Point cloud density adjustment method, electronic device, and storage medium

Abstract

The application relates to the technical field of point cloud processing, and provides a point cloud density adjustment method, an electronic device and a storage medium.The method comprises the following steps: acquiring an initial point cloud map and a distance determination threshold value of a robot; determining a plurality of target regions in the initial point cloud map, and calculating an environment complexity value of each target region; cutting the initial point cloud map into a plurality of sub-maps; determining a point cloud density coefficient of each sub-map according to the environment complexity value of each sub-map; and adjusting the initial point cloud map according to the point cloud density coefficient to obtain a target point cloud map.The application cuts the initial point cloud map into a plurality of sub-maps according to the environment complexity value, and merges adjacent target regions with consistent environment complexity into the same sub-map, so that the number of sub-maps is reduced, and the adjustment efficiency and accuracy of the point cloud density are improved.

Description

Technical Field

[0001] This application relates to the field of point cloud processing technology, specifically to a point cloud density adjustment method, electronic device, and storage medium. Background Technology

[0002] Point cloud maps can represent the outlines and specific locations of objects in space. Typically, point cloud maps are very large and require a lot of storage space. A 640*480 image will generate about 300,000 spatial points. However, many spatial points are not necessary and instead waste space and increase the amount of computation. For example, if the point cloud in the point cloud map is too dense, it will consume a lot of computing resources and storage space. If the point cloud is too sparse, the space between the points in the point cloud map cannot be described, and it cannot provide obstacles avoidance or navigation for robots. Summary of the Invention

[0003] In view of the above, it is necessary to propose a point cloud density adjustment method, electronic device and storage medium, which divides the initial point cloud map into multiple sub-maps according to the environmental complexity value, and merges adjacent target areas with the same environmental complexity into the same sub-map, thereby reducing the number of sub-maps and improving the efficiency and accuracy of point cloud density adjustment.

[0004] A first aspect of this application provides a point cloud density adjustment method, the method comprising: acquiring an initial point cloud map and size parameters of a robot, and calculating a distance determination threshold based on the size parameters; determining multiple target regions in the initial point cloud map, and calculating an environmental complexity value for each target region; dividing the initial point cloud map into multiple sub-maps based on the environmental complexity value; determining a point cloud density coefficient for each sub-map based on the environmental complexity value of each sub-map; and adjusting the initial point cloud map based on the point cloud density coefficient to obtain a target point cloud map, wherein the maximum distance between adjacent spatial points in the target point cloud map is less than the distance determination threshold.

[0005] Optionally, determining multiple target regions in the initial point cloud map includes: using a preset pane to perform non-overlapping sliding on the initial point cloud map, and determining the region corresponding to each sliding of the pane as a target region in the initial point cloud map.

[0006] Optionally, determining multiple target regions in the initial point cloud map includes: identifying multiple target objects from the initial point cloud map using an identification algorithm, and determining the region corresponding to each target object as a target region in the initial point cloud map.

[0007] Optionally, calculating the environmental complexity value of each target region includes: obtaining the depth value of a pixel within the target region; calculating the standard deviation of the depth values ​​of the pixels to obtain the standard deviation of the corresponding target region; and determining the environmental complexity value of the target region based on the standard deviation.

[0008] Optionally, the step of dividing the initial point cloud map into multiple sub-maps based on the environmental complexity value includes: determining whether the environmental complexity value of adjacent target areas meets a preset division requirement; when the environmental complexity value of adjacent target areas meets the preset division requirement, dividing the adjacent target areas into two sub-maps.

[0009] Optionally, the method further includes: merging the adjacent target areas into a single sub-map when the environmental complexity value of adjacent target areas does not meet the preset cutting requirements.

[0010] Optionally, determining the point cloud density coefficient of each sub-map based on the environmental complexity value of each sub-map includes: dividing the environmental complexity value into multiple environmental complexity levels according to a preset division rule; and determining the point cloud density coefficient of each sub-map based on the multiple environmental complexity levels.

[0011] Optionally, the step of calculating the distance determination threshold based on the size parameters includes: determining the maximum distance that the robot can pass through based on the size parameters; obtaining a preset distance coefficient; and calculating the product of the maximum distance that can be passed through and the distance coefficient to obtain the distance determination threshold.

[0012] A second aspect of this application provides an electronic device including a processor and a memory, wherein the processor is configured to implement the point cloud density adjustment method by executing a computer program stored in the memory.

[0013] A third aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the point cloud density adjustment method.

[0014] In summary, the point cloud density adjustment method, electronic device, and storage medium described in this application, on the one hand, divide the initial point cloud map into multiple sub-maps based on the environmental complexity value. Since the complexity of the pane regions corresponding to different standard deviations is different, dividing the initial cloud map based on the environmental complexity value of the panes ensures the consistency of environmental complexity in each sub-map after division. Furthermore, merging adjacent target regions with consistent environmental complexity into the same sub-map reduces the number of sub-maps, thereby improving the efficiency and accuracy of point cloud density adjustment. On the other hand, the point cloud density coefficient of each sub-map is determined based on its environmental complexity value. During the determination process, the environmental complexity of all sub-maps is divided into multiple environmental complexity levels. Each environmental complexity level can include one or more sub-maps. This avoids the phenomenon of slow point cloud map density adjustment caused by determining a point cloud density coefficient for each sub-map, thus improving the accuracy and efficiency of point cloud density adjustment. Finally, the initial point cloud map is adjusted according to the point cloud density coefficient to obtain the target point cloud map. The maximum distance between adjacent spatial points in the target point cloud map is less than the distance judgment threshold, which can ensure that the density in the target point cloud map will not be too dense or too sparse, thus improving the accuracy of point cloud density adjustment and the utilization rate of the point cloud map. Attached Figure Description

[0015] Figure 1 This is a flowchart of a point cloud density adjustment method provided in a preferred embodiment of this application.

[0016] Figure 2 This is a schematic diagram of the environmental complexity levels provided in a preferred embodiment of this application.

[0017] Figure 3 This is a first schematic diagram of a point cloud that is too sparse, provided by a preferred embodiment of this application.

[0018] Figure 4 This is a second schematic diagram of a point cloud that is too sparse, provided in a preferred embodiment of this application.

[0019] Figure 5 This is a first schematic diagram of a point cloud that is too dense, provided in a preferred embodiment of this application.

[0020] Figure 6 This is a second schematic diagram of a point cloud that is too dense, provided in a preferred embodiment of this application.

[0021] Figure 7 This is a schematic diagram of the target point cloud map adjusted by the point cloud density adjustment method provided in a preferred embodiment of this application.

[0022] Figure 8 This is a schematic diagram of the structure of an electronic device provided in a preferred embodiment of this application. Detailed Implementation

[0023] To better understand the above-mentioned objectives, features, and advantages of this application, the application will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, unless otherwise specified, the embodiments and features described herein can be combined with each other.

[0024] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application.

[0025] Figure 1 This is a flowchart of a point cloud density adjustment method provided in a preferred embodiment of this application.

[0026] In this embodiment, the point cloud density adjustment method can be applied to electronic devices. For electronic devices that require automatic point cloud density adjustment, the automatic point cloud density adjustment function provided by the method of this application can be directly integrated into the electronic device, or it can be run in the electronic device in the form of a software development kit (SDK).

[0027] like Figure 1 As shown, the point cloud density adjustment method specifically includes the following steps. Depending on different needs, the order of the steps in this flowchart can be changed, and some steps can be omitted.

[0028] S11, obtain the initial point cloud map and the robot's size parameters, and calculate the distance determination threshold based on the size parameters.

[0029] In this embodiment, when a user adjusts the point cloud density, they initiate a point cloud density adjustment request to the server via a client. Specifically, the client can be a smartphone, iPad, or other smart device. The server can be a point cloud density adjustment subsystem. During the point cloud density adjustment process, the client can send a point cloud density adjustment request to the point cloud density adjustment subsystem, which receives the request. In this embodiment, when the server receives the point cloud density adjustment request, it parses the request to obtain an initial point cloud map and the robot's size parameters. The robot can be a robotic vacuum cleaner, a robotic dog, a robotic cat, or other intelligent robots. The robot's size parameters include, but are not limited to, the robot's length, width, and height when moving.

[0030] In this embodiment, the distance determination threshold is used to characterize the distance between adjacent spatial points of the initial point cloud map determined based on the robot's size parameters.

[0031] In an optional embodiment, calculating the distance determination threshold based on the size parameters includes: determining the maximum distance the robot can travel based on the size parameters; obtaining a preset distance coefficient; and calculating the product of the maximum travelable distance and the distance coefficient to obtain the distance determination threshold.

[0032] In this embodiment, the maximum distance that the robot can pass through adjacent spatial points in the initial point cloud map is calculated in advance based on the robot's size parameters.

[0033] In this embodiment, a distance coefficient can be set, wherein the preset distance coefficient is a random number between 0 and 1. The preset distance coefficient is obtained, and the distance determination threshold of the initial point cloud map is determined based on the preset distance coefficient and the maximum distance.

[0034] S12, determine multiple target regions in the initial point cloud map, and calculate the environmental complexity value of each target region.

[0035] In this embodiment, multiple target areas in the initial point cloud map can be determined based on a sliding pane or an identification algorithm.

[0036] Specifically, in an optional embodiment, determining multiple target regions in the initial point cloud map includes: using a preset pane to perform non-overlapping sliding on the initial point cloud map, and determining the region corresponding to each sliding of the pane as a target region in the initial point cloud map.

[0037] In this embodiment, the panes and sliding methods can be preset. Specifically, the panes are set to (h×w), where h represents the length of each pane and x represents the width of each pane. The length and width of the panes can be set according to the user's needs. The sliding method can also be preset. Specifically, the preset sliding method can be sliding sequentially from left to right on the initial point cloud map, or sliding sequentially from top to bottom on the initial point cloud map, or the sliding method can be set according to the customer's needs. This embodiment does not impose any limitations on this.

[0038] In an optional embodiment, determining multiple target regions in the initial point cloud map includes: identifying multiple target objects from the initial point cloud map using an identification algorithm, and determining the region corresponding to each target object as a target region in the initial point cloud map.

[0039] In this embodiment, the identification algorithm is used to identify target objects in the image. The algorithm identifies all target objects from the initial point cloud map and reads the depth value corresponding to each pixel of each target object. Since the depth values ​​corresponding to different target objects may vary greatly, the standard deviation of each target object is obtained by cutting each target object into a target region and calculating the standard deviation of all depth values ​​corresponding to all pixels in each target region. This avoids the inaccuracy of the standard deviation caused by cutting multiple target objects into a single target region and improves the accuracy of the standard deviation of each target region.

[0040] In an optional embodiment, calculating the environmental complexity value of each target region includes: obtaining the depth value of a pixel within the target region; calculating the standard deviation of the depth values ​​of the pixels to obtain the standard deviation of the corresponding target region; and determining the environmental complexity value of the target region based on the standard deviation.

[0041] In this embodiment, the standard deviation is used to characterize the degree of dispersion between spatial points in each target region. For example, if the depth corresponding to the pixels in the target region is close to a linear distribution, that is, the standard deviation is small, it can be determined that the surface of the target region is relatively smooth; if the depth corresponding to the pixels in the target region is relatively discrete, that is, the standard deviation is large, it can be determined that the surface of the target region is not smooth.

[0042] In this embodiment, a database can be pre-set, and the environmental complexity value of each target region corresponding to the standard deviation of each target region can be matched with the standard deviation in the preset database to obtain the target standard deviation. The environmental complexity corresponding to the target standard deviation is the environmental complexity value of the corresponding target region.

[0043] S13, the initial point cloud map is divided into multiple sub-maps according to the environmental complexity value.

[0044] In this embodiment, since the complexity of the pane areas corresponding to different standard deviations is different, cutting the initial cloud map according to the standard deviation of the panes can ensure the consistency of the environmental complexity of each sub-map after cutting.

[0045] In an optional embodiment, the step of dividing the initial point cloud map into multiple sub-maps based on the environmental complexity value includes: determining whether the environmental complexity value of adjacent target areas meets a preset division requirement; when the environmental complexity value of adjacent target areas meets the preset division requirement, dividing the adjacent target areas into two sub-maps; or, when the environmental complexity value of adjacent target areas does not meet the preset division requirement, merging the adjacent target areas into the same sub-map.

[0046] In this embodiment, when performing initial point cloud map segmentation, it is determined whether the environmental complexity values ​​of adjacent target areas meet the preset segmentation requirements, that is, whether the standard deviations of adjacent target areas are close. When the standard deviations of adjacent target areas are not close, it is determined that there is a large difference in the regional environmental complexity of adjacent target areas, and each pane is treated as a sub-map. When the standard deviations of adjacent target areas are close, it is determined that the regional environmental complexity of adjacent target areas is basically the same, and the adjacent target areas are merged into the same sub-map. This can reduce the number of sub-maps and thus improve the efficiency and accuracy of point cloud density adjustment.

[0047] S14, determine the point cloud density coefficient of each sub-map based on the environmental complexity value of each sub-map.

[0048] In this embodiment, S can be used to represent the point cloud density coefficient, where S∈(0,1), S=1 indicates that the interval between adjacent spatial points in each sub-map is the maximum value, and the smaller S is, the denser the point cloud is.

[0049] In an optional embodiment, determining the point cloud density coefficient of each sub-map based on the environmental complexity value of each sub-map includes: dividing the environmental complexity value into multiple environmental complexity levels according to a preset division rule; and determining the point cloud density coefficient of each sub-map based on the multiple environmental complexity levels.

[0050] In this embodiment, since the standard deviation is used to characterize the degree of dispersion between spatial points in each target area, the environmental complexity value of the target area can be determined based on the standard deviation. If the standard deviation of each sub-map is small, it can be determined that the surface of the area corresponding to each sub-map is relatively smooth and the environment is not complex; if the standard deviation of each sub-map is large, it can be determined that the surface of the area corresponding to each sub-map is not smooth, the undulation is large, and the environment is relatively complex.

[0051] In this embodiment, a pre-set partitioning rule can be used to divide the environmental complexity of all sub-maps into multiple environmental complexity levels. Each environmental complexity level may include one or more sub-maps. This avoids the phenomenon of slow point cloud map density adjustment caused by determining a point cloud density coefficient for each sub-map, and improves the accuracy and efficiency of point cloud density adjustment.

[0052] See Figure 2As shown, based on user needs, the environmental complexity values ​​of all sub-maps are divided into four segments, namely four environmental complexity levels: very dense, dense, sparse, and very sparse. The point cloud density coefficient of the sub-map with an environmental complexity level of very dense is determined to be 0.25; the point cloud density coefficient of the sub-map with an environmental complexity level of dense is determined to be 0.5; the point cloud density coefficient of the sub-map with an environmental complexity level of sparse is determined to be 0.75; and the point cloud density coefficient of the sub-map with an environmental complexity level of very sparse is determined to be 1.

[0053] S15, adjust the initial point cloud map according to the point cloud density coefficient to obtain the target point cloud map, wherein the maximum distance between adjacent spatial points in the target point cloud map is less than the distance determination threshold.

[0054] In this embodiment, the target point cloud map is an initial point cloud map with adjusted density. The density of each sub-map is adjusted according to the distance determination threshold and the point cloud density coefficient of each sub-map, which can ensure that the density in each sub-map is not too dense or too sparse, thereby improving the accuracy of point cloud density adjustment and the utilization rate of point cloud map.

[0055] In this embodiment, when adjusting the point cloud density of each sub-map, the distance between adjacent spatial points in each sub-map is adjusted according to the point cloud density coefficient of each sub-map, and the maximum distance between adjacent spatial points is less than the distance judgment threshold. This avoids the problem that the robot mistakenly believes that adjacent points can pass each other, which would prevent the robot from avoiding obstacles and navigating. This improves the accuracy and utilization of point cloud map adjustment.

[0056] For example, the distance determination threshold is 7mm, and the initial point cloud map is divided into 4 levels based on the environmental complexity value (see [reference]). Figure 2 As shown): Very dense, dense, sparse, and very sparse. If the environmental complexity level is determined to be very dense (S=0.25), then the distance between adjacent spatial points in the submap corresponding to the very dense environmental complexity level is adjusted to 7×0.25mm=1.75mm; if the environmental complexity level is determined to be dense (S=0.5), then the distance between adjacent spatial points in the submap corresponding to the dense environmental complexity level is adjusted to 7×0.5mm=3.5mm.

[0057] In this embodiment, when using point cloud maps, if the point cloud is too sparse, the space between adjacent points in the point cloud map will be too large to describe wall protrusions. This will cause the robot to perceive the wall as smooth and collide with the protrusions, failing to provide obstacle avoidance and navigation for the robot (see...). Figure 3 and Figure 4(as shown); if the point cloud is too dense, it increases unnecessary computational storage space. For example, in areas with smooth surfaces, not many point clouds are needed to represent the shape and outline of the surface (see...). Figure 5 and Figure 6 As shown in the figure, this embodiment obtains the target point cloud map by automatically adjusting the density of the initial point cloud map according to the complexity of the environment. This solves the problems that the spatial relationships between points in the point cloud map cannot be described due to the sparseness of the point cloud, and that the point cloud that is too dense will occupy a lot of computing resources and storage space. See [reference]. Figure 7 The diagram shows a target point cloud map adjusted by the point cloud density adjustment method. The density of adjacent spatial points in smooth areas is adjusted to a sparser point cloud, while the density of adjacent spatial points in uneven areas is adjusted to a denser point cloud, thus improving the accuracy and efficiency of point cloud density adjustment.

[0058] In summary, the point cloud density adjustment method described in this embodiment, on the one hand, divides the initial point cloud map into multiple sub-maps based on the environmental complexity value. Since the complexity of the pane regions corresponding to different standard deviations is different, dividing the initial cloud map based on the environmental complexity value of the panes ensures the consistency of environmental complexity in each sub-map after division. Furthermore, merging adjacent target regions with consistent environmental complexity into the same sub-map reduces the number of sub-maps, thereby improving the efficiency and accuracy of point cloud density adjustment. On the other hand, it determines the point cloud density coefficient of each sub-map based on its environmental complexity value. In this process, the environmental complexity of all sub-maps is divided into multiple environmental complexity levels. Each environmental complexity level can include one or more sub-maps. This avoids the phenomenon of slow point cloud map density adjustment caused by determining a point cloud density coefficient for each sub-map, thus improving the accuracy and efficiency of point cloud density adjustment. Finally, the initial point cloud map is adjusted according to the point cloud density coefficient to obtain the target point cloud map. The maximum distance between adjacent spatial points in the target point cloud map is less than the distance judgment threshold, which can ensure that the density in the target point cloud map is not too dense or too sparse, thus improving the accuracy of point cloud density adjustment and the utilization rate of the point cloud map.

[0059] See Figure 8 The diagram shown is a structural schematic of an electronic device provided in a preferred embodiment of this application. In a preferred embodiment of this application, the electronic device 8 includes a memory 81, at least one processor 82, at least one communication bus 83, and a transceiver 84.

[0060] Those skilled in the art should understand that Figure 8The structure of the electronic device shown does not constitute a limitation of the embodiments of this application. It can be a bus structure or a star structure. The electronic device 8 may also include more or fewer other hardware or software than shown, or different component arrangements.

[0061] In some embodiments, the electronic device 8 is an electronic device capable of automatically performing numerical calculations and / or information processing according to pre-set or stored instructions. Its hardware includes, but is not limited to, microprocessors, application-specific integrated circuits (ASICs), programmable gate arrays (FPGAs), digital processors, and embedded devices. The electronic device 8 may also include client devices, including, but not limited to, any electronic product capable of human-computer interaction with a client via a keyboard, mouse, remote control, touchpad, or voice control device, such as personal computers, tablet computers, smartphones, and digital cameras.

[0062] It should be noted that the electronic device 8 is merely an example. Other existing or future electronic products that are suitable for this application should also be included within the scope of protection of this application and are incorporated herein by reference.

[0063] In some embodiments, the memory 81 is used to store program code and various data, and to enable high-speed, automatic access to programs or data during the operation of the electronic device 8. The memory 81 includes read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electrically-erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, disk storage, magnetic tape storage, or any other computer-readable medium capable of carrying or storing data.

[0064] In some embodiments, the at least one processor 82 may be composed of integrated circuits, such as a single-packaged integrated circuit or multiple integrated circuits packaged with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The at least one processor 82 is the control unit of the electronic device 8, connecting various components of the entire electronic device 8 via various interfaces and lines. It executes programs or modules stored in the memory 81 and calls data stored in the memory 81 to perform various functions and process data in the electronic device 8.

[0065] In some embodiments, the at least one communication bus 83 is configured to enable communication between the memory 81 and the at least one processor 82, etc.

[0066] Although not shown, the electronic device 8 may also include a power supply (such as a battery) to power various components. Optionally, the power supply may be logically connected to the at least one processor 82 via a power management device, thereby enabling functions such as charging, discharging, and power consumption management. The power supply may also include one or more DC or AC power sources, recharging devices, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device 8 may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0067] It should be understood that the embodiments described are for illustrative purposes only and are not limited to this structure in the scope of the patent application.

[0068] The integrated unit implemented as a software functional module described above can be stored in a computer-readable storage medium. This software functional module, stored in a storage medium, includes several instructions to cause a computer device (which may be a personal computer, electronic device, or network device, etc.) or processor to execute portions of the methods described in the various embodiments of this application.

[0069] The memory 81 stores program code, and the at least one processor 82 can call the program code stored in the memory 81 to perform related functions.

[0070] In one embodiment of this application, the memory 81 stores a plurality of instructions which are executed by the at least one processor 82 to achieve the function of automatic adjustment of point cloud density.

[0071] Specifically, the implementation method of the above instructions by the at least one processor 82 can be found in [reference needed]. Figures 1 to 8 The descriptions of the relevant steps in the corresponding embodiments are not repeated here.

[0072] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0073] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0074] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0075] It will be apparent to those skilled in the art that this application is not limited to the details of the exemplary embodiments described above, and that this application can be implemented in other specific forms without departing from the spirit or essential characteristics of this application. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of this application is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be embraced within this application. No reference numerals in the claims should be construed as limiting the scope of the claims. Furthermore, it is clear that the word "comprising" does not exclude other elements or, and the singular does not exclude the plural. Multiple elements or devices recited in this application may also be implemented by a single element or device through software or hardware. The terms "first," "second," etc., are used to indicate names and do not indicate any particular order.

[0076] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application and are not intended to limit it. Although this application has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of this application without departing from the spirit and scope of the technical solutions of this application.

Claims

1. A point cloud density adjustment method, characterized in that, The method includes: The process of obtaining an initial point cloud map and the robot's size parameters, and calculating a distance determination threshold based on the size parameters, includes: determining the maximum distance the robot can travel based on the size parameters; obtaining a preset distance coefficient; and calculating the product of the maximum travelable distance and the distance coefficient to obtain the distance determination threshold, wherein the preset distance coefficient is a random number between 0 and 1. The process involves identifying multiple target regions in the initial point cloud map and calculating the environmental complexity value for each target region, including: obtaining the depth values ​​of pixels within the target region; calculating the standard deviation of the depth values ​​of the pixels to obtain the standard deviation of the corresponding target region; and determining the environmental complexity value of the target region based on the standard deviation. The initial point cloud map is divided into multiple sub-maps based on the environmental complexity value, including: determining whether the environmental complexity value of adjacent target areas meets the preset cutting requirements; when the environmental complexity value of adjacent target areas meets the preset cutting requirements, the adjacent target areas are divided into two sub-maps. The point cloud density coefficient of each sub-map is determined based on the environmental complexity value of each sub-map; The distance between adjacent spatial points in the corresponding sub-map is adjusted according to the point cloud density coefficient of each sub-map to obtain the target point cloud map. The maximum distance between adjacent spatial points in the target point cloud map is less than the distance determination threshold.

2. The point cloud density adjustment method as described in claim 1, characterized in that, Determining the multiple target regions in the initial point cloud map includes: Using a preset pane, non-overlapping sliding is performed on the initial point cloud map, and the area corresponding to each sliding of the pane is determined as the target area in the initial point cloud map.

3. The point cloud density adjustment method as described in claim 1, characterized in that, Determining the multiple target regions in the initial point cloud map includes: Multiple target objects are identified from the initial point cloud map using an identification algorithm, and the area corresponding to each target object is determined as the target area in the initial point cloud map.

4. The point cloud density adjustment method as described in claim 1, characterized in that, The method further includes: When the environmental complexity value of adjacent target areas does not meet the preset cutting requirements, the adjacent target areas are merged into the same sub-map.

5. The point cloud density adjustment method as described in claim 1, characterized in that, The process of determining the point cloud density coefficient of each sub-map based on the environmental complexity value of each sub-map includes: The environmental complexity value is divided into multiple environmental complexity levels according to a preset classification rule; The point cloud density coefficient of each sub-map is determined based on the multiple environmental complexity levels.

6. An electronic device, characterized in that, The electronic device includes a processor and a memory, wherein the processor is configured to implement the point cloud density adjustment method as described in any one of claims 1 to 5 when executing a computer program stored in the memory.

7. A computer-readable storage medium storing a computer program thereon, characterized in that, When the computer program is executed by the processor, it implements the point cloud density adjustment method as described in any one of claims 1 to 5.

Images