Three-dimensional two-dimensional code surface information reconstruction method and device, equipment and storage medium

Abstract

The invention provides a three-dimensional two-dimensional code surface information reconstruction method, device and equipment and a storage medium, and belongs to the technical field of image processing and three-dimensional reconstruction, and the method comprises the steps: carrying out the contrast enhancement of an initial image set of a three-dimensional two-dimensional code based on an exposure fusion contrast enhancement algorithm, and obtaining a contrast-enhanced image set, the initial image set comprises three-dimensional two-dimensional code images obtained by lighting and shooting the three-dimensional two-dimensional code at four different space angles; normal vector field reconstruction is carried out on the surface of the stereo two-dimensional code based on a four-light-source photometric stereo method and a contrast enhancement image set; converting the established normal vector field into a depth image based on a Poisson solution; and obtaining a reconstructed two-dimensional code image based on the depth image. According to the invention, the technical problem that the error of the surface information of the low-contrast stereo two-dimensional code extracted in a complex environment in the prior art is large is effectively solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of image processing and three-dimensional reconstruction, and particularly relates to a method and device for reconstructing surface information of a three-dimensional two-dimensional code, an equipment and a storage medium. BACKGROUND

[0002] With the rapid development of information technology, two-dimensional codes, as an efficient and convenient information storage and transmission method, have been widely used in product anti-counterfeiting, logistics tracking, information payment, advertising, and other fields. Traditional two-dimensional codes usually use planar graphic design and rely on high-contrast black and white or color patterns to encode information to ensure that they can be quickly and accurately recognized and decoded in various environments. However, in actual application scenarios, especially on special material surfaces (such as rubber tires, metals, plastics, etc.), due to factors such as light reflection, material properties, or surface wear, the contrast of two-dimensional codes is often significantly reduced, making it difficult for scanning devices to effectively recognize and analyze the information in the two-dimensional code, thereby limiting the widespread application and reliability of two-dimensional codes.

[0003] To overcome this technical problem, researchers have begun to explore three-dimensional two-dimensional code technology, which changes the physical form of two-dimensional codes (such as forming concave-convex structures, using multi-layer structures, etc.), increases the recognition dimension of two-dimensional codes, and improves their recognition rate in low-contrast environments. However, existing three-dimensional two-dimensional code technology focuses more on the innovation of physical form, and there are still many challenges in how to effectively reconstruct and analyze the surface information of these low-contrast three-dimensional two-dimensional codes. In particular, for the three-dimensional two-dimensional code surface on the laser marking of the automobile tire, the surface texture contrast is extremely low, and traditional image processing methods often have difficulty in accurately extracting and restoring the original information in the two-dimensional code.

[0004] Current three-dimensional two-dimensional code technology faces problems such as insufficient contrast and large noise interference on low reflectivity material surfaces, making it difficult for traditional vision systems to decode. Existing technologies rely more on hardware improvements (such as high-resolution cameras or special light sources) or single image enhancement algorithms (such as histogram equalization), but these methods can easily amplify noise or produce artifacts, and cannot meet the needs of low-contrast scenarios. When processing symmetrical targets (such as two-dimensional code modules), the error accumulation is significant. SUMMARY

[0005] Therefore, it is necessary to provide a method and device for reconstructing surface information of a three-dimensional two-dimensional code, an equipment and a storage medium to solve the technical problem of large error in the surface information of a low-contrast three-dimensional two-dimensional code extracted by existing technologies in complex environments.

[0006] To achieve the above technical effects, in a first aspect, the present application provides a method for reconstructing surface information of a three-dimensional two-dimensional code, comprising: The initial image set of the stereoscopic two-dimensional code is subjected to contrast enhancement based on an exposure fusion contrast enhancement algorithm to obtain a contrast-enhanced image set, wherein the initial image set comprises stereoscopic two-dimensional code images obtained by lighting and shooting the stereoscopic two-dimensional code at four different spatial angles respectively; The surface of the stereoscopic two-dimensional code is subjected to normal vector field reconstruction based on a four-light-source photometric stereo method and the contrast-enhanced image set; The established normal vector field is converted into a depth image based on a Poisson solution method; The reconstructed two-dimensional code image is obtained based on the depth image.

[0007] In some embodiments of the present application, the exposure fusion contrast enhancement algorithm is used to enhance the contrast of the initial image set of the stereoscopic two-dimensional code, comprising: An image fusion weight matrix is generated based on an illumination estimation algorithm; A multi-exposure image set is generated based on a camera response function and the initial image set; The exposure of the underexposed area in the multi-exposure image set is adjusted; The initial image set and the multi-exposure image set after exposure adjustment are fused based on the weight matrix to obtain the contrast-enhanced image set.

[0008] In some embodiments of the present application, the initial image set and the multi-exposure image set after exposure adjustment are fused based on the weight matrix to obtain the contrast-enhanced image set, comprising: The weight matrix, the initial image set and the multi-exposure image set are substituted into a preset image fusion formula to obtain the contrast-enhanced image, wherein the image fusion formula comprises:

[0009] In the formula, represents the enhancement result; represents the color channel index; represents the number of images; represents the weight map, which comes from the weight matrix; represents the first i image in the exposure image set.

[0010] In some embodiments of the present application, the surface of the stereoscopic two-dimensional code is subjected to normal vector field reconstruction based on the four-light-source photometric stereo method and the contrast-enhanced image set, comprising: The normal vector of the contrast-enhanced image set is solved pixel by pixel based on the four-light-source photometric stereo method; The normal vector is subjected to normalization processing to obtain a unit normal vector; The unit normal vector is sorted and an integrated normal vector field is output.

[0011] In some embodiments of the present application, the normal vector field is converted into a depth image based on a Poisson solver, comprising: deriving a gradient field from the normal vector field; constructing a Poisson equation based on the relationship between the normal vector field and the gradient field; solving the Poisson equation to obtain a depth vector; converting the depth vector into a depth image.

[0012] In some embodiments of the present application, the depth vector is obtained by solving the Poisson equation, comprising: discretizing the Poisson equation to obtain a linear matrix ; creating a sparse matrix , a depth matrix and a normal vector matrix ; solving the linear matrix based on a preset boundary condition and a sparse linear solver to obtain the depth vector.

[0013] In some embodiments of the present application, the reconstructed two-dimensional code image is obtained based on the depth image, comprising: graying and thresholding the top view of the depth image to obtain the reconstructed two-dimensional code image.

[0014] In a second aspect, the present application further provides a device for reconstructing surface information of a three-dimensional two-dimensional code, comprising: an image processing module, configured to perform contrast enhancement on an initial image set of the three-dimensional two-dimensional code based on an exposure fusion contrast enhancement algorithm to obtain a contrast enhanced image set, wherein the initial image set comprises four three-dimensional two-dimensional code images with different spatial angles; a vector reconstruction module, configured to reconstruct a normal vector field of a surface of the three-dimensional two-dimensional code based on a four-light-source photometric stereo method and the contrast enhanced image set; an image conversion module, configured to convert the obtained normal vector field into a depth image based on a Poisson solver; an image reconstruction module, configured to obtain a reconstructed two-dimensional code image based on the depth image.

[0015] In a third aspect, the present application further provides a device, comprising: a memory, configured to store a program; a processor, coupled to the memory, configured to execute the program stored in the memory to implement the steps of the method for reconstructing surface information of a three-dimensional two-dimensional code according to any one of the above methods.

[0016] In a fourth aspect, the present application further provides a storage medium comprising: for storing computer-readable programs or instructions, which are executed by a processor to implement the steps of the stereoscopic two-dimensional code surface information reconstruction method in any one of the above method items.

[0017] The present application has the following beneficial effects: the stereoscopic two-dimensional code surface information reconstruction method provided by the present application applies the four-light-source detection method to the surface information acquisition of a stereoscopic two-dimensional code, and applies the exposure fusion contrast enhancement algorithm to the processing of the acquired two-dimensional code image, which can not only perform illumination enhancement on dark areas, but also perform illumination weakening on overexposed areas, improve the contrast and detail retention capability of the image, and thus has wider adaptability to the identification of stereoscopic two-dimensional codes on complex material surfaces. Then, the normal vector field of the stereoscopic two-dimensional code is established by the four-light-source photometric stereoscopic method, which can effectively restore the microstructure and depth information of the object surface, and further realize high-precision reconstruction of the stereoscopic two-dimensional code in a low-contrast environment, effectively solving the technical problem of large error of the surface information of the low-contrast stereoscopic two-dimensional code extracted in the prior art in a complex environment. BRIEF DESCRIPTION OF DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor on the basis of these drawings.

[0019] Figure 1 The structural schematic diagram of the stereoscopic two-dimensional code surface information reconstruction system provided by the present application Figure 2 The flowchart of an embodiment of the stereoscopic two-dimensional code surface information reconstruction method provided by the present application Figure 3 The flowchart of an embodiment of the step S201 in the stereoscopic two-dimensional code surface information reconstruction method provided by the present application Figure 2 The flowchart of an embodiment of the step S202 in the stereoscopic two-dimensional code surface information reconstruction method provided by the present application Figure 4 Figure 2 The flowchart of an embodiment of the step S203 in the stereoscopic two-dimensional code surface information reconstruction method provided by the present application Figure 5 The flowchart of an embodiment of the step S503 in the stereoscopic two-dimensional code surface information reconstruction method provided by the present application Figure 2 The flowchart of an embodiment of the step S503 in the stereoscopic two-dimensional code surface information reconstruction method provided by the present application Figure 6 Figure 5 The structural schematic diagram of an embodiment of the stereoscopic two-dimensional code surface information reconstruction device provided by the present application Figure 7 The structural schematic diagram of an embodiment of the stereoscopic two-dimensional code surface information reconstruction device provided by the present application Figure 8 ​​The structural schematic diagram of an embodiment of the device provided by the present application. DETAILED DESCRIPTION

[0020] The technical solutions in the embodiments of the present application will be clearly and completely described in connection with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by a person skilled in the art without creative work fall within the protection scope of the present application.

[0021] In the description of the embodiments of the present application, unless otherwise specified, the meaning of "a plurality of" is two or more than two. The association relationship of the associated objects is described by "and / or", which means that there can be three relationships, for example: A and / or B, which can represent the three cases of A alone, A and B together, and B alone.

[0022] The "first", "second" and the like described in the embodiments of the present application are only for the purpose of description, and cannot be understood as indicating or implying the relative importance of the indicated technical features or implicitly indicating the number of the indicated technical features. Therefore, the technical features limited by "first" and "second" can explicitly or implicitly include at least one of the features.

[0023] In this document, the reference to "embodiments" means that the specific features, structures or characteristics described in connection with the embodiments can be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily mean that all the embodiments refer to the same embodiment, nor are they independent or alternative embodiments to each other. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0024] Before the embodiments of the present application are presented, the following concepts are first explained: (1) Four-light-source photometric stereo algorithm: Four-light-source photometric stereo is an image processing technology based on illumination model, which obtains three-dimensional information of the object surface by illuminating the object with four light sources in different directions, and is commonly used for detecting surface defects of the object.

[0025] (2) Exposure fusion contrast enhancement algorithm: It is an image processing technology based on exposure fusion framework, aiming to improve the contrast and brightness of the image, so as to improve the visual effect and applicability of the image. The algorithm combines multiple images with different exposures and uses a weight matrix to fuse them to achieve the best visual effect.

[0026] (3) Camera Reaction Function (CRF): refers to a mathematical model that describes how a camera sensor converts incident light intensity into digital pixel values. CRF relates scene radiance to image brightness and is usually a nonlinear function used to convert the irradiance of an image point into image brightness.

[0027] The present invention provides a method, device, equipment and storage medium for reconstructing the surface information of a three-dimensional two-dimensional code, which are described below respectively.

[0028] like Figure 1 As shown, this embodiment also provides a low-contrast three-dimensional two-dimensional code surface reconstruction system, including a low-contrast three-dimensional two-dimensional code sample 1, an LED light source group 2, a camera 3, a bracket 4, a light source controller 5, a control terminal 6, and an optical platform 7, wherein the LED light source group 2, the camera 3, the bracket 4, the light source controller 5, and the optical platform 7 constitute an image acquisition device.

[0029] In this embodiment, the control terminal 6 controls the light source controller to adjust the brightness and on / off of the LED light source group 2. The control terminal 6 is also used to control the camera 3 to capture images. In addition, the control terminal 6 performs image preprocessing and photometric stereo reconstruction on the images captured by the camera 3.

[0030] Figure 2 This is a flow chart of an embodiment of the path planning method provided by the present invention, which is applied to the main control chip installed on the car, such as Figure 2 As shown, the method for reconstructing the surface information of a three-dimensional two-dimensional code includes: S201 , performing contrast enhancement on an initial image set of a three-dimensional two-dimensional code based on an exposure fusion contrast enhancement algorithm to obtain a contrast enhanced image set.

[0031] The initial image set includes: stereoscopic two-dimensional code images obtained by lighting and photographing the stereoscopic two-dimensional code at four different spatial angles.

[0032] Preferably, the lighting is applied in time-sharing manner from four directions of 0°, 90°, 180° and 270° to obtain low-contrast three-dimensional two-dimensional code image sequences {P1, P2, P3, P4} respectively.

[0033] like Figure 3 In some embodiments of the present invention, step S201 includes: S301: Generate a weight matrix for image fusion based on an illumination estimation algorithm.

[0034] Specifically, for each input image, the illumination estimation is performed to determine the intensity of illumination or exposure degree of each pixel in the image, which can be achieved by calculating the brightness value of the pixel, using an illumination estimation algorithm or other methods. Then, according to the result of the illumination estimation, a weight value is assigned to each pixel. Generally, a well-exposed pixel is given a higher weight, while an underexposed or overexposed pixel is given a lower weight.

[0035] It should be noted that the weight matrix assigns weight values according to the exposure of the pixels, ensuring that well-exposed pixels account for a larger proportion in the fusion result, thereby obtaining better visual effects and detail performance.

[0036] Preferably, the weight matrix is designed as: (1) In formula (1), is a local window centered on the pixel is a small constant to avoid a zero denominator.

[0037] S302, generating a multi-exposure image set based on the camera response function and the initial image set.

[0038] It should be noted that the camera response model describes the process by which the camera sensor converts the physical intensity of illumination of a scene into digital image pixel values. Through the model and a specified exposure ratio, a series of images with different exposure degrees, including overexposed images and underexposed images, can be generated.

[0039] S303, adjusting the exposure of the underexposed area in the multi-exposure image set.

[0040] It should be noted that after obtaining the multi-exposure image set, the best exposure rate needs to be found. The algorithm will evaluate the exposure effect of the synthesized image in the original image underexposed area under different exposure rates, and select an exposure rate that can make the underexposed area well exposed and not cause too much loss of details in the overexposed area as the best exposure rate.

[0041] S304, fusing the initial image set and the multi-exposure image set with adjusted exposure based on the weight matrix to obtain a contrast-enhanced image set.

[0042] Specifically, according to the weight matrix, the input image and the multi-exposure image synthesized according to the best exposure rate are fused. For each pixel, according to its weight in the weight matrix, the contribution proportion of the input image and the synthesized image is assigned, thereby obtaining the final enhanced contrast image.

[0043] In some embodiments of the present application, step S304 comprises: ​The weight matrix, the initial image set and the multi-exposure image set are substituted into a preset image fusion formula to obtain a contrast-enhanced image, wherein the image fusion formula comprises: (2) In formula (2), represents an enhancement result; represents a color channel index; represents an image number; represents a weight map, which is from the weight matrix; represents the i-th image in the exposure image set. i represents the i-th image in the exposure image set.

[0044] S202, based on the four-light-source photometric stereo method and the contrast-enhanced image set, a normal vector field of the surface of the stereoscopic two-dimensional code is reconstructed.

[0045] As Figure 4 , in some embodiments of the present application, step S202 comprises: S401, based on the four-light-source photometric stereo method, a normal vector is solved pixel by pixel for the contrast-enhanced image set.

[0046] S402, the normal vector is normalized to obtain a unit normal vector.

[0047] S403, the unit normal vector is arranged and a complete normal vector field is output.

[0048] It should be noted that the normal vector field of the stereoscopic two-dimensional code is established by the four-light-source photometric stereo method, which can effectively restore the microstructure of the surface of the object.

[0049] S203, based on the Poisson solution method, the established normal vector field is converted into a depth image.

[0050] As Figure 5 , in some embodiments of the present application, step S203 comprises: S501, a gradient field is derived from the normal vector field.

[0051] S502, a Poisson equation is constructed based on the relationship between the normal vector field and the gradient field.

[0052] Specifically, assuming that the normal vector field is , the depth image can be represented by a two-dimensional function , according to the relationship between the normal vector and the depth image, there is , which can be regarded as a Poisson equation problem, wherein the gradient field is related to the normal vector field.

[0053] S503, the Poisson equation is solved to obtain a depth vector.

[0054] As Figure 6 , step S503 comprises: S601, discretize the Poisson equation to obtain a linear matrix .

[0055] Specifically, after discretizing the Poisson equation, at each pixel point of the two-dimensional grid, an equation can be obtained, which is a discrete approximation of the gradient: .

[0056] These equations can be written in matrix form , where is a sparse matrix, is a depth matrix, is a normal vector matrix.

[0057] S602, create sparse matrix , depth matrix and normal vector matrix .

[0058] Specifically, the creation process is as follows: 1. Construction of sparse matrix : Sparse matrix is constructed using the five-point difference method of the two-dimensional pixel grid of the image, which is used to represent the constraint relationship between depth gradients. For each non-boundary pixel point in the image, let its adjacent pixel points be the upper, lower, left and right neighborhood pixels, then we have:

[0059] After forming a set of linear equations, the sparse matrix is formed, which has a dimension of N x N, where N is the total number of pixels in the image.

[0060] 2. Generation of normal vector matrix : The normal vector of each pixel position is , then the depth gradient of the point in the x and y directions is: ,

[0061] The gradient divergence of each pixel point is calculated using the above gradient, which is an element of the vector , representing the local change information of each pixel point in the image to the depth.

[0062] 3. Depth vector : Vector is the variable to be solved, representing the depth value of each pixel in the image, with the dimension of N*10.

[0063] S603, based on the preset boundary condition and the sparse linear solver, the system is solved to obtain a depth vector.

[0064] Specifically, the boundary condition is introduced to constrain the depth of the edge pixel (for example, the depth of the edge pixel is set to zero or smoothly transitions with the adjacent inner point), and a sparse linear solver (such as a conjugate gradient method) is used to solve the equation group to obtain a depth value vector .

[0065] S504, the depth vector is converted into a depth image.

[0066] The vector is restored to a two-dimensional matrix form, that is, a complete depth image.

[0067] S204, based on the depth image, a reconstructed two-dimensional code image is obtained.

[0068] In some embodiments of the present application, step S204 comprises: Grayscale and threshold segmentation are performed on the top view of the depth image to obtain a reconstructed two-dimensional code image.

[0069] Compared with the prior art, the method provided by the present application applies four light source detection to the surface information acquisition of the three-dimensional two-dimensional code, and applies an exposure fusion contrast enhancement algorithm to process the acquired two-dimensional code image, which not only can enhance the illumination in dark areas, but also can weaken the illumination in overexposed areas, improves the contrast and detail retention capability of the image, and thus has wider adaptability to the three-dimensional two-dimensional code identification on complex material surfaces. Then, the normal vector field of the three-dimensional two-dimensional code is established by the four light source photometric stereo method, which can effectively restore the microstructure and depth information of the object surface, and further realize high-precision reconstruction of the three-dimensional two-dimensional code in a low-contrast environment, and effectively solve the technical problem of large error of the surface information of the low-contrast three-dimensional two-dimensional code extracted in the prior art in a complex environment.

[0070] As Figure 7 , in a second aspect, the present application further provides a three-dimensional two-dimensional code surface information reconstruction device 70, comprising: An image processing module 710 is configured to perform contrast enhancement on an initial image set of a three-dimensional two-dimensional code based on an exposure fusion contrast enhancement algorithm to obtain a contrast-enhanced image set, wherein the initial image set comprises four three-dimensional two-dimensional code images with different spatial angles. ​The vector reconstruction module 720 reconstructs the normal vector field of the surface of the three-dimensional code based on the four-light-source photometric stereo method and the contrast-enhanced image set; The image conversion module 730 converts the established normal vector field into a depth image based on the Poisson solution method. The image reconstruction module 740 obtains a reconstructed two-dimensional code image based on the depth image.

[0071] As Figure 8 In a third aspect, the present application further provides a device 80, comprising: The memory 810 is configured to store a program. The processor 820 is coupled to the memory 810 and is configured to execute the program stored in the memory 810 to implement the steps of the three-dimensional code surface information reconstruction method in any one of the above method items.

[0072] In a fourth aspect, the present application further provides a storage medium, comprising: The storage medium is configured to store a computer-readable program or instruction, and the program or instruction is executed by a processor to implement the steps of the three-dimensional code surface information reconstruction method in any one of the above method items.

[0073] The above describes in detail the three-dimensional code surface information reconstruction method, device, equipment and storage medium provided by the present application. The principles and implementation manners of the present application are described by applying specific examples. The above examples are only used to help understand the method and core idea of the present application. Meanwhile, for those skilled in the art, the specific implementation manner and application range of the present application can be changed according to the idea of the present application. In summary, the content of the present application should not be understood as a limitation of the present application.

Claims

1. A method for reconstructing the surface information of a three-dimensional two-dimensional code, characterized in that: include: Performing contrast enhancement on an initial image set of the 3D QR code based on an exposure fusion contrast enhancement algorithm to obtain a contrast-enhanced image set, wherein the initial image set includes: 3D QR code images obtained by respectively lighting and photographing the 3D QR code at four different spatial angles; Reconstructing the normal vector field of the surface of the three-dimensional QR code based on the four-light source photometric stereo method and the contrast enhanced image set; The established normal vector field is converted into a depth image based on the Poisson solution; A reconstructed two-dimensional code image is obtained based on the depth image.

2. The method for reconstructing the surface information of a three-dimensional code according to claim 1, characterized in that: The method of performing contrast enhancement on the initial image set of the 3D two-dimensional code based on the exposure fusion contrast enhancement algorithm includes: Generate image fusion weight matrix based on illumination estimation algorithm; generating a multi-exposure image set based on a camera response function and the initial image set; adjusting the exposure of underexposed areas in the multi-exposure image set; The initial image set and the multi-exposure image set after adjusting the exposure are fused based on the weight matrix to obtain the contrast enhanced image set.

3. The method for reconstructing the surface information of a three-dimensional two-dimensional code according to claim 2, characterized in that: The fusing the initial image set and the multi-exposure image set after adjusting the exposure based on the weight matrix to obtain the contrast enhanced image set includes: Substituting the weight matrix, the initial image set, and the multi-exposure image set into a preset image fusion formula to obtain the contrast enhanced image, wherein the image fusion formula includes: Where, Indicates enhanced results; Represents the color channel index; Indicates the number of images; Represents the weight map, which comes from the weight matrix; Indicates the exposure image set i images.

4. The method for reconstructing the surface information of a three-dimensional two-dimensional code according to claim 1, wherein: The method of reconstructing the normal vector field of the surface of the three-dimensional two-dimensional code based on the four-light source photometric stereo method and the contrast enhanced image set includes: Solving the normal vector for the contrast enhanced image set pixel by pixel based on a four-light source photometric stereo method; Normalizing the normal vector to obtain a unit normal vector; The unit normal vectors are sorted and the complete normal vector field is output.

5. The method for reconstructing the surface information of a three-dimensional two-dimensional code according to any one of claim 1, characterized in that: The method of converting the normal vector field obtained by the Poisson solution into a depth image includes: deriving a gradient field from the normal vector field; Construct Poisson's equation based on the relationship between the normal vector field and the gradient field; Solving the Poisson equation to obtain a depth vector; The depth vector is converted into a depth image.

6. The method for reconstructing the surface information of a three-dimensional two-dimensional code according to claim 5, characterized in that: Solving the Poisson equation to obtain the depth vector includes: Discretize the Poisson equation and get the linear matrix ; Creating a sparse matrix , depth matrix and the normal matrix ; Solve the linear matrix based on preset boundary conditions and sparse linear solver solution system , get the depth vector.

7. The method for reconstructing the surface information of a three-dimensional two-dimensional code according to claim 1, characterized in that: The reconstructed two-dimensional code image based on the depth image includes: Grayscale conversion and threshold segmentation are performed on the top view of the depth image to obtain a reconstructed two-dimensional code image.

8. A device for reconstructing three-dimensional two-dimensional code surface information, characterized in that: include: An image processing module is configured to perform contrast enhancement on an initial image set of a 3D two-dimensional code based on an exposure fusion contrast enhancement algorithm to obtain a contrast-enhanced image set, wherein the initial image set includes: 3D two-dimensional code images at four different spatial angles; A vector reconstruction module, which reconstructs the normal vector field of the surface of the three-dimensional QR code based on the four-light source photometric stereo method and the contrast enhanced image set; An image conversion module, used for converting the established normal vector field into a depth image based on a Poisson solution; An image reconstruction module is used to obtain a reconstructed two-dimensional code image based on the depth image.

9. A device, characterized in that include: Memory, used to store programs; A processor, coupled to the memory, is used to execute the program stored in the memory to implement the steps in the three-dimensional two-dimensional code surface information reconstruction method described in any one of claims 1 to 8.

10. A storage medium, characterized in that: include: Used to store computer-readable programs or instructions, which, when executed by a processor, can implement the steps of the three-dimensional two-dimensional code surface information reconstruction method described in any one of claims 1 to 8.

Images