3 A structural diagram of a regional division device provided by the embodiment of the present application.

[0019] Figure 4 A schematic diagram of a computer device provided by the embodiment of the present application. DETAILED DESCRIPTION

[0020] In order to make the objectives, technical schemes and advantages of the present application clearer and more apparent, the present application will be further described below with reference to the drawings and specific embodiments. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0021] Figure 1 A flowchart of a regional division method provided by the embodiment of the present application is shown in FIG. 1, which comprises the following steps. Figure 1 Step 101: The classification threshold of the standard deviation set of the InSAR amplitude image sequence is determined by using the Otsu method.

[0022] Step 102: The pixel points corresponding to the standard deviation set are divided into stable point classes and non-stable point classes according to the classification threshold.

[0023] In this step, the pixel points corresponding to the standard deviations less than the classification threshold are divided into stable point classes, and the pixel points corresponding to the standard deviations greater than the classification threshold are divided into non-stable point classes, i.e. water bodies and their adjacent regions, the reflection characteristics of which change dramatically with time and have poor stability.

[0024] Step 103: The non-stable point classes are expanded by using a region growing algorithm to obtain a growing region. ​

[0025] In this step, it is judged whether the neighborhood pixels of each unstable point satisfy the tolerance condition; if it is judged that the neighborhood pixels satisfy the tolerance condition, the neighborhood pixels are divided into the unstable point class; if it is judged that the neighborhood pixels do not satisfy the tolerance condition, the neighborhood pixels are divided into the stable point class; the step of judging whether the neighborhood pixels of each unstable point satisfy the tolerance condition is continuously executed until all the neighborhood pixels of each unstable point are traversed, and the region formed by the unstable point class is taken as the growth region. The neighborhood pixels are eight pixel points adjacent to the unstable point, which are respectively located above, below, left, right, upper left, lower left, upper right and lower right of the unstable point.

[0026] In the embodiment of the present application, the tolerance condition is:

[0027] wherein, the standard deviation of the neighborhood pixels is denoted as σn, the standard deviation of the unstable point is denoted as σu, the tolerance is denoted as δ. That is, the tolerance condition is that the absolute value of the difference between the standard deviation of the neighborhood pixels and the standard deviation of the unstable point is less than or equal to the preset tolerance. In actual application, the size of the tolerance can be set based on the actual situation. For example, the tolerance is set to 5% to 10% of the average value of the standard deviation of the unstable point class.

[0028] In step 104, the growth region is subjected to hole filling and small region elimination to generate the unstable region.

[0029] In this step, each pixel point in the growth region is respectively taken as the center point of the convolution kernel, and all the pixel points in the convolution kernel are divided into the unstable point class to complete the hole filling. For example, the convolution kernel is a 5*5 convolution kernel, and the pixel point in the growth region is taken as the center point of the convolution kernel. At this time, the 24 pixel points falling within the 5*5 convolution kernel range around the center point are all divided into the unstable point class.

[0030] In the embodiment of the present application, the growth region is one or more. When there are multiple growth regions, the number of pixel points of each growth region is respectively counted, and it is judged whether the number of pixel points of the growth region is less than the preset number threshold; if it is judged that the number of pixel points of the growth region is less than the number threshold, the growth region is deleted; if it is judged that the number of pixel points of the growth region is greater than or equal to the number threshold, the growth region is retained; the unstable region is formed according to all the retained growth regions, and the region outside the unstable region is the stable region. Through the above region division, the noise influence is reduced, reliable input data is provided for subsequent InSAR deformation analysis, and thus the accuracy and stability of InSAR analysis are improved.

[0031] The technical scheme provided by the embodiment of the application takes the standard deviation as a physical quantitative index for measuring scattering stability, automatically determines a classification threshold based on the standard deviation through the Otsu method, and realizes automatic division of pixel points according to the classification threshold, thereby avoiding subjective threshold setting, improving the rationality of the classification threshold, and meeting the requirements of rapid processing of large-scale multi-temporal InSAR data and improving the regional division efficiency.

[0032] Figure 2 A flowchart for determining a classification threshold in the regional division method provided by the embodiment of the application is shown in FIG. 1, and the method comprises the following steps. Figure 2 Step 1011: Calculate the standard deviation of all amplitude values of each pixel point in the InSAR amplitude image sequence to obtain a standard deviation set.

[0033] In this step, the InSAR amplitude image sequence is a multi-temporal InSAR amplitude image sequence that has completed radiation calibration and registration, and each pixel point corresponds to a set of time series amplitude values. The standard deviation of all amplitude values corresponding to each pixel point is calculated to obtain a standard deviation set. The standard deviation is used to reflect the fluctuation of the amplitude values of each pixel point over time. The greater the standard deviation, the more intense the fluctuation of the amplitude values; the smaller the standard deviation, the more stable the amplitude value data.

[0034] For the i-th pixel point in the amplitude image sequence, the time series amplitude value corresponding to the pixel point is:

[0035] where T represents the length of the time series.

[0036] The amplitude mean of the pixel point is:

[0037] where μ represents the amplitude mean, T represents the length of the time series. The standard deviation of the amplitude value of the pixel point is:

[0038] where σ represents the standard deviation,

[0039] T represents the length of the time series, and μ represents the amplitude mean. Step 1012: Quantize the standard deviation set into multiple intervals and determine the probability of each interval.

[0040] In this step, it is assumed that the standard deviation set is

[0041] In this step, the standard deviation set is quantized into multiple intervals, and the probability of each interval is determined. ​​The standard deviation set is quantized into multiple intervals. In actual applications, the standard deviation set can be quantized into multiple equal-width intervals, equal-frequency intervals or custom intervals based on actual requirements. Among them, the custom interval is obtained by customizing the interval boundary to realize the personalized setting of interval quantization. For example, the standard deviation set is quantized into a first interval [a, b], , a second interval [b, c] and a third interval [c, d].

[0042] In the embodiment of the application, the sum of the probabilities of the multiple intervals is 1. The ratio of the number of pixel points in the jth interval to the total number of pixel points is taken as the probability of the jth interval.

[0043] Step 1013, respectively calculate the class probability, class mean and overall mean of the stable point class and the non-stable point class based on the probability of each interval.

[0044] In this step, the class probability calculation formula is:

[0045]

[0046] wherein, P represents the class probability of the stable point class, P represents the class probability of the non-stable point class, P represents the probability of the jth interval.

[0047] The calculation formula of the class mean is:

[0048]

[0049] wherein, P represents the class mean of the stable point class, P represents the class mean of the non-stable point class, P represents the class probability of the stable point class, P represents the class probability of the non-stable point class, P represents the probability of the jth interval.

[0050] The calculation formula of the overall mean is:

[0051] wherein, P represents the overall mean, P represents the probability of the jth interval. ​​​​

[0052] Step 1014: Calculate the inter-class variance based on the class probability, class mean, and population mean.

[0053] In this step, the formula for calculating the inter-class variance is:

[0054] in, Represents the variance between classes. The class mean of the stable point class. This represents the class mean of the non-stationary point class. This represents the population mean. Represents the class probability of a stable point class. Represents the class probability of an unstable point class. This represents the probability of the j-th interval.

[0055] Step 1015: Traverse the boundary values ​​of multiple intervals and select the boundary value with the smallest inter-class variance as the classification threshold.

[0056] In this embodiment of the invention, the quantized interval is taken as the first interval. , ), second interval [ , ) and the third interval [ , For example, the boundary value of the interval is , , and Iterate through the above boundary values ​​and select the boundary value with the smallest inter-class variance as the classification threshold.

[0057] In this embodiment of the invention, by quantizing the standard deviation set into multiple intervals, the number of traversals when determining the classification threshold is reduced, and the situation of setting the classification threshold as an extreme value or outlier is avoided, thereby improving the rationality of the classification threshold.

[0058] Figure 3 This is a schematic diagram of a region division device provided in an embodiment of the present invention, as shown below. Figure 3 As shown, the device includes a determination module 11, a partitioning module 12, a growth module 13, and a generation module 14. The determination module 11 is used to determine the classification threshold of the standard deviation set of the Interferometric Synthetic Aperture Radar (InSAR) amplitude map sequence using the Otsu method; the partitioning module 12 is used to divide the pixels corresponding to the standard deviation set into stable point classes and unstable point classes according to the classification threshold; the growth module 13 is used to expand the unstable point classes using a region growing algorithm to obtain a grown region; and the generation module 14 is used to fill holes and remove small regions from the grown region to generate an unstable region.

[0059] In the embodiment of the present application, the determining module 11 comprises: a first calculating submodule for calculating the standard deviation of all amplitude values of each pixel point in the InSAR amplitude sequence to obtain a standard deviation set; a determining submodule for quantizing the standard deviation set into multiple intervals and determining the probability of each interval; a second calculating submodule for calculating the class probability, class mean and overall mean of the stable point class and the non-stable point class respectively based on the probability of each interval; a third calculating submodule for calculating the inter-class variance according to the class probability, the class mean and the overall mean; and a selecting submodule for traversing the boundary values of the multiple intervals and selecting the boundary value with the minimum inter-class variance as the classification threshold.

[0060] In the embodiment of the present application, the growing module 13 is configured to determine whether the neighborhood pixels of each non-stable point satisfy the tolerance condition; if it is determined that the neighborhood pixels satisfy the tolerance condition, the neighborhood pixels are divided into the non-stable point class; if it is determined that the neighborhood pixels do not satisfy the tolerance condition, the neighborhood pixels are divided into the stable point class; the step of determining whether the neighborhood pixels of each non-stable point satisfy the tolerance condition is continuously executed until all neighborhood pixels of each non-stable point are traversed, and the region formed by the non-stable point class is taken as the growing region.

[0061] In the embodiment of the present application, the tolerance condition is that the absolute value of the difference between the standard deviation of the neighborhood pixels and the standard deviation of the non-stable point is less than or equal to the preset tolerance.

[0062] In the embodiment of the present application, the generating module 14 is specifically configured to take each pixel point in the growing region as the center point of the convolution kernel and divide all pixel points in the convolution kernel into the non-stable point class.

[0063] In the embodiment of the present application, the growing region is one or more. The generating module 14 is specifically configured to, when there are multiple growing regions, respectively count the number of pixel points of each growing region; determine whether the number of pixel points of the growing region is less than a preset number threshold; if it is determined that the number of pixel points of the growing region is less than the number threshold, the growing region is deleted; if it is determined that the number of pixel points of the growing region is greater than or equal to the number threshold, the growing region is retained; and a non-stable region is formed according to all retained growing regions.

[0064] In the technical scheme provided by the embodiment of the present application, the standard deviation is taken as a physical quantitative index for measuring the scattering stability, the classification threshold is automatically determined based on the standard deviation by the Otsu method, and the automatic division of the pixel points is realized according to the classification threshold, thereby avoiding subjective threshold setting, improving the rationality of the classification threshold, and being capable of meeting the rapid processing of large-scale multi-time InSAR data and improving the region division efficiency.

[0065] The embodiment of the present application provides a computer readable storage medium, which comprises a stored program, wherein when the program is run, the computer readable storage medium controls the device where the computer readable storage medium is located to execute each step of the embodiment of the region division method, and the specific description can be referred to the embodiment of the region division method.

[0066] Figure 4 A schematic diagram of a computer device provided by the embodiment of the present application is shown in the figure, the computer device 3 of the embodiment comprises a processor 301, a memory 302, and a computer program 303 stored in the memory 302 and executable on the processor 301. The processor 301 implements the steps in each method embodiment described above when executing the computer program 303. Alternatively, the processor 301 implements the functions of each module / unit in each device embodiment described above when executing the computer program 303. Figure 4

[0067] The computer device 3 can be a desktop computer, a notebook computer, a palm computer, a cloud computer device and the like electronic devices. The computer device 3 can comprise but is not limited to the processor 301 and the memory 302. Those skilled in the art can understand that the computer device 3 is only an example of the computer device 3 and does not constitute a limitation to the computer device 3, and can comprise more or less components or different components than those shown in the figure. Figure 4

[0068] The processor 301 can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0069] The memory 302 can be an internal storage unit of the computer device 3, for example, a hard disk or a memory of the computer device 3. The memory 302 can also be an external storage device of the computer device 3, for example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card and the like provided on the computer device 3. The memory 302 can also comprise both the internal storage unit and the external storage device of the computer device 3. The memory 302 is used to store the computer program and other programs and data required by the electronic device.​​

[0070] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of each functional unit and module is exemplified, and in actual application, the above-mentioned functions can be completed by different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the above-described functions. Each functional unit and module in the embodiment can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be realized in the form of hardware or in the form of software functional unit.

[0071] The above is only a preferred specific embodiment of the present application, but the protection scope of the present application is not limited to this. Any skilled person in the art can easily think of changes or replacements within the technical range disclosed by the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for dividing regions, characterized in that, The method includes: The classification threshold of the standard deviation set of the Interferometric Synthetic Aperture Radar (InSAR) amplitude map sequence was determined using the Otsu method. Based on the classification threshold, the pixels corresponding to the standard deviation set are divided into stable point class and unstable point class; The unstable point class is expanded using a region growing algorithm to obtain the growing region; The growth region is filled with pores and small areas are removed to generate an unstable region.

2. The method according to claim 1, characterized in that, The method of determining the classification threshold of the standard deviation set of InSAR amplitude map sequences using the Otsu method includes: The standard deviation of all amplitude values ​​for each pixel in the InSAR amplitude map sequence is calculated to obtain the standard deviation set; The standard deviation set is quantized into multiple intervals, and the probability of each interval is determined; Calculate the class probability, class mean, and population mean of the stable point class and the unstable point class based on the probability of each interval. Calculate the inter-class variance based on the class probability, the class mean, and the population mean; The boundary values ​​of the multiple intervals are traversed, and the boundary value with the smallest inter-class variance is selected as the classification threshold.

3. The method according to claim 1, characterized in that, The process of expanding the unstable points using a region growing algorithm to obtain a grown region includes: Determine whether the neighboring pixels of each unstable point satisfy the tolerance condition; If it is determined that the neighboring pixels meet the tolerance condition, then the neighboring pixels are classified as unstable points. If it is determined that the neighboring pixels do not meet the tolerance condition, then the neighboring pixels are classified as stable points. Continue executing the step of determining whether the neighboring pixels of each unstable point meet the tolerance condition, until all neighboring pixels of each unstable point are traversed, and the region formed by the unstable point class is taken as the growth region.

4. The method according to claim 3, characterized in that, The tolerance condition is that the absolute value of the difference between the standard deviation of the neighboring pixels and the standard deviation of the unstable point is less than or equal to a preset tolerance.

5. The method according to claim 1, characterized in that, The process of filling pores and removing small areas in the growth region to generate an unstable region includes: Each pixel in the growth region is taken as the center point of the convolution kernel, and all pixels within the convolution kernel are classified into unstable point classes.

6. The method according to claim 1, characterized in that, The growth region can be one or more, and the process of filling holes and removing small regions in the growth region to generate an unstable region includes: When there are multiple growth regions, count the number of pixels in each growth region separately. Determine whether the number of pixels in the growth region is less than a preset threshold. If it is determined that the number of pixels in the growth region is less than the number threshold, then the growth region is deleted; If it is determined that the number of pixels in the growth region is greater than or equal to the number threshold, then the growth region is retained; The unstable region is formed based on all the retained growth regions.

7. A region division device, characterized in that, The device includes: The determination module is used to determine the classification threshold of the standard deviation set of the Interferometric Synthetic Aperture Radar (InSAR) amplitude map sequence using the Otsu method; The segmentation module is used to divide the pixels corresponding to the standard deviation set into stable point class and unstable point class according to the classification threshold. The growth module is used to expand the unstable point class using a region growth algorithm to obtain a growth region; The generation module is used to fill holes and remove small areas in the growth region to generate an unstable region.

8. The apparatus according to claim 7, characterized in that, The determining module includes: The first calculation submodule is used to calculate the standard deviation of all amplitude values ​​of each pixel in the InSAR amplitude map sequence to obtain a standard deviation set. The determination submodule is used to quantize the standard deviation set into multiple intervals and determine the probability of each interval; The second calculation submodule is used to calculate the class probability, class mean, and overall mean of the stable point class and the unstable point class based on the probability of each interval. The third calculation submodule is used to calculate the inter-class variance based on the class probability, the class mean, and the population mean; A selection submodule is used to traverse the boundary values ​​of the multiple intervals and select the boundary value with the smallest inter-class variance as the classification threshold.

9. A computer device, characterized in that, The computer device includes one or more processors; a memory; and one or more computer programs, wherein the one or more computer programs are stored in the memory, and the one or more computer programs include instructions that, when executed by the computer device, cause the computer device to perform the region partitioning method according to any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device on which the computer-readable storage medium is located to perform the region partitioning method as described in any one of claims 1-6.

Images