Method, system, controller, and storage medium for repairing a point cloud

Abstract

The application discloses a method, a system, a controller and a storage medium for repairing a point cloud. The method comprises the following steps: determining an initial point cloud according to initial point cloud data sent by a measuring device; determining a type to which missing data in the initial point cloud belongs; in the case that the type to which the missing data belongs is a hole type, repairing the missing data based on a gradient vector of a neighboring point of the missing data to obtain a target point cloud; and in the case that the type to which the missing data belongs is a non-hole type, repairing the missing data based on a near-neighbor repair strategy to obtain the target point cloud. The application can reduce measurement errors and improve measurement accuracy by repairing the missing data based on the type to which the missing data belongs.

Description

Technical Field

[0001] This application relates to the field of point cloud repair technology, and specifically to a method, system, controller, and storage medium for repairing point clouds. Background Technology

[0002] Concrete raw materials are typically stored in open or closed storage yards, mainly including gravel and sand. Different material types are separated by walls to create storage areas. Usually, a specialized concrete placing trolley moves a conveyor belt to load materials into different areas. LiDAR sensors are installed at both ends of the placing trolley, allowing for 3D modeling of the material yard using laser scanning and ranging technology. However, in existing technologies, due to structures such as beams and columns in the material yard, scanning blind spots are likely to exist, resulting in missing point cloud data and large errors in 3D laser scanning measurements. Therefore, existing technologies suffer from significant measurement errors due to missing point cloud data. Summary of the Invention

[0003] The purpose of this application is to provide a method, system, controller, and storage medium for repairing point clouds, so as to solve the problem of large measurement errors caused by the loss of some point cloud data in the prior art.

[0004] To achieve the above objectives, the first aspect of this application provides a method for repairing point clouds, applied to a controller, the controller communicating with a measuring device, the method comprising:

[0005] The initial point cloud is determined based on the initial point cloud data sent by the measuring device;

[0006] Determine the type of missing data in the initial point cloud;

[0007] When the missing data belongs to the hole type, the missing data is repaired based on the gradient vector of the nearest neighbor point to obtain the target point cloud;

[0008] If the missing data belongs to a non-hole type, the missing data is repaired based on the nearest patching strategy to obtain the target point cloud.

[0009] In this embodiment of the application, repairing missing data based on the gradient vectors of the nearest neighbors of the missing data includes:

[0010] Determine the curvature of the nearest neighbor;

[0011] Missing data is repaired using spline curves based on the gradient vectors and curvature of nearest neighbors.

[0012] In this embodiment of the application, repairing missing data based on a proximity repair strategy includes:

[0013] Determine the distance parameters;

[0014] Determine the neighborhood range of missing data based on distance parameters;

[0015] The pixel coordinates of the missing data are determined based on the nearest neighbor points within the neighborhood range.

[0016] In this embodiment, the distance parameter satisfies formula (1):

[0017]

[0018] Where D is the distance parameter, D x D is the minimum distance between the missing data and its nearest neighbor in the first direction. y This represents the minimum distance between the missing data and its nearest neighbor in the second direction.

[0019] In this embodiment, the pixel coordinates of the missing data include pixel coordinate values ​​in the first direction and pixel coordinate values ​​in the second direction, and the pixel coordinate values ​​in the first direction satisfy formula (2):

[0020]

[0021] The pixel coordinates in the second direction satisfy formula (3):

[0022]

[0023] Among them, P bx P represents the pixel coordinates in the first direction. by P represents the pixel coordinates in the second direction. x P represents the pixel coordinates of the nearest neighbor points in the first direction. y D represents the pixel coordinates of the nearest neighbor in the second direction. x D is the minimum distance between the missing data and its nearest neighbor in the first direction. y D is the minimum distance between the missing data and the nearest neighbor in the second direction, where D is the distance parameter.

[0024] In this embodiment of the application, when the missing data belongs to a non-hole type, the missing data is repaired based on a proximity patching strategy, including:

[0025] Traverse the nearest neighbors;

[0026] Determine the average pixel value of the nearest neighbors;

[0027] The average pixel value is assigned as the pixel value of the missing data.

[0028] In this embodiment of the application, determining the type of missing data in the initial point cloud includes:

[0029] Remove interference points from the initial point cloud to obtain the point cloud after removing interference points;

[0030] Identify missing data in the point cloud after removing interference points;

[0031] Determine if the region containing the missing data is closed;

[0032] If the region containing the missing data is closed, the missing data is determined to be of the hole type.

[0033] If the region containing the missing data is not closed, the type of the missing data is determined to be non-holey.

[0034] A second aspect of this application provides a controller, comprising:

[0035] The memory is configured to store instructions; and

[0036] The processor is configured to retrieve instructions from memory and, when executing the instructions, to implement the aforementioned method for repairing point clouds.

[0037] A third aspect of this application provides a system for repairing point clouds, comprising:

[0038] Controller;

[0039] The measuring device, which communicates with the controller, is configured to acquire initial point cloud data.

[0040] A fourth aspect of this application provides a machine-readable storage medium storing instructions that cause a machine to perform the aforementioned method for repairing point clouds.

[0041] The above technical solution determines the initial point cloud based on the initial point cloud data sent by the measuring device. Then, it determines the type of missing data in the initial point cloud. If the missing data belongs to the hole type, the missing data is repaired based on the gradient vectors of the nearest neighbor points to obtain the target point cloud. If the missing data belongs to the non-hole type, the missing data is repaired based on a nearest neighbor repair strategy to obtain the target point cloud. This application, by determining the type of missing data in the initial point cloud and repairing the initial point cloud according to the type of missing data, can reduce measurement errors and improve measurement accuracy.

[0042] Other features and advantages of the embodiments of this application will be described in detail in the following detailed description section. Attached Figure Description

[0043] The accompanying drawings are provided to further illustrate the embodiments of this application and form part of the specification. They are used together with the following detailed description to explain the embodiments of this application, but do not constitute a limitation on the embodiments of this application. In the drawings:

[0044] Figure 1 A flowchart illustrating a method for repairing point clouds according to an embodiment of this application is shown schematically.

[0045] Figure 2 This illustration schematically shows a diagram of missing data of a void type according to a specific embodiment of this application;

[0046] Figure 3 This illustration schematically shows a diagram of a non-hole type of missing data according to a specific embodiment of this application;

[0047] Figure 4 The diagram illustrates a principle for determining pixel coordinates of missing data according to a specific embodiment of this application.

[0048] Figure 5 A schematic block diagram of a controller according to an embodiment of this application is shown. Detailed Implementation

[0049] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only for illustration and explanation of the embodiments of this application and are not intended to limit the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0050] It should be noted that if the embodiments of this application involve directional indicators (such as up, down, left, right, front, back, etc.), the directional indicators are only used to explain the relative positional relationship and movement of the components in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indicators will also change accordingly.

[0051] Furthermore, if the embodiments of this application involve descriptions such as "first" or "second," these descriptions are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, features defined with "first" or "second" may explicitly or implicitly include at least one of those features. Additionally, the technical solutions of various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. If the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed in this application.

[0052] Figure 1 A flowchart illustrating a method for repairing point clouds according to an embodiment of this application is shown schematically. Figure 1 As shown in the figure, this application provides a method for repairing point clouds, applied to a controller, which communicates with a measuring device. The method may include the following steps:

[0053] Step 101: Determine the initial point cloud based on the initial point cloud data sent by the measuring device;

[0054] Step 102: Determine the type of missing data in the initial point cloud;

[0055] Step 103: If the missing data belongs to the hole type, repair the missing data based on the gradient vector of the nearest neighbor of the missing data to obtain the target point cloud;

[0056] Step 104: If the missing data belongs to a non-hole type, repair the missing data based on the nearest patching strategy to obtain the target point cloud.

[0057] The method for repairing point clouds provided in this application can be applied to scenarios involving the inventory of concrete raw materials in material yards with structural interference, as well as other scenarios.

[0058] In this embodiment, the method for repairing point clouds is applied to a controller, which communicates with a measuring device. The measuring device can be a lidar. After the measuring device acquires initial point cloud data, it can send the initial point cloud data to the controller, allowing the controller to determine the initial point cloud. Further, the controller can remove interference points from the initial point cloud to obtain a point cloud after interference point removal, enabling the controller to determine missing data in the point cloud after interference point removal. Furthermore, the controller can determine the type of missing data by judging whether the region containing the missing data is closed. Missing data refers to the set of all missing points in the point cloud after interference point removal, including unscanned missing points and oscillation points caused by vibration of the measuring device. Typically, the controller can determine whether the pixel value of a pixel is 255; if the pixel value is 255, then the pixel can be identified as a missing point. After determining the missing points, the set of missing points is obtained, i.e., the missing data. The type of missing data can include hole-type and non-hole-type. In the case where the missing data belongs to the hole-type, the controller can repair the missing data based on the gradient vectors of the nearest neighbors to obtain the target point cloud. If the missing data belongs to a non-hole type, the controller can repair the missing data based on a proximity patching strategy to obtain the target point cloud.

[0059] The above technical solution determines the initial point cloud based on the initial point cloud data sent by the measuring device. Then, it determines the type of missing data in the initial point cloud. If the missing data belongs to the hole type, the missing data is repaired based on the gradient vectors of the nearest neighbor points to obtain the target point cloud. If the missing data belongs to the non-hole type, the missing data is repaired based on a nearest neighbor repair strategy to obtain the target point cloud. This application, by determining the type of missing data in the initial point cloud and repairing the initial point cloud according to the type of missing data, can reduce measurement errors and improve measurement accuracy.

[0060] In this embodiment of the application, step 102, determining the type of missing data in the initial point cloud, may include:

[0061] Remove interference points from the initial point cloud to obtain the point cloud after removing interference points;

[0062] Identify missing data in the point cloud after removing interference points;

[0063] Determine if the region containing the missing data is closed;

[0064] If the region containing the missing data is closed, the missing data is determined to be of the hole type.

[0065] If the region containing the missing data is not closed, the type of the missing data is determined to be non-holey.

[0066] Specifically, after determining the initial point cloud, the controller can remove interfering points from the initial point cloud to obtain a point cloud after removing interfering points. Interfering points include floating points caused by airborne objects and trailing points caused by edge effects. With the point cloud after removing interfering points, missing data can be identified. Typically, the controller can determine if a pixel's pixel value is 255. If a pixel's pixel value is 255, then that pixel can be identified as a missing point. After identifying the missing points, a set of missing points can be obtained, i.e., the missing data.

[0067] The controller can then determine whether the region containing the missing data is closed, and use this to determine the type of missing data. Figure 2 This illustration schematically depicts a type of missing data with voids according to a specific embodiment of this application. Figure 2 As shown in a specific embodiment of this application, the area where the missing data is located is closed, therefore, the type of the missing data is a hole type. Figure 3 This illustration schematically depicts a non-hole type of missing data according to a specific embodiment of this application. For example... Figure 3 As shown in a specific embodiment of this application, the area containing the missing data is not closed; therefore, the type of the missing data is non-holey. After determining the type of the missing data, the controller can repair the missing data according to its type to obtain the target point cloud.

[0068] In this embodiment of the application, repairing missing data based on the gradient vectors of the nearest neighbors of the missing data may include:

[0069] Determine the curvature of the nearest neighbor;

[0070] Missing data is repaired using spline curves based on the gradient vectors and curvature of nearest neighbors.

[0071] Specifically, after determining that the missing data belongs to the "hole" type, the controller can repair the missing data based on the gradient vectors of the nearest neighbors. Nearest neighbors refer to points within the neighborhood of the missing data. In the process of repairing missing data based on the gradient vectors of nearest neighbors, the controller can first determine the curvature of the nearest neighbors and then determine the weight corresponding to each nearest neighbor based on the curvature. After determining the gradient vector, curvature, and weight of each nearest neighbor, the controller can combine these parameters to repair the missing data using a spline curve method, thereby obtaining the target point cloud. The spline curve method refers to a method of determining a curve based on multiple points. In this way, the controller can complete the repair of the missing data and obtain the target point cloud.

[0072] In this application embodiment, repairing missing data based on a proximity repair strategy may include:

[0073] Determine the distance parameters;

[0074] Determine the neighborhood range of missing data based on distance parameters;

[0075] The pixel coordinates of the missing data are determined based on the nearest neighbor points within the neighborhood range.

[0076] Specifically, after determining that the missing data belongs to a non-hole type, the controller can repair the missing data based on a nearest neighbor repair strategy. First, the controller can determine a distance parameter. The distance parameter can be used to control the neighborhood range. The distance parameter and the neighborhood range are positively correlated. A larger distance parameter results in a smoother repair result, but also leads to a longer repair time. Therefore, to ensure repair efficiency and quality, the controller can adjust the distance parameter based on the size of the initial point cloud and the size of the region where the missing data is located. In one example, the neighborhood range is a square region. If the distance parameter is r, then a neighborhood range centered on the missing data with a side length of 2r+1 can be determined. After determining the neighborhood range, the controller can determine the nearest neighbor points within the neighborhood range and further determine the pixel coordinates of the missing data based on these nearest neighbor points.

[0077] In this embodiment, the distance parameter can satisfy formula (1):

[0078]

[0079] Where D is the distance parameter, D x D is the minimum distance between the missing data and its nearest neighbor in the first direction. y This represents the minimum distance between the missing data and its nearest neighbor in the second direction.

[0080] Specifically, the controller can use a direction parallel to the horizontal plane as the first direction and a direction perpendicular to the horizontal plane as the second direction. Based on the minimum distance between the missing data and its nearest neighbor in the first direction and the minimum distance between the missing data and its nearest neighbor in the second direction, the controller can determine the distance parameter.

[0081] Figure 4 This diagram schematically illustrates a principle for determining pixel coordinates of missing data according to a specific embodiment of this application. Figure 4 As shown, in a specific embodiment of this application, the pixel coordinates of the missing data include pixel coordinate values ​​in the first direction and pixel coordinate values ​​in the second direction. The pixel coordinate values ​​in the first direction can satisfy formula (2):

[0082]

[0083] The pixel coordinates in the second direction can satisfy formula (3):

[0084]

[0085] Among them, P bx P represents the pixel coordinates in the first direction. by P represents the pixel coordinates in the second direction. x P represents the pixel coordinates of the nearest neighbor points in the first direction. y D represents the pixel coordinates of the nearest neighbor in the second direction. x D is the minimum distance between the missing data and its nearest neighbor in the first direction. y D is the minimum distance between the missing data and the nearest neighbor in the second direction, where D is the distance parameter.

[0086] Specifically, the controller can establish a coordinate system with a direction parallel to the horizontal plane as the first direction and a direction perpendicular to the horizontal plane as the second direction. By determining the minimum distance between nearest neighbors in the first direction, the minimum distance between the missing data and the nearest neighbors in the second direction, the pixel coordinates of the nearest neighbors in the first direction, the pixel coordinates of the nearest neighbors in the second direction, and the distance parameters, the controller can determine the pixel coordinates of the missing data.

[0087] In this embodiment of the application, when the missing data belongs to a non-hole type, repairing the missing data based on a proximity patching strategy may include:

[0088] Traverse the nearest neighbors;

[0089] Determine the average pixel value of the nearest neighbors;

[0090] The average pixel value is assigned as the pixel value of the missing data.

[0091] Specifically, the controller can iterate through nearest neighbor points and determine whether the pixels of these nearest neighbor points are valid. Nearest neighbor points refer to points within the neighborhood of the missing data. If the pixels of a nearest neighbor point are valid, the pixel value of that nearest neighbor point is stored, allowing the controller to further determine the average pixel value of multiple nearest neighbor points. After determining the average pixel value of multiple nearest neighbor points, the controller can assign this average pixel value as the pixel value of the missing data, thereby completing the repair of the missing data and obtaining the target point cloud. Furthermore, it should be noted that the method for determining the pixel value of missing data is not limited to this; the controller can also adjust the aforementioned method for determining the pixel value of missing data based on specific image features.

[0092] Figure 5 A schematic block diagram of a controller according to an embodiment of this application is shown. Figure 5 As shown in the figure, this application provides a controller that may include:

[0093] Memory 510 is configured to store instructions; and

[0094] The processor 520 is configured to retrieve instructions from memory 510 and, when executing the instructions, to implement the aforementioned method for repairing point clouds.

[0095] Specifically, in this embodiment of the application, the processor 520 can be configured to:

[0096] The initial point cloud is determined based on the initial point cloud data sent by the measuring device;

[0097] Determine the type of missing data in the initial point cloud;

[0098] When the missing data belongs to the hole type, the missing data is repaired based on the gradient vector of the nearest neighbor point to obtain the target point cloud;

[0099] If the missing data belongs to a non-hole type, the missing data is repaired based on the nearest patching strategy to obtain the target point cloud.

[0100] Furthermore, the processor 520 can also be configured as follows:

[0101] Determine the curvature of the nearest neighbor;

[0102] Missing data is repaired using spline curves based on the gradient vectors and curvature of nearest neighbors.

[0103] Furthermore, the processor 520 can also be configured as follows:

[0104] Determine the distance parameters;

[0105] Determine the neighborhood range of missing data based on distance parameters;

[0106] The pixel coordinates of the missing data are determined based on the nearest neighbor points within the neighborhood range.

[0107] In this embodiment, the distance parameter satisfies formula (1):

[0108]

[0109] Where D is the distance parameter, D x D is the minimum distance between the missing data and its nearest neighbor in the first direction. y This represents the minimum distance between the missing data and its nearest neighbor in the second direction.

[0110] In this embodiment, the pixel coordinates of the missing data include pixel coordinate values ​​in the first direction and pixel coordinate values ​​in the second direction, and the pixel coordinate values ​​in the first direction satisfy formula (2):

[0111]

[0112] The pixel coordinates in the second direction satisfy formula (3):

[0113]

[0114] Among them, P bx P represents the pixel coordinates in the first direction. by P represents the pixel coordinates in the second direction. x P represents the pixel coordinates of the nearest neighbor points in the first direction. y D represents the pixel coordinates of the nearest neighbor in the second direction. x D is the minimum distance between the missing data and its nearest neighbor in the first direction. y D is the minimum distance between the missing data and the nearest neighbor in the second direction, where D is the distance parameter.

[0115] Furthermore, the processor 520 can also be configured as follows:

[0116] Traverse the nearest neighbor points within the neighborhood range;

[0117] Determine the average pixel value of the nearest neighbors;

[0118] The average pixel value is assigned as the pixel value of the missing data.

[0119] Furthermore, the processor 520 can also be configured as follows:

[0120] Remove interference points from the initial point cloud to obtain the point cloud after removing interference points;

[0121] Identify missing data in the point cloud after removing interference points;

[0122] Determine if the region containing the missing data is closed;

[0123] If the region containing the missing data is closed, the missing data is determined to be of the hole type.

[0124] If the region containing the missing data is not closed, the type of the missing data is determined to be non-holey.

[0125] The above technical solution determines the initial point cloud based on the initial point cloud data sent by the measuring device. Then, it determines the type of missing data in the initial point cloud. If the missing data belongs to the hole type, the missing data is repaired based on the gradient vectors of the nearest neighbor points to obtain the target point cloud. If the missing data belongs to the non-hole type, the missing data is repaired based on a nearest neighbor repair strategy to obtain the target point cloud. This application, by determining the type of missing data in the initial point cloud and repairing the initial point cloud according to the type of missing data, can reduce measurement errors and improve measurement accuracy.

[0126] This application also provides a system for repairing point clouds, including:

[0127] Controller;

[0128] The measuring device, which communicates with the controller, is configured to acquire initial point cloud data.

[0129] Specifically, the system for repairing point clouds includes a controller and a measuring device. The controller communicates with the measuring device. The measuring device can be a lidar unit, used to acquire initial point cloud data and transmit the initial point cloud data to the controller. Thus, the controller can execute a method for repairing the point cloud based on the initial point cloud data sent by the measuring device.

[0130] This application also provides a machine-readable storage medium storing instructions that cause a machine to perform the above-described method for repairing point clouds.

[0131] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0132] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0133] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0134] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0135] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0136] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0137] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0138] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0139] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for repairing point clouds, characterized in that, Applied to a controller that communicates with a measuring device, the method includes: The initial point cloud is determined based on the initial point cloud data sent by the measuring device; Determine the type of missing data in the initial point cloud; If the missing data belongs to the hole type, the missing data is repaired based on the gradient vector of the nearest neighbor point to obtain the target point cloud; If the missing data belongs to a non-hole type, the missing data is repaired based on a proximity repair strategy to obtain the target point cloud; The method of repairing the missing data based on the gradient vectors of the nearest neighbors includes: determining the curvature of the nearest neighbors; and repairing the missing data using a spline curve method based on the gradient vectors and curvatures of the nearest neighbors. Repairing the missing data based on the nearest neighbor repair strategy includes: determining a distance parameter; determining the neighborhood range of the missing data based on the distance parameter; determining the pixel coordinates of the missing data based on the nearest neighbor points within the neighborhood range; traversing the nearest neighbor points; determining the average pixel value of the nearest neighbor points; and assigning the average pixel value as the pixel value of the missing data to the missing data. The distance parameter satisfies formula (1): ；（1） in, The distance parameter is... The minimum distance between the missing data and its nearest neighbor in the first direction. The minimum distance between the missing data and its nearest neighbor in the second direction; The pixel coordinates of the missing data include pixel coordinate values ​​in the first direction and pixel coordinate values ​​in the second direction, wherein the pixel coordinate values ​​in the first direction satisfy formula (2): ；（2） The pixel coordinates in the second direction satisfy formula (3): ；（3） in, The pixel coordinates in the first direction. The pixel coordinates in the second direction. The pixel coordinates of the nearest neighbor points in the first direction. The pixel coordinates of the nearest neighbor points in the second direction. The minimum distance between the missing data and its nearest neighbor in the first direction. The minimum distance between the missing data and its nearest neighbor in the second direction. The distance parameter is denoted as .

2. The method according to claim 1, characterized in that, Determining the type of missing data in the initial point cloud includes: Remove interference points from the initial point cloud to obtain a point cloud after removing interference points; Identify the missing data in the point cloud after removing the interference points; Determine whether the region containing the missing data is closed; If the area containing the missing data is closed, the missing data is determined to be of the hole type. If the region containing the missing data is not closed, the type of the missing data is determined to be non-hole type.

3. A controller, characterized in that, include: The memory is configured to store instructions; as well as A processor is configured to retrieve the instructions from the memory and, when executing the instructions, to implement the method for repairing point clouds according to any one of claims 1 to 2.

4. A system for repairing point clouds, characterized in that, include: The controller according to claim 3; The measuring device, which communicates with the controller, is configured to acquire initial point cloud data.

5. A machine-readable storage medium, characterized in that, The machine-readable storage medium stores instructions for causing the machine to perform the method for repairing point clouds according to any one of claims 1 to 2.

Images