Region of interest segmentation method and device, electronic equipment and readable storage medium

By acquiring natural boundary elements and integrating area and population into a combination of area and population, the problem of insufficient accuracy and precision of existing geographical area segmentation methods is solved, and high accuracy and high precision region segmentation is achieved.

CN118982546APending Publication Date: 2024-11-19AUTONAVI SOFTWARE CO LTD
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
CN202410370275.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-03-28
Publication Date
2024-11-19

AI Technical Summary

Technical Problem

The accuracy and precision of the existing geographical area segmentation methods are insufficient, making it difficult to meet the current business needs for high accuracy and high accuracy.

Method used

By obtaining the natural boundary elements in the area to be divided for preliminary segmentation, and combining the area and population of the initial segmented area of ​​interest to obtain the final area of ​​interest.

Benefits of technology

It improves the accuracy and precision of interest region segmentation, ensures the targetedness of segmentation, and is suitable for regional segmentation needs in the fields of business and people's livelihood.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118982546A_ABST
    Figure CN118982546A_ABST
Patent Text Reader

Abstract

The embodiment of the invention discloses a region-of-interest segmentation method and device, electronic equipment and a readable storage medium. The method comprises the steps that natural boundary elements located in a to-be-segmented region are acquired; based on the natural boundary elements, segmenting the to-be-segmented region into at least one initial segmentation region of interest; and based on the area and population number of each initial segmentation region of interest, fusing the at least one initial segmentation region of interest to obtain a final segmentation region of interest of the to-be-segmented region. According to the technical scheme, by means of initial division of the region of interest and based on human-ground data fusion, the pertinence of region-of-interest segmentation can be guaranteed, and the accuracy and fineness of region-of-interest segmentation can be effectively improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the technical field of map data processing, and in particular to a method, device, electronic device and readable storage medium for segmenting a region of interest. Background Art

[0002] With the development of social economy, the targeted demand for geographic region segmentation is becoming more and more urgent. For example, the commercial field needs to segment commercial areas, the livelihood field needs to segment living areas or residential areas, etc. However, the accuracy and precision of the current geographic region segmentation methods are both lacking, and it is difficult to meet the high accuracy and high precision requirements of the current different business operations for geographic region segmentation. Therefore, there is an urgent need for a region of interest segmentation method that can effectively improve accuracy and precision. Summary of the invention

[0003] Embodiments of the present disclosure provide a method, an apparatus, an electronic device, and a readable storage medium for segmenting a region of interest.

[0004] In a first aspect, a method for segmenting a region of interest is provided in an embodiment of the present disclosure.

[0005] Specifically, the region of interest segmentation method includes:

[0006] Obtain natural boundary elements located in the area to be segmented;

[0007] Based on the natural boundary elements, the area to be segmented is segmented into at least one initial segmented region of interest; based on the area and population of each of the initial segmented regions of interest, the at least one initial segmented region of interest is fused to obtain a final segmented region of interest of the area to be segmented.

[0008] In a second aspect, an apparatus for segmenting a region of interest is provided in an embodiment of the present disclosure.

[0009] Specifically, the region of interest segmentation device includes:

[0010] An acquisition module is configured to acquire natural boundary elements located in the area to be segmented;

[0011] A segmentation module is configured to segment the area to be segmented into at least one initial segmentation region of interest based on the natural boundary elements;

[0012] The fusion module is configured to fuse the at least one initially segmented region of interest based on the area and population of the at least one initially segmented region of interest to obtain a final segmented region of interest of the area to be segmented.

[0013] In a third aspect, an embodiment of the present disclosure provides an electronic device, comprising a memory and at least one processor, wherein the memory is used to store one or more computer instructions, and wherein the one or more computer instructions are executed by the at least one processor to implement the above method.

[0014] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium having computer instructions stored thereon, wherein the computer instructions implement the above method when executed by a processor.

[0015] The technical solution provided by the embodiments of the present disclosure may have the following beneficial effects:

[0016] The above technical solution first uses natural boundary elements to preliminarily segment the area to be segmented, and then fuses the initial segmented interest regions according to the area and population of the initial segmented interest regions to obtain the final segmented interest regions of the area to be segmented. This technical solution can not only ensure the pertinence of interest region segmentation by means of the initial division of interest regions and the fusion based on human and land data, but also effectively improve the accuracy and precision of interest region segmentation.

[0017] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Other features, objectives and advantages of the present disclosure will become more apparent through the following detailed description of non-limiting embodiments in conjunction with the accompanying drawings. In the accompanying drawings:

[0019] Figure 1 A flowchart showing a method for segmenting a region of interest according to an embodiment of the present disclosure is shown;

[0020] Figure 2A A schematic diagram of a region to be segmented according to an embodiment of the present disclosure is shown;

[0021] Figure 2B A schematic diagram of an initial segmentation region of interest according to an embodiment of the present disclosure is shown;

[0022] Figure 2C A schematic diagram showing an initial segmented region of interest before removing discontinuous roads according to an embodiment of the present disclosure;

[0023] Figure 2D A schematic diagram of a region of interest obtained after removing discontinuous roads according to an embodiment of the present disclosure is shown;

[0024] Figure 2E A schematic diagram of a region of interest before removing an initially segmented region of interest that is too small according to an embodiment of the present disclosure is shown;

[0025] Figure 2F A schematic diagram of a region of interest obtained after removing an initially segmented region of interest that is too small according to an embodiment of the present disclosure is shown;

[0026] Figure 2G A schematic diagram of a region of interest before fusion according to an embodiment of the present disclosure is shown;

[0027] Figure 2H A schematic diagram of a region of interest obtained after fusion according to an embodiment of the present disclosure is shown;

[0028] Fig.2I A schematic diagram of a region of interest before fusion according to an embodiment of the present disclosure is shown;

[0029] Figure 2J A schematic diagram of a region of interest obtained after region of interest fusion is achieved using a spectral clustering algorithm according to an embodiment of the present disclosure is shown;

[0030] Figure 3 A structural block diagram of a device for segmenting a region of interest according to an embodiment of the present disclosure is shown;

[0031] Figure 4 A structural block diagram of an electronic device according to an embodiment of the present disclosure is shown;

[0032] Figure 5 It is a structural schematic diagram of a computer system suitable for implementing a method for segmenting a region of interest according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0033] Hereinafter, exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings so that those skilled in the art can easily implement them. In addition, for the sake of clarity, parts not related to the description of the exemplary embodiments are omitted in the accompanying drawings.

[0034] In the present disclosure, it should be understood that terms such as "include" or "have" are intended to indicate the presence of features, numbers, steps, behaviors, components, parts, or a combination thereof disclosed in the present specification, and are not intended to exclude the possibility that one or more other features, numbers, steps, behaviors, components, parts, or a combination thereof exist or are added.

[0035] It should also be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present disclosure may be combined with each other. The present disclosure will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0036] The user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0037] Figure 1 A flowchart of a method for segmenting a region of interest according to an embodiment of the present disclosure is shown. Figure 1 As shown, the region of interest segmentation method includes the following steps S101-S103:

[0038] In step S101, natural boundary elements located in the area to be segmented are obtained;

[0039] In step S102, based on the natural boundary elements, the area to be segmented is segmented into at least one initial segmentation region of interest;

[0040] In step S103, based on the area and population of each of the initially segmented regions of interest, the at least one initially segmented region of interest is fused to obtain a final segmented region of interest of the area to be segmented.

[0041] As mentioned above, with the development of social economy, the targeted demand for geographic region segmentation is becoming more and more urgent. For example, the commercial field needs to segment commercial areas, the livelihood field needs to segment living areas or residential areas, etc. However, the accuracy and precision of the current geographic region segmentation methods are both lacking, and it is difficult to meet the current high accuracy and high precision requirements of geographic region segmentation for different business operations. Therefore, there is an urgent need for a region of interest segmentation solution that can effectively improve accuracy and precision.

[0042] In view of the above defects, in this embodiment, a method for segmenting a region of interest is provided, which first uses natural boundary elements to perform a preliminary segmentation of the region to be segmented, and then fuses the initial segmented regions of interest according to the area and population of the initial segmented regions of interest to obtain the final segmented regions of interest of the region to be segmented. This technical solution can not only ensure the pertinence of the segmentation of the region of interest by means of the initial division of the region of interest and the fusion based on human and land data, but also effectively improve the accuracy and precision of the segmentation of the region of interest.

[0043] In the present disclosure, the region of interest segmentation method may be integrated into software capable of segmenting the region of interest, and the software may be installed in an electronic device such as a mobile device, and the method is then executed by the electronic device.

[0044] The area to be segmented refers to an area that needs to be segmented into at least one region of interest. The area to be segmented may be, for example, an administrative region obtained based on boundary division, such as Figure 2A shown.

[0045] The natural boundary elements refer to naturally formed map elements with boundary functions, such as road networks, water systems, railways, etc.

[0046] Among them, based on the area and population size of each of the initially segmented regions of interest, the fusion of at least one of the initially segmented regions of interest refers to the fusion processing of the population size of the corresponding region of interest while considering the area of ​​the initially segmented region of interest. The region of interest obtained after the fusion can fully reflect the human and land characteristics of the region of interest, so that the segmentation of the region of interest has higher accuracy and precision.

[0047] In the above implementation, firstly, the natural boundary elements located in the area to be segmented are obtained; then, based on the natural boundary elements, the area to be segmented is preliminarily segmented to obtain at least one initial segmented region of interest; then, based on the area and population of each of the initial segmented regions of interest, the at least one initial segmented region of interest is fused to obtain the final result of segmenting the area to be segmented. The above technical solution can not only ensure the pertinence of the segmentation of the region of interest by means of the initial division of the region of interest and the fusion based on human and land data, but also effectively improve the accuracy and precision of the segmentation of the region of interest.

[0048] In an embodiment of the present disclosure, the step S102, i.e., the step of segmenting the area to be segmented into at least one initial segmented region of interest based on the natural boundary element, may include the following steps:

[0049] Gathering the natural boundary elements to obtain a natural boundary line;

[0050] Expanding the natural boundary line by a first distance in a direction from the center of the area to be segmented toward the periphery;

[0051] shrinking the expanded natural boundary line by a second distance along the periphery of the region to be segmented toward the center;

[0052] The region to be segmented is segmented into at least one initial segmented region of interest using the shrunk natural boundary line.

[0053] In this embodiment, when the area to be segmented is segmented into at least one initial segmented interest area based on the natural boundary elements, firstly, all the natural boundary elements located in the area to be segmented are collected to obtain a natural boundary line, that is, a union operation is performed on all the natural boundary elements in the area to be segmented to obtain a natural boundary line formed by all the natural boundary elements; then, in order to avoid the problem of uneven road connection in the interest area obtained by segmentation, a processing method of first expanding and then contracting the natural boundary line can be adopted, that is, firstly, the natural boundary line is expanded by a first distance along the center of the area to be segmented toward the periphery, and then the expanded natural boundary line is contracted by a second distance along the periphery of the area to be segmented toward the center. In one embodiment of the present disclosure, the expansion of the natural boundary line can be realized based on a buffer algorithm, and the contraction of the natural boundary line can be realized based on a debuffer algorithm. After a line is expanded by a first distance using a buffer algorithm, an expanded area will be formed, and the expanded area takes the line as the center line, and the distance from the center line to the area boundary line is the first distance. Since the natural boundary line is the union of all natural boundary elements of the area to be segmented, the use of the buffer to expand the natural boundary line can be understood as expanding the natural boundary elements separately, and the expansion areas obtained by the expansion are connected in parallel to obtain the expansion area corresponding to the natural boundary line, and the expansion area corresponding to the natural boundary line can be understood as the minimum enclosing area surrounding the expansion areas corresponding to each natural boundary element. Therefore, even if there may be some unevenness between the natural boundary elements, a complete expansion area will be formed after expansion, and after the expansion area is contracted, a corresponding smooth boundary line, that is, a smooth road, can be obtained. Therefore, in this embodiment, the natural boundary line is expanded by a first distance along the center of the area to be segmented toward the periphery through the buffer algorithm, and then the expanded natural boundary line is contracted by a second distance along the periphery of the area to be segmented toward the center through the debuffer algorithm, so as to achieve the smoothing effect of the road connection in the segmented area of ​​interest. Among them, the center of the area to be segmented can be, for example, the geometric center or geographical center of the area to be segmented; the first distance and the second distance can be set according to the needs of actual application. For example, if you want to enhance the smoothing effect of road connection, you can set the values ​​of the first distance and the second distance to be larger. Conversely, if you want to weaken the smoothing effect of road connection, you can set the values ​​of the first distance and the second distance to be smaller. In addition, the values ​​of the first distance and the second distance can be the same or different. The present disclosure does not specifically limit the specific values ​​of the first distance and the second distance. All values ​​of the first distance and the second distance that can eliminate the uneven road connection effect fall within the protection scope of the present disclosure; finally, the area to be segmented is segmented using the shrunk natural boundary line to obtain at least one initial segmented area of ​​interest.

[0054] The direction of the expansion process may also be considered as the direction from the center of the region to be segmented to the boundary point of the region to be segmented. Similarly, the direction of the contraction process may also be considered as the opposite direction from the center of the region to be segmented to the boundary point of the region to be segmented.

[0055] Taking into account that there may be established natural areas of a certain area such as oceans, lakes, rivers, canals, roads, and breeding green spaces in the area to be segmented, in order to protect the integrity of these established natural areas and avoid the boundaries of these established natural areas from affecting the segmentation of the area to be segmented, thereby improving the accuracy and precision of the segmentation of the area of ​​interest, in one embodiment of the present disclosure, these established natural areas in the area to be segmented may be removed first, and then based on the natural boundary elements, the area to be segmented may be segmented into at least one initial segmented area of ​​interest.

[0056] That is, in an embodiment of the present disclosure, before the step of segmenting the area to be segmented into at least one initial segmented region of interest based on the natural boundary element, the method may further include the following steps:

[0057] Acquire natural area elements located in the area to be segmented;

[0058] The natural area elements located in the area to be segmented are removed.

[0059] Among them, the natural area elements refer to the established natural areas of a certain area such as the oceans, lakes, rivers, canals, roads, and aquaculture green spaces mentioned above.

[0060] for Figure 2A The region to be segmented is segmented based on the natural boundary elements in the region to be segmented, and the initial segmented interest region obtained can be as follows Figure 2B shown.

[0061] Considering that after the preliminary segmentation of the region to be segmented, there will be some discontinuous roads formed by irregular roads such as internal roads in the initial segmented region of interest, and such initial segmented region of interest including discontinuous roads does not meet the requirement of region of interest segmentation for smoothness of regional boundaries. In addition, due to the existence of some complex road networks, such as overpasses, the initial segmented region of interest obtained based on the segmentation of these complex road networks is too small, and these regions of interest with too small areas are usually not considered in practical applications. Therefore, it is necessary to correct the above-mentioned irregular regions of interest to remove the discontinuous roads in the initial segmented region of interest, and / or remove the initial segmented region of interest with too small areas.

[0062] That is, in one embodiment of the present disclosure, after the step of segmenting the area to be segmented into at least one initial segmented region of interest based on the natural boundary element, the method may further include the following steps:

[0063] The initially segmented region of interest is corrected.

[0064] Specifically, in one embodiment of the present disclosure, the step of performing correction processing on the initially segmented region of interest may include the following steps:

[0065] Using the boundary line of the initially segmented region of interest, removing discontinuous roads in the initially segmented region of interest; and / or,

[0066] The boundary lines of the initially segmented interest regions are used to remove the initially segmented interest regions whose areas are smaller than a preset area threshold.

[0067] More specifically, in an embodiment of the present disclosure, the step of removing discontinuous roads in the initially segmented region of interest by using the boundary line of the initially segmented region of interest may include the following steps:

[0068] Expanding the boundary line of the initially segmented region of interest by a third distance in a direction from the center of the initially segmented region of interest toward the periphery;

[0069] The boundary line of the initially segmented region of interest after expansion is shrunk by a third distance in a direction from the periphery of the initially segmented region of interest toward the center.

[0070] In this embodiment, when using the boundary line of the initial segmented region of interest to remove the discontinuous road in the initial segmented region of interest, the boundary line expansion and contraction scheme is still considered, that is, firstly, the boundary line of the initial segmented region of interest is expanded by a third distance along the center of the initial segmented region of interest toward the periphery, and then the expanded boundary line of the initial segmented region of interest is contracted by a third distance along the periphery of the initial segmented region of interest toward the center. In one embodiment of the present disclosure, the expansion of the boundary line of the initial segmented region of interest can be achieved based on a buffer algorithm, and the contraction of the boundary line of the initial segmented region of interest can be achieved based on a debuffer algorithm. As described above, after the expansion of each boundary element in the boundary line in this embodiment, the corresponding expansion area will be combined to form a complete expansion area corresponding to the boundary line. The complete expansion area eliminates the discontinuities between the boundary elements, so that after the complete expansion area is contracted, the boundary line obtained is continuous. Therefore, in this embodiment, the boundary line of the initial segmented region of interest is expanded by a third distance along the center of the initial segmented region of interest toward the periphery through a buffer algorithm, and then the boundary line of the expanded initial segmented region of interest is contracted by a third distance along the periphery of the initial segmented region of interest toward the center through a debuffer algorithm, so as to achieve the effect of removing the discontinuous roads in the initial segmented region of interest. The third distance can also be set according to the needs of the actual application. For example, if you want to enhance the removal effect of the discontinuous roads in the initial segmented region of interest, you can set the value of the third distance to be larger. Conversely, if you want to weaken the removal effect of the discontinuous roads in the initial segmented region of interest, you can set the value of the third distance to be smaller. Figure 2C FIG. 1 is a schematic diagram of an initial segmentation region of interest before removing discontinuous roads according to an embodiment of the present disclosure. Figure 2D FIG. 4 is a schematic diagram of a region of interest obtained after removing discontinuous roads according to an embodiment of the present disclosure.

[0071] Specifically, in an embodiment of the present disclosure, the step of removing the initially segmented interest regions whose areas are smaller than a preset area threshold by using the boundary lines of the initially segmented interest regions may include the following steps:

[0072] shrinking the boundary line of the initially segmented region of interest by a fourth distance along the periphery of the initially segmented region of interest toward the center;

[0073] If the initially segmented region of interest still exists after the boundary line shrinks, retaining the initially segmented region of interest;

[0074] If the initially segmented region of interest disappears after the boundary line shrinks, the initially segmented region of interest is deleted.

[0075] In this embodiment, when using the boundary line of the initial segmented region of interest to remove the initial segmented region of interest whose area is smaller than the preset area threshold, the shrinkage of the boundary line is used to determine whether the initial segmented region of interest is a region of interest with an area that is too small. Specifically, the boundary line of the initial segmented region of interest is first shrunk by a fourth distance along the periphery of the initial segmented region of interest toward the center, and then it is determined whether the initial segmented region of interest still exists after the boundary line of the initial segmented region of interest is shrunk. If the initial segmented region of interest exists, it means that the area of ​​the initial segmented region of interest is not too small. At this time, the initial segmented region of interest is retained. If the initial segmented region of interest no longer exists, it means that the area of ​​the initial segmented region of interest is indeed too small. At this time, the initial segmented region of interest is deleted. In one embodiment of the present disclosure, the shrinkage of the boundary line of the initial segmented region of interest can be achieved based on a debuffer algorithm. Among them, the fourth distance can also be set according to the needs of actual application. For example, if you want to enhance the effect of removing the interest region with too small area in the initial segmentation interest region, the value of the fourth distance can be set to be larger. Conversely, if you want to weaken the effect of removing the interest region with too small area in the initial segmentation interest region, the value of the fourth distance can be set to be smaller. Figure 2E FIG. 1 is a schematic diagram of a region of interest before removing an initially segmented region of interest with an area too small according to an embodiment of the present disclosure. Figure 2F It is a schematic diagram of a region of interest obtained after removing the initially segmented region of interest with too small an area according to an embodiment of the present disclosure.

[0076] After the above preliminary segmentation of the area to be segmented, the interest region with higher segmentation accuracy can be obtained. However, in order to meet the segmentation requirements of the interest region in actual application scenarios, it is also necessary to further integrate the interest region based on the area and population size of the interest region, so that the integrated interest region can reflect the geographical characteristics such as the area and population size of the interest region, thereby facilitating the development of related businesses based on the interest region.

[0077] In one embodiment of the present disclosure, the step S103, i.e., fusing the at least one initially segmented region of interest based on the area and population of the at least one initially segmented region of interest to obtain the final segmented region of interest of the region to be segmented, may include the following steps:

[0078] Acquire a topological connection relationship between the at least one initially segmented region of interest;

[0079] Based on the area, population and topological connection relationship of the at least one initial segmented region of interest, the at least one initial segmented region of interest is fused to obtain a final segmented region of interest of the area to be segmented, wherein the total population of the final segmented region of interest is greater than or equal to a preset population threshold.

[0080] In this embodiment, when the at least one initially segmented region of interest is fused based on the area and population of the at least one initially segmented region of interest, the at least one initially segmented region of interest is fused with the help of the topological connection relationship between the at least one initially segmented region of interest, the area and population of the at least one initially segmented region of interest, so that the total population of each region of interest obtained after fusion is greater than or equal to a preset population threshold. The preset population threshold is related to the segmentation purpose of the region of interest and can be set according to the needs of the actual application. The topological connection relationship between the initially segmented regions of interest is used to express the relative position relationship between the initially segmented regions of interest, such as whether two initially segmented regions of interest are adjacent or non-adjacent.

[0081] Specifically, in one embodiment of the present disclosure, the step of fusing the at least one initially segmented region of interest based on the area, population and topological connection relationship of the at least one initially segmented region of interest to obtain the final segmented region of interest of the region to be segmented may include the following steps:

[0082] Sorting the at least one initially segmented region of interest in ascending order of area of ​​the at least one initially segmented region of interest to obtain an initially segmented region of interest sequence;

[0083] For the unprocessed initial segmentation region of interest with the smallest area in the sequence of initial segmentation regions of interest, if it is determined that its population is greater than or equal to the preset population threshold, the initial segmentation region of interest is used as a final segmentation region of interest of the area to be segmented, and the next unprocessed initial segmentation region of interest in the sequence of initial segmentation regions of interest is processed; if it is determined that its population is less than the preset population threshold, the unprocessed initial segmentation region of interest in the sequence of initial segmentation regions of interest closest to the initial segmentation region of interest is determined according to the topological connection relationship, the populations of the two initial segmentation regions of interest are added, and if it is determined that the total population after the addition is greater than or equal to the preset population threshold, the two initial segmentation regions of interest are merged as the A final segmented interest region of the area to be segmented, continue to process the next unprocessed initial segmented interest region in the initial segmented interest region sequence; if it is determined that the total population after addition is less than the preset population threshold, the two interest regions are merged, and the unprocessed initial segmented interest region in the initial segmented interest region sequence that is closest to the interest region obtained by merging the two interest regions is determined according to the topological connection relationship, and the steps of adding the population and comparing with the preset population threshold are performed until the total population of the obtained interest region is greater than or equal to the preset population threshold, and the obtained interest region is used as a final segmented interest region of the area to be segmented; and so on, the final segmented interest region of the area to be segmented is obtained.

[0084] In this implementation, the initially segmented regions of interest may be directly merged based on the area, population, and topological connection relationship of the initially segmented regions of interest. Specifically:

[0085] Firstly, the at least one initially segmented region of interest is sorted in ascending order of area of ​​the at least one initially segmented region of interest to obtain an initially segmented region of interest sequence;

[0086] Then, for the first unprocessed initial segmented interest region in the sequence of initial segmented interest regions, that is, the unprocessed initial segmented interest region with the smallest area, it is determined whether its population is greater than or equal to the preset population threshold. If the population of the interest region is greater than or equal to the preset population threshold, it means that the interest region can meet the segmentation condition of the interest region, that is, the total population of the fused interest region is greater than or equal to the preset population threshold. It does not need to be merged with other interest regions, and can be directly used as a final segmented interest region of the to-be-segmented region. Then, the next unprocessed initial segmented interest region in the sequence of initial segmented interest regions can be processed, that is, the second unprocessed initial segmented interest region in the sequence of initial segmented interest regions.

[0087] If the population of the region of interest is less than the preset population threshold, it means that the region of interest does not meet the segmentation condition of the region of interest at present, and it needs to be merged with other regions of interest before judgment. When merging it with other regions of interest, the unprocessed initial segmentation region of interest closest to the initial segmentation region of interest in the sequence of initial segmentation regions of interest can be determined according to the topological connection relationship between the regions of interest obtained in advance, and the populations of the two initial segmentation regions of interest are added, and then it is judged whether the total population after the addition is greater than or equal to the preset population threshold. If the total population after the addition is greater than or equal to the preset population threshold, it means that the two initial segmentation regions of interest can meet the segmentation condition of the region of interest after fusion, that is, the region of interest obtained after the fusion of the two initial segmentation regions of interest can be used as a final segmentation region of interest of the region to be segmented, and then the next unprocessed initial segmentation region of interest in the sequence of initial segmentation regions of interest can be processed;

[0088] If the total population after addition is still less than the preset population threshold, it means that even if the two interest regions are fused, the segmentation conditions of the interest region cannot be met, and it is necessary to continue to fuse the interest region obtained after the fusion of the two interest regions with other interest regions before making another judgment. When the interest region obtained after the fusion of the two interest regions is fused with other interest regions again, similar to the above description, the interest region closest to the fused interest region is still determined based on the topological connection relationship between the interest regions obtained in advance, and then the population of the fused interest region and the interest region closest to it are added, and then it is judged whether the total population after addition is greater than or equal to the preset population threshold, and so on, until the total population of the interest region is greater than or equal to the preset population threshold. Figure 2G FIG. 1 is a schematic diagram of a region of interest before fusion according to an embodiment of the present disclosure. Figure 2H Shown is a schematic diagram of a region of interest obtained after fusion according to an embodiment of the present disclosure.

[0089] In another embodiment of the present disclosure, the fusion judgment can also be started from the initial segmented interest region with the largest area, and when the population is insufficient, the current interest region is fused with the area with the smallest area among the n nearest unprocessed initial segmented interest regions, so that the area distribution of the final segmented interest region is more uniform.

[0090] That is, in another embodiment of the present disclosure, the step of fusing the at least one initially segmented region of interest based on the area, population and topological connection relationship of the at least one initially segmented region of interest to obtain the final segmented region of interest of the area to be segmented may include the following steps:

[0091] Sorting the at least one initially segmented region of interest in descending order of area to obtain an initially segmented region of interest sequence;

[0092] For the unprocessed initial segmented interest region with the largest area in the sequence of initial segmented interest regions, if it is determined that its population is greater than or equal to the preset population threshold, the initial segmented interest region is used as a final segmented interest region of the region to be segmented, and the next unprocessed initial segmented interest region in the sequence of initial segmented interest regions is processed continuously; if it is determined that its population is less than the preset population threshold, the population of the unprocessed initial segmented interest region with the smallest area among the N unprocessed initial segmented interest regions closest to the initial segmented interest region in the sequence of initial segmented interest regions is added according to the topological connection relationship; if it is determined that the total population after the addition is greater than or equal to the preset population threshold, the two initial segmented interest regions are merged as the region to be segmented. A final segmented interest region of the segmented area, continue to process the next unprocessed initial segmented interest region in the initial segmented interest region sequence; if it is determined that the total population after addition is less than the preset population threshold, the two interest regions are merged, and the N unprocessed initial segmented interest regions with the smallest area among the interest region obtained by merging the two interest regions in the initial segmented interest region sequence that are closest to the interest region obtained by merging the two interest regions are determined according to the topological connection relationship, and the steps of adding the population numbers and comparing with the preset population threshold are performed until the total population number of the obtained interest region is greater than or equal to the preset population threshold, and the obtained interest region is used as a final segmented interest region of the area to be segmented; and so on, the final segmented interest region of the area to be segmented is obtained.

[0093] In one embodiment of the present disclosure, the above-mentioned fusion process of the regions of interest can also be implemented with the help of a graph node structure established based on the regions of interest. For example, the initially segmented regions of interest can be used as nodes in the graph node structure, and the node attributes of each node may include attribute data such as the area size, population size, and region type of the corresponding region of interest. The graph node structure also includes a corresponding topological structure relationship stack, wherein the topological structure relationship stack describes the topological relationship between the regions of interest and sorts the regions of interest in order from small to large in terms of area. When the graph node structure is used to fuse the regions of interest, each unprocessed graph node in the graph node structure can be traversed in sequence according to the fusion scheme described above to achieve the fusion of the regions of interest. The present disclosure will not go into details about the specific traversal process.

[0094] In another embodiment of the present disclosure, the spectral clustering algorithm may be used to realize the fusion of interest regions. That is, in yet another embodiment of the present disclosure, the step of fusing the at least one initially segmented interest region based on the area and population of the at least one initially segmented interest region to obtain the final segmented interest region of the area to be segmented may include the following steps:

[0095] Acquire a topological connection relationship between the at least one initially segmented region of interest;

[0096] Generate a graph node structure corresponding to the at least one initially segmented region of interest according to the topological connection relationship, wherein the graph node of the graph node structure is the initially segmented region of interest, and the graph node attributes include at least the area size and population of the initially segmented region of interest;

[0097] Extracting a feature vector of the graph node, wherein the feature vector can represent the area size and population size of the graph node;

[0098] Clustering fusion based on area size and population size is performed according to the feature vectors of the graph nodes to obtain the final segmented region of interest of the area to be segmented, wherein the total population of the final segmented region of interest is greater than or equal to a preset population threshold, and the area variance of the final segmented region of interest is less than a preset variance threshold.

[0099] In this embodiment, when the spectral clustering algorithm is used to realize the fusion of the interest region, it is also necessary to first obtain the topological connection relationship between the at least one initial segmented interest region; then, based on the topological connection relationship, generate the graph node structure corresponding to the at least one initial segmented interest region, similar to the above description, the graph node of the graph node structure is the initial segmented interest region, and the graph node attributes at least include the area size and population of the initial segmented interest region; then extract the feature vector of the graph node, wherein the feature vector is used to characterize the area size and population of the graph node, and perform clustering fusion based on the area size and population based on the feature vector of the graph node to obtain the final segmented interest region of the area to be segmented, so that the total population of the final segmented interest region is greater than or equal to the preset population threshold, and the area variance of the final segmented interest region is less than the preset variance threshold. Among them, the feature vector of the graph node can be selected according to the needs of the actual application, that is, the selection and extraction of the feature vector of the graph node, and the clustering fusion based on the area size and population based on the feature vector of the graph node belong to the skills that those skilled in the art should master, and the present disclosure does not repeat its specific implementation process. Fig.2I FIG. 1 is a schematic diagram of a region of interest before fusion according to an embodiment of the present disclosure. Figure 2J It is a schematic diagram of a region of interest obtained after the region of interest is fused using a spectral clustering algorithm according to an embodiment of the present disclosure.

[0100] The following are embodiments of the apparatus of the present disclosure, which can be used to execute embodiments of the method of the present disclosure.

[0101] Figure 3 FIG. 1 is a block diagram showing a structure of a device for segmenting a region of interest according to an embodiment of the present disclosure. The device can be implemented as part or all of an electronic device through software, hardware, or a combination of both. Figure 3 As shown, the region of interest segmentation device includes:

[0102] An acquisition module 301 is configured to acquire natural boundary elements located in the area to be segmented;

[0103] The segmentation module 302 is configured to segment the area to be segmented into at least one initial segmentation region of interest based on the natural boundary elements;

[0104] The fusion module 303 is configured to fuse the at least one initially segmented region of interest based on the area and population of the at least one initially segmented region of interest to obtain a final segmented region of interest of the area to be segmented.

[0105] As mentioned above, with the development of social economy, the targeted demand for geographic region segmentation is becoming more and more urgent. For example, the commercial field needs to segment commercial areas, the livelihood field needs to segment living areas or residential areas, etc. However, the accuracy and precision of the current geographic region segmentation schemes are both lacking, and it is difficult to meet the high accuracy and high precision requirements of the current different business operations for geographic region segmentation. Therefore, there is an urgent need for a region of interest segmentation scheme that can effectively improve accuracy and precision.

[0106] In view of the above defects, in this embodiment, a device for segmenting a region of interest is provided, which first uses natural boundary elements to perform preliminary segmentation of the region to be segmented, and then fuses the initial segmented regions of interest according to the area and population of the initial segmented regions of interest to obtain the final segmented regions of interest of the region to be segmented. This technical solution can not only ensure the pertinence of the segmentation of the region of interest by means of the initial division of the region of interest and the fusion based on human and land data, but also effectively improve the accuracy and precision of the segmentation of the region of interest.

[0107] In the present disclosure, the apparatus for segmenting the region of interest may be implemented as an electronic device such as a mobile device installed with software capable of segmenting the region of interest.

[0108] The area to be segmented refers to an area that needs to be segmented into at least one region of interest. The area to be segmented may be, for example, an administrative region obtained based on boundary division, such as Figure 2A shown.

[0109] The natural boundary elements refer to naturally formed map elements with boundary functions, such as road networks, water systems, railways, etc.

[0110] Among them, based on the area and population size of each of the initially segmented regions of interest, the fusion of at least one of the initially segmented regions of interest refers to the fusion processing of the population size of the corresponding region of interest while considering the area of ​​the initially segmented region of interest. The region of interest obtained after the fusion can fully reflect the human and land characteristics of the region of interest, so that the segmentation of the region of interest has higher accuracy and precision.

[0111] In the above implementation, firstly, the natural boundary elements located in the area to be segmented are obtained; then, based on the natural boundary elements, the area to be segmented is preliminarily segmented to obtain at least one initial segmented region of interest; then, based on the area and population of each of the initial segmented regions of interest, the at least one initial segmented region of interest is fused to obtain the final result of segmenting the area to be segmented. The above technical solution can not only ensure the pertinence of the segmentation of the region of interest by means of the initial division of the region of interest and the fusion based on human and land data, but also effectively improve the accuracy and precision of the segmentation of the region of interest.

[0112] In one embodiment of the present disclosure, the segmentation module may be configured as follows:

[0113] Gathering the natural boundary elements to obtain a natural boundary line;

[0114] Expanding the natural boundary line by a first distance in a direction from the center of the area to be segmented toward the periphery;

[0115] shrinking the expanded natural boundary line by a second distance along the periphery of the region to be segmented toward the center;

[0116] The region to be segmented is segmented into at least one initial segmented region of interest using the shrunk natural boundary line.

[0117] In this embodiment, when the area to be segmented is segmented into at least one initial segmentation area of ​​interest based on the natural boundary elements, firstly, all the natural boundary elements located in the area to be segmented are collected to obtain a natural boundary line, that is, a union operation is performed on all the natural boundary elements in the area to be segmented to obtain a natural boundary line formed by all the natural boundary elements; then, in order to avoid the problem of uneven road connections in the segmented area of ​​interest, a processing method of first expanding and then contracting the natural boundary line can be adopted, that is, firstly the natural boundary line is expanded by a first distance along the center of the area to be segmented toward the periphery, and then the expanded natural boundary line is contracted by a second distance along the periphery of the area to be segmented toward the center. In one embodiment of the present disclosure, the expansion of the natural boundary line can be achieved based on a buffer algorithm, and the contraction of the natural boundary line can be achieved based on a debuffer algorithm. After a line is expanded by a first distance using the buffer algorithm, an expanded area will be formed, and the expanded area has the line as the center line, and the distance from the center line to the area boundary line is the first distance. Since the natural boundary line is the union of all natural boundary elements of the area to be segmented, the use of the buffer to expand the natural boundary line can be understood as expanding the natural boundary elements separately, and the expansion areas obtained by the expansion are connected in parallel to obtain the expansion area corresponding to the natural boundary line, and the expansion area corresponding to the natural boundary line can be understood as the minimum enclosing area surrounding the expansion areas corresponding to each natural boundary element. Therefore, even if there may be some unevenness between the natural boundary elements, a complete expansion area will be formed after expansion, and after the expansion area is contracted, a corresponding smooth boundary line, that is, a smooth road, can be obtained. Therefore, in this embodiment, the natural boundary line is expanded by a first distance along the center of the area to be segmented toward the periphery through the buffer algorithm, and then the expanded natural boundary line is contracted by a second distance along the periphery of the area to be segmented toward the center through the debuffer algorithm, so as to achieve the smoothing effect of the road connection in the segmented area of ​​interest. Among them, the center of the area to be segmented can be, for example, the geometric center or geographical center of the area to be segmented; the first distance and the second distance can be set according to the needs of actual application. For example, if you want to enhance the smoothing effect of road connection, you can set the values ​​of the first distance and the second distance to be larger. Conversely, if you want to weaken the smoothing effect of road connection, you can set the values ​​of the first distance and the second distance to be smaller. In addition, the values ​​of the first distance and the second distance can be the same or different. The present disclosure does not specifically limit the specific values ​​of the first distance and the second distance. All values ​​of the first distance and the second distance that can eliminate the uneven road connection effect fall within the protection scope of the present disclosure; finally, the area to be segmented is segmented using the shrunk natural boundary line to obtain at least one initial segmented area of ​​interest.

[0118] The direction of the expansion process may also be considered as the direction from the center of the region to be segmented to the boundary point of the region to be segmented. Similarly, the direction of the contraction process may also be considered as the opposite direction from the center of the region to be segmented to the boundary point of the region to be segmented.

[0119] Taking into account that there may be established natural areas of a certain area such as oceans, lakes, rivers, canals, roads, and breeding green spaces in the area to be segmented, in order to protect the integrity of these established natural areas and avoid the boundaries of these established natural areas from affecting the segmentation of the area to be segmented, thereby improving the accuracy and precision of the segmentation of the area of ​​interest, in one embodiment of the present disclosure, these established natural areas in the area to be segmented may be removed first, and then based on the natural boundary elements, the area to be segmented may be segmented into at least one initial segmented area of ​​interest.

[0120] That is, in one embodiment of the present disclosure, before the segmentation module, the device may further include:

[0121] The removal module is configured to obtain the natural area elements located in the area to be segmented; and remove the natural area elements located in the area to be segmented.

[0122] Among them, the natural area elements refer to the established natural areas of a certain area such as the oceans, lakes, rivers, canals, roads, and aquaculture green spaces mentioned above.

[0123] for Figure 2A The region to be segmented is segmented based on the natural boundary elements in the region to be segmented, and the initial segmented interest region obtained can be as follows Figure 2B shown.

[0124] Considering that after the preliminary segmentation of the region to be segmented, there will be some discontinuous roads formed by irregular roads such as internal roads in the initial segmented region of interest, and such initial segmented region of interest including discontinuous roads does not meet the requirement of region of interest segmentation for smoothness of regional boundaries. In addition, due to the existence of some complex road networks, such as overpasses, the initial segmented region of interest obtained based on the segmentation of these complex road networks is too small, and these regions of interest with too small areas are usually not considered in practical applications. Therefore, it is necessary to correct the above-mentioned irregular regions of interest to remove the discontinuous roads in the initial segmented region of interest, and / or remove the initial segmented region of interest with too small areas.

[0125] That is, in one embodiment of the present disclosure, after the segmentation module, the device may further include:

[0126] The correction module is configured to perform correction processing on the initially segmented region of interest.

[0127] Specifically, in one embodiment of the present disclosure, the correction module may be configured as follows:

[0128] Using the boundary line of the initially segmented region of interest, removing discontinuous roads in the initially segmented region of interest; and / or,

[0129] The boundary lines of the initially segmented interest regions are used to remove the initially segmented interest regions whose areas are smaller than a preset area threshold.

[0130] More specifically, in an embodiment of the present disclosure, the use of the boundary line of the initially segmented region of interest to remove the discontinuous road portion in the initially segmented region of interest may be configured as follows:

[0131] Expanding the boundary line of the initially segmented region of interest by a third distance in a direction from the center of the initially segmented region of interest toward the periphery;

[0132] The boundary line of the initially segmented region of interest after expansion is shrunk by a third distance in a direction from the periphery of the initially segmented region of interest toward the center.

[0133] In this embodiment, when using the boundary line of the initial segmented region of interest to remove the discontinuous road in the initial segmented region of interest, the boundary line expansion and contraction scheme is still considered, that is, firstly, the boundary line of the initial segmented region of interest is expanded by a third distance along the center of the initial segmented region of interest toward the periphery, and then the expanded boundary line of the initial segmented region of interest is contracted by a third distance along the periphery of the initial segmented region of interest toward the center. In one embodiment of the present disclosure, the expansion of the boundary line of the initial segmented region of interest can be achieved based on a buffer algorithm, and the contraction of the boundary line of the initial segmented region of interest can be achieved based on a debuffer algorithm. As described above, after the expansion of each boundary element in the boundary line in this embodiment, the corresponding expansion area will be combined to form a complete expansion area corresponding to the boundary line. The complete expansion area eliminates the discontinuities between the boundary elements, so that after the complete expansion area is contracted, the boundary line obtained is continuous. Therefore, in this embodiment, the boundary line of the initial segmented region of interest is expanded by a third distance along the center of the initial segmented region of interest toward the periphery through a buffer algorithm, and then the boundary line of the expanded initial segmented region of interest is contracted by a third distance along the periphery of the initial segmented region of interest toward the center through a debuffer algorithm, so as to achieve the effect of removing the discontinuous roads in the initial segmented region of interest. The third distance can also be set according to the needs of the actual application. For example, if you want to enhance the removal effect of the discontinuous roads in the initial segmented region of interest, you can set the value of the third distance to be larger. Conversely, if you want to weaken the removal effect of the discontinuous roads in the initial segmented region of interest, you can set the value of the third distance to be smaller. Figure 2C FIG. 1 is a schematic diagram of an initial segmentation region of interest before removing discontinuous roads according to an embodiment of the present disclosure. Figure 2D FIG. 4 is a schematic diagram of a region of interest obtained after removing discontinuous roads according to an embodiment of the present disclosure.

[0134] Specifically, in an embodiment of the present disclosure, the use of the boundary line of the initially segmented region of interest to remove a portion of the initially segmented region of interest whose area is smaller than a preset area threshold may be configured as follows:

[0135] shrinking the boundary line of the initially segmented region of interest by a fourth distance in a direction from the periphery of the initially segmented region of interest toward the center;

[0136] If the initially segmented region of interest still exists after the boundary line shrinks, retaining the initially segmented region of interest;

[0137] If the initially segmented region of interest disappears after the boundary line shrinks, the initially segmented region of interest is deleted.

[0138] In this embodiment, when using the boundary line of the initial segmented region of interest to remove the initial segmented region of interest whose area is smaller than the preset area threshold, the shrinkage of the boundary line is used to determine whether the initial segmented region of interest is a region of interest with an area that is too small. Specifically, the boundary line of the initial segmented region of interest is first shrunk by a fourth distance along the periphery of the initial segmented region of interest toward the center, and then it is determined whether the initial segmented region of interest still exists after the boundary line of the initial segmented region of interest is shrunk. If the initial segmented region of interest exists, it means that the area of ​​the initial segmented region of interest is not too small. At this time, the initial segmented region of interest is retained. If the initial segmented region of interest no longer exists, it means that the area of ​​the initial segmented region of interest is indeed too small. At this time, the initial segmented region of interest is deleted. In one embodiment of the present disclosure, the shrinkage of the boundary line of the initial segmented region of interest can be achieved based on a debuffer algorithm. Among them, the fourth distance can also be set according to the needs of actual application. For example, if you want to enhance the effect of removing the interest region with too small area in the initial segmentation interest region, the value of the fourth distance can be set to be larger. Conversely, if you want to weaken the effect of removing the interest region with too small area in the initial segmentation interest region, the value of the fourth distance can be set to be smaller. Figure 2E FIG. 1 is a schematic diagram of a region of interest before removing an initially segmented region of interest with an area too small according to an embodiment of the present disclosure. Figure 2F It is a schematic diagram of a region of interest obtained after removing the initially segmented region of interest with too small an area according to an embodiment of the present disclosure.

[0139] After the above preliminary segmentation of the area to be segmented, the interest region with higher segmentation accuracy can be obtained. However, in order to meet the segmentation requirements of the interest region in actual application scenarios, it is also necessary to further integrate the interest region based on the area and population size of the interest region, so that the integrated interest region can reflect the geographical characteristics such as the area and population size of the interest region, thereby facilitating the development of related businesses based on the interest region.

[0140] In one embodiment of the present disclosure, the fusion module may be configured as follows:

[0141] Acquire a topological connection relationship between the at least one initially segmented region of interest;

[0142] Based on the area, population and topological connection relationship of the at least one initial segmented region of interest, the at least one initial segmented region of interest is fused to obtain a final segmented region of interest of the area to be segmented, wherein the total population of the final segmented region of interest is greater than or equal to a preset population threshold.

[0143] In this embodiment, when the at least one initially segmented region of interest is fused based on the area and population of the at least one initially segmented region of interest, the at least one initially segmented region of interest is fused with the help of the topological connection relationship between the at least one initially segmented region of interest, the area and population of the at least one initially segmented region of interest, so that the total population of each region of interest obtained after fusion is greater than or equal to a preset population threshold. The preset population threshold is related to the segmentation purpose of the region of interest and can be set according to the needs of the actual application. The topological connection relationship between the initially segmented regions of interest is used to express the relative position relationship between the initially segmented regions of interest, such as whether two initially segmented regions of interest are adjacent or non-adjacent.

[0144] Specifically, in one embodiment of the present disclosure, the part of fusing the at least one initially segmented region of interest based on the area, population and topological connection relationship of the at least one initially segmented region of interest to obtain the final segmented region of interest of the region to be segmented may be configured as follows:

[0145] Sorting the at least one initially segmented region of interest in ascending order of area of ​​the at least one initially segmented region of interest to obtain an initially segmented region of interest sequence;

[0146] For the unprocessed initial segmentation region of interest with the smallest area in the sequence of initial segmentation regions of interest, if it is determined that its population is greater than or equal to the preset population threshold, the initial segmentation region of interest is used as a final segmentation region of interest of the area to be segmented, and the next unprocessed initial segmentation region of interest in the sequence of initial segmentation regions of interest is processed; if it is determined that its population is less than the preset population threshold, the unprocessed initial segmentation region of interest in the sequence of initial segmentation regions of interest closest to the initial segmentation region of interest is determined according to the topological connection relationship, the populations of the two initial segmentation regions of interest are added, and if it is determined that the total population after the addition is greater than or equal to the preset population threshold, the two initial segmentation regions of interest are merged as the A final segmented interest region of the area to be segmented, continue to process the next unprocessed initial segmented interest region in the initial segmented interest region sequence; if it is determined that the total population after addition is less than the preset population threshold, the two interest regions are merged, and the unprocessed initial segmented interest region in the initial segmented interest region sequence that is closest to the interest region obtained by merging the two interest regions is determined according to the topological connection relationship, and the steps of adding the population and comparing with the preset population threshold are performed until the total population of the obtained interest region is greater than or equal to the preset population threshold, and the obtained interest region is used as a final segmented interest region of the area to be segmented; and so on, the final segmented interest region of the area to be segmented is obtained.

[0147] In this implementation, the initially segmented regions of interest may be directly merged based on the area, population, and topological connection relationship of the initially segmented regions of interest. Specifically:

[0148] Firstly, the at least one initially segmented region of interest is sorted in ascending order of area of ​​the at least one initially segmented region of interest to obtain an initially segmented region of interest sequence;

[0149] Then, for the first unprocessed initial segmented interest region in the sequence of initial segmented interest regions, that is, the unprocessed initial segmented interest region with the smallest area, it is determined whether its population is greater than or equal to the preset population threshold. If the population of the interest region is greater than or equal to the preset population threshold, it means that the interest region can meet the segmentation condition of the interest region, that is, the total population of the fused interest region is greater than or equal to the preset population threshold. It does not need to be merged with other interest regions, and can be directly used as a final segmented interest region of the to-be-segmented region. Then, the next unprocessed initial segmented interest region in the sequence of initial segmented interest regions can be processed, that is, the second unprocessed initial segmented interest region in the sequence of initial segmented interest regions.

[0150] If the population of the region of interest is less than the preset population threshold, it means that the region of interest does not meet the segmentation condition of the region of interest at present, and it needs to be merged with other regions of interest before judgment. When merging it with other regions of interest, the unprocessed initial segmentation region of interest closest to the initial segmentation region of interest in the sequence of initial segmentation regions of interest can be determined according to the topological connection relationship between the regions of interest obtained in advance, and the populations of the two initial segmentation regions of interest are added, and then it is judged whether the total population after the addition is greater than or equal to the preset population threshold. If the total population after the addition is greater than or equal to the preset population threshold, it means that the two initial segmentation regions of interest can meet the segmentation condition of the region of interest after fusion, that is, the region of interest obtained after the fusion of the two initial segmentation regions of interest can be used as a final segmentation region of interest of the region to be segmented, and then the next unprocessed initial segmentation region of interest in the sequence of initial segmentation regions of interest can be processed;

[0151] If the total population after addition is still less than the preset population threshold, it means that even if the two interest regions are fused, the segmentation conditions of the interest region cannot be met, and it is necessary to continue to fuse the interest region obtained after the fusion of the two interest regions with other interest regions before making another judgment. When the interest region obtained after the fusion of the two interest regions is fused with other interest regions again, similar to the above description, the interest region closest to the fused interest region is still determined based on the topological connection relationship between the interest regions obtained in advance, and then the population of the fused interest region and the interest region closest to it are added, and then it is judged whether the total population after addition is greater than or equal to the preset population threshold, and so on, until the total population of the interest region is greater than or equal to the preset population threshold. Figure 2G FIG. 1 is a schematic diagram of a region of interest before fusion according to an embodiment of the present disclosure. Figure 2H Shown is a schematic diagram of a region of interest obtained after fusion according to an embodiment of the present disclosure.

[0152] In another embodiment of the present disclosure, the fusion judgment can also be started from the initial segmented interest region with the largest area, and when the population is insufficient, the current interest region is fused with the area with the smallest area among the n nearest unprocessed initial segmented interest regions, so that the area distribution of the final segmented interest region is more uniform.

[0153] That is, in another embodiment of the present disclosure, the part of fusing the at least one initially segmented region of interest based on the area, population and topological connection relationship of the at least one initially segmented region of interest to obtain the final segmented region of interest of the region to be segmented may be configured as follows:

[0154] Sorting the at least one initially segmented region of interest in descending order of area to obtain an initially segmented region of interest sequence;

[0155] For the unprocessed initial segmented interest region with the largest area in the sequence of initial segmented interest regions, if it is determined that its population is greater than or equal to the preset population threshold, the initial segmented interest region is used as a final segmented interest region of the region to be segmented, and the next unprocessed initial segmented interest region in the sequence of initial segmented interest regions is processed continuously; if it is determined that its population is less than the preset population threshold, the population of the unprocessed initial segmented interest region with the smallest area among the N unprocessed initial segmented interest regions closest to the initial segmented interest region in the sequence of initial segmented interest regions is added according to the topological connection relationship; if it is determined that the total population after the addition is greater than or equal to the preset population threshold, the two initial segmented interest regions are merged as the region to be segmented. A final segmented interest region of the segmented area, continue to process the next unprocessed initial segmented interest region in the initial segmented interest region sequence; if it is determined that the total population after addition is less than the preset population threshold, the two interest regions are merged, and the N unprocessed initial segmented interest regions with the smallest area among the interest region obtained by merging the two interest regions in the initial segmented interest region sequence that are closest to the interest region obtained by merging the two interest regions are determined according to the topological connection relationship, and the steps of adding the population numbers and comparing with the preset population threshold are performed until the total population number of the obtained interest region is greater than or equal to the preset population threshold, and the obtained interest region is used as a final segmented interest region of the area to be segmented; and so on, the final segmented interest region of the area to be segmented is obtained.

[0156] In one embodiment of the present disclosure, the above-mentioned fusion process of the regions of interest can also be implemented with the help of a graph node structure established based on the regions of interest. For example, the initially segmented regions of interest can be used as nodes in the graph node structure, and the node attributes of each node may include attribute data such as the area size, population size, and region type of the corresponding region of interest. The graph node structure also includes a corresponding topological structure relationship stack, wherein the topological structure relationship stack describes the topological relationship between the regions of interest and sorts the regions of interest in order from small to large in terms of area. When the graph node structure is used to fuse the regions of interest, each unprocessed graph node in the graph node structure can be traversed in sequence according to the fusion scheme described above to achieve the fusion of the regions of interest. The present disclosure will not go into details about the specific traversal process.

[0157] In another embodiment of the present disclosure, the fusion of interest regions can also be achieved by using a spectral clustering algorithm. That is, in another embodiment of the present disclosure, the fusion module can be configured as follows:

[0158] Acquire a topological connection relationship between the at least one initially segmented region of interest;

[0159] Generate a graph node structure corresponding to the at least one initially segmented region of interest according to the topological connection relationship, wherein the graph node of the graph node structure is the initially segmented region of interest, and the graph node attributes include at least the area size and population of the initially segmented region of interest;

[0160] Extracting a feature vector of the graph node, wherein the feature vector can represent the area size and population size of the graph node;

[0161] Clustering fusion based on area size and population size is performed according to the feature vectors of the graph nodes to obtain the final segmented region of interest of the area to be segmented, wherein the total population of the final segmented region of interest is greater than or equal to a preset population threshold, and the area variance of the final segmented region of interest is less than a preset variance threshold.

[0162] In this embodiment, when the spectral clustering algorithm is used to realize the fusion of the interest region, it is also necessary to first obtain the topological connection relationship between the at least one initial segmented interest region; then, based on the topological connection relationship, generate the graph node structure corresponding to the at least one initial segmented interest region, similar to the above description, the graph node of the graph node structure is the initial segmented interest region, and the graph node attributes at least include the area size and population of the initial segmented interest region; then extract the feature vector of the graph node, wherein the feature vector is used to characterize the area size and population of the graph node, and perform clustering fusion based on the area size and population based on the feature vector of the graph node to obtain the final segmented interest region of the area to be segmented, so that the total population of the final segmented interest region is greater than or equal to the preset population threshold, and the area variance of the final segmented interest region is less than the preset variance threshold. Among them, the feature vector of the graph node can be selected according to the needs of the actual application, that is, the selection and extraction of the feature vector of the graph node, and the clustering fusion based on the area size and population based on the feature vector of the graph node belong to the skills that those skilled in the art should master, and the present disclosure does not repeat its specific implementation process. Fig.2I FIG. 1 is a schematic diagram of a region of interest before fusion according to an embodiment of the present disclosure. Figure 2J It is a schematic diagram of a region of interest obtained after the region of interest is fused using a spectral clustering algorithm according to an embodiment of the present disclosure.

[0163] The present disclosure also discloses an electronic device, Figure 4 A structural block diagram of an electronic device according to an embodiment of the present disclosure is shown. Figure 4 As shown, the electronic device 400 includes a memory 401 and a processor 402; wherein,

[0164] The memory 401 is used to store one or more computer instructions, wherein the one or more computer instructions are executed by the processor 402 to implement the above method steps.

[0165] Figure 5 It is a structural schematic diagram of a computer system suitable for implementing a method for segmenting a region of interest according to an embodiment of the present disclosure.

[0166] like Figure 5As shown, the computer system 500 includes a processing unit 501, which can perform various processes in the above-mentioned embodiments according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage part 508 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the computer system 500 are also stored. The processing unit 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0167] The following components are connected to the I / O interface 505: an input part 506 including a keyboard, a mouse, etc.; an output part 507 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker; a storage part 508 including a hard disk, etc.; and a communication part 509 including a network interface card such as a LAN card, a modem, etc. The communication part 509 performs communication processing via a network such as the Internet. The drive 510 is also connected to the I / O interface 505 as needed. Removable media 511, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., are installed on the drive 510 as needed, so that the computer program read therefrom is installed into the storage part 508 as needed. Among them, the processing unit 501 can be implemented as a processing unit such as a CPU, a GPU, a TPU, an FPGA, an NPU, etc.

[0168] In particular, according to an embodiment of the present disclosure, the method described above can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program tangibly contained on a readable medium thereof, and the computer program includes a program code for executing the method. In such an embodiment, the computer program can be downloaded and installed from a network through the communication part 509, and / or installed from a removable medium 511.

[0169] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, functions and operations of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the road map or block diagram can represent a part of a module, program segment or code, and the part of the module, program segment or code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a different order from the order marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0170] The units or modules involved in the embodiments described in the present disclosure may be implemented by software or hardware. The units or modules described may also be set in a processor, and the names of these units or modules do not constitute limitations on the units or modules themselves in some cases.

[0171] As another aspect, the present disclosure further provides a computer-readable storage medium, which may be a computer-readable storage medium included in the device described in the above embodiment; or a computer-readable storage medium that exists independently and is not assembled into the device. The computer-readable storage medium stores one or more programs, and the programs are used by one or more processors to execute the method described in the present disclosure.

[0172] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the present disclosure is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the inventive concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other.

Claims

1. A method for segmenting a region of interest, the method comprising: Obtain natural boundary elements located in the area to be segmented; Based on the natural boundary elements, segmenting the area to be segmented into at least one initial segmentation region of interest; Based on the area and population of each of the initially segmented regions of interest, the at least one initially segmented region of interest is fused to obtain a final segmented region of interest of the area to be segmented.

2. The method according to claim 1, wherein the step of segmenting the area to be segmented into at least one initial segmentation region of interest based on the natural boundary element comprises: Gathering the natural boundary elements to obtain a natural boundary line; Expanding the natural boundary line by a first distance in a direction from the center of the area to be segmented toward the periphery; shrinking the expanded natural boundary line by a second distance along the periphery of the region to be segmented toward the center; The region to be segmented is segmented into at least one initial segmented region of interest using the shrunk natural boundary line.

3. The method according to claim 1, wherein: After the region to be segmented is segmented into at least one initial segmentation region of interest based on the natural boundary element, the method further includes: The initially segmented region of interest is corrected.

4. The method according to claim 3, wherein: The correcting process of the initially segmented region of interest comprises: Using the boundary line of the initially segmented region of interest, removing discontinuous roads in the initially segmented region of interest; and / or, The boundary lines of the initially segmented interest regions are used to remove the initially segmented interest regions whose areas are smaller than a preset area threshold.

5. The method according to claim 4, wherein: The removing of discontinuous roads in the initially segmented region of interest by using the boundary line of the initially segmented region of interest comprises: Expanding the boundary line of the initially segmented region of interest by a third distance in a direction from the center of the initially segmented region of interest toward the periphery; The boundary line of the initially segmented region of interest after expansion is shrunk by a third distance in a direction from the periphery of the initially segmented region of interest toward the center.

6. The method according to claim 4, wherein: The removing of the initially segmented interest regions whose areas are smaller than a preset area threshold by using the boundary lines of the initially segmented interest regions comprises: shrinking the boundary line of the initially segmented region of interest by a fourth distance in a direction from the periphery of the initially segmented region of interest toward the center; If the initially segmented region of interest still exists after the boundary line shrinks, retaining the initially segmented region of interest; If the initially segmented region of interest disappears after the boundary line shrinks, the initially segmented region of interest is deleted.

7. The method according to any one of claims 1 to 6, wherein: The step of fusing the at least one initially segmented region of interest based on the area and population of the at least one initially segmented region of interest to obtain a final segmented region of interest of the region to be segmented includes: Acquire a topological connection relationship between the at least one initially segmented region of interest; Based on the area, population and topological connection relationship of the at least one initial segmented region of interest, the at least one initial segmented region of interest is fused to obtain a final segmented region of interest of the area to be segmented, wherein the total population of the final segmented region of interest is greater than or equal to a preset population threshold.

8. The method according to claim 7, wherein: The step of fusing the at least one initially segmented region of interest based on the area, population and topological connection relationship of the at least one initially segmented region of interest to obtain a final segmented region of interest of the region to be segmented includes: Sorting the at least one initially segmented region of interest in ascending order of area of ​​the at least one initially segmented region of interest to obtain an initially segmented region of interest sequence; For the unprocessed initial segmentation region of interest with the smallest area in the sequence of initial segmentation regions of interest, if it is determined that its population is greater than or equal to the preset population threshold, the initial segmentation region of interest is used as a final segmentation region of interest of the area to be segmented, and the next unprocessed initial segmentation region of interest in the sequence of initial segmentation regions of interest is processed; if it is determined that its population is less than the preset population threshold, the unprocessed initial segmentation region of interest in the sequence of initial segmentation regions of interest closest to the initial segmentation region of interest is determined according to the topological connection relationship, the populations of the two initial segmentation regions of interest are added, and if it is determined that the total population after the addition is greater than or equal to the preset population threshold, the two initial segmentation regions of interest are merged as the A final segmented interest region of the area to be segmented, continue to process the next unprocessed initial segmented interest region in the initial segmented interest region sequence; if it is determined that the total population after addition is less than the preset population threshold, the two interest regions are merged, and the unprocessed initial segmented interest region in the initial segmented interest region sequence that is closest to the interest region obtained by merging the two interest regions is determined according to the topological connection relationship, and the steps of adding the population and comparing with the preset population threshold are performed until the total population of the obtained interest region is greater than or equal to the preset population threshold, and the obtained interest region is used as a final segmented interest region of the area to be segmented; and so on, the final segmented interest region of the area to be segmented is obtained.

9. The method according to claim 7, wherein: The step of fusing the at least one initially segmented region of interest based on the area, population and topological connection relationship of the at least one initially segmented region of interest to obtain a final segmented region of interest of the region to be segmented includes: Sorting the at least one initially segmented region of interest in descending order of area to obtain an initially segmented region of interest sequence; For the unprocessed initial segmented interest region with the largest area in the sequence of initial segmented interest regions, if it is determined that its population is greater than or equal to the preset population threshold, the initial segmented interest region is used as a final segmented interest region of the region to be segmented, and the next unprocessed initial segmented interest region in the sequence of initial segmented interest regions is processed continuously; if it is determined that its population is less than the preset population threshold, the population of the unprocessed initial segmented interest region with the smallest area among the N unprocessed initial segmented interest regions closest to the initial segmented interest region in the sequence of initial segmented interest regions is added according to the topological connection relationship; if it is determined that the total population after the addition is greater than or equal to the preset population threshold, the two initial segmented interest regions are merged as the region to be segmented. A final segmented interest region of the segmented area, continue to process the next unprocessed initial segmented interest region in the initial segmented interest region sequence; if it is determined that the total population after addition is less than the preset population threshold, the two interest regions are merged, and the N unprocessed initial segmented interest regions with the smallest area among the interest region obtained by merging the two interest regions in the initial segmented interest region sequence that are closest to the interest region obtained by merging the two interest regions are determined according to the topological connection relationship, and the steps of adding the population numbers and comparing with the preset population threshold are performed until the total population number of the obtained interest region is greater than or equal to the preset population threshold, and the obtained interest region is used as a final segmented interest region of the area to be segmented; and so on, the final segmented interest region of the area to be segmented is obtained.

10. The method according to any one of claims 1 to 6, wherein: The step of fusing the at least one initially segmented region of interest based on the area and population of the at least one initially segmented region of interest to obtain a final segmented region of interest of the region to be segmented includes: Acquire a topological connection relationship between the at least one initially segmented region of interest; Generate a graph node structure corresponding to the at least one initially segmented region of interest according to the topological connection relationship, wherein the graph node of the graph node structure is the initially segmented region of interest, and the graph node attributes include at least the area size and population of the initially segmented region of interest; Extracting a feature vector of the graph node, wherein the feature vector can represent the area size and population size of the graph node; Clustering fusion based on area size and population size is performed according to the feature vectors of the graph nodes to obtain the final segmented region of interest of the area to be segmented, wherein the total population of the final segmented region of interest is greater than or equal to a preset population threshold, and the area variance of the final segmented region of interest is less than a preset variance threshold.

11. A device for segmenting a region of interest, the device comprising: An acquisition module is configured to acquire natural boundary elements located in the area to be segmented; A segmentation module is configured to segment the area to be segmented into at least one initial segmentation region of interest based on the natural boundary element; The fusion module is configured to fuse the at least one initially segmented region of interest based on the area and population of the at least one initially segmented region of interest to obtain a final segmented region of interest of the area to be segmented.

12. An electronic device comprising a memory and at least one processor; wherein: The memory is used to store one or more computer instructions, wherein the one or more computer instructions are executed by the at least one processor to implement the method according to any one of claims 1 to 10.

13. A computer-readable storage medium having computer instructions stored thereon, wherein: When the computer instructions are executed by a processor, the method according to any one of claims 1 to 10 is implemented.

Citation Information

Patent Citations

  • Acoustic environment functional area partitioning method based on road network and interest points

    CN104834666A

  • Method and device for region division

    CN108242203A

  • A region of interest generation method and device, a storage medium and an electronic device

    CN109669999A

  • Geographic region segmentation method and device based on road network and electronic device

    CN110827048A

  • Detection point site selection method and device, electronic equipment and readable storage medium

    CN116450958A