Wall surface detection method and device, computer device and wall surface detection system

Abstract

The application relates to a wall surface detection method, a wall surface detection device, computer equipment and a wall surface detection system. The method is applied to the wall surface detection system, the wall surface detection system comprises a depth camera, and the depth camera is used for collecting a depth image; the method comprises the following steps: acquiring the depth image of a target wall surface, processing the depth image to obtain a plurality of local images of the target wall surface; processing each local image to obtain the flatness of the wall surface corresponding to each local image; and determining a fitable region based on the flatness of each local image and the perpendicularity of the depth image; and the fitable region is used for fitting a target part. The method can improve the detection accuracy of the wall surface, and further improves the installation quality of the elevator.

Description

Technical Field

[0001] This application relates to the field of elevator installation technology, and in particular to a wall detection method, device, computer equipment, wall detection system, and storage medium. Background Technology

[0002] Due to the characteristics of elevator installation, the elevator guide rail bracket surface needs to be flush against the elevator shaft wall. The better the fit, the better the installation quality. If the wall surface at the point where the elevator guide rail bracket surface meets the elevator shaft wall does not meet the requirements, it will result in poor fit between the elevator guide rail bracket surface and the elevator shaft wall, thus affecting the installation quality, causing installation difficulties, or even requiring additional parts to adjust the shaft wall surface to suit the installation needs.

[0003] However, current wall inspection methods or traditional approaches suffer from low inspection accuracy, leading to poor elevator installation quality. Summary of the Invention

[0004] Therefore, it is necessary to provide a wall detection method, device, computer equipment, wall detection system, and storage medium that can improve detection accuracy in response to the above-mentioned technical problems.

[0005] Firstly, this application provides a wall detection method. The method is applied to a wall detection system, which includes a depth camera for acquiring depth images; the method includes:

[0006] Acquire a depth image of the target wall surface, and process the depth image to obtain several local images of the target wall surface;

[0007] Process each local image to obtain the flatness of the wall surface corresponding to each local image;

[0008] Based on the flatness of each local image and the perpendicularity of the depth image, the bonding area is determined; the bonding area is used to bond the target part.

[0009] In one embodiment, the fitting area is determined based on the flatness of each local image and the verticality of the depth image, including:

[0010] Target regions are selected based on the flatness error threshold and the flatness of each local image;

[0011] Process the depth image to obtain the verticality of the target region;

[0012] If the perpendicularity meets the allowable error, then obtain the dimensions of the target area;

[0013] If the size of the target area is larger than the size of the target part, then the target area is defined as the fitable area.

[0014] In one embodiment, processing the depth image to obtain several local images of the target wall surface further includes:

[0015] The depth image is segmented based on the detection bounding box to obtain several local images.

[0016] In one embodiment, the depth image is segmented to obtain several local images, including:

[0017] Based on the depth image, generate point cloud data of the target wall surface;

[0018] The point cloud data is segmented based on the detection bounding box to obtain several local images.

[0019] In one embodiment, processing each local image to obtain the flatness of the wall surface corresponding to each local image includes:

[0020] Select at least four points in the local image to obtain the flatness of the wall surface corresponding to the local image.

[0021] In one embodiment, the size of the detection frame is determined based on the size of the smallest protrusion on the target wall.

[0022] Secondly, this application provides a wall detection device. The device is applied to a wall detection system, which includes a depth camera for acquiring depth images; the device includes:

[0023] The depth image acquisition module is used to acquire a depth image of the target wall and process the depth image to obtain several local images of the target wall.

[0024] The flatness determination module is used to process each local image and obtain the flatness of the wall surface corresponding to each local image;

[0025] The bonding area determination module is used to determine the bonding area based on the flatness of each local image and the perpendicularity of the depth image; the bonding area is used to bond the target part.

[0026] Thirdly, this application provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the method described above.

[0027] Fourthly, this application provides a wall surface inspection system. The system includes:

[0028] Depth cameras are used to acquire depth images;

[0029] A computer device is connected to a depth camera; the computer device includes a memory and a processor, the memory stores a computer program, and the processor executes the computer program to implement the steps of the method described above.

[0030] Fifthly, this application provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements the steps of the above-described method.

[0031] The aforementioned wall detection method, apparatus, computer equipment, wall detection system, and storage medium, wherein the method is applied to a wall detection system, which includes a depth camera for acquiring depth images; the method includes: acquiring a depth image of a target wall; processing the depth image to obtain several local images of the target wall; processing each local image to obtain the flatness of the wall corresponding to each local image; and determining the mating area for fitting the target part based on the flatness of each local image and the perpendicularity of the depth image. Through this method, the accuracy of wall detection can be improved, accurately detecting the wall area that meets the fitting requirements of the target part, thus improving the accurate and reliable installation posture for the target part, and enhancing installation quality and efficiency. Attached Figure Description

[0032] Figure 1 This is a flowchart illustrating a wall detection method in one embodiment;

[0033] Figure 2 This is a flowchart illustrating the wall inspection steps in one embodiment;

[0034] Figure 3 This is a schematic diagram of the detection frame in one embodiment;

[0035] Figure 4 This is a schematic diagram of the detection frame in another embodiment;

[0036] Figure 5 This is a flowchart illustrating the wall inspection steps in another embodiment;

[0037] Figure 6(a) is a schematic diagram of fitting a reference surface based on a local image in one embodiment;

[0038] Figure 6(b) is a schematic diagram of obtaining flatness based on local images in another embodiment;

[0039] Figure 7 This is a schematic diagram of the flatness of a depth image in one embodiment;

[0040] Figure 8 This is a structural block diagram of a wall detection device in one embodiment;

[0041] Figure 9 This is an internal structural diagram of a computer device in one embodiment;

[0042] Figure 10 This is a schematic diagram of a depth camera in one embodiment. Detailed Implementation

[0043] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0044] It's important to note that during elevator installation, the elevator guide rail bracket surface must be flush against the elevator shaft wall. A better fit results in a higher quality installation. If the wall surface at the point of contact between the guide rail bracket surface and the shaft wall does not meet requirements, the fit will be poor, affecting the installation quality, causing installation difficulties, or even requiring additional components to adjust the shaft wall to fit the installation needs. However, current wall inspection methods or traditional approaches suffer from low inspection accuracy, leading to poor elevator installation quality.

[0045] In one embodiment, such as Figure 1 The present invention provides a wall surface detection method. The method is applied to a wall surface detection system, which includes a depth camera for acquiring depth images; the method includes:

[0046] Step 110: Obtain a depth image of the target wall and process the depth image to obtain several local images of the target wall.

[0047] Specifically, depth images of the target wall, including the elevator shaft wall, can be acquired by a depth camera. By processing the depth images of the target wall, several local images of the target wall can be obtained, which can then be used to evaluate the flatness of the target wall locally and accurately determine the range of the fitable area.

[0048] In some examples, the depth camera can be a 3D camera; the size of the depth image can cover the entire target wall; the size of each local image can be the same, and multiple local images can cover the target part to be fitted.

[0049] Step 120: Process each local image to obtain the flatness of the wall surface corresponding to each local image;

[0050] Specifically, each local image can be processed separately to obtain the flatness of the wall surface corresponding to each local image. Each local image includes the depth information of each point on the corresponding wall surface. Several points in a local image can be selected to obtain the flatness of the wall surface corresponding to that local image, so as to measure whether the wall surface corresponding to the local image is flat and suitable for bonding.

[0051] In some examples, a reference plane can be determined, and at least three points can be selected on the local image to obtain the distance between each point and the reference plane, thereby obtaining the flatness of the wall surface corresponding to the local image. The flatness of the wall surface corresponding to the local image can be used to measure whether the wall surface corresponding to the local image is flat and suitable for bonding.

[0052] Step 130: Based on the flatness of each local image and the perpendicularity of the depth image, determine the bonding area; the bonding area is used to bond the target part.

[0053] Specifically, based on the flatness of each local image, local images that meet the flatness requirements can be selected; furthermore, the perpendicularity of the depth image can be obtained, and if both the flatness of the local images and the perpendicularity of the depth image meet the fitting requirements,

[0054] In some examples, the target part may include an elevator guide rail bracket. If a suitable area is identified, the depth camera can be controlled to stop acquiring depth images; if a suitable area cannot be identified, the depth camera can be controlled to pan up, down, left, and right to select the next target wall surface for depth image acquisition.

[0055] This application proposes a wall detection method, which is applied to a wall detection system including a depth camera for acquiring depth images. The method includes: acquiring a depth image of a target wall; processing the depth image to obtain several local images of the target wall; processing each local image to obtain the flatness of the wall corresponding to each local image; and determining the mating area for fitting a target part based on the flatness of each local image and the perpendicularity of the depth image. This method improves the accuracy of wall detection, precisely detecting wall areas that meet the mating requirements of the target part, thus providing accurate and reliable installation posture for the target part, and improving installation quality and efficiency.

[0056] In one embodiment, such as Figure 2 As shown, based on the flatness of each local image and the verticality of the depth image, the fitting area is determined, including:

[0057] Step 210: Filter target regions based on the flatness error threshold and the flatness of each local image;

[0058] Step 220: Process the depth image to obtain the verticality of the target region;

[0059] Step 230: If the perpendicularity meets the allowable error, then obtain the dimensions of the target area;

[0060] Step 240: If the size of the target area is larger than the size of the target part, then the target area is determined as the fitable area.

[0061] Specifically, the target region can be filtered based on a flatness error threshold and the flatness of each local image. For example, if the flatness of a local image meets the flatness error threshold, the area of ​​the wall corresponding to that local image can be filtered out until the corresponding filtering is completed for each local image to obtain the target region. Further, the depth image can be processed to obtain the verticality of the target region. If the verticality of the target region meets the verticality tolerance requirement, the size of the target region can be obtained. If the size of the target region is compared with the size of the target part, and it is determined that the target region can accommodate the target part, then the target region can be identified as the mating area for fitting the target part.

[0062] In some examples, the local image can be rectangular, and correspondingly, the target region can include several rectangles. The dimensions of the target region can include both length and height dimensions. The length and height dimensions of the target region can be compared with the length and width of the target part to determine if the target region fits the target part sufficiently. The determined target region satisfies the dimensional requirements of the target part in both the length and width directions.

[0063] In one embodiment, processing the depth image to obtain several local images of the target wall surface further includes:

[0064] The depth image is segmented based on the detection bounding box to obtain several local images.

[0065] Specifically, such as Figure 3 As shown, by setting the size of the detection frame, the depth image can be divided into several local images of the size of the detection frame, and the wall areas corresponding to each local image do not need to overlap.

[0066] In some examples, such as Figure 4 As shown, the size of the wall area corresponding to the image composed of the segmented local images can be larger than the size of the target part, thereby avoiding the final fitable area failing to meet the size requirements of the target part.

[0067] In one embodiment, such as Figure 5As shown, the depth image is segmented to obtain several local images, including:

[0068] Step 510: Generate point cloud data of the target wall based on the depth image;

[0069] Step 520: Segment the point cloud data based on the detection bounding box to obtain several local images.

[0070] Specifically, point cloud data of the target wall can be generated based on a depth image of the target wall. The depth image is a two-dimensional image, while the point cloud data can be a three-dimensional image, meaning the two-dimensional points in the depth image are mapped into three-dimensional space to obtain the point cloud data. Furthermore, the point cloud data can be segmented based on detection frames. For example, the point cloud data can be sequentially segmented based on the size of the detection frames to obtain several local images of the size of the detection frames. Each local image can include the three-dimensional point cloud generated from the wall region corresponding to the size of the detection frame.

[0071] In some examples, a local image as shown in Figure 6(a) can be obtained. Based on each point in the local image, the reference plane z = ax + by + c can be determined, where x is the horizontal coordinate, y is the vertical coordinate, and a, b, and c are coefficients. a, b, and c can be obtained by fitting the reference plane to each point in the local image. Then, at least three points δi = axi + byi - zi + c are selected from the local image, where i is a label. The distance between each point and the reference plane as shown in Figure 6(b) can be obtained to obtain the flatness of the wall surface corresponding to the local image.

[0072] In one embodiment, processing each local image to obtain the flatness of the wall surface corresponding to each local image includes:

[0073] Select at least four points in the local image to obtain the flatness of the wall surface corresponding to the local image.

[0074] Specifically, at least four points in the 3D point cloud of a local image can be selected to obtain the distance between each point and the reference plane, thereby obtaining the flatness of the wall surface corresponding to the local image, which can improve the accuracy of the obtained flatness.

[0075] In some examples, such as Figure 7 As shown, this represents the flatness value of the wall surface corresponding to each local image in the depth image. The flatness value of the wall surface corresponding to the local image can be used to measure whether the wall surface corresponding to the local image is flat and suitable for fitting. Therefore, the local images can be filtered based on the flatness to determine the target area. For example, local images with a flatness less than or equal to 0.002 can be selected to form the target area.

[0076] In one embodiment, the size of the detection frame is determined based on the size of the smallest protrusion on the target wall.

[0077] Specifically, the size of the detection frame determines the size of the resulting local image. The size of the detection frame can be determined based on the size of the smallest protrusion on the target wall. For example, the size of the detection frame can be greater than or equal to the size of the smallest protrusion on the target wall, so that the local image can completely contain the smallest protrusion on the target wall, and the flatness of the wall corresponding to the local image can be obtained more accurately to measure whether the wall corresponding to the local image is flat and suitable for fitting.

[0078] In some examples, the minimum protrusion on the target wall can be steel bars on the elevator shaft wall, and the size of the minimum protrusion on the target wall can be obtained by using a preset value.

[0079] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0080] Based on the same inventive concept, this application also provides a wall detection device for implementing the wall detection method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more wall detection device embodiments provided below can be found in the limitations of the wall detection method described above, and will not be repeated here.

[0081] In one embodiment, such as Figure 8 As shown, a wall detection device is provided. The device is applied to a wall detection system, which includes a depth camera for acquiring depth images; the device includes:

[0082] The depth image acquisition module 810 is used to acquire a depth image of the target wall and process the depth image to obtain several local images of the target wall.

[0083] The flatness determination module 820 is used to process each local image and obtain the flatness of the wall surface corresponding to each local image;

[0084] The bonding area determination module 830 is used to determine the bonding area based on the flatness of each local image and the perpendicularity of the depth image; the bonding area is used to bond the target part.

[0085] In one embodiment, the fitable area determination module 830 is further configured to filter target areas based on a flatness error threshold and the flatness of each local image; process the depth image to obtain the verticality of the target area; if the verticality meets the verticality tolerance error, obtain the size of the target area; if the size of the target area is greater than the size of the target part, determine the target area as a fitable area.

[0086] In one embodiment, the depth image acquisition module 810 is further configured to segment the depth image based on the detection frame to obtain several local images.

[0087] In one embodiment, the depth image acquisition module 810 is further configured to generate point cloud data of the target wall based on the depth image; and to segment the point cloud data based on the detection frame to obtain several local images.

[0088] In one embodiment, the flatness determination module 820 is further configured to select at least four points in the local image to obtain the flatness of the wall surface corresponding to the local image.

[0089] Each module in the aforementioned wall detection device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0090] In one embodiment, a computer device is provided. The computer device includes a memory and a processor, the memory storing a computer program. When the processor executes the computer program, it performs the following steps:

[0091] Acquire a depth image of the target wall surface, and process the depth image to obtain several local images of the target wall surface;

[0092] Process each local image to obtain the flatness of the wall surface corresponding to each local image;

[0093] Based on the flatness of each local image and the perpendicularity of the depth image, the bonding area is determined; the bonding area is used to bond the target part.

[0094] In one embodiment, when the processor performs the step of determining the fitable region based on the flatness of each local image and the verticality of the depth image, it implements the following steps:

[0095] Target regions are selected based on the flatness error threshold and the flatness of each local image;

[0096] Process the depth image to obtain the verticality of the target region;

[0097] If the perpendicularity meets the allowable error, then obtain the dimensions of the target area;

[0098] If the size of the target area is larger than the size of the target part, then the target area is defined as the fitable area.

[0099] In one embodiment, when the processor performs the step of processing the depth image to obtain several local images of the target wall, it implements the following steps:

[0100] The depth image is segmented based on the detection bounding box to obtain several local images.

[0101] In one embodiment, the depth image is segmented to obtain several local images, including:

[0102] Based on the depth image, generate point cloud data of the target wall surface;

[0103] The point cloud data is segmented based on the detection bounding box to obtain several local images.

[0104] In one embodiment, when the processor performs the step of processing each local image to obtain the flatness of the wall surface corresponding to each local image, it implements the following steps:

[0105] Select at least four points in the local image to obtain the flatness of the wall surface corresponding to the local image.

[0106] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 9As shown, the computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a wall detection method. The display unit is used to form a visually visible image and can be a display screen, projection device, or virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0107] Those skilled in the art will understand that Figure 9 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0108] In one embodiment, a wall detection system is provided. The system includes:

[0109] Depth cameras are used to acquire depth images;

[0110] A computer device is connected to a depth camera; the computer device includes a memory and a processor, the memory stores a computer program, and the processor executes the computer program to implement the steps of the method described above.

[0111] Specifically, the following can be adopted: Figure 10 The depth camera shown is used for this purpose, where D is the distance between the depth camera and the target wall, and θ is the viewing angle of the depth camera. The depth camera's lens can move up and down and / or left and right under the control of a computer device. The wall detection system can detect whether the perpendicularity of the elevator guide rail support surface to the elevator shaft wall meets the requirements before installation, thus improving elevator installation quality and efficiency.

[0112] In some examples, the depth camera can be mounted on a device that can move up and down and / or left and right within an elevator shaft. The device is connected to a computer, which can control the depth camera to move up and down and / or left and right within the elevator shaft.

[0113] In one embodiment, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements the steps of the method described above.

[0114] In one embodiment, a computer program product is provided, comprising a computer program, characterized in that, when executed by a processor, the computer program implements the steps of the method described above.

[0115] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0116] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0117] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for detecting wall surfaces, characterized in that, The method is applied to a wall detection system, which includes a depth camera for acquiring depth images; the method includes: Acquire the depth image of the target wall surface, and process the depth image to obtain several local images of the target wall surface; Process each of the local images to obtain the flatness of the wall surface corresponding to each local image; Based on the flatness of each local image and the perpendicularity of the depth image, a bonding area is determined; the bonding area is used to bond to the target part. The step of determining the fitable region based on the flatness of each of the local images and the perpendicularity of the depth image includes: filtering target regions based on a flatness error threshold and the flatness of each of the local images; processing the depth image to obtain the perpendicularity of the target region; if the perpendicularity meets the perpendicularity tolerance error, then obtaining the size of the target region; if the size of the target region is larger than the size of the target part, then determining the target region as the fitable region. The process of processing the depth image to obtain several local images of the target wall surface further includes: segmenting the depth image based on the detection frame to obtain several local images; The step of segmenting the depth image to obtain several local images includes: generating point cloud data of the target wall based on the depth image; and segmenting the point cloud data based on the detection frame to obtain several local images. The method further includes: if a suitable area is determined, the depth camera can be controlled to stop acquiring depth images; if a suitable area cannot be determined, the depth camera can be controlled to move up, down, left, and right to select the next target wall surface for depth image acquisition. The size of the detection frame is determined based on the size of the smallest protrusion on the target wall; the size of the smallest protrusion is obtained by using a preset value.

2. The method according to claim 1, characterized in that, The process of processing each of the local images to obtain the flatness of the wall surface corresponding to each local image includes: Select at least four points from the local image to obtain the flatness of the wall surface corresponding to the local image.

3. A wall surface detection device, characterized in that, The device is applied to a wall detection system, which includes a depth camera for acquiring depth images; the device includes: A depth image acquisition module is used to acquire the depth image of the target wall and process the depth image to obtain several local images of the target wall. A flatness determination module is used to process each of the local images to obtain the flatness of the wall surface corresponding to each of the local images; The bonding area determination module is used to determine the bonding area based on the flatness of each of the local images and the perpendicularity of the depth image; the bonding area is used to bond to the target part; The fitable area determination module is further configured to: filter target areas based on a flatness error threshold and the flatness of each local image; process the depth image to obtain the verticality of the target area; if the verticality meets the verticality tolerance error, obtain the size of the target area; if the size of the target area is greater than the size of the target part, determine the target area as the fitable area. The depth image acquisition module is further configured to segment the depth image based on the detection frame to obtain several local images; The depth image acquisition module is further configured to generate point cloud data of the target wall based on the depth image; and to segment the point cloud data based on the detection frame to obtain several local images. The depth image acquisition module is also used to control the depth camera to stop acquiring depth images if a suitable area is determined; if a suitable area cannot be determined, the depth camera can be controlled to move up, down, left, and right to select the next target wall surface for depth image acquisition. The size of the detection frame is determined based on the size of the smallest protrusion on the target wall; the size of the smallest protrusion is obtained by using a preset value.

4. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method of claim 1 or 2.

5. A wall surface inspection system, characterized in that, The system includes: A depth camera, used to acquire depth images; A computer device connected to the depth camera; the computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the method of claim 1 or 2.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method of claim 1 or 2.

Images