Image reconstruction method and device, electronic equipment and readable medium

By constructing a tensor principal component analysis and reconstruction mathematical model based on plug-and-play alternating direction multiplier in the CUP-VISAR system, combining the full variation prior term and tensor low-rank constraint, the CUP-VISAR two-dimensional compressed image is solved The problem of low reconstruction quality has achieved high-quality three-dimensional image reconstruction and stability improvement.

CN118918251AActive Publication Date: 2024-11-08GUANGDONG UNIV OF TECH +1
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202410948424.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-16
Publication Date
2024-11-08
Estimated Expiration
2044-07-16

AI Technical Summary

Technical Problem

The reconstruction quality of CUP-VISAR two-dimensional compressed images is not high, and there are problems such as information loss, noise pollution, TV constraints leading to detail loss and excessive smoothing, regularization parameters affecting the reconstruction effect, and low-rank matrix damages the three-dimensional image block structure relationship.

Method used

The CUP-VISAR system was used to sample the observed signals, and a mathematical model of tensor principal component analysis and reconstruction based on plug-and-play alternating direction multiplier was constructed. Image reconstruction was carried out through total variation prior terms, tensor low-rank constraints, and sparse constraints. , decompose and optimize sub-problems for iterative solution to avoid information loss and noise pollution, and improve reconstruction quality.

Benefits of technology

High-quality three-dimensional striped image reconstruction is realized, which avoids local information loss, improves the stability and accuracy of the reconstruction image, and enhances the representation ability of the internal structure of the image block.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118918251A_ABST
    Figure CN118918251A_ABST
Patent Text Reader

Abstract

The invention provides an image reconstruction method and device, electronic equipment and a readable medium, and the method comprises the steps: carrying out the sampling of an observation signal through employing a CUP-VISAR system, and obtaining a two-dimensional compression observation image; constructing a tensor principal component analysis reconstruction mathematical model based on a plug-and-play alternating direction multiplier by taking a total variation priori term, a tensor low-rank constraint and a sparse constraint as priori constraints according to the two-dimensional compression observation image; and decomposing the image reconstruction mathematical model into a plurality of optimization sub-problems, and carrying out iterative solution to obtain a reconstructed image. According to the method, an image reconstruction mathematical model is established based on a plug-and-play alternating direction multiplier framework, and the solution of a complex optimization problem is converted into the solution of several simple sub-problems, so that the representation of the structural characteristics of reconstructed three-dimensional stripe image data is completed, and the loss of local information is avoided.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and in particular to an image reconstruction method, an image reconstruction device, an electronic device and a computer-readable medium. Background Art

[0002] Laser-driven inertial confinement fusion (ICF) is a very challenging research field in controlled nuclear fusion, and its diagnostic technology is an important research direction to promote the development of controlled nuclear fusion. Among them, the imaging type arbitrary reflector velocity interferometer (Velocity Interferometer System for Any Reflector, VISAR) is the most widely used diagnostic equipment for ICF, which is used to record the one-dimensional wavefront information with picosecond time resolution generated by ICF, but this information is limited to the velocity change of a line on the target surface. If the slit of the streak camera is fully opened, due to the characteristics of the streak camera, the streak images of different periods detected on the internal recording CCD will overlap, resulting in information errors. Therefore, it is usually used to detect the one-dimensional spatial information of the laser-driven shock wave velocity as a function of time, and cannot provide the velocity distribution of all points on the target surface, that is, the two-dimensional velocity field information with high time resolution.

[0003] In recent years, compressed sensing can sample signals at a rate lower than the Nyquist sampling rate, and simultaneously achieve signal compression, and reconstruct the original signal from the compressed data using a suitable reconstruction algorithm. It has been widely used in a wide range of fields. In 2014, GAO et al. applied compressed sensing to ultrafast imaging, achieving compressed ultrafast photography (CUP) of two-dimensional images with a time resolution of 2ps and an imaging number of 1011 frames / s. In 2019, Wang Feng's team coupled line imaging VISAR with compressed ultrafast photography (CUP), and initially applied CUP to the field of ICF diagnosis, realizing the reconstruction of the dynamic evolution of the two-dimensional shock wave velocity field through a reconstruction algorithm. Subsequently, the generalized alternating projection (GAP) method based on low-rank matrices and the alternating direction multiplier (ADMM) method were developed.

[0004] However, the reconstruction quality and accuracy of CUP-VISAR two-dimensional compressed images are not high, and there are several main disadvantages:

[0005] a. There are factors such as information loss and noise pollution in the CUP-VISAR measurement process, and the quality of the obtained observation compression image is not high;

[0006] b. TV constraint can promote image segmentation smoothness and preserve edge details, but it is prone to problems such as detail loss and over-smoothing;

[0007] c. The TV-TwIST (TwIST based on total variation constraint) algorithm is easily affected by the regularization parameters, resulting in unstable reconstruction effect;

[0008] d. Low matrix rank will destroy the internal structural relationship of the 3D image block. Summary of the invention

[0009] In view of the above problems, the present invention is proposed to provide an image reconstruction method and a corresponding image reconstruction device, an electronic device and a computer-readable medium that overcome the above problems or at least partially solve the above problems.

[0010] The present invention discloses an image reconstruction method, comprising:

[0011] The CUP-VISAR system is used to sample the observation signal and obtain a two-dimensional compressed observation image;

[0012] According to the two-dimensional compressed observation image, a tensor principal component analysis reconstruction mathematical model based on plug-and-play alternating direction multipliers is constructed with total variation prior terms, tensor low-rank constraints, and sparse constraints as prior constraints.

[0013] The mathematical model of image reconstruction is decomposed into several optimization sub-problems, and the reconstructed image is obtained by iterative solution.

[0014] As a further improvement of the present invention, the step of sampling the observation signal using the CUP-VISAR system to obtain a two-dimensional compressed observation image includes:

[0015] The VISAR system carries the target surface information and generates interference to form an interference fringe image at the imaging plane, thus obtaining a time-varying two-dimensional fringe image.

[0016] The time-varying two-dimensional fringe image is input into the CUP system, and the time-varying two-dimensional fringe image is encoded, shifted and superimposed to form a two-dimensional compressed observation image.

[0017] As a further improvement of the present invention, the expression of the two-dimensional compressed observation image is:

[0018] Y=AI

[0019] Where I is a three-dimensional stripe image with a pixel size of m×n×k that varies with time; Y is a two-dimensional observation image recorded by a streak camera, with a size of (m+k-1)×n; A is the observation matrix, and A=MSC, where M is the spatiotemporal integration operator, S is the time shear operator, and C is the spatial mask operator.

[0020] As a further improvement of the present invention, the step of constructing a tensor principal component analysis reconstruction mathematical model based on plug-and-play alternating direction multipliers according to the two-dimensional compressed observation image with total variation prior terms, tensor low rank constraints, and sparse constraints as prior constraints includes:

[0021] Add a priori constraints to be evaluated for the expression of the two-dimensional compressed observation image and transform the expression of the two-dimensional compressed observation image into:

[0022]

[0023] Where X is the quantity to be determined, Φ(I) is the regularization term, ||·||2 is the l2 norm, and ∈ is a positive parameter that depends on the noise variance;

[0024] After decomposing the quantity X into low-rank part, sparse noise and Gaussian noise, the expression of the quantity X is:

[0025] X=L+S+R+N

[0026] Where L is the clean signal, S and R are sparse noise, and N is Gaussian noise;

[0027] Substitute the expression of the desired quantity X into the expression of the two-dimensional compressed observation image obtained by transformation, and apply the total variation prior term and tensor low rank constraint at the same time, and we get:

[0028]

[0029] ||·|| tv is the total variation regularization function, ||·|| 3DTNN is the three-dimensional tensor nuclear norm, ||·||1 is the l1 norm, ||R|| 2,1 is the mixed norm and is the sum of all Frobenius norms of the side slices of R, that is, is the index;

[0030] Based on the plug-and-play alternating direction multiplier framework, the above formula is converted into a mathematical model for image reconstruction:

[0031]

[0032] Where τ, λ, α, β, γ, and μ are regularization parameters, U is the auxiliary variable, Λ is the dual variable, and ρ is the augmented Lagrangian parameter.

[0033] As a further improvement of the present invention, the plurality of optimization sub-problems include: a desired quantity X sub-problem, an auxiliary variable U sub-problem, a clean signal L sub-problem, a sparse noise S sub-problem, a sparse noise R sub-problem, and a Gaussian noise N sub-problem.

[0034] As a further improvement of the present invention, the step of decomposing the image reconstruction mathematical model into a plurality of optimization sub-problems and solving them to obtain the reconstructed image includes:

[0035] Update and solve the subproblem of quantity X;

[0036] Update and solve the auxiliary variable U subproblem;

[0037] Update and solve the clean signal L subproblem;

[0038] Update and solve the sparse noise S subproblem;

[0039] Update and solve the sparse noise R subproblem;

[0040] Update and solve the Gaussian noise N subproblems;

[0041] Update the dual variable Λ;

[0042] Update the augmented Lagrangian parameter ρ;

[0043] If the convergence condition is met, the updating is stopped and the updated value to be evaluated and the clean signal are output to obtain the interference fringe image.

[0044] As a further improvement of the present invention, the convergence condition includes: the error value e ζ Less than or equal to the preset error value in,

[0045]

[0046] The present invention also discloses an image reconstruction device, which is used to implement the image reconstruction method of the present invention, comprising:

[0047] CUP-VISAR system, used to sample the observation signal and obtain a two-dimensional compressed observation image;

[0048] Image reconstruction mathematical model building module, used to build a tensor principal component analysis reconstruction mathematical model based on plug-and-play alternating direction multipliers according to the two-dimensional compressed observation image, with total variation prior terms, tensor low rank constraints, and sparse constraints as prior constraints;

[0049] The model solving module is used to decompose the image reconstruction mathematical model into several optimization sub-problems and solve them to obtain the reconstructed image.

[0050] The present invention also discloses an electronic device, comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus;

[0051] The memory is used to store computer programs;

[0052] The processor is used to implement the image reconstruction method of the present invention when executing the program stored in the memory.

[0053] The present invention also discloses one or more computer-readable media, on which instructions are stored. When executed by one or more processors, the processors are enabled to perform the image reconstruction method according to the present invention.

[0054] The present invention includes the following advantages:

[0055] The image reconstruction method of the present invention obtains a two-dimensional compressed observation image by sampling the observation signal using a CUP-VISAR system; based on the two-dimensional compressed observation image, a tensor principal component analysis reconstruction mathematical model based on plug-and-play alternating direction multipliers is constructed with total variation prior terms, tensor low-rank constraints, and sparse constraints as prior constraints; the image reconstruction mathematical model is decomposed into several optimization sub-problems, and the reconstructed image is obtained by iterative solution. The present invention establishes an image reconstruction mathematical model based on a plug-and-play generalized alternating projection framework, and transforms the solution of a complex optimization problem into the solution of several simple sub-problems, thereby completing the representation of the structural characteristics of the reconstructed three-dimensional stripe image data and avoiding the loss of local information. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 is a flowchart of the steps of an image reconstruction method provided by the present invention;

[0057] Figure 2 is a schematic diagram of a CUP-VISAR system of the present invention;

[0058] Figure 3 is a schematic diagram of the compression imaging principle in step S1 of the present invention;

[0059] Figure 4 is a diagram of the compressed image reconstruction process of the present invention;

[0060] Figure 5 It is the solution flow chart in step S3 of the present invention;

[0061] Figure 6 It is a one-dimensional VISAR diagram used in the verification process of the present invention;

[0062] Figure 7a is the original three-dimensional tensor fringe image used in the verification process of the present invention;

[0063] Figure 7b It is a three-dimensional tensor fringe image with noise used in the verification process of the present invention;

[0064] Figure 8a is the coding diagram used in the verification process of the present invention;

[0065] Figure 8b is the simulated compressed image used in the verification process of the present invention;

[0066] Fig. 9 is the fringe image reconstructed by the ADMM-TV algorithm during the verification process of the present invention;

[0067] Fig.10 is the fringe image reconstructed by the ADMM-TVLR algorithm during the verification process of the present invention;

[0068] Fig.11 is a fringe image reconstructed by the image reconstruction method of the present invention during the verification process of the present invention;

[0069] Fig.12a This is a comparison chart of peak signal-to-noise ratio (PSNR) of ADMM-TVLR, ADMM-TV, and ADMM-TLRTN;

[0070] Figure 12b This is the structural similarity SSIM comparison chart of ADMM-TVLR, ADMM-TV, and ADMM-TLRTN;

[0071] Fig.13 It is a structural block diagram of an image reconstruction device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0072] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0073] Reference Figure 1 , showing an image reconstruction method provided by the present invention, comprising:

[0074] S1. The CUP-VISAR system is used to sample the observation signal to obtain a two-dimensional compressed observation image.

[0075] like Figure 2 As shown, in an embodiment of the present invention, a CUP-VISAR system is used to obtain a two-dimensional compressed observation image to provide basic data for subsequent image reconstruction. The CUP-VISAR system mainly includes a VISAR system and a CUP system. The CUP-VISAR system is used to sample the observation signal to obtain a two-dimensional compressed observation image, which includes the following steps:

[0076] S11. The VISAR system carries the target surface information and interferes to form an interference fringe image at the imaging plane to obtain a time-varying two-dimensional fringe image. Specifically, the probe light first passes through lens L1, compensation lens COM1, beam splitter BS2, reflector M1, reflector M2, lens L2, and lens L3 in sequence to reach the target surface TSF, and then returns to the original path. After being collected and collimated by reflector M3, it passes through lens L4, interferometer, and lens L5 in sequence to form an image at imaging point IP2. At this time, a time-varying two-dimensional fringe image is obtained.

[0077] S12, input the time-varying two-dimensional fringe image into the CUP system, encode, offset and superimpose the time-varying two-dimensional fringe image to form a two-dimensional compressed observation image. On the one hand, the image is collected and recorded by the streak camera with the slit not fully opened through lens L10, reflector M7 and lens L11. On the other hand, the image is introduced into the digital micromirror device (DMD) through the 4f imaging system composed of tube lens L6 and microscope objective lens L7 for encoding. The encoded image enters the streak camera through lenses L8 and L9 and is offset by the offset of the electron tube of the streak camera to achieve the offset of the encoded image at different times to complete its shearing in time. Finally, the offset encoded image is recorded and superimposed on the charge-coupled device (CCD) built into the streak camera to obtain a two-dimensional compressed observation image.

[0078] S2. According to the two-dimensional compressed observation image, a tensor principal component analysis reconstruction mathematical model based on plug-and-play alternating direction multipliers is constructed with total variation prior, tensor low rank constraint and sparsity constraint as prior constraints.

[0079] Specifically, step S2 includes the following steps:

[0080] S21. First, construct the expression of the two-dimensional compressed observation image:

[0081] Y=AI (1)

[0082] Where I is a three-dimensional stripe image with a pixel size of m×n×k that varies with time; Y is a two-dimensional observation image recorded by a streak camera, with a size of (m+k-1)×n; A is the observation matrix, and A=MSC, where M is the spatiotemporal integration operator, S is the time shear operator, and C is the spatial mask operator.

[0083] S22. In formula (1), it can be seen that the number of unknowns m×n×k is much greater than the number of equations (m+k-1)×n. It is a problem of solving an ill-conditioned equation. Therefore, it is necessary to add a priori constraints to be evaluated for the expression of the two-dimensional compressed observation image and convert it into an optimization problem. The expression of the two-dimensional compressed observation image is converted into:

[0084]

[0085] Where X is the quantity to be determined, Φ(I) is the regularization term, ||·||2 is the l2 norm, and ∈ is a positive parameter that depends on the noise variance.

[0086] S23. Considering that the quantity to be determined X contains structural information as well as noise, the quantity to be determined X is decomposed into a low-rank part, sparse noise, and Gaussian noise. The expression of the quantity to be determined X is:

[0087] X=L+S+R+N (3)

[0088] Where L is the clean signal, S and R are sparse noise, and N is Gaussian noise;

[0089] S24. Substitute the expression of the quantity to be determined X into the expression of the two-dimensional compressed observation image obtained by transformation, and apply the total variation prior term and tensor low rank constraint at the same time to obtain:

[0090]

[0091] ||·|| tv is the total variation regularization function, ||·|| 3DTNN is the three-dimensional tensor nuclear norm, ||·||1 is the l1 norm, ||R|| 2,1 is the mixed norm and is the sum of all Frobenius norms of the side slices of R, that is, is the index;

[0092] S25. For the solution of formula (4), based on the plug-and-play alternating direction multiplier framework, formula (4) is converted into an image reconstruction mathematical model:

[0093]

[0094] Where τ, λ, α, β, γ, and μ are regularization parameters, U is the auxiliary variable, Λ is the dual variable, and ρ is the augmented Lagrangian parameter.

[0095] S3. Decompose the image reconstruction mathematical model into several optimization sub-problems, and perform iterative solutions to obtain the reconstructed image, wherein the several optimization sub-problems include: the desired quantity X sub-problem, the auxiliary variable U sub-problem, the clean signal L sub-problem, the sparse noise S sub-problem, the sparse noise R sub-problem, and the Gaussian noise N sub-problem.

[0096] like Figure 3 and Figure 4 As shown, step S3 includes the following steps:

[0097] S31. Update and solve the subproblem X to be solved, and obtain the subproblem X to be solved from formula (5):

[0098]

[0099] Formula (6) is a least squares problem, and its solution is as follows:

[0100] X (t) =(AA T +ρ (t-1) +μ) -1 (A T Y+ρ (t-1) U (t-1) -Λ+μ(L (t-1) +S (t-1) +R (t-1) +N (t-1) )) (7)

[0101] Where t (t≥1) is the number of iterations.

[0102] S32. Update and solve the auxiliary variable U subproblem. The auxiliary variable U subproblem is given by the following formula:

[0103]

[0104] Formula (8) is solved by the following total variation approximation operator:

[0105]

[0106] Where D TV is the TV denoising operator.

[0107] S33. Update and solve the clean signal L subproblem. Similarly, the clean signal L subproblem is given by the following formula:

[0108]

[0109] in, and i3 (i3=1,2,...,k) is the index, is the weight, is the result of the third mode Fourier transform (FFT) along L, ||·|| TNN is the tensor nuclear norm. Three auxiliary tensors are introduced Then equation 10 can be transformed into the following form:

[0110]

[0111] In the formula, Λ i is the dual variable, ρ i is the augmented Lagrangian parameter. Similarly, equation 11 can be decomposed into the following sub-problems to update:

[0112]

[0113] The solution is as follows:

[0114]

[0115] in, D tnnθ (·) represents the tensor singular value threshold operator, * i (i=1,2,3) is the mode-n product, Tensor Orthogonal tensors, orthogonal tensors, and diagonal tensors of singular value decomposition,

[0116]

[0117] S34. Update and solve the sparse noise S subproblem. Similarly, the sparse noise S subproblem is given by the following formula:

[0118]

[0119] The solution is as follows:

[0120]

[0121] Among them STH ζ (·) is the soft threshold operator, which is defined as STH ζ (·) = sgn(·)max(|·|-ζ), where sgn(·) is a real sign function.

[0122] S35. Update and solve the sparse noise R subproblem. Similarly, the sparse noise R subproblem is given by the following formula:

[0123]

[0124] because The subproblem of equation 17 is divided into (n-t) subproblems along the second dimension, and the i2-th subproblem is as follows:

[0125]

[0126] in, They are X(:, i2,:), L(:, i2,:), S(:, i2,:), R(:, i2,:), and N(:, i2,:).

[0127] Equation 18 is a least squares problem, and its closed form solution is as follows

[0128]

[0129] in, ||·|| F is the F-norm.

[0130] S36. Update and solve the Gaussian noise N sub-problem. The Gaussian noise N sub-problem is given by the following formula:

[0131]

[0132] The solution is as follows:

[0133]

[0134] S37, update dual variables Λ, Λ i (i=1, 2, 3):

[0135] Λ (t) =Λ (t-1) +ρ (t-1) (X (t) -U (t) ) (twenty two)

[0136]

[0137] (1) S38, Updated augmented Lagrangian parameter ρρ i (i=1,2,3)

[0138]

[0139] In the formula, p and P i (i=1,2,3) is the original residual and p=||X (t) -U (t) ||2 and q and q i (i=1,2,3) is the dual residual and q=ρ (t-1) ||U (t-1) -U (t) ||2 and τ incr (τ incr>1) and τ decr (τ decr >1) is the balance factor, ε(ε>1) is the residual tolerance, usually τ inc r = 1.1, τ decr =1.1,ε=1.5.

[0140] S39, as the iteration proceeds, that is, when t=t+1 (t>1), determine whether the convergence condition is met. If the convergence condition is met, stop updating and output the updated X (t) , L (t) , the image is reconstructed and the interference fringe image is obtained. If the convergence condition is not met, the above steps are repeated to continue the iteration.

[0141] The convergence conditions include: the error value e ζ Less than or equal to the preset error value in,

[0142]

[0143] is the preset error.

[0144] Next, the effectiveness of the image reconstruction method provided by the present invention is verified:

[0145] A numerical method is used to verify the feasibility and effectiveness of the proposed method, and the alternating multiplier method based on total variation (ADMM-TV) and the alternating multiplier method based on total variation and low-rank constraint (ADMM-LRTV) are used as control groups. Peak signal-to-noise ratio and structural similarity are used to quantitatively evaluate the quality of the reconstructed image. Then, a set of simulated images are produced based on a set of shock wave velocity data measured by the line-VISAR system, such as Figure 6 As shown. Figure 6 The phases of 35 representative time points are extracted from the image data shown in Figure 1, and the original third-order fringe tensor data with a size of 540×800×35 pixels is generated. At the same time, in order to be closer to the real complex environment, Salt&Pepper noise and Gaussian noise with a variance of 0.1 are introduced into the third-order fringe tensor data. The original third-order fringe tensor data and the noisy third-order fringe tensor are shown in Figure 7. In addition, due to the actual experimental conditions and the saturation characteristics of the streak camera with a fully open slit, a coded mask with a coded aperture of 8×8 is used, as shown in Figure 8(a). Based on the noisy third-order fringe tensor data and the coded mask image data, by simulating the data acquisition process of CUP-VISAR, the corresponding observed image data with a size of 574×800 pixels is shown in Figure 8(b). Finally, the third-order fringe tensor is reconstructed from the observed image data using ADMM-TV, ADMM-TVLR and ADMM-TLRTN (the proposed method).

[0146] The reconstructed third-order fringe tensor obtained by these methods is as follows Fig. 9 , Fig.10 and Fig.11 As shown in Figure 2, the quality of each reconstructed fringe image obtained by ADMM-TV is blurry. In contrast, the reconstructed image obtained by ADMM-TLRTN is better and clearer. In order to quantitatively evaluate the quality of the reconstructed image, the PSNR and SSIM of the reconstructed third-order fringe tensor are shown in Figure 2. Fig.13 As shown in Figure 12, the PSNR and SSIM of the stripe images reconstructed using ADMM-TV and ADMM-TVLR are less than 20dB and 0.8, respectively. For the ADMM-TLRTR method, the curves of PSNR and SSIM are relatively flat, and the PSNR values ​​and SSIM values ​​are between 18.097dB-21.376dB and 0.803-0.887, respectively. At the same time, the PSNR and SSIM of each frame are not much different, indicating that the inter-frame information is well preserved. In addition, compared with ADMM-TV and ADMM-TVLR, the average PSNR and average SSIM increased by 8.426dB, 4.586dB, 32.6%, and 17.5%, respectively. From the above results, the quality of the reconstructed image of each frame obtained by this method is more stable and better.

[0147] It should be noted that, for the sake of simplicity, the method embodiments are described as a series of action combinations, but those skilled in the art should be aware that the embodiments of the present invention are not limited by the order of the actions described, because according to the embodiments of the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

[0148] Reference Fig.13 , shows an image reconstruction device provided in an embodiment of the present invention, which is used to implement the image reconstruction method described in SHANG, including: a CUP-VISAR system, an image reconstruction mathematical model construction module and a model solving module; the CUP-VISAR system is used to sample the observation signal to obtain a two-dimensional compressed observation image; the image reconstruction mathematical model construction module is used to construct a tensor principal component analysis reconstruction mathematical model based on plug-and-play alternating direction multipliers according to the two-dimensional compressed observation image, with total variation prior terms, tensor low rank constraints, and sparse constraints as prior constraints; the model solving module is used to decompose the image reconstruction mathematical model into several optimization sub-problems, and solve them to obtain a reconstructed image.

[0149] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0150] In addition, an embodiment of the present invention further provides an electronic device, including a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus.

[0151] Memory, used to store computer programs;

[0152] The processor is used to implement the image reconstruction method described in the above embodiment when executing the program stored in the memory.

[0153] The communication bus mentioned in the above terminal can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0154] The communication interface is used for communication between the above terminal and other devices.

[0155] The memory may include a random access memory (RAM) or a non-volatile memory, such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0156] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0157] In another embodiment of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium stores instructions, which, when executed on a computer, enable the computer to execute the image reconstruction method described in the above embodiment.

[0158] In another embodiment of the present invention, a computer program product including instructions is provided. When the computer program product is run on a computer, the computer executes the image reconstruction method described in the above embodiment.

[0159] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented by software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state hard disk Solid State Disk (SSD)), etc.

[0160] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0161] Each embodiment in this specification is described in a related manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0162] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention are included in the protection scope of the present invention.

Claims

1. An image reconstruction method, It is characterized in that include: The CUP-VISAR system is used to sample the observation signal and obtain a two-dimensional compressed observation image; According to the two-dimensional compressed observation image, a tensor principal component analysis reconstruction mathematical model based on plug-and-play alternating direction multipliers is constructed with total variation prior terms, tensor low-rank constraints, and sparse constraints as prior constraints. The mathematical model of image reconstruction is decomposed into several optimization sub-problems, and the reconstructed image is obtained by iterative solution.

2. The image reconstruction method according to claim 1, It is characterized in that The step of sampling the observation signal using the CUP-VISAR system to obtain a two-dimensional compressed observation image includes: The VISAR system carries the target surface information and generates interference to form an interference fringe image at the imaging plane, thus obtaining a time-varying two-dimensional fringe image. The time-varying two-dimensional fringe image is input into the CUP system, and the time-varying two-dimensional fringe image is encoded, shifted and superimposed to form a two-dimensional compressed observation image.

3. The image reconstruction method according to claim 1, It is characterized in that The expression of the two-dimensional compressed observation image is: Y=AI Where I is a three-dimensional stripe image with a pixel size of m×n×k that varies with time; Y is a two-dimensional observation image recorded by a streak camera, with a size of (m+k-1)×n; A is the observation matrix, and A=MSC, where M is the spatiotemporal integration operator, S is the time shear operator, and C is the spatial mask operator.

4. The image reconstruction method according to claim 3, It is characterized in that The step of constructing a tensor principal component analysis reconstruction mathematical model based on plug-and-play alternating direction multipliers according to the two-dimensional compressed observation image with total variation prior terms, tensor low rank constraints, and sparse constraints as prior constraints includes: Add a priori constraints to be evaluated for the expression of the two-dimensional compressed observation image and transform the expression of the two-dimensional compressed observation image into: Where X is the quantity to be determined, Φ(I) is the regularization term, ‖·‖ 2 for l 2 The norm, ∈, is a positive parameter that depends on the noise variance; After decomposing the quantity X into the low-rank part of the tensor, sparse noise and Gaussian noise, the expression of the quantity X is: X=L+S+R+N Where L is the clean signal, S and R are sparse noise, and N is Gaussian noise; Substitute the expression of the desired quantity X into the expression of the two-dimensional compressed observation image obtained by transformation, and apply the total variation prior term and tensor low rank constraint at the same time, and we get: ‖·‖ tv is the total variation regularization function, ‖·‖ 3DTNN is the nuclear norm of the three-dimensional tensor, ‖·‖ 1 for l 1 norm,||R|| 2,1 is the mixed norm and is the sum of all Frobenius norms of the side slices of R, that is, i 2 (i 2 =1,2,…,n) is the index; Based on the plug-and-play alternating direction multiplier framework, the above formula is converted into a mathematical model for image reconstruction: Where τ, λ, α, β, γ, and μ are regularization parameters, U is the auxiliary variable, Λ is the dual variable, and ρ is the augmented Lagrangian parameter.

5. The image reconstruction method according to claim 4, It is characterized in that The optimization sub-problems include: the desired quantity X sub-problem, the auxiliary variable U sub-problem, the clean signal L sub-problem, the sparse noise S sub-problem, the sparse noise R sub-problem, and the Gaussian noise N sub-problem.

6. The image reconstruction method according to claim 5, It is characterized in that The step of decomposing the image reconstruction mathematical model into a plurality of optimization sub-problems and solving them to obtain the reconstructed image comprises: Update and solve the subproblem of the quantity X to be solved; Update and solve the auxiliary variable U subproblem; Update and solve the clean signal L subproblem; Update and solve the sparse noise S subproblem; Update and solve the sparse noise R subproblem; Update and solve the Gaussian noise N subproblems; Update the dual variable Λ; Update the augmented Lagrangian parameter ρ; If the convergence condition is met, the updating is stopped and the updated value to be evaluated and the clean signal are output to obtain the interference fringe image.

7. The image reconstruction method according to claim 6, It is characterized in that The convergence conditions include: the error value e ζ Less than or equal to the preset error value in, 8. An image reconstruction device, It is characterized in that Used to implement the image reconstruction method according to any one of claims 1 to 7, comprising: CUP-VISAR system, used to sample the observation signal and obtain a two-dimensional compressed observation image; Image reconstruction mathematical model building module, used to build a tensor principal component analysis reconstruction mathematical model based on plug-and-play alternating direction multipliers according to the two-dimensional compressed observation image, with total variation prior terms, tensor low rank constraints, and sparse constraints as prior constraints; The model solving module is used to decompose the image reconstruction mathematical model into several optimization sub-problems and solve them to obtain the reconstructed image.

9. An electronic device, It is characterized in that It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; The memory is used to store computer programs; The processor is used to implement the image reconstruction method according to any one of claims 1 to 7 when executing the program stored in the memory.

10. One or more computer-readable media having instructions stored thereon, which, when executed by one or more processors, enable the processors to perform the image reconstruction method according to any one of claims 1 to 7.

Citation Information

Patent Citations

  • Dynamic magnetic resonance image reconstruction method based on improved robust tensor principal component analysis

    CN110533736A

  • GAP rapid inversion method based on low-rank constraint, storage medium and equipment

    CN116502441A

  • CUP-VISAR compressed image inversion method and device

    CN116503279A

  • Multi-constraint fast inversion method based on dual-channel random coding, medium and equipment

    CN116883278A

  • Method for reconstructing compressed ultrafast photographic image, storage medium and equipment

    CN117408875A