Generative single-frequency millimeter-wave self-focusing near-field imaging method based on diffusion model

Abstract

The present invention relates to the field of millimeter wave human body security inspection technology, and in particular to a generative single-frequency millimeter wave self-focusing near-field imaging method based on a diffusion model, comprising: obtaining single-frequency raw echo data using radar equipment; imaging the single-frequency raw echo data to obtain a single-frequency imaging defocus result; inputting the single-frequency imaging defocus result into a pre-constructed spatial convolutional neural network to obtain a network coding result; embedding the network coding result into a pre-trained noise reduction diffusion model to obtain a conditional diffusion model; using the conditional diffusion model to gradually reconstruct the residual value between the network coding result and the ideal broadband imaging result to obtain a diffusion model prediction result, which is then added to the network coding result to obtain a final single-frequency self-focusing imaging result. Thus, the method solves the problems that traditional single-frequency millimeter wave imaging methods cannot generate high-quality focused images, and that single-frequency imaging methods based on self-focusing have insufficient imaging capabilities in complex object scenes.

Description

Technical Field

[0001] The present invention relates to the technical field of millimeter wave human body security inspection, and in particular to a generative single-frequency millimeter wave self-focusing near-field imaging method based on a diffusion model. Background Art

[0002] Millimeter waves have adequate penetrating power, allowing them to detect hidden objects through common materials like clothing and packages without posing a threat to human health. Active millimeter-wave security scanners based on millimeter-wave radar achieve millimeter-level resolution in azimuth, fully meeting the requirements for safe, high-precision, and contactless human inspections. These devices have already been piloted in key locations.

[0003] The key technology of active millimeter-wave security inspection devices is millimeter-wave near-field imaging. Traditional near-field imaging methods are based on the Nyquist sampling theory. They use matched filtering in the spatial or spatial frequency domain to complete the inversion process from echo data to a preset spatial distribution. While meeting the requirements of spatial sampling and imaging bandwidth, they can achieve three-dimensional imaging with high azimuth and range resolution. However, the stringent requirements of traditional near-field imaging methods on imaging conditions have brought difficulties to the implementation of imaging systems. In order to achieve higher range resolution, frequency-modulated continuous waves are often used as the waveform system of imaging radars in radar design. This will undoubtedly greatly increase the complexity of the radar system and bring challenges to the specific implementation process. In addition, as imaging conditions improve, the amount of three-dimensional echo data collected by the radar will increase, which will have an adverse impact on real-time data transmission and subsequent imaging processes.

[0004] Imaging using single-frequency echo data can significantly reduce the dimensionality of echo data while breaking free from the constraints of broadband radar systems. However, due to sampling constraints, direct use of traditional millimeter-wave near-field imaging methods cannot produce good imaging results. Existing self-focusing single-frequency millimeter-wave imaging methods perform poorly when dealing with targets with complex surfaces or spatial structures, such as the human body.

[0005] In near-field single-frequency millimeter-wave imaging, traditional near-field imaging methods only produce images lacking range resolution, also known as out-of-focus images. Image autofocusing exploits the property of the preset to form a unique spatial structure in the out-of-focus image, completing the image focusing process and achieving high-quality imaging results. A well-developed image autofocusing method can effectively filter out diffuse sidelobes surrounding the preset in the out-of-focus image and restore the preset position. Current single-frequency image autofocusing methods can be categorized into focal plane selection and preset position estimation. The focal plane selection method first calculates the image focus at all reference distance planes and plots a focus-distance curve. A threshold is then set or manually selected as the focal plane distance corresponding to the point where the focus is significantly high in the curve, retaining the imaging results at that distance. There are two types of preset position estimation methods: one estimates the spatial position of the preset, images the hypothetical preset, and then uses the difference between the imaging result and the actual measurement as an optimization criterion to iteratively update the preset position. The other employs a sliding window strategy, measuring the focus at all reference distances within each sliding window to determine the possible distance of the preset within the window. These traditional autofocus methods perform well in simple preset scenarios, but often fail when faced with presets with complex spatial structures, and the preset position estimation method requires long iterative calculations.

[0006] Furthermore, traditional near-field imaging methods require imaging at multiple reference distance planes, resulting in a three-dimensional image with two azimuth dimensions and one range dimension. Feature extraction neural networks typically employing two-dimensional convolutional layers only have three dimensions: image length, width, and channel dimensions. Directly inputting the range dimension as the channel dimension can lose the spatial structure of the image. Furthermore, the fitting capabilities of a single neural network architecture are often limited, and the choice of training loss function can impact the final imaging quality. Summary of the Invention

[0007] The present invention provides a generative single-frequency millimeter-wave self-focusing near-field imaging method based on a diffusion model to solve the problems that traditional single-frequency millimeter-wave imaging methods cannot generate high-quality focused images and that single-frequency imaging methods based on self-focusing have insufficient imaging capabilities in complex object scenes.

[0008] The first aspect of the present invention provides a generative single-frequency millimeter-wave self-focusing near-field imaging method based on a diffusion model, comprising the following steps: obtaining single-frequency original echo data using radar equipment; imaging the single-frequency original echo data to obtain a single-frequency imaging defocus result; inputting the single-frequency imaging defocus result into a pre-constructed spatial convolutional neural network to obtain a network coding result; embedding the network coding result into a pre-trained noise reduction diffusion model to obtain a conditional diffusion model; using the conditional diffusion model to gradually reconstruct the residual value between the network coding result and a preset ideal broadband imaging result to obtain a diffusion model prediction result, and adding the diffusion model prediction result to the network coding result to obtain a final single-frequency self-focusing imaging result.

[0009] Optionally, imaging the single-frequency raw echo data to obtain a single-frequency imaging defocus result includes:

[0010] Based on the phase shift method in the millimeter wave near-field imaging method, the single-frequency raw echo data is imaged on several equally spaced reference planes in a pre-selected imaging space to obtain the single-frequency imaging defocus result.

[0011] Optionally, the solution formula for the single-frequency imaging defocus result is:

[0012]

[0013] in, is the inverse transform of the two-dimensional Fourier transform, FT 2D is the two-dimensional Fourier transform, e is the natural logarithm, j is the imaginary unit, k z′ is k in the spatial wave number domain x′ With k y′ The spherical function, z is the plane represented by multiple reference distances, σ s (x, y, z) is the single-frequency imaging defocus result of the scattering point coordinates, and s(x′, y′, k0) is the single-frequency original echo data with a spatial wave number of k0 received by the planar array transceiver element at the coordinate (x′, y′).

[0014] Optionally, inputting the single-frequency imaging defocus result into a pre-built spatial convolutional neural network to obtain a network coding result includes:

[0015] Acquiring broadband echo data using a broadband imaging device, and extracting single-frequency echo data from the broadband echo data;

[0016] Imaging the broadband echo data and the single-frequency echo data respectively to obtain a broadband imaging focusing result and a single-frequency imaging defocusing result;

[0017] Converting the broadband imaging focusing result into a maximum projection result as a training label;

[0018] Obtaining the amplitude value of the single-frequency imaging defocus result as training data;

[0019] Pre-training the pre-constructed spatial convolutional neural network using the training labels and the training data, performing supervised training with mean square error as loss, and obtaining a trained spatial convolutional neural network;

[0020] The single-frequency imaging defocus result is input into the trained spatial convolutional neural network for training to obtain the network coding result.

[0021] Optionally, the solution formula for the network coding result is:

[0022] x c =F θ {PSM{s(x′,y′,k0)}}

[0023] Among them, x c is the network coding result, F θ {·} is the trained spatial convolutional neural network, PSM{·} is the near-field imaging method, and s(x′, y′, k0) is the single-frequency original echo data with a spatial wave number of k0 received by the planar array transceiver element at the coordinate (x′, y′).

[0024] Optionally, the solution formula for the diffusion model prediction result is:

[0025]

[0026] Among them, x0(x1,x c ,1) is the prediction result of the diffusion model, x1 is the input of the preset diffusion model at time step 1, β1 is the time-correlated noise increase hyperparameter when the time step is 1, α1, is the hyperparameter of the conditional diffusion model when the time step is 1, ∈ θ (x1,x c ,1) is the conditional noise predictor in the conditional diffusion model when the time step is 1.

[0027] The second aspect of the present invention provides a generative single-frequency millimeter-wave self-focusing near-field imaging device based on a diffusion model, including: an acquisition module for acquiring single-frequency original echo data using radar equipment. An imaging module for imaging the single-frequency original echo data to obtain a single-frequency imaging defocus result. An input module for inputting the single-frequency imaging defocus result into a pre-constructed spatial convolutional neural network to obtain a network coding result. An embedding module for embedding the network coding result into a pre-trained noise reduction diffusion model to obtain a conditional diffusion model. A prediction module for using the conditional diffusion model to gradually reconstruct the residual value between the network coding result and the preset ideal broadband imaging result to obtain a diffusion model prediction result, and adding the diffusion model prediction result to the network coding result to obtain the final single-frequency self-focusing imaging result.

[0028] An embodiment of the third aspect of the present invention provides an electronic device, comprising: a memory, a processor, and a computer program stored on the memory and runnable on the processor, wherein the processor executes the program to implement the generative single-frequency millimeter-wave self-focusing near-field imaging method based on the diffusion model as described in the above embodiment.

[0029] A fourth aspect of the present invention provides a computer program product. When the computer program / instructions are executed by a processor, the computer program / instructions implement the above-mentioned generative single-frequency millimeter-wave self-focusing near-field imaging method based on the diffusion model.

[0030] A fifth aspect of the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the above-mentioned generative single-frequency millimeter-wave self-focusing near-field imaging method based on a diffusion model.

[0031] The generative single-frequency millimeter-wave self-focusing near-field imaging method based on the diffusion model proposed in the embodiment of the present invention can reconstruct high-quality image results by self-focusing under the condition of using only single-frequency millimeter-wave echo data; the echo data is converted into the imaging domain by using the traditional near-field imaging method, and then the focal plane selection and target position estimation process are replaced by a neural network with strong fitting ability to realize self-focusing imaging; a spatial feature extraction neural network using three-dimensional convolution is designed, and the three-dimensional convolution is combined with the feature extraction structure so that the network has four dimensions of image length, width, distance, and channel, which effectively extracts the spatial structure existing in the three-dimensional defocused image and greatly reduces the fitting difficulty of the neural network; combining the advantages of the generative model, a single-frequency millimeter-wave image reconstruction framework based on the conditional diffusion model is proposed, and the feature map extracted by the spatial convolution network in the defocused image is used as a condition to guide the iterative process of high-quality image restoration.

[0032] Additional aspects and advantages of the present invention will be set forth in part in the description which follows and, in part, will be obvious from the description which follows, or may be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0034] Figure 1 A flow chart of a generative single-frequency millimeter-wave self-focusing near-field imaging method based on a diffusion model provided by an embodiment of the present invention;

[0035] Figure 2 A schematic diagram illustrating a specific implementation of a generative single-frequency millimeter-wave self-focusing near-field imaging method based on a diffusion model provided by an embodiment of the present invention;

[0036] Figure 3 A schematic diagram of the structure of a pre-built spatial convolutional neural network provided by an embodiment of the present invention;

[0037] Figure 4 Schematic diagrams comparing the imaging effects of the front face, front left arm, and front left hand of a human body using a conventional imaging method and an imaging method of the present invention, respectively, provided in an embodiment of the present invention, wherein (a1), (a2), (a3), and (a4) are all conventional imaging effects, and (b1), (b2), (b3), and (b4) are all imaging effects of the present invention;

[0038] Figure 5 A schematic block diagram of a generative single-frequency millimeter-wave self-focusing near-field imaging device based on a diffusion model provided by an embodiment of the present invention;

[0039] Figure 6 This is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0040] The following describes embodiments of the present invention in detail, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and are not to be construed as limiting the present invention.

[0041] The following describes a generative single-frequency millimeter wave self-focusing near-field imaging method based on a diffusion model according to an embodiment of the present invention with reference to the accompanying drawings. In response to the problems mentioned in the background technology center above, such as the inability of traditional single-frequency millimeter wave imaging methods to generate high-quality focused images and the insufficient imaging capability of single-frequency imaging methods based on self-focusing in complex object scenes, the present invention provides a generative single-frequency millimeter wave self-focusing near-field imaging method based on a diffusion model. In this method, the spatial structure of the traditional near-field imaging result is extracted by a spatial convolutional neural network, and the extracted feature map is used as a condition to guide the diffusion model generation process, and finally the reconstruction process from single-frequency echo data to a clear image is completed. Thus, the problem of the inability of traditional single-frequency millimeter wave imaging methods to generate high-quality focused images and the insufficient imaging capability of single-frequency imaging methods based on self-focusing in complex object scenes is solved.

[0042] In order to facilitate those skilled in the art to understand the generative single-frequency millimeter-wave self-focusing near-field imaging method based on the diffusion model of the present application, the parameter symbols involved in the present invention are explained through the following table.

[0043]

[0044]

[0045] Specifically, Figure 1 A schematic flow chart of a generative single-frequency millimeter-wave self-focusing near-field imaging method based on a diffusion model provided by an embodiment of the present invention.

[0046] like Figure 1 As shown, the generative single-frequency millimeter-wave self-focusing near-field imaging method based on the diffusion model includes the following steps:

[0047] In step S101 , single-frequency raw echo data is acquired using radar equipment.

[0048] Specifically, the preset millimeter-wave body scanner is run to correct the amplitude and delay inconsistencies between signals from different channels, and the single-frequency original echo data s(x′, y′, k0) corresponding to the spatial wave number k0 is obtained.

[0049] In step S102 , the single-frequency raw echo data is imaged to obtain a single-frequency imaging defocus result.

[0050] In some embodiments, imaging single-frequency raw echo data to obtain a single-frequency imaging defocus result includes:

[0051] Based on the phase shift method in the millimeter-wave near-field imaging method, the single-frequency raw echo data is imaged on several equally spaced reference planes in a pre-selected imaging space to obtain the single-frequency imaging defocus result.

[0052] Specifically, the phase shift PSM method in the millimeter wave near-field imaging method is used to obtain the On the plane represented by , the single-frequency original echo data s(x′, y′, k0) on the extracted wave number sampling k0 is imaged to obtain the single-frequency imaging defocus result σ s (x,y,z), which is represented as follows:

[0053] The solution formula for the defocus result of single-frequency imaging is:

[0054]

[0055] in, is the inverse transform of the two-dimensional Fourier transform, FT 2D is the two-dimensional Fourier transform, e is the natural logarithm, j is the imaginary unit, k z′ is k in the spatial wave number domain x′ With k y′ The spherical function of z is a plane represented by multiple reference distances, σ s (x, y, z) is the single-frequency imaging defocus result of the scattering point coordinates, and s(x′, y′, k0) is the single-frequency original echo data with a spatial wave number of k0 received by the planar array transceiver element at the coordinate (x′, y′).

[0056] In step S103, the single-frequency imaging defocus result is input into a pre-built spatial convolutional neural network to obtain a network coding result.

[0057] In some embodiments, the single-frequency imaging defocus result is input into a pre-built spatial convolutional neural network to obtain a network coding result, including:

[0058] During the training process, broadband imaging equipment is used to collect broadband echo data s′(x′, y′, k), and single-frequency echo data s′(x′, y′, k0) is extracted from the broadband echo data;

[0059] The broadband echo data and the single frequency echo data are imaged respectively to obtain the broadband imaging focusing result σ′ f (x, y, z) and single-frequency imaging defocus result σ′ s (x,y,z);

[0060] Convert the broadband imaging focusing result into the maximum projection result as the training label x s ;

[0061] Get the amplitude value of the single-frequency imaging defocus result as training data x f ;

[0062] The pre-built spatial convolutional neural network is pre-trained using training labels and training data, and supervised training is performed with mean square error as loss to obtain the trained spatial convolutional neural network F. θ ;

[0063] The single-frequency imaging defocus result is input into the trained spatial convolutional neural network for training to obtain the network coding result x c .

[0064] Specifically, if Figure 2 and 3 As shown in Figure 1, during the training process, broadband imaging equipment is used to collect broadband echo data s′(x′, y′, k), and single-frequency echo data s′(x′, y′, k0) corresponding to the spatial wavenumber in the broadband echo data is extracted to form focusing results and defocusing results respectively. The solution formula for the broadband imaging focusing result is:

[0065]

[0066] Among them, σ′ f (x, y, z) is the broadband imaging focusing result of the scattering point coordinates, PSM{·} is the near-field imaging method, s′(x′, y′, k) is the original echo data of k spatial wave numbers received by the coordinates of the planar array transceiver element, is the inverse transform of the two-dimensional Fourier transform, FT 2D is the two-dimensional Fourier transform, e is the natural logarithm, j is the imaginary unit, k z′ is k in the spatial wave number domain x′ With k y′ The spherical function of z is a plane represented by multiple reference distances.

[0067] In order to facilitate the calculation without losing the spatial characteristics of the input three-dimensional defocused image, the amplitude value of the complex single-frequency imaging defocused result is retained to establish the training data x of the spatial convolutional network. s , and while simplifying the input data, the maximum projection result of the broadband imaging focusing result is used as the training label x f . Network training data x s With training data x s It is expressed as follows, where MIP{·} represents the maximum projection operation for converting a three-dimensional image to a two-dimensional image:

[0068] x s =|σ′ s (x,y,z)|=PSM{s′(x′,y′,k0)}

[0069] x f =MIP{σ′ f(x,y,z)}

[0070] When using input and label pairs (x s ,x f ) After the spatial convolutional network is supervised and trained with mean square error as loss, the single frequency echo data s(x′, y′, k0) that needs to be self-focused is imaged by the PSM method and input into the pre-trained network to obtain a two-dimensional feature map x c (i.e., network coding result), is expressed as follows:

[0071] x c =F θ {PSM{s(x′,y′,k0)}}

[0072] Among them, x c is the network coding result, F θ {·} is the trained spatial convolutional neural network, PSM{·} is the near-field imaging method, and s(x′, y′, k0) is the single-frequency original echo data with a spatial wave number of k0 received by the planar array transceiver element at the coordinate (x′, y′).

[0073] It should be noted that each single-frequency input has a unique corresponding two-dimensional feature map, which can be used repeatedly in subsequent tasks once generated.

[0074] In step S104, the network coding result is embedded into the preset diffusion model as conditional information to obtain a conditional diffusion model.

[0075] Specifically, if Figure 3 As shown, the two-dimensional feature map x obtained by spatial convolutional network encoding c The variables transferred between each time step of the preset diffusion model remain the same in terms of spatial size and number of channels. Therefore, we can simply use the matrix element-by-element addition method to embed the network coding results as conditions into the preset diffusion model to achieve fusion, and obtain the conditional diffusion model, which is expressed as follows:

[0076]

[0077] in, Represents the element-by-element addition of the matrix, x t is the input of the preset diffusion model at time step t. TIN{·} represents the preprocessing of the input, which consists of a two-dimensional convolutional layer with fixed parameters and a Mish activation function.

[0078] In addition, the conditional diffusion model also accepts the specific number of time steps at each time step as the system's inherent information input. Referring to the Transformer network structure, the sinusoidal position encoding SIN{·} is used to encode the independent specific time step values ​​into a matrix, and the matrix addition method is also used to embed the time code:

[0079]

[0080] The network coding and time step coding results simultaneously provide the conditional information required by the diffusion model.

[0081] In step S105, the conditional diffusion model is used to gradually reconstruct the residual value between the network coding result and the preset ideal broadband imaging result to obtain the diffusion model prediction result, and the diffusion model prediction result is added to the network coding result to obtain the final single-frequency self-focusing imaging result.

[0082] Specifically, the core and trainable part of the conditional diffusion model is the conditional noise predictor ∈ θ (x t ,x c ,t), the loss function used by the predictor during training As shown below:

[0083]

[0084] in, represents the expectation of the calculation under the current input conditions, ||·|| 2 Represents the two-norm of the calculation matrix, ∈ is the standard Gaussian noise sample added at the current time step.

[0085] After completing the embedding representation in step S104, the residual value between the encoding result and the broadband imaging result is gradually reconstructed. In the pre-trained diffusion model with a total time step of T, the number of time steps and conditional information are combined to predict the amount of noise that needs to be subtracted from the output of the current time step through the pre-trained noise predictor, and the residual result x of each time step is sequentially predicted. T ,…,x0. The prediction process for each time step is expressed as follows:

[0086]

[0087] For the last time step closest to the clear image, the prediction result does not need to add additional Gaussian noise, which is expressed as follows:

[0088]

[0089] Among them, x0(x1,x c ,1) is the prediction result of the diffusion model, x1 is the input of the preset diffusion model at time step 1, β1 is the time-correlated noise increase hyperparameter when the time step is 1, which needs to be manually defined before training or prediction, α1, is the hyperparameter of the conditional diffusion model when the time step is 1, α t =1-β t 、 is a hyperparameter derived parameter that controls the mixing ratio of the prediction noise and the current time step input. z is a sampling result of the standard Gaussian noise step, ∈ θ (x1,x c ,1) is the conditional noise predictor in the conditional diffusion model when the time step is 1.

[0090] Specifically, if Figure 3 As shown, due to the adoption of residual prediction strategy to accelerate the convergence of network training, the network prediction result is a high-quality image and the network coding result x c After obtaining the result x0 output by the network after T time steps, it is also necessary to compare it with the network coding result x c Add element by element to get the final high-quality image result x h (i.e. the final imaging result):

[0091]

[0092] It should be noted that this is the last step in the network inference process and can be omitted during the network training process.

[0093] Therefore, if Figure 4 As shown in the figure, the imaging effects of the front of the human body, the front left arm, and the front left hand are respectively obtained by using the traditional near-field imaging method and the imaging method of the present invention. It can be seen that the generative single-frequency millimeter-wave self-focusing near-field imaging method based on the diffusion model proposed in the embodiment of the present invention can easily cope with objects with complex surfaces or spatial structures such as the human body. While reducing the fitting difficulty of the neural network, it can reconstruct high-quality image results that are almost the same as those of traditional near-field imaging through self-focusing using only single-frequency millimeter-wave echo data.

[0094] In summary, the generative single-frequency millimeter-wave self-focusing near-field imaging method based on the diffusion model proposed in the embodiment of the present invention has the following beneficial effects:

[0095] (1) Unlike common neural network methods that directly map input from the echo data domain to the imaging domain, the embodiments of the present invention use traditional millimeter-wave near-field imaging methods to reconstruct single-frequency raw echo data into a three-dimensional defocused image, reducing the difficulty of neural network fitting. Furthermore, the three-dimensional convolution is used to extract the spatial structure in the defocused image, and these spatial structures are used as input conditions into the diffusion model to iteratively reconstruct a high-quality millimeter-wave image.

[0096] (2) A spatial feature extraction network using three-dimensional convolution is designed. This network takes into account the spatial structure of the target point spread function in the three-dimensional defocused image. By replacing the original two-dimensional convolution in the feature extraction network with three-dimensional convolution, the spatial structural features in the three-dimensional defocused image can be effectively extracted and the extracted features are mapped into a feature map with smaller dimensions, reducing the number of parameters in the overall network.

[0097] (3) To address the problems of insufficient fitting capability of a single neural network and difficulty in selecting a loss function, an embodiment of the present invention embeds a three-dimensional spatial feature extraction network as a conditional encoder into a conditional diffusion model, guiding the iterative reconstruction process of the diffusion model at multiple time steps, and ultimately recovering a high-quality focused image from single-frequency echo data.

[0098] Next, a generative single-frequency millimeter-wave self-focusing near-field imaging device based on a diffusion model proposed in an embodiment of the present invention will be described with reference to the accompanying drawings.

[0099] Figure 5 It is a block diagram of a generative single-frequency millimeter-wave self-focusing near-field imaging device based on a diffusion model according to an embodiment of the present invention.

[0100] like Figure 5 As shown, the generative single-frequency millimeter-wave self-focusing near-field imaging device 50 based on the diffusion model includes: an acquisition module 501, an imaging module 502, an input module 503, an embedding module 504 and a prediction module 505.

[0101] Among them, the acquisition module 501 is used to obtain single-frequency original echo data using radar equipment. The imaging module 502 is used to image the single-frequency original echo data to obtain a single-frequency imaging defocus result. The training module 503 is used to input the single-frequency imaging defocus result into a pre-constructed spatial convolutional neural network to obtain a network coding result. The embedding module 504 is used to embed the network coding result into a pre-trained noise reduction diffusion model to obtain a conditional diffusion model. The prediction module 505 is used to use the conditional diffusion model to gradually reconstruct the residual value between the network coding result and the preset ideal broadband imaging result to obtain the diffusion model prediction result, and add the diffusion model prediction result to the network coding result to obtain the final single-frequency self-focusing imaging result.

[0102] In some embodiments, imaging module 502 includes:

[0103] Based on the phase shift method in the millimeter-wave near-field imaging method, the single-frequency raw echo data is imaged on several equally spaced reference planes in a pre-selected imaging space to obtain the single-frequency imaging defocus result.

[0104] Among them, the solution formula for the single-frequency imaging defocus result is:

[0105]

[0106] in, is the inverse transform of the two-dimensional Fourier transform, FT 2D is the two-dimensional Fourier transform, e is the natural logarithm, j is the imaginary unit, k z′ is k in the spatial wave number domain x′ With k y′ The spherical function, z is the plane represented by multiple reference distances, σ s (x, y, z) is the single-frequency imaging defocus result of the scattering point coordinates, and s(x′, y′, k0) is the single-frequency original echo data with a spatial wave number of k0 received by the planar array transceiver element at the coordinate (x′, y′).

[0107] In some embodiments, the input module 503 includes:

[0108] The single-frequency imaging defocus results are input into the pre-built spatial convolutional neural network for training to obtain network coding results, including:

[0109] Using a broadband imaging device to collect broadband echo data, and extracting single frequency echo data from the broadband echo data;

[0110] The broadband echo data and the single-frequency echo data are imaged respectively to obtain the broadband imaging focusing result and the single-frequency imaging defocusing result;

[0111] Convert the broadband imaging focusing results into maximum projection results to serve as training labels;

[0112] Obtain the amplitude value of the single-frequency imaging defocus result as training data;

[0113] The pre-built spatial convolutional neural network is pre-trained using training labels and training data, and supervised training is performed using mean square error as loss to obtain the trained spatial convolutional neural network.

[0114] The single-frequency imaging defocus results are input into the trained spatial convolutional neural network for training to obtain the network coding results.

[0115] In some embodiments, the network coding result is solved by:

[0116] x c =F θ {PSM{s(x′,y′,k0)}}

[0117] Among them, x c is the network coding result, F θ{·} is the trained spatial convolutional neural network, PSM{·} is the near-field imaging method, and s(x′, y′, k0) is the single-frequency original echo data with a spatial wave number of k0 received by the planar array transceiver element at the coordinate (x′, y′).

[0118] In some embodiments, the solution formula for the diffusion model prediction result is:

[0119]

[0120] Among them, x0(x1,x c ,1) is the prediction result of the diffusion model, x1 is the input of the preset diffusion model at time step 1, β1 is the time-correlated noise increase hyperparameter when the time step is 1, α1, is the hyperparameter of the conditional diffusion model when the time step is 1, ∈ θ (x1,x c ,1) is the conditional noise predictor in the conditional diffusion model when the time step is 1.

[0121] It should be noted that the above explanation of the embodiment of the generative single-frequency millimeter-wave self-focusing near-field imaging method based on the diffusion model is also applicable to the generative single-frequency millimeter-wave self-focusing near-field imaging device based on the diffusion model of this embodiment, and will not be repeated here.

[0122] The generative single-frequency millimeter-wave self-focusing near-field imaging device based on the diffusion model proposed in an embodiment of the present invention has the following beneficial effects:

[0123] (1) Unlike common neural network methods that directly map input from the echo data domain to the imaging domain, the embodiments of the present invention use traditional millimeter-wave near-field imaging methods to reconstruct single-frequency raw echo data into a three-dimensional defocused image, reducing the difficulty of neural network fitting. Furthermore, the three-dimensional convolution is used to extract the spatial structure in the defocused image, and these spatial structures are used as input conditions into the diffusion model to iteratively reconstruct a high-quality millimeter-wave image.

[0124] (2) A spatial feature extraction network using three-dimensional convolution is designed. This network takes into account the spatial structure of the target point spread function in the three-dimensional defocused image. By replacing the original two-dimensional convolution in the feature extraction network with three-dimensional convolution, the spatial structural features in the three-dimensional defocused image can be effectively extracted and the extracted features are mapped into a feature map with smaller dimensions, reducing the number of parameters in the overall network.

[0125] (3) To address the problems of insufficient fitting capability of a single neural network and difficulty in selecting a loss function, an embodiment of the present invention embeds a three-dimensional spatial feature extraction network as a conditional encoder into a conditional diffusion model, guiding the iterative reconstruction process of the diffusion model at multiple time steps, and ultimately recovering a high-quality focused image from single-frequency echo data.

[0126] Figure 6 This is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. The electronic device may include:

[0127] A memory 601 , a processor 602 , and a computer program stored in the memory 601 and executable on the processor 602 .

[0128] When the processor 602 executes the program, the generative single-frequency millimeter-wave self-focusing near-field imaging method based on the diffusion model provided in the above embodiment is implemented.

[0129] Furthermore, the electronic device further includes:

[0130] The communication interface 603 is used for communication between the memory 601 and the processor 602 .

[0131] The memory 601 is used to store computer programs that can be run on the processor 602 .

[0132] The memory 601 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0133] If the memory 601, processor 602, and communication interface 603 are implemented independently, the communication interface 603, memory 601, and processor 602 can be connected to each other via a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 6 Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0134] Optionally, in a specific implementation, if the memory 601, the processor 602 and the communication interface 603 are integrated on a chip, the memory 601, the processor 602 and the communication interface 603 can communicate with each other through an internal interface.

[0135] The processor 602 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention.

[0136] An embodiment of the present invention further provides a computer program product, which, when executed by a processor, implements the above-mentioned generative single-frequency millimeter-wave self-focusing near-field imaging method based on a diffusion model.

[0137] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned generative single-frequency millimeter-wave self-focusing near-field imaging method based on a diffusion model.

[0138] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and the features of different embodiments or examples without contradiction.

[0139] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of technical features indicated. Thus, a feature specified as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "N" means at least two, such as two, three, etc., unless otherwise specifically defined.

[0140] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or N executable instructions for implementing a custom logical function or step of a process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may be performed out of the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present invention pertain.

[0141] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or N wires (electronic devices), a portable computer disk cartridge (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and programmable read-only memory (EPROM or flash memory), fiber optic devices, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program can be obtained electronically by optically scanning the paper or other medium and then editing, interpreting or processing it in other suitable ways as necessary, and then storing it in a computer memory.

[0142] It should be understood that various parts of the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiment, the N steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. If implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used: a discrete logic circuit having logic gate circuits for implementing logic functions on data signals, an application-specific integrated circuit having suitable combinational logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0143] Those skilled in the art will understand that all or part of the steps in the method of the above embodiment can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0144] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing module, or each unit may exist physically separately, or two or more units may be integrated into a single module. The aforementioned integrated modules may be implemented in the form of hardware or in the form of software functional modules. If the integrated modules are implemented in the form of software functional modules and sold or used as independent products, they may also be stored in a computer-readable storage medium.

[0145] The storage medium mentioned above may be a read-only memory, a magnetic disk, or an optical disk, etc. Although the embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and are not to be construed as limiting the present invention. Persons skilled in the art may make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention.

Claims

1. A generative single-frequency millimeter-wave self-focusing near-field imaging method based on a diffusion model, characterized in that: The following steps are involved: Using radar equipment to obtain single-frequency raw echo data; Imaging the single-frequency raw echo data to obtain a single-frequency imaging defocus result; Inputting the single-frequency imaging defocus result into a pre-built spatial convolutional neural network to obtain a network coding result; Embedding the network coding result into a pre-trained denoising diffusion model to obtain a conditional diffusion model; The conditional diffusion model is used to gradually reconstruct the residual value between the network coding result and the preset ideal broadband imaging result to obtain the diffusion model prediction result, and the diffusion model prediction result is added to the network coding result to obtain the final single-frequency self-focusing imaging result.

2. The generative single-frequency millimeter-wave self-focusing near-field imaging method based on a diffusion model according to claim 1, characterized in that: Imaging the single-frequency raw echo data to obtain a single-frequency imaging defocus result includes: Based on the phase shift method in the millimeter wave near-field imaging method, the single-frequency raw echo data is imaged on several equally spaced reference planes in a pre-selected imaging space to obtain the single-frequency imaging defocus result.

3. The generative single-frequency millimeter-wave self-focusing near-field imaging method based on a diffusion model according to claim 2, characterized in that: The solution formula for the single-frequency imaging defocus result is: in, is the inverse 2D Fourier transform, is the two-dimensional Fourier transform, is the natural logarithm, is the imaginary unit, In the spatial wavenumber domain and The spherical function, is a plane represented by multiple reference distances, is the defocus result of single-frequency imaging of the scattering point coordinates, is the near-field imaging method, For coordinates The spatial wave number received by the plane array transceiver element is Single frequency raw echo data.

4. The generative single-frequency millimeter-wave self-focusing near-field imaging method based on a diffusion model according to claim 1, characterized in that: The step of inputting the single-frequency imaging defocus result into a pre-built spatial convolutional neural network to obtain a network coding result comprises: Acquiring broadband echo data using a broadband imaging device, and extracting single-frequency echo data from the broadband echo data; Imaging the broadband echo data and the single-frequency echo data respectively to obtain a broadband imaging focusing result and a single-frequency imaging defocusing result; Converting the broadband imaging focusing result into a maximum projection result as a training label; Obtaining the amplitude value of the single-frequency imaging defocus result as training data; Pre-training the pre-constructed spatial convolutional neural network using the training labels and the training data, performing supervised training with mean square error as loss, and obtaining a trained spatial convolutional neural network; The single-frequency imaging defocus result is input into the trained spatial convolutional neural network for training to obtain the network coding result.

5. The generative single-frequency millimeter-wave self-focusing near-field imaging method based on a diffusion model according to claim 4, characterized in that: The solution formula for the network coding result is: in, is the network coding result, is the trained spatial convolutional neural network, is the near-field imaging method, For coordinates The spatial wave number received by the plane array transceiver element is Single frequency raw echo data.

6. The generative single-frequency millimeter-wave self-focusing near-field imaging method based on a diffusion model according to claim 1, characterized in that: The solution formula for the diffusion model prediction result is: in, is the diffusion model prediction result, For the preset diffusion model at time step When input, Add hyperparameters for time-correlated noise at time step 1, 、 is the conditional diffusion model hyperparameter when the time step is 1, is the conditional noise predictor in the conditional diffusion model at time step 1.

7. A generative single-frequency millimeter-wave self-focusing near-field imaging device based on a diffusion model, characterized in that: include: An acquisition module, used to acquire single-frequency raw echo data using radar equipment; An imaging module, configured to image the single-frequency raw echo data to obtain a single-frequency imaging defocus result; An input module, configured to input the single-frequency imaging defocus result into a pre-built spatial convolutional neural network to obtain a network coding result; An embedding module, configured to embed the network coding result into a pre-trained denoising diffusion model to obtain a conditional diffusion model; A prediction module is used to use the conditional diffusion model to gradually reconstruct the residual value between the network coding result and the preset ideal broadband imaging result to obtain a diffusion model prediction result, and add the diffusion model prediction result to the network coding result to obtain a final single-frequency self-focusing imaging result.

8. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the generative single-frequency millimeter-wave self-focusing near-field imaging method based on a diffusion model as described in any one of claims 1 to 6.

9. A computer program product, characterized in that When the computer program / instruction is executed by a processor, the generative single-frequency millimeter-wave self-focusing near-field imaging method based on the diffusion model described in any one of claims 1 to 6 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the generative single-frequency millimeter-wave self-focusing near-field imaging method based on a diffusion model as described in any one of claims 1 to 6.

Images