Surface fitting-based pit detection method, device, equipment and storage medium

Abstract

The present invention provides a surface fitting-based pit detection method, apparatus, device, and storage medium for performing pit detection on a sample, wherein the sample includes a pit area and a healthy area. The method comprises: obtaining a three-dimensional scanning model of the sample, and determining a first elevation value of each first target point in the pit area and a second elevation value of each second target point in the healthy area based on the three-dimensional scanning model; constructing a surface fitting model, and determining a fitting area corresponding to the pit area based on the surface fitting model and the second elevation value; obtaining a first three-dimensional coordinate of the first target point and a second three-dimensional coordinate of each third target point in the fitting area, and determining a deformation amount of the first target point in the pit area based on the first three-dimensional coordinate and the second three-dimensional coordinate. The present invention directly utilizes the deformation amount of the first target point obtained from the obtained three-dimensional scanning model, thereby improving pit detection efficiency; and also reduces surface deviation after fitting, thereby improving pit detection accuracy.

Description

Technical Field

[0001] The present invention relates to the technical field of pit detection, and in particular to a pit detection method, device, equipment and storage medium based on surface fitting. Background Art

[0002] With the rapid development of my country's industrial sector, inspection standards for industrial products have been raised, and the complexity of corresponding inspection methods has gradually increased. Manual inspection methods for pit defects are inefficient, seriously affecting inspection efficiency on the production line. Semi-automated 3D inspection systems can accurately and efficiently obtain the location of pits on sample parts, extract deformation parameters, and accurately identify defective products that need to be returned for repair.

[0003] The existing technology includes three methods for detecting pits in semi-automated three-dimensional detection systems: 1. Detecting pits based on CAD digital models. 2. Detecting pits based on spline interpolation. 3. Reverse modeling of pits to obtain fitting surfaces, thereby realizing the detection of pits. Detecting pits based on CAD digital models relies on real design data. For objects with complex parts such as cars and airplanes, the cost of equipment deployment and CAD data acquisition is high, and the three-dimensional scanning data needs to be aligned with the CAD digital model before detection, resulting in technical problems such as low pit detection efficiency and detection accuracy. Detecting pits based on the spline interpolation method can only maintain the continuity between the curves of each segment of the sampling point, and cannot guarantee the smoothness of the entire curve. It is easy to cause large deviations in the surface after fitting, which in turn causes technical problems such as low pit detection accuracy. 3. The method based on reverse modeling requires reverse modeling of the data to realize pit detection. The reverse modeling process is complicated, resulting in low pit detection efficiency.

[0004] Therefore, there is an urgent need to provide a pit detection method, device, equipment and storage medium based on surface fitting to solve the technical problems of low pit detection efficiency and detection accuracy in the existing technology. Summary of the Invention

[0005] In view of this, it is necessary to provide a pit detection method, device, equipment and storage medium based on surface fitting to solve the technical problems of low pit detection efficiency and detection accuracy in the existing technology.

[0006] In one aspect, the present invention provides a surface fitting-based pit detection method for performing pit detection on a sample, wherein the sample includes a pit area and a healthy area. The surface fitting-based pit detection method includes:

[0007] Obtaining a three-dimensional scanning model of the sample, and determining a first elevation value of each first target point in the pit area and a second elevation value of each second target point in the healthy area according to the three-dimensional scanning model;

[0008] Constructing a surface fitting model, and determining a fitting area corresponding to the pit area according to the surface fitting model and the second elevation value;

[0009] The first three-dimensional coordinates of the first target point and the second three-dimensional coordinates of each third target point in the fitting area are obtained, and the deformation amount of the first target point in the pit area is determined according to the first three-dimensional coordinates and the second three-dimensional coordinates.

[0010] In some possible implementations, determining the first elevation value of each first target point in the pit area and the second elevation value of each second target point in the healthy area according to the three-dimensional scanning model includes:

[0011] Selecting the three-dimensional scan model to determine the pit area and the healthy area;

[0012] A first elevation value of each first target point in the pit area and a second elevation value of each second target point in the healthy area are determined.

[0013] In some possible implementations, the surface fitting model is:

[0014] f(x-2)-4f(x-1)+6f(x)-4f(x+1)+f(x+2)=0

[0015] Where f(x) is the first elevation value of the x-th first target point; f(x-2) is the second elevation value of the x-2th second target point; f(x-1) is the second elevation value of the x-1th second target point; f(x+1) is the second elevation value of the x+1th second target point; and f(x+2) is the second elevation value of the x+2th second target point.

[0016] In some possible implementations, the deformation amount is:

[0017]

[0018] In the formula, D is the deformation variable; (x1, y1, z1) is the first three-dimensional coordinate; (x0, y0, z0) is the second three-dimensional coordinate; (a, b, c) is the normal vector at the first fitting point.

[0019] In some possible implementations, the surface fitting-based pit detection method further includes:

[0020] determining an average deformation amount of the first target point based on the deformation amount;

[0021] determining a standard deviation of the dimple area based on the average deformation amount and the deformation amount;

[0022] The quality of the sample is evaluated based on the standard deviation.

[0023] In some possible implementations, the standard deviation is:

[0024]

[0025] Wherein, SD is the standard deviation; x i is the deformation variable of the i-th first target point; is the average deformation; N is the total number of the first target points.

[0026] In some possible implementations, the surface fitting-based pit detection method further includes:

[0027] Acquire a click instruction from the user to click the first target point;

[0028] The deformation amount of the first target point is acquired and displayed according to the click instruction.

[0029] On the other hand, the present invention further provides a surface fitting-based pit detection device for performing pit detection on a sample, wherein the sample includes a pit area and a healthy area. The surface fitting-based pit detection device includes:

[0030] a three-dimensional scanning unit, configured to obtain a three-dimensional scanning model of the sample, and determine a first elevation value of each first target point in the pit area and a second elevation value of each second target point in the healthy area according to the three-dimensional scanning model;

[0031] a surface fitting unit, configured to construct a surface fitting model and determine a fitting area corresponding to the concave area according to the surface fitting model and the second elevation value;

[0032] A deformation variable determination unit is used to obtain the first three-dimensional coordinates of the first target point and the second three-dimensional coordinates of each third target point in the fitting area, and determine the deformation variable of the first target point in the pit area based on the first three-dimensional coordinates and the second three-dimensional coordinates.

[0033] On the other hand, the present invention also provides an electronic device, including a memory and a processor, wherein:

[0034] The memory is used to store programs;

[0035] The processor is coupled to the memory and is configured to execute the program stored in the memory to implement the steps of the pit detection method based on surface fitting described in any one of the above implementations.

[0036] On the other hand, the present invention also provides a computer-readable storage medium for storing computer-readable programs or instructions, which, when executed by a processor, can implement the steps of the surface fitting-based pit detection method described in any of the above-mentioned implementation methods.

[0037] The beneficial effects of the above-described embodiment are as follows: the surface fitting-based pit detection method provided by the present invention obtains a three-dimensional scanning model of a sample and determines a first elevation value and a second elevation value based on the three-dimensional scanning model; constructs a surface fitting model, and determines a first fitting value for each first fitting point in a fitting area corresponding to the pit area based on the surface fitting model and the second elevation value; then obtains the first three-dimensional coordinates of the first target point and the second three-dimensional coordinates of each third target point in the fitting area, and determines the deformation of the first target point in the pit area based on the first three-dimensional coordinates and the second three-dimensional coordinates. The present invention directly uses the second elevation value obtained from the obtained three-dimensional scanning model to obtain the fitting area, eliminating the need for reverse modeling and other operations, significantly reducing the complexity and time of pit detection, thereby improving the detection efficiency of pit detection.

[0038] Furthermore, the present invention determines the fitting area through the surface fitting model and the second elevation value. Compared with obtaining the fitting area through the spline interpolation method, it ensures the surface continuity of the entire sample and reduces the surface deviation after fitting, thereby improving the detection accuracy of pit detection.

[0039] Furthermore, the present invention can determine the deformation of the first target point by obtaining the first three-dimensional coordinates of the first target point and the second three-dimensional coordinates of the third target point without contact measurement, thereby further improving the efficiency of pit detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0041] Figure 1 A schematic flow chart of an embodiment of a pit detection method based on surface fitting provided by the present invention;

[0042] Figure 2 A schematic structural diagram of an embodiment of a sample provided by the present invention;

[0043] Figure 3 A schematic structural diagram of an embodiment of a sample after surface fitting provided by the present invention;

[0044] Figure 4For the present invention Figure 1 A schematic flow chart of an embodiment of S101;

[0045] Figure 5 A schematic diagram of a flow chart of an embodiment of the present invention for evaluating sample quality;

[0046] Figure 6 A schematic diagram of a flow chart of an embodiment of displaying deformation amount provided by the present invention;

[0047] Figure 7 A schematic structural diagram of an embodiment of a pit detection device based on surface fitting provided by the present invention;

[0048] Figure 8 This is a schematic structural diagram of an embodiment of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0049] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative efforts shall fall within the scope of protection of the present invention.

[0050] It should be understood that the schematic drawings are not drawn to scale. The flowcharts used in the present invention illustrate operations implemented according to some embodiments of the present invention. It should be understood that the operations in the flowcharts may be implemented out of sequence, and steps that do not have a logical contextual relationship may be reversed or performed simultaneously. In addition, those skilled in the art, guided by the present disclosure, may add one or more additional operations to the flowcharts or remove one or more operations from the flowcharts.

[0051] In the description of the embodiment of the present invention, "and / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent three situations: A exists alone, A and B exist at the same time, and B exists alone.

[0052] Some of the blocks shown in the accompanying drawings are functional entities that do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different networks and / or processor systems and / or microcontroller systems.

[0053] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present invention. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute a separate or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0054] The embodiments of the present invention provide a pit detection method, apparatus, device and storage medium based on surface fitting, which are described below respectively.

[0055] Figure 1 This is a flow chart of an embodiment of a pit detection method based on surface fitting provided by the present invention. Figure 2 A schematic structural diagram of an embodiment of the sample provided by the present invention, Figure 3 This is a schematic diagram of an embodiment of the sample structure after surface fitting provided by the present invention, as shown in FIG. Figure 1-Figure 3 As shown, the sample 100 includes a pit area 110 and a healthy area 120. The pit detection method based on surface fitting includes:

[0056] S101, obtaining a three-dimensional scanning model of the sample 100, and determining a first elevation value of each first target point in the pit area 110 and a second elevation value of each second target point in the healthy area 120 based on the three-dimensional scanning model;

[0057] S102, constructing a surface fitting model, and determining a fitting area 130 corresponding to the pit area 110 according to the surface fitting model and the second elevation value;

[0058] S103 , obtaining the first three-dimensional coordinates of the first target point and the second three-dimensional coordinates of each third target point in the fitting area 130 , and determining the deformation of the first target point in the pit area 110 according to the first three-dimensional coordinates and the second three-dimensional coordinates.

[0059] Compared to the prior art, the surface fitting-based pit detection method provided in the embodiments of the present invention obtains a three-dimensional scanning model of the sample 100 and determines a first elevation value and a second elevation value based on the three-dimensional scanning model. A surface fitting model is constructed, and first fitting values ​​for each first fitting point in the fitting region 130 corresponding to the pit region are determined based on the surface fitting model and the second elevation value. The first three-dimensional coordinates of the first target point and the second three-dimensional coordinates of each third target point in the fitting region 130 are then obtained, and the deformation of the first target point in the pit region 110 is determined based on the first and second three-dimensional coordinates. The present invention directly utilizes the second elevation value obtained from the three-dimensional scanning model to obtain the fitting region 130, eliminating the need for reverse modeling and other operations. This significantly reduces the complexity and time of pit detection, thereby improving pit detection efficiency.

[0060] Furthermore, the embodiment of the present invention obtains the fitting area 130 through the surface fitting model and the second elevation value. Compared with the spline interpolation method, it ensures the surface continuity of the entire sample 100 and reduces the surface deviation after fitting, thereby improving the detection accuracy of pit detection.

[0061] Furthermore, the embodiment of the present invention can determine the deformation of the first target point by obtaining the first three-dimensional coordinates of the first target point and the second three-dimensional coordinates of the third target point without contact measurement, thereby further improving the efficiency of pit detection.

[0062] It should be understood that the 3D scanned model in step S101 may be a 3D point cloud model and / or a 3D mesh model. Specifically, the sample 100 may be scanned by a 3D scanner to obtain a 3D point cloud model or a 3D mesh model.

[0063] It should also be understood that the first three-dimensional coordinates in step S103 can be obtained from the three-dimensional scan model, and the second three-dimensional coordinates can be determined based on the obtained fitting area 130 .

[0064] In some embodiments of the present invention, Figure 4 As shown, step S101 includes:

[0065] S401, select the 3D scan model to determine the pit area 110 and the healthy area 120;

[0066] S402 : Determine a first elevation value of each first target point in the pit area 110 and a second elevation value of each second target point in the healthy area 120 .

[0067] In a specific embodiment of the present invention, step S401 may specifically include: manually interactively selecting the pit area 110 and the healthy area 120 in the 3D scanning software.

[0068] In some embodiments of the present invention, the surface fitting model is:

[0069] f(x-2)-4f(x-1)+6f(x)-4f(x+1)+f(x+2)=0

[0070] Where f(x) is the first elevation value of the x-th first target point; f(x-2) is the second elevation value of the x-2th second target point; f(x-1) is the second elevation value of the x-1th second target point; f(x+1) is the second elevation value of the x+1th second target point; and f(x+2) is the second elevation value of the x+2th second target point.

[0071] The theoretical derivation process of the above surface fitting model is as follows:

[0072] For the cross section of any three-dimensional surface, especially the cross section of sample 100, it is essentially a smooth curve. For the curved segment deformed by impact, we only need to restore its curvature to be consistent with the surrounding area.

[0073] For a smooth curve, the derivative f of its surroundings x (x) (i.e., slope) satisfies the following rules:

[0074]

[0075] Where h is the step size.

[0076] If you want to smoothly fit a point, the change in the derivative in its neighborhood should be as small as possible, that is, minimize the integral of the second-order derivative in the neighborhood. You can define the following energy function E(f):

[0077]

[0078] Where, f xx is the second-order derivative; m is the lower limit of the range; n is the upper limit of the range.

[0079] Assume that the function t(x) satisfies t(m)=t(n)=0, and its first-order derivative t x (m) = t x (n) = 0, introduce the scalar λ and substitute it into the energy function formula to get E(f(x) + t(x)λ). When the derivative of this function and λ are 0, the energy function obtains the optimal solution:

[0080]

[0081] Using the variational differentiation method to simplify formula (3) we can get:

[0082]

[0083] For this type of fourth-order derivative problem, we will find that the quadratic Laplace operator of f inside the function is 0, that is, Δf=f xx , which means that f in formula (4) xxxx =0, which is equivalent to:

[0084] ΔΔf=Δ 2 f=0(5)

[0085] Δ 2 is the quadratic Laplace operator, and formula (1) is transformed to obtain:

[0086]

[0087] For the second-order derivative:

[0088]

[0089] Substituting into the quadratic Laplace operator, we get:

[0090]

[0091] Combining formula (8) and formula (5) can obtain the surface fitting model in the embodiment of the present invention.

[0092] It should be noted that if the pit area includes n first target points, n first fitting values ​​corresponding to the n first target points can be solved by listing n equations based on the surface fitting model.

[0093] That is, the pit area 110 can be repaired through the surface fitting model.

[0094] In some embodiments of the present invention, the deformation amount in step S103 is:

[0095]

[0096] Where D is the shape variable; (x1, y1, z1) is the first-dimensional coordinate; (x0, y0, z0) is the second-dimensional coordinate; (a, b, c) is the normal vector at the first fitting point.

[0097] In some embodiments of the present invention, Figure 5 As shown, the pit detection method based on surface fitting also includes:

[0098] S501, determining an average deformation amount of a first target point based on the deformation amount;

[0099] S502, determining the standard deviation of the pit area 110 according to the average deformation amount and the deformation amount;

[0100] S503 : Evaluate the quality of the sample 100 based on the standard deviation.

[0101] The embodiment of the present invention can quickly distinguish qualified samples from unqualified samples by setting up a quality evaluation of the sample 100 based on the standard deviation, thereby improving the quality reliability of the sample 100.

[0102] In a specific embodiment of the present invention, step S503 is specifically: determining whether the standard deviation is greater than the deviation threshold; if the standard deviation is greater than the deviation threshold, the sample 100 is an unqualified sample; if the standard deviation is less than or equal to the deviation threshold, the sample 100 is a qualified sample.

[0103] In some embodiments of the invention, the standard deviation is:

[0104]

[0105] Where SD is the standard deviation; x i is the deformation variable of the i-th first target point; is the average deformation; N is the total number of the first target points.

[0106] In order to enable the user to quickly know the deformation amount, in some embodiments of the present invention, such as Figure 6 As shown, the pit detection method based on surface fitting also includes:

[0107] S601: Obtain a click instruction from a user to click on a first target point;

[0108] S602: Obtain and display the deformation of the first target point according to the click instruction.

[0109] In a specific embodiment of the present invention, the click instruction in step S601 can be controlled by the user to click the mouse. In step S602, the deformation amount of the first target point can be displayed by generating a message pop-up window.

[0110] It should be noted that step S602 may also be: acquiring and displaying the deformation amount and standard deviation of the first target point according to the click instruction, so that the operator can know the qualification of the sample 100 in time through the standard deviation.

[0111] In order to better implement the concave detection method based on surface fitting in the embodiment of the present invention, on the basis of the concave detection method based on surface fitting, the embodiment of the present invention also provides a concave detection device based on surface fitting, wherein the multiple data sources include a first data source and at least one second data source, such as Figure 7 As shown, the pit detection device 700 based on surface fitting includes:

[0112] A three-dimensional scanning unit 701 is used to obtain a three-dimensional scanning model of the sample, and determine a first elevation value of each first target point in the pit area and a second elevation value of each second target point in the healthy area based on the three-dimensional scanning model;

[0113] A surface fitting unit 702 is configured to construct a surface fitting model and determine a fitting area corresponding to the pit area according to the surface fitting model and the second elevation value;

[0114] The deformation amount determining unit 703 is used to obtain the first three-dimensional coordinates of the first target point and the second three-dimensional coordinates of each third target point in the fitting area, and determine the deformation amount of the first target point in the pit area based on the first three-dimensional coordinates and the second three-dimensional coordinates.

[0115] The surface fitting-based pit detection device 700 provided in the above embodiment can implement the technical solution described in the above embodiment of the surface fitting-based pit detection method. The specific implementation principles of the above modules or units can be found in the corresponding contents in the above embodiment of the surface fitting-based pit detection method, which will not be repeated here.

[0116] like Figure 8 As shown, the present invention also provides an electronic device 800. The electronic device 800 includes a processor 801, a memory 802 and a display 803. Figure 8 Only some of the components of the electronic device 800 are shown, but it should be understood that implementation of all of the shown components is not required, and more or fewer components may be implemented instead.

[0117] In some embodiments, the processor 801 may be a central processing unit (CPU), a microprocessor, or other data processing chip, configured to execute program codes or process data stored in the memory 802, such as the surface fitting-based pit detection method of the present invention.

[0118] In some embodiments, processor 801 may be a single server or a server group. The server group may be centralized or distributed. In some embodiments, processor 801 may be local or remote. In some embodiments, processor 801 may be implemented on a cloud platform. In one embodiment, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an on-premises cloud, a multi-cloud, or any combination thereof.

[0119] In some embodiments, the memory 802 may be an internal storage unit of the electronic device 800, such as a hard disk or memory of the electronic device 800. In other embodiments, the memory 802 may also be an external storage device of the electronic device 800, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 800.

[0120] Furthermore, the memory 802 may include both an internal storage unit of the electronic device 800 and an external storage device. The memory 802 is used to store application software installed in the electronic device 800 and various data.

[0121] In some embodiments, the display 803 can be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen. The display 803 is used to display information on the electronic device 800 and to display a visual user interface. Components 801-803 of the electronic device 800 communicate with each other via a system bus.

[0122] In one embodiment, when the processor 801 executes the surface fitting-based pit detection program in the memory 802, the following steps may be implemented:

[0123] Obtaining a three-dimensional scanning model of the sample, and determining a first elevation value of each first target point in the pit area and a second elevation value of each second target point in the healthy area based on the three-dimensional scanning model;

[0124] Constructing a surface fitting model, and determining a fitting area corresponding to the pit area according to the surface fitting model and the second elevation value;

[0125] The first three-dimensional coordinates of the first target point and the second three-dimensional coordinates of each third target point in the fitting area are obtained, and the deformation amount of the first target point in the pit area is determined according to the first three-dimensional coordinates and the second three-dimensional coordinates.

[0126] It should be understood that, when the processor 801 executes the surface fitting-based pit detection program in the memory 802 , in addition to the above functions, it can also implement other functions. For details, please refer to the description of the corresponding method embodiment above.

[0127] Furthermore, the embodiment of the present invention does not specifically limit the type of the electronic device 800 mentioned. The electronic device 800 may be a portable electronic device such as a mobile phone, a tablet computer, a personal digital assistant (PDA), a wearable device, a laptop computer, or the like. Exemplary embodiments of portable electronic devices include but are not limited to portable electronic devices equipped with iOS, Android, Microsoft, or other operating systems. The above-mentioned portable electronic devices may also be other portable electronic devices, such as a laptop computer with a touch-sensitive surface (e.g., a touch panel). It should also be understood that in some other embodiments of the present invention, the electronic device 800 may not be a portable electronic device, but a desktop computer with a touch-sensitive surface (e.g., a touch panel).

[0128] Accordingly, an embodiment of the present application also provides a computer-readable storage medium, which is used to store computer-readable programs or instructions. When the program or instructions are executed by a processor, it can implement the steps or functions of the pit detection method based on surface fitting provided in the above-mentioned method embodiments.

[0129] Those skilled in the art will appreciate that all or part of the process steps of the above-described embodiments can be implemented by instructing related hardware (such as a processor, a controller, etc.) through a computer program, and the computer program can be stored in a computer-readable storage medium. The computer-readable storage medium may be a magnetic disk, an optical disk, a read-only memory, or a random access memory.

[0130] The above is a detailed introduction to the pit detection method, device, equipment and storage medium based on surface fitting provided by the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core ideas. At the same time, for those skilled in the art, according to the ideas of the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A pit detection method based on surface fitting, characterized in that: The method is used to detect pits on a sample, wherein the sample includes a pit area and a healthy area. The pit detection method based on surface fitting includes: Obtaining a three-dimensional scanning model of the sample, and determining a first elevation value of each first target point in the pit area and a second elevation value of each second target point in the healthy area according to the three-dimensional scanning model; constructing a surface fitting model, and determining a fitting area corresponding to the pit area according to the surface fitting model and the second elevation value; Obtaining first three-dimensional coordinates of the first target point and second three-dimensional coordinates of each third target point in the fitting area, and determining a deformation amount of the first target point in the pit area based on the first three-dimensional coordinates and the second three-dimensional coordinates; The surface fitting model is: Where, is the first elevation value of the xth first target point; is the second elevation value of the x-2th second target point; is the second elevation value of the x-1th second target point; is the second elevation value of the x+1th second target point; is the second elevation value of the x+2th second target point; The pit detection method based on surface fitting also includes: determining an average deformation amount of the first target point based on the deformation amount; determining a standard deviation of the dimple area based on the average deformation amount and the deformation amount; The quality of the sample is evaluated based on the standard deviation.

2. The pit detection method based on surface fitting according to claim 1, characterized in that: The determining, based on the three-dimensional scanning model, a first elevation value of each first target point in the pit area and a second elevation value of each second target point in the healthy area comprises: Selecting the three-dimensional scan model to determine the pit area and the healthy area; A first elevation value of each first target point in the pit area and a second elevation value of each second target point in the healthy area are determined.

3. The pit detection method based on surface fitting according to claim 1, characterized in that: The deformation amount is: Wherein, D is the deformation variable; (x1, y1, z1) is the first three-dimensional coordinate; (x0, y0, z0) is the second three-dimensional coordinate; ( , , ) is the normal vector at the third target point.

4. The pit detection method based on surface fitting according to claim 1, characterized in that: The standard deviation is: Where, is the standard deviation; is the deformation variable of the i-th first target point; is the average deformation; N is the total number of the first target points.

5. The pit detection method based on surface fitting according to claim 1, characterized in that: The pit detection method based on surface fitting also includes: Acquire a click instruction from the user to click the first target point; The deformation amount of the first target point is acquired and displayed according to the click instruction.

6. A pit detection device based on surface fitting, characterized in that: Used to perform pit detection on a sample, the sample including a pit area and a healthy area, the pit detection device based on surface fitting includes: a three-dimensional scanning unit, configured to obtain a three-dimensional scanning model of the sample, and determine a first elevation value of each first target point in the pit area and a second elevation value of each second target point in the healthy area according to the three-dimensional scanning model; a surface fitting unit, configured to construct a surface fitting model and determine a fitting area corresponding to the concave area according to the surface fitting model and the second elevation value; a deformation amount determining unit, configured to obtain a first three-dimensional coordinate of the first target point and a second three-dimensional coordinate of each third target point in the fitting area, and determine a deformation amount of the first target point in the pit area based on the first three-dimensional coordinate and the second three-dimensional coordinate; The surface fitting model is: Where, is the first elevation value of the xth first target point; is the second elevation value of the x-2th second target point; is the second elevation value of the x-1th second target point; is the second elevation value of the x+1th second target point; is the second elevation value of the x+2th second target point; The pit detection method based on surface fitting also includes: determining an average deformation amount of the first target point based on the deformation amount; determining a standard deviation of the dimple area based on the average deformation amount and the deformation amount; The quality of the sample is evaluated based on the standard deviation.

7. An electronic device, characterized in that: comprising a memory and a processor, wherein, The memory is used to store programs; The processor is coupled to the memory and is configured to execute the program stored in the memory to implement the steps of the pit detection method based on surface fitting as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that Used to store computer-readable programs or instructions, which, when executed by a processor, can implement the steps of the pit detection method based on surface fitting as described in any one of claims 1 to 5.

Images