Synthetic aperture radar image speckle suppression method based on diffusion sampling

Abstract

The invention discloses a synthetic aperture radar image speckle suppression method based on diffusion sampling, and relates to the field of synthetic aperture radar image processing. The method is based on a sampling scheme of an approximate score function, inverse transfer distribution and application of a multiplicative noise model, solves the problem of multiplicative noise degradation in the synthetic aperture radar image, and avoids supervised training and logarithmic transformation of the SAR image.

Description

Technical Field

[0001] The present application relates to the field of synthetic aperture radar image processing, and in particular to a synthetic aperture radar image coherent speckle suppression method based on diffusion sampling. Background Art

[0002] The processing and interpretation of Synthetic Aperture Radar (SAR) images is an ill-posed inverse problem. When processing SAR images, it is necessary to add appropriate prior conditions to the clear SAR images. Diffusion models are widely used in inverse image processing problems, such as image deblurring, image restoration, and image super-resolution, due to their powerful deep generative priors. However, the image degradation solved by these inverse problems is additive in nature, and their application in multiplicative noise degradation problems such as SAR image speckle suppression is only in its infancy.

[0003] SAR-DDPM (SAR-Denoising Diffusion Probabilistic Model) uses optical images and synthetic speckle images to train the noise prediction network. However, since speckle noise is diverse, the noise predictor trained initially cannot fully simulate the diverse speckle noise. In addition, when the intensity or type of speckle noise changes slightly, SAR-DDPM needs to be re-supervised and trained. To solve these problems, subsequent methods have used logarithmic transformation on the speckle noise image and used Gaussian distribution instead of the speckle noise distribution in the logarithmic domain. Such transformation and approximation are relatively rough. Summary of the invention

[0004] The purpose of this application is to provide a method for suppressing coherent speckles in synthetic aperture radar images based on diffusion sampling to solve the problem of multiplicative noise degradation in synthetic aperture radar images and avoid supervised training and logarithmic transformation of SAR images.

[0005] To achieve the above objectives, this application provides the following solutions.

[0006] In a first aspect, the present application provides a method for suppressing coherent speckle in synthetic aperture radar images based on diffusion sampling, comprising:

[0007] Initialize the diffusion noise image of the Tth time step in the diffusion inversion process, and initialize the time step t=T, where T is the total time step of the diffusion inversion process;

[0008] Based on the diffuse noise image at the t-th time step, the prior state estimate at the t-1th time step is calculated using an unconditional deep neural network;

[0009] According to the observed image and the diffuse noise image at the t-th time step, the likelihood score function value at the t-th time step is estimated using the multiplicative noise model;

[0010] Calculate the diffuse noise image at the t-1th time step according to the prior state estimate at the t-1th time step and the likelihood score function value at the tth time step;

[0011] Subtract 1 from the value of t, and return to the step of "calculating the prior state estimate at the t-1th time step using an unconditional deep neural network based on the diffuse noise image at the tth time step" until the value of t is 0, and output the diffuse noise image at the 0th time step as a clear image obtained by performing speckle suppression on the observed image.

[0012] In a second aspect, the present application provides a synthetic aperture radar image coherent speckle suppression device based on diffuse sampling, wherein the synthetic aperture radar image coherent speckle suppression device based on diffuse sampling applies the synthetic aperture radar image coherent speckle suppression method based on diffuse sampling, and the synthetic aperture radar image coherent speckle suppression device based on diffuse sampling comprises:

[0013] An initialization module is used to initialize the diffusion noise image at the Tth time step in the diffusion inversion process, where the initialization time step t=T, and T is the total time step of the diffusion inversion process;

[0014] A priori state estimation calculation module is used to calculate the priori state estimation at the t-1th time step based on the diffusion noise image at the tth time step using an unconditional deep neural network;

[0015] A likelihood score function value estimation module is used to estimate the likelihood score function value at the t-th time step based on the observed image and the diffuse noise image at the t-th time step using a multiplicative noise model;

[0016] A diffusion noise image calculation module is used to calculate the diffusion noise image at the t-1th time step according to the prior state estimation at the t-1th time step and the likelihood score function value at the tth time step;

[0017] The return module is used to reduce the value of t by 1 and return to the prior state estimation calculation module until the value of t is 0, and output the diffusion noise image at the 0th time step as a clear image obtained by performing coherent speckle suppression on the observed image.

[0018] In a third aspect, the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-mentioned synthetic aperture radar image coherent speckle suppression method based on diffuse sampling.

[0019] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned synthetic aperture radar image coherent speckle suppression method based on diffusion sampling.

[0020] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the above-mentioned synthetic aperture radar image coherent speckle suppression method based on diffusion sampling.

[0021] According to the specific embodiments provided in this application, this application has the following technical effects.

[0022] The present application provides a method for suppressing coherent speckle in synthetic aperture radar images based on diffusion sampling. The method of the present application is based on a sampling scheme of an approximate scoring function, an inverse transfer distribution, and an application of a multiplicative noise model, thereby solving the problem of multiplicative noise degradation in synthetic aperture radar images and avoiding supervised training and logarithmic transformation of SAR images. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0024] Figure 1 A schematic flow chart of a method for suppressing coherent speckle in synthetic aperture radar images based on diffusion sampling is provided in one embodiment of the present application.

[0025] Figure 2 This is an example diagram of an observation image provided in an embodiment of the present application.

[0026] Figure 3 An embodiment of the present application provides Figure 2 Schematic diagram of the suppression results of each observation image in .

[0027] Figure 4 This is a comparison diagram of the effects provided in one embodiment of the present application.

[0028] Figure 5 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0029] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0030] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0031] In an exemplary embodiment, Figure 1 As shown, a method for suppressing coherent speckles in synthetic aperture radar images based on diffusion sampling is provided, including the following steps 101 to 105.

[0032] Step 101, initialize the diffusion noise image of the Tth time step in the diffusion inversion process, and initialize the time step t=T, where T is the total time step of the diffusion inversion process.

[0033] Step 102, based on the diffuse noise image at the t-th time step, using an unconditional deep neural network, calculate the prior state estimate at the t-1th time step.

[0034] Step 103, based on the observed image and the diffuse noise image at the t-th time step, using a multiplicative noise model, estimate the likelihood score function value at the t-th time step.

[0035] Step 104, calculating the diffuse noise image at the t-1th time step according to the prior state estimate at the t-1th time step and the likelihood score function value at the tth time step.

[0036] Step 105, subtract 1 from the value of t, and return to the step of "calculating the prior state estimate of the t-1th time step using an unconditional deep neural network based on the diffuse noise image of the tth time step", until the value of t is 0, and output the diffuse noise image of the 0th time step as a clear image obtained by performing coherent speckle suppression on the observed image.

[0037] The implementation of the above steps 101 to 105 can solve the problem of multiplicative noise degradation in synthetic aperture radar images and avoid supervised training and logarithmic transformation of SAR images.

[0038] In another exemplary embodiment, in the above step 101, an observed SAR image affected by speckle noise is further input, that is, the observed image y, given the number of views L, the noise variance sequence of the diffuse positive process single-step noise addition Weight coefficient γ and total noise variance sequence Initialization parameters: Pick

[0039] In another exemplary embodiment, the above steps 102 to 105 constitute a diffusion sampling scheme based on a score function, which utilizes the powerful depth generation prior of the diffusion model, estimates the inverse transfer distribution, and uses the multiplicative noise model to suppress multiplicative noise. Experiments were conducted on synthetic and real SAR images, and the experimental results show the superiority of the synthetic aperture radar image coherent speckle suppression method based on diffusion sampling of the present application, and the specific principle is as follows.

[0040] S1. Establishment of SAR image speckle suppression model based on diffusion model.

[0041] For the SAR image speckle suppression task, using the diffusion model to suppress the SAR image speckle is equivalent to realizing the inverse image denoising process guided by the SAR image under the influence of speckle noise. In this process, it can be expressed as a stochastic differential equation of the inverse time process, that is, the SAR image speckle suppression model based on the diffusion model:

[0042]

[0043] Where y is the SAR image under the influence of coherent speckle noise, also called the observed image, and x t is the diffusion noise image at the tth time step in the diffusion inverse process. When t = 0, x0 is the clear image to be obtained. is the posterior conditional score function, is the time-reverse Wiener process, β t Indicates that from x t-1 to x t Variance of the added Gaussian noise.

[0044] The specific form of the posterior conditional score function is:

[0045]

[0046] The first term in the posterior conditional score function is the score function of the unconditional diffusion model, which is obtained by the pre-trained noise estimation network (i.e., unconditional deep neural network) It is estimated that the second likelihood score function is The solution is the key to the SAR image speckle suppression model based on the diffusion model.

[0047] S2. Estimation of the inverse transfer distribution.

[0048] In order to solve the unknown terms of the SAR image speckle suppression model based on the diffusion model in step S1 This step estimates the inverse transfer distribution.

[0049] First, S1 leaves unknown items It can be written as:

[0050] p(y|x t ) = ∫p(y|x0)p(x0|x t )dx0(2)

[0051] Among them, p(x0|x t ) is the inverse transfer distribution, and p(y|x0) can be obtained from the positive process of SAR image degradation by coherent speckle. In this step, the inverse transfer distribution is estimated first. t )dx0 is regarded as a probability measure, then:

[0052]

[0053] Will Recorded as and in, By unconditional deep neural network Then, the inverse transfer distribution is estimated using the single point distribution, that is, This achieves the purpose of reducing computational complexity.

[0054] S3. Estimation of the likelihood score function.

[0055] Further, the likelihood score function is Solve and express p(y|x0):

[0056]

[0057] Where C0=(L L / Γ(L) d , the SAR image coherent speckle obeys the Γ distribution Γ(L,L / α), where are the number of views and the basic reflectivity, respectively, Γ(·) is the Γ function, and Q(·) can be expressed as Therefore, combining S1 and S2, we can get:

[0058]

[0059] Let R = logp(y|x t ), the likelihood score function can be written as:

[0060]

[0061] in ⊙ is element-by-element multiplication, I is the unit matrix, is the Jacobi operator acting on a vector function.

[0062] Based on the above principles, the following formula is obtained:

[0063] 1. The formula for calculating the prior state estimate at the t-1 time step is:

[0064]

[0065] in, is the prior state estimate at the t-1th time step, α t is the noise variance β at the tth time step t The relevant variable, α t =1-β t , x t is the diffuse noise image at the tth time step, is an unconditional deep neural network, which is used to output the score function of the unconditional diffusion model The value of is the gradient symbol, p t (x t ) is the distribution of the diffuse noise image at the tth time step, is the total noise variance at the tth time step, η t is the random Gaussian noise at the tth time step, is a standard normal distribution.

[0066] 2. The formula for estimating the likelihood score function value at the tth time step is:

[0067]

[0068] in, is the likelihood score function, is the gradient symbol, p(y|x t ) is the positive process distribution of the observed image obtained from the diffuse noise image at the tth time step, y is the observed image, x t is the diffuse noise image at the tth time step, is the first intermediate variable, is α from 1 to t t The value obtained by multiplication is is the score function of the unconditional diffusion model, p t (x t ) is the distribution of the diffuse noise image at the tth time step, R is the second intermediate variable, R = log p (y | x t );

[0069] L is the given number of views, ⊙ is the element-by-element multiplication, I is the identity matrix, is the Jacobi operator acting on a vector function, is an unconditional deep neural network, which is used to output the score function of the unconditional diffusion model The value of .

[0070] 3. The formula for calculating the diffuse noise image at the t-1 time step is:

[0071]

[0072] Among them, x t-1 is the diffuse noise image at the tth time step, is the prior state estimate of the t-1th time step, γ is the weight coefficient, α t is the noise variance β at the tth time step t The relevant variable, α t =1-β t , is the likelihood score function value at the tth time step.

[0073] In another exemplary embodiment, the following experiment was conducted to verify the effect of the above method.

[0074] Using the method of the above embodiment Figure 2 The SAR image (i.e., the observed image) shown in FIG. is subjected to speckle suppression. Figure 2 SAR1, SAR2, SAR3 and SAR4 in the figure are SAR images with the number of views L being 1, 2, 3 and 4 respectively. The suppression results are as follows: Figure 3 As shown, the contrast effect is as follows Figure 4 As shown, Figure 4 The comparison methods in the example are SAR-BM3D and SAR-DDPM. In order to quantitatively evaluate the performance of the above methods, the present embodiment selects two indicators, peak value and signal-to-noise ratio (PSNR). The larger the value of these indicators, the higher the quality of the SAR image. The results are shown in Table 1. The results show that the method proposed in the present application is superior to the comparison method in terms of image quality improvement and image fidelity.

[0075] Table 1 Quantitative results of speckle suppression

[0076]

[0077] Based on the same inventive concept, the embodiment of the present application also provides a synthetic aperture radar image speckle suppression device based on diffuse sampling for implementing the synthetic aperture radar image speckle suppression method based on diffuse sampling. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations of one or more embodiments of the synthetic aperture radar image speckle suppression device based on diffuse sampling provided below can refer to the limitations of the synthetic aperture radar image speckle suppression method based on diffuse sampling above, and will not be repeated here.

[0078] In an exemplary embodiment, a synthetic aperture radar image speckle suppression device based on diffusion sampling is provided, comprising:

[0079] The initialization module is used to initialize the diffusion noise image of the Tth time step in the diffusion inversion process, and the initialization time step t=T, where T is the total time step of the diffusion inversion process.

[0080] The prior state estimation calculation module is used to calculate the prior state estimation at the t-1th time step based on the diffuse noise image at the tth time step using an unconditional deep neural network.

[0081] The likelihood score function value estimation module is used to estimate the likelihood score function value at the t-th time step based on the observed image and the diffuse noise image at the t-th time step using a multiplicative noise model.

[0082] The diffusion noise image calculation module is used to calculate the diffusion noise image at the t-1th time step according to the prior state estimation at the t-1th time step and the likelihood score function value at the tth time step.

[0083] The return module is used to reduce the value of t by 1 and return to the prior state estimation calculation module until the value of t is 0, and output the diffusion noise image at the 0th time step as a clear image obtained by performing coherent speckle suppression on the observed image.

[0084] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 5As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for suppressing coherent speckles in a synthetic aperture radar image based on diffusion sampling is implemented.

[0085] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components. In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0086] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0087] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0088] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0089] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0090] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0091] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0092] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for suppressing coherent speckle in synthetic aperture radar images based on diffusion sampling, characterized in that: include: Initialize the diffusion noise image of the Tth time step in the diffusion inversion process, and initialize the time step t=T, where T is the total time step of the diffusion inversion process; Based on the diffuse noise image at the t-th time step, the prior state estimate at the t-1th time step is calculated using an unconditional deep neural network; According to the observed image and the diffuse noise image at the t-th time step, the likelihood score function value at the t-th time step is estimated using the multiplicative noise model; Calculate the diffuse noise image at the t-1th time step according to the prior state estimate at the t-1th time step and the likelihood score function value at the tth time step; Subtract 1 from the value of t, and return to the step of "calculating the prior state estimate at the t-1th time step using the unconditional deep neural network based on the diffuse noise image at the tth time step" until the value of t is 0, and output the diffuse noise image at the 0th time step as the clear image obtained by performing speckle suppression on the observed image.

2. The method for suppressing coherent speckle in synthetic aperture radar images based on diffusion sampling according to claim 1, characterized in that: The formula for calculating the prior state estimate at the t-1 time step is: in, is the prior state estimate at the t-1 time step, α t is the noise variance β at the tth time step t The relevant variable, α t =1-β t , x t is the diffuse noise image at the tth time step, is an unconditional deep neural network, which is used to output the score function of the unconditional diffusion model The value of is the gradient symbol, p t (x t ) is the distribution of the diffuse noise image at the tth time step, is the total noise variance at the tth time step, η t is the random Gaussian noise at the tth time step, is a standard normal distribution.

3. The method for suppressing coherent speckle in synthetic aperture radar images based on diffusion sampling according to claim 1, characterized in that: The formula for estimating the likelihood score function value at the tth time step is: in, is the likelihood score function, is the gradient symbol, p(y|x t ) is the positive process distribution of the observed image obtained from the diffuse noise image at the tth time step, y is the observed image, x t is the diffuse noise image at the tth time step, is the first intermediate variable, is α from 1 to t t The value obtained by multiplication is is the score function of the unconditional diffusion model, pt(xt) is the distribution of the diffusion noise image at the tth time step, R is the second intermediate variable, R = logp(y|x t ); L is the given number of views, ⊙ is the element-by-element multiplication, I is the identity matrix, is the Jacobi operator acting on a vector function, is an unconditional deep neural network, which is used to output the score function of the unconditional diffusion model The value of .

4. The method for suppressing coherent speckle in synthetic aperture radar images based on diffusion sampling according to claim 1, characterized in that: The formula for calculating the diffuse noise image at the t-1 time step is: Among them, x t-1 is the diffuse noise image at the tth time step, is the prior state estimate of the t-1th time step, γ is the weight coefficient, α t is the noise variance β at the tth time step t The relevant variable, α t =1-β t , is the likelihood score function value at the tth time step.

5. A synthetic aperture radar image speckle suppression device based on diffusion sampling, characterized in that: The synthetic aperture radar image coherent speckle suppression device based on diffuse sampling applies the synthetic aperture radar image coherent speckle suppression method based on diffuse sampling according to any one of claims 1 to 4, and the synthetic aperture radar image coherent speckle suppression device based on diffuse sampling comprises: An initialization module is used to initialize the diffusion noise image at the Tth time step in the diffusion inversion process, where the initialization time step t=T, and T is the total time step of the diffusion inversion process; A priori state estimation calculation module is used to calculate the priori state estimation at the t-1th time step based on the diffusion noise image at the tth time step using an unconditional deep neural network; A likelihood score function value estimation module is used to estimate the likelihood score function value at the t-th time step based on the observed image and the diffuse noise image at the t-th time step using a multiplicative noise model; A diffusion noise image calculation module is used to calculate the diffusion noise image at the t-1th time step according to the prior state estimation at the t-1th time step and the likelihood score function value at the tth time step; The return module is used to reduce the value of t by 1 and return to the prior state estimation calculation module until the value of t is 0, and output the diffusion noise image at the 0th time step as a clear image obtained by performing coherent speckle suppression on the observed image.

6. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for suppressing coherent speckles in synthetic aperture radar images based on diffuse sampling as described in any one of claims 1 to 4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for suppressing coherent speckles in synthetic aperture radar images based on diffusion sampling described in any one of claims 1 to 4 is implemented.

8. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for suppressing coherent speckles in synthetic aperture radar images based on diffusion sampling described in any one of claims 1 to 4 is implemented.

Images