Camera Area Duplicate Removal Method, Device, Electronic Device and Computer Program Product

Abstract

The present application provides a method, apparatus, electronic device and computer program product for camera area deduplication. The method includes: selecting one camera area from multiple camera areas to be deduplicated as an initial target area; traversing and selecting each unselected camera area from the multiple camera areas; for any camera area selected during traversal, determining the non-overlapping area in the camera area and determining the non-overlapping area in the camera area as an additional target area; in the case where there are no unselected camera areas among the multiple camera areas, determining the current target areas as the deduplicated camera areas. This method can achieve deduplication of multiple camera areas and provides technical support for accurate display and statistics of heat map data in the case of partial overlap of multiple camera areas.

Description

Technical Field

[0001] This application relates to the field of monitoring technologies, and in particular, to a method, apparatus, electronic device, and computer program product for removing duplicates from camera regions. Background Art

[0002] A heat map refers to converting the meaning values of the heat map matrix data of a single monitoring camera (usually a fisheye camera, which is taken as an example of a fisheye camera hereinafter) into pixel values through a heat map synthesis library, and pasting them on a plane base map, which is shown as a lot of colors covering the plane base map, and the depth of the colors indicates the size of the heat map data values.

[0003] Fisheye cameras are usually installed in a top-mounted and overlooking manner, and each fisheye camera is responsible for monitoring an area (which can be called a monitoring area). In actual situations, there are usually overlaps between the monitoring areas of each fisheye camera. For the overlapping areas, duplicate removal processing is required both when calculating the heat value of the overall base map and the heat map value of the sub-region to ensure more accurate data.

[0004] In the case where there are overlaps between the monitoring areas of multiple fisheye cameras, how to remove duplicates from the monitoring areas of multiple fisheye cameras has become a difficult problem. Summary of the Invention

[0005] In view of this, this application provides a method, apparatus, electronic device, and computer program product for removing duplicates from camera regions, so as to achieve removing duplicates from multiple camera regions in the case where there are overlaps between multiple camera regions.

[0006] According to the first aspect of the embodiments of this application, a method for removing duplicates from camera regions is provided, including:

[0007] Selecting one camera region from multiple camera regions to be de-duplicated as an initial target region;

[0008] Traversing and selecting each unselected camera region among the multiple camera regions;

[0009] For any camera region selected by traversing, determining the non-overlapping region in this camera region, and determining the non-overlapping region in this camera region as a newly added target region, where the non-overlapping region is the region in this camera region that does not overlap with the current target regions;

[0010] In the case where there are no unselected camera regions among the multiple camera regions, determining the current target regions as the de-duplicated camera regions.

[0011] According to the second aspect of the embodiments of this application, a device for removing duplicates from camera regions is provided, including:

[0012] A selection unit for selecting one camera area from multiple camera areas to be deduplicated as an initial target area;

[0013] The selection unit is further configured to traverse and select each unselected camera area among the multiple camera areas;

[0014] A first determination unit for, for any camera area traversed and selected, determining the non-overlapping area in the camera area and determining the non-overlapping area in the camera area as a newly added target area, where the non-overlapping area is the area in the camera area that does not overlap with any current target areas;

[0015] A second determination unit for, when there are no unselected camera areas among the multiple camera areas, determining the current target areas as the deduplicated camera areas.

[0016] According to the third aspect of the embodiments of the present application, there is provided an electronic device including a processor and a memory, where

[0017] The memory is used to store a computer program;

[0018] The processor is configured to, when executing the program stored on the memory, implement the camera area deduplication method provided in the first aspect.

[0019] According to the fourth aspect of the embodiments of the present application, there is provided a computer program product, where a computer program is stored in the computer program product, and when the processor executes the computer program, it causes the processor to implement the camera area deduplication method provided in the first aspect.

[0020] According to the fifth aspect of the embodiments of the present application, there is provided a machine-readable storage medium storing machine-executable instructions that can be executed by a processor; wherein the processor is configured to execute the machine-executable instructions to implement the camera area deduplication method provided in the first aspect.

[0021] The camera area deduplication method according to the embodiments of the present application selects one camera area from multiple camera areas to be deduplicated as an initial target area, traverses and selects each unselected camera area among the multiple camera areas, for any camera area traversed and selected, determines the non-overlapping area in the camera area and determines the non-overlapping area in the camera area as a newly added target area, and when there are no unselected camera areas among the multiple camera areas, determines the current target areas as the deduplicated camera areas, thus realizing the deduplication of multiple camera areas and providing technical support for the accurate display and statistics of heat map data in the case of partial overlap of multiple camera areas. Description of the Drawings

[0022] Figure 1 It is a schematic flowchart of a method for removing duplicate camera regions provided by an embodiment of the present application;

[0023] Figure 2 It is a schematic flowchart of the implementation process for removing duplicate camera regions provided by an embodiment of the present application;

[0024] Figure 3 It is a schematic diagram of the non-overlapping region between region Y and region X provided by an embodiment of the present application;

[0025] Figure 4A It is a schematic diagram of camera region 1, camera region 2, and camera region 3 provided by an embodiment of the present application;

[0026] Figure 4B It is a schematic diagram of removing duplicates from camera region 2 with camera region 1 as the initial target region provided by an embodiment of the present application;

[0027] Figure 4C It is a schematic diagram of removing duplicates from camera region 2 and camera region 3 with camera region 1 as the initial target region provided by an embodiment of the present application;

[0028] Figure 5 It is a schematic diagram of the overlapping region where a custom region spans multiple camera regions provided by an embodiment of the present application;

[0029] Figure 6 It is a schematic structural diagram of a device for removing duplicate camera regions provided by an embodiment of the present application;

[0030] Figure 7 It is a schematic hardware structure diagram of an electronic device provided by an embodiment of the present application. Detailed implementation manners

[0031] Here, exemplary embodiments will be described in detail, and the examples are shown in the drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementation manners described in the following exemplary embodiments do not represent all implementation manners consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0032] The terms used in the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. The singular forms "a", "the", and "said" used in the present application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise.

[0033] In order to enable those skilled in the art to better understand the technical solutions provided by the embodiments of the present application, some technical terms involved in the embodiments of the present application are explained below.

[0034] 1. Global heat map: Multiple surveillance cameras (such as fisheye cameras) of the same model and configuration are placed at different locations on a base map. Each camera has a rectangular monitoring area. The surveillance camera can detect, save, and report the heat values of people staying in the monitoring area. The platform synthesizes the heat value matrix of all surveillance cameras on a base map to form a global heat map.

[0035] 2. Plane base map: In a single surveillance camera heat map, the plane base map Figure 1 It is usually a picture captured by a camera. In the global heat map, a separate plane base map needs to be configured in the platform system (such as the HCP (HikCentral Professional) system).

[0036] 3. Custom regions: These are areas drawn on the global heat map's base map. For example, fisheye cameras are deployed in a large shopping mall to collect heat map data. Some cameras cover areas encompassing multiple stores, and each store focuses on heat map data for its specific area. In this case, the area corresponding to each store can be drawn on the mall's base map. This area is called a custom region.

[0037] Exemplarily, the custom area may include but is not limited to a rectangular area, a circular area, a parallelogram area, or the like.

[0038] In order to make the above-mentioned purposes, features and advantages of the embodiments of the present application more obvious and easy to understand, the technical solutions in the embodiments of the present application are further described in detail below with reference to the accompanying drawings.

[0039] It should be noted that the serial numbers of the steps in the embodiments of the present application do not mean the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0040] See Figure 1 , is a flow chart of a camera area deduplication method provided in an embodiment of the present application, such as Figure 1 As shown, the camera area deduplication method may include the following steps:

[0041] Step S100: Select one camera area from multiple camera areas to be deduplicated as an initial target area.

[0042] In the embodiments of the present application, in order to achieve deduplication of camera regions, one camera region can be selected from multiple camera regions to be deduplicated as an initial target region. This initial target region can be used as an initial deduplication benchmark, that is, when other camera regions are being deduplicated, it is necessary to ensure that there is no overlapping region with this initial target region.

[0043] For example, one camera region can be randomly selected from multiple camera regions to be deduplicated as the initial target region.

[0044] Exemplarily, the target region is a camera region that has no overlapping region with other camera regions after deduplication.

[0045] Exemplarily, the camera region of a surveillance camera can include all or part of the surveillance area of this surveillance camera.

[0046] Exemplarily, a target region can be part or all of a camera region.

[0047] Step S110: Traverse and select each unselected camera region from multiple camera regions to be deduplicated.

[0048] In the embodiments of the present application, when the initial target region is determined, other camera regions among multiple camera regions to be deduplicated can be deduplicated with this initial target region as the initial deduplication benchmark.

[0049] Exemplarily, each unselected camera region of multiple camera regions to be deduplicated can be traversed, and deduplication processing can be performed according to the selection of each unselected camera region.

[0050] For example, assume that multiple camera regions to be deduplicated include camera regions 1 to 3, and camera region 1 is selected as the initial target region. Then the unselected camera regions can include camera region 2 and camera region 3. Camera regions 2 and 3 can be traversed, and camera region 2 and camera region 3 can be selected in turn for deduplication processing.

[0051] In one example, in order to improve the management of camera regions to be deduplicated, the camera regions to be deduplicated can be stored in the original camera region storage space.

[0052] Exemplarily, this storage space can include but is not limited to a list or a queue, etc.

[0053] For the convenience of description and understanding, in the following, the storage space is taken as an example of a list.

[0054] Exemplarily, in step 100, a camera area can be selected from the original camera area storage space (hereinafter referred to as the first list) as the initial target area; in step S110, each unselected camera area in the first list can be traversed and selected.

[0055] Exemplarily, in order to improve the traversal efficiency of camera areas, for the camera areas selected from the first list, they can be taken out from the first list, that is, the first list only stores unselected camera areas, and the traversal of the camera areas in the first list is to select unselected camera areas.

[0056] In step S120, for any camera area selected through traversal, determine the non-overlapping area in this camera area, and determine the non-overlapping area in this camera area as the newly added target area, where the non-overlapping area is the area in this camera area that does not overlap with the current target areas.

[0057] In the embodiment of the present application, for any camera area selected through traversal, the area in this camera area that does not overlap with the current target areas (referred to as the non-overlapping area in this text) can be determined.

[0058] Exemplarily, in the initial state, the current target areas include the initial target area.

[0059] However, during the process of removing duplicates for other camera areas, new target areas (which can be called newly added target areas) can be determined. In the case where the newly added target areas are determined, the current target areas can include the initial target area and the newly added target areas, that is, when removing duplicates for different camera areas, the current target areas can change (new target areas can be added).

[0060] Exemplarily, for any camera area selected through traversal, in the case where the non-overlapping area in this camera area is determined, the non-overlapping area in this camera area can be determined as the newly added target area.

[0061] Still taking the previous example, assume that camera area 2 is first selected for duplicate removal processing. Then, taking camera area 1 as the reference, determine the non-overlapping area in camera area 2, and use the non-overlapping area in camera area 2 as the newly added target area; when performing duplicate removal processing on camera area 3, the current target areas include camera area 1 (i.e., the initial target area) and the non-overlapping area in camera area 2 (i.e., the newly added target area); in the case where the non-overlapping area in camera area 3 is determined, the current target areas include camera area 1 (i.e., the initial target area), the non-overlapping area in camera area 2, and the non-overlapping area in camera area 3 (i.e., the newly added target area).

[0062] Step S130: When there is no unselected camera area among multiple camera areas, determine each current target area as each de-duplicated camera area.

[0063] In the embodiments of the present application, when there is no unselected camera area among multiple camera areas, that is, when de-duplication processing has been performed on each camera area, each current target area can be determined as each de-duplicated camera area.

[0064] It can be seen that in Figure 1 the method flow shown, by selecting one camera area from multiple camera areas to be de-duplicated as the initial target area, and traversing and selecting each unselected camera area among the multiple camera areas, for any camera area traversed and selected, determining the non-overlapping area in the camera area, and determining the non-overlapping area in the camera area as the newly added target area, when there is no unselected camera area among the multiple camera areas, determining each current target area as each de-duplicated camera area, de-duplication of multiple camera areas is achieved, providing technical support for the accurate display and statistics of heat map data in the case of partial overlap of multiple camera areas.

[0065] In some embodiments, in step S120, for any camera area traversed and selected, determining the non-overlapping area in the camera area may include:

[0066] Traverse and select each unselected target area among each current target area;

[0067] For any target area traversed and selected, determine the non-overlapping area between the currently reserved area in the camera area and the target area, and update the currently reserved area in the camera area to the non-overlapping area;

[0068] When there is no unselected target area among each current target area, determine the currently reserved area in the camera area as the non-overlapping area in the camera area.

[0069] Exemplarily, during the process of de-duplicating any camera area, each unselected target area among each current target area can be traversed and each unselected target area can be selected in turn.

[0070] For any target area traversed and selected, the non-overlapping area between the currently reserved area in the camera area and the target area can be determined, and the currently reserved area in the camera area can be updated to the non-overlapping area.

[0071] Exemplarily, for any camera area, the currently reserved area in the camera area is the camera area in the initial state.

[0072] Exemplarily, in the case that there are unselected target regions among the current target regions, continue to traverse and select the unselected target regions among the current target regions.

[0073] In the case that there are no unselected target regions among the current target regions, determine the currently retained region in the camera region as the non-overlapping region in the camera region.

[0074] In some embodiments, the target regions are stored in a result storage space;

[0075] Before traversing and selecting the unselected target regions among the current target regions, it may further include:

[0076] Copy the target regions in the current result list to a storage space for results to be compared.

[0077] The above-mentioned traversing and selecting the unselected target regions among the current target regions may include:

[0078] Traverse the storage space for results to be compared, and take out the selected target regions from the storage space for results to be compared.

[0079] The above-mentioned situation where there are no unselected target regions among the current target regions may include:

[0080] The storage space for results to be compared is empty.

[0081] Exemplarily, in order to improve the management efficiency of target regions, the target regions can be stored in a result storage space (hereinafter referred to as a result list).

[0082] In order to improve the traversal efficiency of target regions, for any camera region, during the process of deduplication of the camera region, the target regions in the current result list can be copied to a storage space for results to be compared (hereinafter referred to as a second list).

[0083] During the process of traversing and selecting target regions, the second list can be traversed, and the selected target regions are taken out from the second list, that is, the unselected target regions will be retained in the second list, and the selected target regions will be deleted from the second list.

[0084] Exemplarily, in the case that the second list is empty, it can be determined that there are no unselected target regions among the current target regions.

[0085] In some embodiments, the above-mentioned traversing and selecting the unselected camera regions among multiple camera regions may include:

[0086] Traverse the unselected camera regions among multiple camera regions, and select an unselected camera region to add to the storage space of the camera regions to be compared.

[0087] For any target region selected by traversal, determining the non-overlapping region between the currently retained region in the camera region and the target region, and updating the currently retained region in the camera region to the non-overlapping region may include:

[0088] Traverse each region in the storage space of the camera regions to be compared, and take out the selected region from the storage space of the camera regions to be compared; wherein, each region in the storage space of the camera regions to be compared is the currently retained region in the camera region.

[0089] Determine the non-overlapping region between the taken-out region and the target region, and add the non-overlapping region to the storage space of the retained regions; the storage space of the retained regions is used to store the non-overlapping region between the currently retained region in the camera region and the target region.

[0090] When the storage space of the camera regions to be compared is empty, move the non-overlapping region in the storage space of the retained regions from the storage space of the retained regions into the storage space of the camera regions to be compared.

[0091] Exemplarily, in order to ensure the management efficiency of the duplicate removal process for each camera region, during the duplicate removal process for any camera region, the camera region or the non-overlapping region in the camera region can be saved through the storage space of the camera regions to be compared (hereinafter referred to as the third list).

[0092] In addition, in order to improve the accuracy of the duplicate removal process and the operation efficiency of the duplicate removal process, the non-overlapping region between the camera region and each target region determined during the duplicate removal process can be saved through the storage space of the retained regions (hereinafter referred to as the fourth list).

[0093] Correspondingly, for the camera region selected by traversal, it can be added to the storage space of the camera regions to be compared.

[0094] During the duplicate removal process for the camera region, each unselected target region among the currently selected target regions can be traversed and selected.

[0095] When an unselected target region is selected, each region in the third list, that is, the currently retained region in the camera region, can be traversed, the selected region can be taken out from the third list, and the non-overlapping region between the taken-out region and the target region, that is, the non-overlapping region between the currently retained region in the camera region and the target region, can be determined, and the non-overlapping region between the region and the target region can be added to the fourth list.

[0096] Exemplarily, each region in the third list may include all regions of the currently traversed and selected camera region or partial regions in the camera region.

[0097] Exemplarily, when the third list is not empty, regions in the third list can be continuously traversed and selected to determine non-overlapping regions between the retrieved regions and the target region, and added to the fourth list.

[0098] When the third list is empty, non-overlapping regions in the fourth list can be moved from the fourth list to the third list, that is, the regions currently retained in the camera region are updated to the non-overlapping regions stored in the fourth list, and it is determined whether there are unselected target regions among the current target regions.

[0099] When there are no unselected target regions among the current target regions, for example, when the second list is empty, it can be determined that the regions in the current third list are non-overlapping regions in the currently deduplicated camera region, the regions in the third list are added to the result list, and the third list is cleared.

[0100] Exemplarily, when there are unselected target regions among the current target regions, for example, when the second list is not empty, target regions can be continuously traversed and selected to determine non-overlapping regions between the regions in the third list and the target region.

[0101] For example, assume that the camera regions to be deduplicated include camera region 1, camera region 2, and camera region 3, and camera region 1 is selected as the initial target region. During the deduplication process of camera region 2 and camera region 3, camera region 2 and camera region 3 can be traversed and selected.

[0102] Assume that camera region 2 is selected first. Camera region 2 can be added to the third list, and the target region (currently only including camera region 1) is traversed and selected.

[0103] For the traversed and selected target region (i.e., camera region 1), regions in the third list can be traversed. Since only camera region 2 is currently included in the third list, camera region 2 can be retrieved from the third list (all regions of camera region 2 are the regions currently retained in camera region 2).

[0104] Non-overlapping regions between camera region 2 and camera region 1 can be determined. Assume that region 21 is included, then region 21 can be added to the fourth list.

[0105] When camera region 2 is retrieved from the third list, the third list is empty. In this case, non-overlapping regions in the fourth list can be moved to the third list, that is, the regions currently retained in camera region 2 are updated to region 21.

[0106] In addition, since there is no unselected target area at this time, area 21 is added to the result list as a newly added target area, and the third list is cleared.

[0107] After the duplication removal of camera area 2 is completed, the target areas include camera area 1 and area 21.

[0108] After the duplication removal of camera area 2 is completed, the unselected camera areas (i.e., camera area 3) can be traversed and camera area 3 is added to the third list.

[0109] During the process of removing duplicates from camera area 3, each target area (including camera area 1 and area 21) can be traversed.

[0110] Suppose camera area 1 is selected first. In this case, each area in the third list can be traversed. Since the third list currently only includes camera area 3, camera area 3 can be taken out from the third list (all areas of camera area 3 are the areas currently retained in camera area 3).

[0111] The non-overlapping areas of camera area 3 with respect to camera area 1 can be determined. Suppose they include area 31 and area 32, then area 31 and 32 can be added to the fourth list.

[0112] When camera area 3 is taken out from the third list, the third list becomes empty. In this case, each non-overlapping area in the fourth list can be moved into the third list, that is, the areas currently retained in camera area 3 are updated to area 31 and area 32.

[0113] Continue to traverse and select target areas, and select area 21.

[0114] For area 21, each area in the third list (including area 31 and area 32) can be traversed.

[0115] Suppose area 31 is selected first. Area 31 can be taken out from the third list, and the non-overlapping area of area 31 with respect to area 21 can be determined. Suppose it is area 311, then area 311 can be added to the fourth list.

[0116] Continue to traverse and select each area in the third list (currently only including area 32).

[0117] Area 32 is taken out from the third list, and the non-overlapping areas of area 32 with respect to area 21 are determined. Suppose they include area 321 and area 322, then area 321 and area 322 can be added to the fourth list (currently including area 311, area 321, and area 322), that is, the areas currently retained in camera area 3 are updated to area 311, area 321, and area 322.

[0118] Since the third list is empty, in this case, the non-overlapping regions in the fourth list can be moved into the third list, that is, the regions currently reserved in camera region 3 are updated to region 311, region 321, and region 322.

[0119] In addition, since there are no unselected target regions at this time, therefore, region 311, region 321, and region 322 are added to the result list as newly added target regions, and the third list is cleared.

[0120] In some embodiments, both the camera region and the target region are rectangular regions.

[0121] The non-overlapping region between any camera region and any target region can be determined in the following manner:

[0122] Determine whether the camera region and the target region overlap;

[0123] In the case where the camera region and the target region do not overlap, determine the camera region as the non-overlapping region between the camera region and the target region;

[0124] In the case where the camera region and the target region overlap, determine the non-overlapping region between the camera region and the target region according to the corner coordinates of the camera region and the corner coordinates of the target region.

[0125] It should be noted that in the embodiments of the present application, unless otherwise specified, the coordinates mentioned are all coordinates in a coordinate system with the upper left corner point of the rectangular region as the coordinate origin, the positive x-axis to the right horizontally, and the positive y-axis downward vertically.

[0126] Exemplarily, take the case where both the camera region and the target region are rectangular regions as an example.

[0127] For any camera region and any target region, in order to determine the non-overlapping region between the camera region and the target region, it can first be determined whether the camera region and the target region overlap.

[0128] Exemplarily, it can be determined whether the camera region and the target region overlap according to the corner coordinates of the camera region and the corner coordinates of the target region.

[0129] For example, it can be determined whether the camera region and the target region overlap according to the upper left corner point coordinates, the lower right corner point coordinates of the camera region, and the upper left corner point coordinates, the lower right corner point coordinates of the target region.

[0130] Exemplarily, in the case where the camera region and the target region do not overlap, the camera region can be determined as the non-overlapping region between the camera region and the target region.

[0131] When the camera area overlaps with the target area, the non-overlapping area between the camera area and the target area can be determined based on the corner coordinates of the camera area and the corner coordinates of the target area.

[0132] In one example, when the camera area overlaps with the target area, the candidate non-overlapping areas between the camera area and the target area include:

[0133] The candidate non-overlapping area at the upper left corner of the target area (referred to as the first candidate non-overlapping area in this article), the candidate non-overlapping area directly above the target area (referred to as the second candidate non-overlapping area in this article), the candidate non-overlapping area at the upper right corner of the target area (referred to as the third candidate non-overlapping area in this article), the candidate non-overlapping area directly to the right of the target area (referred to as the fourth candidate non-overlapping area in this article), the candidate non-overlapping area at the lower right corner of the target area (referred to as the fifth candidate non-overlapping area in this article), the candidate non-overlapping area directly below the target area (referred to as the sixth candidate non-overlapping area in this article), the candidate non-overlapping area at the lower left corner of the target area (referred to as the seventh candidate non-overlapping area in this article), and the candidate non-overlapping area directly to the left of the target area (referred to as the eighth candidate non-overlapping area in this article);

[0134] Among them, each candidate non-overlapping area is a rectangular area.

[0135] Exemplarily, the above-mentioned determination of the non-overlapping area between the camera area and the target area based on the corner coordinates of the camera area and the corner coordinates of the target area may include:

[0136] Determine the upper left corner coordinates and lower right corner coordinates of each candidate non-overlapping area based on the first upper left corner coordinates, the first lower right corner coordinates, the second upper left corner coordinates, and the second lower right corner coordinates; wherein, the first upper left corner coordinates and the first lower right corner coordinates are respectively the upper left corner coordinates and the lower right corner coordinates of the camera area, and the second upper left corner coordinates and the second lower right corner coordinates are respectively the upper left corner coordinates and the lower right corner coordinates of the target area;

[0137] Determine the legal candidate non-overlapping areas among the candidate non-overlapping areas as the non-overlapping area between the camera area and the target area based on the upper left corner coordinates and the lower right corner coordinates of each candidate non-overlapping area;

[0138] Among them, for the legal candidate non-overlapping area, the abscissa of the lower right corner coordinates is greater than the abscissa of the upper left corner coordinates, and the ordinate of the lower right corner is greater than the ordinate of the upper left corner.

[0139] Exemplarily, considering any camera region and any target region, when there is an overlap between the camera region and the target region, the non-overlapping region in the camera region with respect to the target region can be at most divided into eight rectangular regions in the directions of the upper left corner, directly above, upper right corner, directly right, lower right corner, directly below, lower left corner, and leftmost of the target region, and the coordinates of these rectangular regions can be determined based on the corner coordinates of the camera region and the corner coordinates of the target region.

[0140] That is, for any camera region and any target region, the non-overlapping region in the camera region with respect to the target region can include at most eight non-overlapping regions (i.e., the above-mentioned first candidate non-overlapping region to the eighth candidate non-overlapping region).

[0141] In addition, considering the case where the target region is not completely included in the camera region, the above eight non-overlapping regions do not exist simultaneously.

[0142] Exemplarily, it is possible to determine whether a candidate non-overlapping region exists based on the upper left corner point coordinates and the lower right corner point coordinates of the candidate non-overlapping region.

[0143] Among them, for a candidate non-overlapping region determined to exist, it can be called a legal candidate non-overlapping region; for a candidate non-overlapping region determined to not exist, it can be called an illegal candidate non-overlapping region.

[0144] Correspondingly, when there is an overlap between the camera region and the target region, it is possible to determine the upper left corner point coordinates and the lower right corner point coordinates of each candidate non-overlapping region based on the upper left corner point coordinates and the lower right corner point coordinates of the camera region (which can be called the first upper left corner point coordinates and the first lower right corner point coordinates), and the upper left corner point coordinates and the lower right corner point coordinates of the target region (which can be called the second upper left corner point coordinates and the second lower right corner point coordinates), and determine the legal candidate non-overlapping regions among the candidate non-overlapping regions as the non-overlapping region between the camera region and the target region based on the upper left corner point coordinates and the lower right corner point coordinates of each candidate non-overlapping region. Its specific implementation will be described in combination with specific examples below.

[0145] It should be noted that in the embodiment of the present application, during the process of removing duplicates in the camera region, for any camera region selected by traversal, it is possible to sequentially determine the overlapping regions of the camera region with each target region, and delete the determined overlapping regions of the camera region with each target region. Furthermore, when the overlapping regions of the camera region with each target region among the current various target regions have been deleted, the remaining region in the camera region can be determined as the non-overlapping region in the camera region.

[0146] In the embodiments of the present application, when duplicate removal has been completed for each camera area, for any custom area, the sub-areas of the custom area in each camera area after duplicate removal can be determined respectively, and the heat data of the custom area can be statistically calculated based on the heat map data of each sub-area.

[0147] Exemplarily, each camera area after duplicate removal can be traversed. For any camera area after duplicate removal, it can be determined whether the camera area after duplicate removal overlaps with the custom area, and when the camera area after duplicate removal overlaps with the custom area, the overlapping area between the camera area after duplicate removal and the custom area can be determined, and the overlapping area can be determined as the sub-area of the custom area in the camera area after duplicate removal.

[0148] For example, assume that the upper left corner coordinates of rectangle A are (X 11 , Y 11 ), and the lower right corner coordinates are (X 12 , Y 12 ), and the upper left corner coordinates of rectangle B are (X 21 , Y 21 ), and the lower right corner coordinates are (X 22 , Y 22 ). Then: the width W1 of rectangle A = X 12 - X 11 , and the height H1 = Y 12 - Y 11 ;

[0149] The width W2 of rectangle B = X 22 - X 21 , and the height H2 = Y 22 - Y 21 ;

[0150] The center coordinates (X 13 , Y 13 ) of rectangle A = ((X 12 + X 11 ) / 2, (Y 12 + Y 11 ) / 2);

[0151] The center coordinates (X 23 , Y 23 ) of rectangle B = ((X 22 + X 21 ) / 2, (Y 22 + Y 21 ) / 2).

[0152] When the following two conditions are simultaneously satisfied, it can be determined that rectangle A and rectangle B overlap:

[0153] |X 23 - X 13|≤W1 / 2 + W2 / 2

[0154] |Y 23 -Y 13 |≤H1 / 2 + H2 / 2

[0155] That is:

[0156] |X 22 +X 21 -X 12 -X 11 |≤X 12 -X 11 +X 22 -X 21

[0157] |Y 22 +Y 21 -Y 12 -Y 11 |≤Y 12 -Y 11 +Y 22 -Y 21

[0158] When it is determined that rectangle A and rectangle B overlap, assuming the overlapping area is rectangle C, and the upper left corner coordinates of rectangle C are (X 31 , Y 31 ), and the lower right corner coordinates are (X 32 , Y 32 ), then:

[0159] X 31 = max(X 11 , X 21 )

[0160] Y 31 = max(Y 11 , Y 21 )

[0161] X 32 = min(X 12 , X 22 )

[0162] Y 32 = min(Y 12 , Y 22 )

[0163] To enable those skilled in the art to better understand the technical solutions provided in the embodiments of the present application, the technical solutions provided in the embodiments of the present application will be described below with specific examples.

[0164] As Figure 2 shown, in this embodiment, the implementation process of camera area duplicate removal processing can be as follows:

[0165] Assume that the original fish-eye camera matrix regions (i.e., the multiple camera regions to be de-duplicated above) are stored in List_A (i.e., the first list above).

[0166] 1. Take out a camera region from List_A and store this camera region in List_Result (i.e., the result list above).

[0167] Exemplarily, List_Result is used to store the non-overlapping regions (i.e., the target regions above) determined in the camera regions.

[0168] Exemplarily, in the initial state, List_Result is empty.

[0169] For the camera region taken out from List_A in step 1, since it is the first region taken out, in this case, there are no other regions for overlapping determination with this region. Therefore, this camera region can be used as a non-overlapping region (i.e., the initial target region above) and added to List_Result.

[0170] It should be noted that when taking out a region from a certain list, this region will be deleted from this list.

[0171] 2. Take out a camera region from List_A and store it in List_C (i.e., the third list above).

[0172] 3. Copy the target regions in List_Result to List_B (i.e., the second list above).

[0173] 4. Take out a region from List_B (assume it is region X).

[0174] 5. Take out a region from List_C (assume it is region Y).

[0175] 6. Determine the non-overlapping region of region Y with region X (the determination method of the non-overlapping region will be described below), and store the non-overlapping region of region Y with region X in List_D (i.e., the fourth list above).

[0176] Exemplarily, for the determined non-overlapping region, it can be saved in List_D in the form of a rectangular region; for a non-rectangular non-overlapping region, multiple rectangular regions can be obtained by cutting.

[0177] 7. If List_C is not empty, go to step 5; if List_C is empty, go to step 8.

[0178] 8. Store the non-overlapping regions in List_D in List_C and empty List_D.

[0179] 9. When List_B is not empty, go to step 4; when List_B is empty, go to step 10.

[0180] 10. Store all the regions in List_C into List_Result and clear List_C.

[0181] 11. When List_A is not empty, go to step 2; when List_A is empty, determine the regions in List_Result as the deduplicated camera regions.

[0182] The implementation of determining the non - overlapping regions of region X in region Y is described below.

[0183] Taking region X as the initial region (or called the reference region), first judge whether region Y overlaps with region X according to the upper - left corner point coordinates and the lower - right corner point coordinates of the rectangle:

[0184] When region Y does not overlap with region X, take region Y as the non - overlapping region of region Y with respect to region X and store it in List_D.

[0185] As Figure 3 shown, when region Y overlaps with region X, then obtain eight candidate non - overlapping regions at the upper - left, directly above, upper - right, directly right, lower - right, directly below, lower - left, and left - most of region Y (i.e., the above - mentioned first candidate non - overlapping region to the eighth candidate non - overlapping region, hereinafter referred to as region 1 - 8 respectively). These eight regions cover all non - overlapping regions in all cases where region Y and region X overlap with each other. Among them:

[0186] Assume that the upper - left corner point coordinates of region X are P1(x1, y1), and the lower - right corner point coordinates are P2(x2, y2);

[0187] The upper - left corner point coordinates of region Y are N1(m1, n1), and the lower - right corner point coordinates are N2(m2, n2);

[0188] max_start_x = max(x1, m1); the maximum value of the upper - left x - coordinate

[0189] min_start_x = min(x1, m1); the minimum value of the upper - left x - coordinate

[0190] max_start_y = max(y1, n1); the maximum value of the upper - left y - coordinate

[0191] min_start_y = min(y1, n1); the minimum value of the upper - left y - coordinate

[0192] max_end_x = max(x2, m2); the maximum value of the x-coordinate of the lower right corner

[0193] min_end_x = min(x2, m2); the minimum value of the x-coordinate of the lower right corner

[0194] max_end_y = max(y2, n2); the maximum value of the y-coordinate of the lower right corner

[0195] min_end_y = min(y2, n2); the minimum value of the y-coordinate of the lower right corner

[0196] Then the coordinates of the upper left corner and the lower right corner of Region 1 are respectively:

[0197] Upper left corner (min_start_x, min_start_y), lower right corner (max_start_x, max_start_y);

[0198] The coordinates of the upper left corner and the lower right corner of Region 2 are respectively:

[0199] Upper left corner (max_start_x, min_start_y), lower right corner (min_end_x, max_start_y);

[0200] The coordinates of the upper left corner and the lower right corner of Region 3 are respectively:

[0201] Upper left corner (min_end_x, min_start_y), lower right corner (max_end_x, max_start_y);

[0202] The coordinates of the upper left corner and the lower right corner of Region 4 are respectively:

[0203] Upper left corner (min_end_x, max_start_y), lower right corner (max_end_x, min_end_y);

[0204] The coordinates of the upper left corner and the lower right corner of Region 5 are respectively:

[0205] Upper left corner (min_end_x, min_end_y), lower right corner (max_end_x, max_end_y);

[0206] The coordinates of the upper left corner and the lower right corner of Region 6 are respectively:

[0207] Upper left corner (max_start_x, min_end_y), lower right corner (min_end_x, max_end_y);

[0208] The coordinates of the upper left corner and the lower right corner of Region 7 are respectively:

[0209] Upper left corner (min_start_x, min_end_y), lower right corner (max_start_x, max_end_y);

[0210] The coordinates of the upper left corner point and the lower right corner point of Region 8 are respectively:

[0211] Upper left corner (min_start_x, max_start_y), lower right corner (max_start_x, min_end_y).

[0212] For the above eight regions, their legality can be checked based on the coordinates of their upper left corner points and lower right corner points.

[0213] For any region, when the abscissa of the lower right corner point of the region is greater than the abscissa of the upper left corner point of the region, and the ordinate of the lower right corner point of the region is greater than the ordinate of the upper left corner point of the region, then it is determined that the region is a legal region and can be used as a non-overlapping region of Region Y with respect to Region X and stored in List_D; otherwise, it is determined that the region is an illegal region and can be removed.

[0214] It should be noted that in the embodiments of the present application, for the non-overlapping regions determined in the above manner, some of the non-overlapping regions can also be merged, and multiple small non-overlapping regions can be merged into larger non-overlapping regions.

[0215] Exemplarily, adjacent non-overlapping regions with a common side (i.e., there is a same side) can be merged.

[0216] For example, for Region 5 and Region 6 above, when both Region 5 and Region 6 are legal regions, Region 5 and Region 6 can be merged.

[0217] Exemplarily, in the case of obtaining a list of all non-overlapping camera regions, the existing coordinates of each region, the coordinates of the parent region of each region (i.e., the camera region to which the region belongs), and the camera information can be saved to facilitate subsequent heat map synthesis and regional heat calculation.

[0218] For example, as Figure 4A shown, assuming that multiple camera regions to be de-duplicated include Camera Region 1, Camera Region 2, and Camera Region 3, then taking Camera Region 1 as the initial target region, the schematic diagrams of de-duplicating Camera Region 2 and Camera Region 3 can be respectively as Figure 4B and Figure 4C shown.

[0219] Exemplarily, in the global heat map configuration, a custom area can be drawn. In the case where the custom area straddles the overlapping area of multiple camera areas, the non-overlapping area occupied by the custom area (i.e., the sub-area in the de-duplicated camera area) can be obtained through the above splitting method, and the heat matrix calculated based on these de-duplicated non-overlapping areas can accurately reflect the heat situation of the drawing area.

[0220] As Figure 5 shown, the non-overlapping area occupied by the custom area includes partial areas in areas A, B, H, G, F, and E, and all of area C. The heat data of the custom area can be statistically analyzed based on the heat map data of the corresponding areas of the custom area in each non-overlapping area.

[0221] Exemplarily, taking the determination of the partial area (i.e., the sub-area) in area A occupied by the custom area as an example, assume that the upper left coordinate of area A is (X a1 , Y a1 ), the lower right coordinate is (X a2 , Y a2 ), the upper left coordinate of the custom area is (X z1 , Y z1 ), the lower right coordinate is (X z2 , Y z2 ), and the upper left coordinate of the sub-area in area A occupied by the custom area is (X u1 , Y u1 ), the lower right coordinate is (X u2 , Y u2 ). Then:

[0222] X u1 = max(X a1 , X z1 )

[0223] Y u1 = max(Y a1 , Y z1 )

[0224] X u2 = min(X a2 , X z2 )

[0225] Y u2 = min(Y a2 , Y z2 )

[0226] The method provided in this application has been described above. Next, the device provided in this application will be described:

[0227] Please refer to Figure 6, which is a schematic structural diagram of a camera area deduplication device provided by an embodiment of the present application. As Figure 6 shown, the camera area deduplication device may include:

[0228] A selection unit 610, configured to select one camera area from multiple camera areas to be deduplicated as an initial target area;

[0229] The selection unit 610 is further configured to traverse and select each unselected camera area among the multiple camera areas;

[0230] A first determination unit 620, configured to, for any camera area selected through traversal, determine the non-overlapping area in the camera area, and determine the non-overlapping area in the camera area as a newly added target area, where the non-overlapping area is the area in the camera area that does not overlap with any current target areas;

[0231] A second determination unit 630, configured to, when there are no unselected camera areas among the multiple camera areas, determine the current target areas as the deduplicated camera areas.

[0232] In some embodiments, the first determination unit 620 is further specifically configured to traverse and select each unselected target area among the current target areas;

[0233] The first determination unit 620 is specifically configured to, for any target area selected through traversal, determine the non-overlapping area between the currently reserved area in the camera area and the target area, and update the currently reserved area in the camera area to the non-overlapping area; when there are no unselected target areas among the current target areas, determine the currently reserved area in the camera area as the non-overlapping area in the camera area.

[0234] In some embodiments, the target areas are stored in a result storage space;

[0235] The selection unit 610 is further configured to copy the target areas in the current result storage space to a storage space for comparison results;

[0236] The first determination unit 620 is specifically configured to traverse the storage space for comparison results and take out the selected target areas from the storage space for comparison results;

[0237] The situation that there are no unselected target areas among the current target areas includes:

[0238] The storage space for comparison results is empty.

[0239] In some embodiments, the selection unit 610 is specifically configured to traverse the unselected camera regions among the multiple camera regions and select an unselected camera region to add to the storage space of the camera regions to be compared.

[0240] The first determination unit 620 is specifically configured to traverse each region in the storage space of the camera regions to be compared and take out the selected region from the storage space of the camera regions to be compared; wherein each region in the storage space of the camera regions to be compared is the currently reserved region in this camera region.

[0241] The first determination unit 620 is specifically configured to determine the non-overlapping region between the taken-out region and the target region, and add the non-overlapping region to the storage space of the reserved regions; wherein the storage space of the reserved regions is used to store the non-overlapping region between the currently reserved region in this camera region and the target region.

[0242] The first determination unit 620 is further configured to, when the storage space of the camera regions to be compared is empty, move the non-overlapping regions in the storage space of the reserved regions from the storage space of the reserved regions into the storage space of the camera regions to be compared.

[0243] In some embodiments, the target region is stored in the result storage space.

[0244] The selection unit 610 is further configured to, when there is no unselected target region among the current target regions, add each region in the storage space of the camera regions to be compared to the result storage space.

[0245] In some embodiments, both the camera region and the target region are rectangular regions.

[0246] The first determination unit 620 is specifically configured to determine whether the camera region overlaps with the target region; when the camera region does not overlap with the target region, determine the camera region as the non-overlapping region between the camera region and the target region; when the camera region overlaps with the target region, determine the non-overlapping region between the camera region and the target region according to the corner coordinates of the camera region and the corner coordinates of the target region.

[0247] In some embodiments, when the camera region overlaps with the target region, the candidate non-overlapping regions between the camera region and the target region include:

[0248] The first candidate non-overlapping region at the upper left corner of the target region, the second candidate non-overlapping region directly above the target region, the third candidate non-overlapping region at the upper right corner of the target region, the fourth candidate non-overlapping region directly to the right of the target region, the fifth candidate non-overlapping region at the lower right corner of the target region, the sixth candidate non-overlapping region directly below the target region, the seventh candidate non-overlapping region at the lower left corner of the target region, and the eighth candidate non-overlapping region directly to the left of the target region;

[0249] Each candidate non-overlapping region is a rectangular region;

[0250] The first determination unit 620 is specifically configured to determine the upper left corner coordinates and the lower right corner coordinates of each candidate non-overlapping region according to the first upper left corner coordinates, the first lower right corner coordinates, the second upper left corner coordinates, and the second lower right corner coordinates; wherein, the first upper left corner coordinates and the first lower right corner coordinates are respectively the upper left corner coordinates and the lower right corner coordinates of the camera region, and the second upper left corner coordinates and the second lower right corner coordinates are respectively the upper left corner coordinates and the lower right corner coordinates of the target region; according to the upper left corner coordinates and the lower right corner coordinates of each candidate non-overlapping region, determine the legal candidate non-overlapping regions in each candidate non-overlapping region as the non-overlapping regions between the camera region and the target region;

[0251] Among them, the abscissa of the lower right corner coordinates of the legal candidate non-overlapping region is greater than the abscissa of the upper left corner coordinates, and the ordinate of the lower right corner is greater than the ordinate of the upper left corner coordinates.

[0252] An embodiment of the present application further provides an electronic device, including a processor and a memory. The memory is used to store a computer program. The processor is used to implement the camera region deduplication method described above when executing the program stored in the memory.

[0253] Please refer to Figure 7 , which is a schematic hardware structure diagram of an electronic device provided by an embodiment of the present application. The electronic device may include a processor 701 and a memory 702 storing machine-executable instructions. The processor 701 and the memory 702 may communicate via a system bus 703. And by reading and executing the machine-executable instructions corresponding to the camera region deduplication logic in the memory 702, the processor 701 may execute the camera region deduplication method described above.

[0254] The memory 702 mentioned in this article can be any electronic, magnetic, optical, or other physical storage device that can contain or store information such as executable instructions, data, and so on. For example, a machine-readable storage medium can be: RAM (Random Access Memory), volatile memory, non-volatile memory, flash memory, storage drives (such as hard disk drives), solid-state drives, any type of storage disk (such as optical discs, DVDs, etc.), or similar storage media, or a combination thereof.

[0255] In some embodiments, a machine-readable storage medium is also provided, such as Figure 7 the memory 702 in []. The machine-readable storage medium stores machine-executable instructions, and when the machine-executable instructions are executed by a processor, the camera area deduplication method described above is implemented. For example, the machine-readable storage medium can be ROM, RAM, CD-ROM, magnetic tapes, floppy disks, and optical data storage devices, etc.

[0256] The embodiments of the present application also provide a computer program product that stores a computer program, and when the processor executes the computer program, it causes the processor to execute the camera area deduplication method described above.

[0257] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "including", "comprising", or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article, or device including a series of elements not only includes those elements but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article, or device. Without further limitation, an element defined by the statement "including a..." does not exclude the existence of additional identical elements in the process, method, article, or device including the element.

[0258] The above are only the preferred embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included within the scope of protection of the present application.

Claims

1. A method for removing duplicates in a camera area, characterized in that, Including: Selecting one camera area from multiple camera areas to be de-duplicated as the initial target area; Traversing and selecting each unselected camera area among the multiple camera areas; For any camera area selected during traversal, determining the non-overlapping area in this camera area and determining the non-overlapping area in this camera area as the newly added target area, where the non-overlapping area is the area in this camera area that does not overlap with any current target areas; When there are no unselected camera areas among the multiple camera areas, determining the current target areas as the de-duplicated camera areas; Among them, for any camera area selected during traversal, determining the non-overlapping area in this camera area includes: Traversing and selecting each unselected target area among the current target areas; For any target area selected during traversal, determining the non-overlapping area between the currently retained area in this camera area and this target area, and updating the currently retained area in this camera area to this non-overlapping area; When there are no unselected target areas among the current target areas, determining the currently retained area in this camera area as the non-overlapping area in this camera area; The traversing and selecting each unselected camera area among the multiple camera areas includes: Traversing the unselected camera areas among the multiple camera areas and selecting an unselected camera area to add to the storage space for camera areas to be compared; For any target area selected during traversal, determining the non-overlapping area between the currently retained area in this camera area and this target area, and updating the currently retained area in this camera area to this non-overlapping area includes: Traversing each area in the storage space for camera areas to be compared and taking out the selected area from the storage space for camera areas to be compared; where each area in the storage space for camera areas to be compared is the currently retained area in this camera area; Determining the non-overlapping area between the taken-out area and this target area and adding this non-overlapping area to the storage space for retained areas; the storage space for retained areas is used to store the non-overlapping area between the currently retained area in this camera area and this target area; When the storage space for camera areas to be compared is empty, moving the non-overlapping area in the storage space for retained areas from the storage space for retained areas into the storage space for camera areas to be compared.

2. The method according to claim 1, characterized in that, The target areas are saved in the result storage space; Before traversing and selecting each unselected target area among the current target areas, it further includes: Copying the target areas in the current result storage space to the storage space for results to be compared; The traversing and selecting each unselected target area among the current target areas includes: Traversing the storage space for results to be compared and taking out the selected target area from the storage space for results to be compared; That there are no unselected target areas among the current target areas includes: That the storage space for results to be compared is empty.

3. The method according to claim 1, wherein The target areas are saved in the result storage space; When there are no unselected target areas among the current target areas, the method further includes: Add each area in the storage space of the camera area to be compared to the result storage space, and clear the storage space of the camera area to be compared.

4. The method according to any one of claims 1 to 3, characterized in that Both the camera area and the target area are rectangular areas; The non-overlapping area between any camera area and any target area is determined by the following method: Determine whether the camera area overlaps with the target area; When the camera area does not overlap with the target area, determine the camera area as the non-overlapping area between the camera area and the target area; When the camera area overlaps with the target area, determine the non-overlapping area between the camera area and the target area according to the corner coordinates of the camera area and the corner coordinates of the target area.

5. The method according to claim 4, wherein When the camera area overlaps with the target area, the candidate non-overlapping areas between the camera area and the target area include: The first candidate non-overlapping area at the upper left corner of the target area, the second candidate non-overlapping area directly above the target area, the third candidate non-overlapping area at the upper right corner of the target area, the fourth candidate non-overlapping area directly to the right of the target area, the fifth candidate non-overlapping area at the lower right corner of the target area, the sixth candidate non-overlapping area directly below the target area, the seventh candidate non-overlapping area at the lower left corner of the target area, and the eighth candidate non-overlapping area directly to the left of the target area; Each candidate non-overlapping area is a rectangular area; The determining the non-overlapping area between the camera area and the target area according to the corner coordinates of the camera area and the corner coordinates of the target area includes: Determine the corner coordinates of the upper left corner and the lower right corner of each candidate non-overlapping area according to the first upper left corner coordinate, the first lower right corner coordinate, the second upper left corner coordinate, and the second lower right corner coordinate; wherein, the first upper left corner coordinate and the first lower right corner coordinate are respectively the corner coordinates of the upper left corner and the lower right corner of the camera area, and the second upper left corner coordinate and the second lower right corner coordinate are respectively the corner coordinates of the upper left corner and the lower right corner of the target area; Determine the legal candidate non-overlapping areas in each candidate non-overlapping area as the non-overlapping area between the camera area and the target area according to the corner coordinates of the upper left corner and the lower right corner of each candidate non-overlapping area; Among them, the abscissa of the lower right corner coordinate of the legal candidate non-overlapping area is greater than the abscissa of the upper left corner coordinate, and the ordinate of the lower right corner is greater than the ordinate of the upper left corner coordinate.

6. A camera area duplicate removal device, characterized in that, It includes: A selection unit for selecting one camera area from multiple camera areas to be de-duplicated as an initial target area; The selection unit is further configured to traverse and select each unselected camera area among the multiple camera areas; A first determination unit for, for any camera area selected by traversal, determining the non-overlapping area in the camera area and determining the non-overlapping area in the camera area as a newly added target area, wherein the non-overlapping area is the area in the camera area that does not overlap with the current target areas; A second determination unit, configured to determine each current target area as each deduplicated camera area when there is no unselected camera area among the multiple camera areas; Wherein, the first determination unit is further specifically configured to traverse and select each unselected target area among the current target areas; The first determination unit is specifically configured to, for any traversed and selected target area, determine a non-overlapping area between the currently reserved area in the camera area and the target area, and update the currently reserved area in the camera area to the non-overlapping area; when there is no unselected target area among the current target areas, determine the currently reserved area in the camera area as the non-overlapping area in the camera area; Wherein, the selection unit is specifically configured to traverse the unselected camera areas among the multiple camera areas and select an unselected camera area to add to the storage space of the camera areas to be compared; The first determination unit is specifically configured to traverse each area in the storage space of the camera areas to be compared and take out the selected area from the storage space of the camera areas to be compared; wherein each area in the storage space of the camera areas to be compared is the currently reserved area in the camera area; The first determination unit is specifically configured to determine a non-overlapping area between the taken-out area and the target area, and add the non-overlapping area to the storage space of the reserved areas; wherein the storage space of the reserved areas is used to store the non-overlapping area between the currently reserved area in the camera area and the target area; The first determination unit is further configured to, when the storage space of the camera areas to be compared is empty, move the non-overlapping areas in the storage space of the reserved areas from the storage space of the reserved areas into the storage space of the camera areas to be compared.

7. The device according to claim 6, characterized in that, The target areas are stored in the result storage space; The selection unit is further configured to copy the target areas in the current result storage space to the storage space of the results to be compared; The first determination unit is specifically configured to traverse the storage space of the results to be compared and take out the selected target area from the storage space of the results to be compared; The situation that there is no unselected target area among the current target areas includes: The storage space of the results to be compared is empty; Wherein, the target areas are stored in the result storage space; The selection unit is further configured to, when there is no unselected target area among the current target areas, add each area in the storage space of the camera areas to be compared to the result storage space and clear the storage space of the camera areas to be compared; And / or Both the camera area and the target area are rectangular areas; The first determination unit is specifically configured to determine whether the camera area overlaps with the target area; when the camera area does not overlap with the target area, determine the camera area as the non-overlapping area between the camera area and the target area; when the camera area overlaps with the target area, determine the non-overlapping area between the camera area and the target area according to the corner coordinates of the camera area and the corner coordinates of the target area; Wherein, when the camera area overlaps with the target area, the candidate non-overlapping areas between the camera area and the target area include: a first candidate non-overlapping area at the upper left corner of the target area, a second candidate non-overlapping area directly above the target area, a third candidate non-overlapping area at the upper right corner of the target area, a fourth candidate non-overlapping area directly to the right of the target area, a fifth candidate non-overlapping area at the lower right corner of the target area, a sixth candidate non-overlapping area directly below the target area, a seventh candidate non-overlapping area at the lower left corner of the target area, and an eighth candidate non-overlapping area directly to the left of the target area; each candidate non-overlapping area is a rectangular area; The first determining unit is specifically configured to determine the upper left corner coordinates and the lower right corner coordinates of each candidate non-overlapping area according to the first upper left corner coordinates, the first lower right corner coordinates, the second upper left corner coordinates, and the second lower right corner coordinates; wherein, the first upper left corner coordinates and the first lower right corner coordinates are respectively the upper left corner coordinates and the lower right corner coordinates of the camera area, and the second upper left corner coordinates and the second lower right corner coordinates are respectively the upper left corner coordinates and the lower right corner coordinates of the target area; according to the upper left corner coordinates and the lower right corner coordinates of each candidate non-overlapping area, determine the legal candidate non-overlapping areas in each candidate non-overlapping area as the non-overlapping areas between the camera area and the target area; Wherein, for a legal candidate non-overlapping area, the abscissa of the lower right corner coordinates is greater than the abscissa of the upper left corner coordinates, and the ordinate of the lower right corner is greater than the ordinate of the upper left corner.

8. An electronic device, characterized in that, It includes a processor and a memory, the memory stores machine-executable instructions that can be executed by the processor, and the processor is configured to execute the machine-executable instructions to implement the method according to any one of claims 1-5.

9. A computer program product, characterized in that, The computer program product stores a computer program, and when the processor executes the computer program, it causes the processor to implement the method according to any one of claims 1-5.

Images