Range-doppler domain reconstruction method, apparatus, device and medium

Abstract

The application provides a range Doppler domain reconstruction method, device, equipment and medium, and belongs to the technical field of radars.The method comprises the following steps: performing pulse emission based on a predetermined pulse emission time, and collecting a non-uniform echo signal; inputting the non-uniform echo signal into a pre-trained range Doppler domain (RD) reconstruction network to obtain an RD reconstruction result; and the training process of the RD reconstruction network comprises the following steps: generating a non-uniform echo signal sample according to a pulse emission time sample, obtaining a reconstruction image according to the non-uniform echo signal sample and a preset reconstruction network, constructing a loss function according to the pulse emission time sample and the reconstruction image, and adjusting the respective parameters of the pulse emission time sample and the reconstruction network according to the loss function.The application combines the pulse emission time and the RD reconstruction technology, so that the parameters of the RD reconstruction technology can fully combine the characteristics of the non-uniform pulse emission mode, the maximum unambiguous detection range is expanded, and the RD reconstruction quality is improved.

Description

Technical Field

[0001] The present invention relates to the field of radar technology, and in particular to a range Doppler domain reconstruction method, device, equipment and medium. Background Art

[0002] Pulse Doppler (PD) radar uses the Doppler effect to measure the radial velocity of an object in the direction of the radar beam. Range Doppler (RD) reconstruction is an important step in extracting target range and velocity, and can provide support for meteorological observation, track tracking, battlefield reconnaissance, and other applications.

[0003] In PD radar, there are a set of inherent constraints between the maximum unambiguous detection range and the maximum unambiguous Doppler. Many researchers have achieved the extension of the maximum unambiguous detection range by increasing the minimum time interval between adjacent pulses. However, the existing technology has not specifically optimized the RD reconstruction algorithm and cannot fully combat aliasing, which to some extent reduces the RD reconstruction performance and accuracy. Summary of the Invention

[0004] The present invention provides a range Doppler domain reconstruction method, device, equipment and medium, which solve the defect that the existing technology cannot fully resist aliasing, thereby reducing the RD reconstruction performance and accuracy.

[0005] The present invention provides a range Doppler domain reconstruction method, comprising:

[0006] Performing pulse transmission based on a predetermined pulse transmission time to collect non-uniform echo signals;

[0007] Inputting the non-uniform echo signal into a pre-trained range-Doppler domain RD reconstruction network to obtain an RD reconstruction result;

[0008] Among them, the training process of the RD reconstruction network includes generating non-uniform echo signal samples based on pulse emission time samples, obtaining a reconstructed image based on the non-uniform echo signal samples and a preset reconstruction network, constructing a loss function based on the pulse emission time samples and the reconstructed image, adjusting the respective parameters of the pulse emission time samples and the reconstruction network according to the loss function, and repeating the training steps until the preset convergence condition is reached.

[0009] As an embodiment, obtaining a reconstructed image according to the non-uniform echo signal sample and a preset reconstruction network includes:

[0010] performing range-matched filtering on the non-uniform echo signal samples;

[0011] Based on the reconstruction network, linear reconstruction and nonlinear filtering are performed for a preset number of iterations on the filtered non-uniform echo signal samples to obtain the reconstructed image.

[0012] As an embodiment, performing linear reconstruction and nonlinear filtering for a preset number of iterations on the filtered non-uniform echo signal samples based on the reconstruction network to obtain the reconstructed image includes:

[0013] Use the zero matrix as the initialization to reconstruct the image;

[0014] Determine a non-uniform inverse Fourier transform matrix and a non-uniform Fourier transform matrix according to the filtered non-uniform echo signal samples;

[0015] Inputting the initialized reconstructed image, the non-uniform inverse Fourier transform matrix and the non-uniform Fourier transform matrix into the reconstruction network to obtain the reconstructed image output by the reconstruction network;

[0016] The reconstruction network is used to determine the linear reconstruction result of the current iteration during each iteration based on the non-uniform inverse Fourier transform matrix, the non-uniform Fourier transform matrix, the filtered non-uniform echo signal samples, and the initialized reconstructed image / reconstruction result of the previous iteration, perform nonlinear filtering on the linear reconstruction result of the current iteration to obtain the reconstruction result of the current iteration, and repeat the preset number of iterations to obtain the reconstructed image.

[0017] As an embodiment, performing nonlinear filtering on the linear reconstruction result of the current iteration to obtain the reconstruction result of the current iteration includes:

[0018] The linear reconstruction result of the current iteration is nonlinearly filtered based on the soft threshold iterative function to obtain the reconstruction result of the current iteration.

[0019] As an embodiment, constructing a loss function based on the pulse emission time samples and the reconstructed image includes:

[0020] The loss function is constructed according to the gap between the reconstructed image and the real image and the minimum value constraint of the samples at the pulse emission moment.

[0021] As an embodiment, the loss function is expressed as follows:

[0022] ;

[0023] in, is the loss function, For the n The reconstructed image corresponding to the sample at the time of pulse emission, N is the total number of samples, For then The real image corresponding to the sample at the moment of pulse emission, is the first sample vector at the moment of pulse emission m numerical values, M is the total number of sample vector values ​​at the time of pulse emission.

[0024] As an embodiment, adjusting the parameters of the pulse emission time sample and the reconstruction network according to the loss function includes:

[0025] generating a set of mask sequences corresponding to the pulse emission time samples based on a random parameter freezing strategy;

[0026] Multiplying the gradient of the loss function with respect to the pulse emission time sample by the mask sequence to achieve random zeroing;

[0027] According to the gradient of the loss function after random zeroing of the pulse emission time sample, the random part parameters of the pulse emission time sample and the parameters of the reconstruction network are updated.

[0028] The present invention also provides a range Doppler domain reconstruction device, comprising:

[0029] a training module, configured to generate non-uniform echo signal samples based on pulse emission time samples, obtain a reconstructed image based on the non-uniform echo signal samples and a preset reconstruction network, construct a loss function based on the pulse emission time samples and the reconstructed image, adjust parameters of the pulse emission time samples and the reconstruction network based on the loss function, and repeat the training steps until a preset convergence condition is reached;

[0030] An acquisition module, configured to perform pulse emission based on a predetermined pulse emission time and acquire a non-uniform echo signal;

[0031] The reconstruction module is used to input the non-uniform echo signal into a pre-trained range Doppler domain RD reconstruction network to obtain an RD reconstruction result.

[0032] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements any of the above-described range Doppler domain reconstruction methods when executing the computer program.

[0033] The present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the range-Doppler domain reconstruction method described above is implemented.

[0034] The present invention further provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements any one of the above-mentioned range-Doppler domain reconstruction methods.

[0035] The range Doppler domain reconstruction method, apparatus, device, and medium provided by the present invention perform pulse transmission based on a predetermined pulse transmission time to collect non-uniform echo signals; the non-uniform echo signals are input into a pre-trained range Doppler domain RD reconstruction network to obtain RD reconstruction results; wherein the training process of the RD reconstruction network includes generating non-uniform echo signal samples based on pulse transmission time samples, obtaining a reconstructed image based on the non-uniform echo signal samples and a preset reconstruction network, constructing a loss function based on the pulse transmission time samples and the reconstructed image, adjusting the parameters of the pulse transmission time samples and the reconstruction network based on the loss function, and repeating the training steps until a preset convergence condition is reached. The present invention combines the pulse transmission time with RD reconstruction technology, so that the parameters of the RD reconstruction technology can fully incorporate the characteristics of a specific non-uniform pulse transmission pattern, and perform targeted optimization of the RD reconstruction algorithm, which can fully combat aliasing and improve the RD reconstruction quality while achieving maximum unambiguous detection range extension. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction is given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0037] Figure 1 This is one of the flow charts of the range Doppler domain reconstruction method provided by the present invention.

[0038] Figure 2 This is the second flow chart of the range Doppler domain reconstruction method provided by the present invention.

[0039] Figure 3 It is a schematic diagram of the training process of the RD reconstruction network provided by the present invention.

[0040] Figure 4a This is a schematic diagram of the reconstruction effect of the existing range Doppler domain reconstruction method. Figure 4b It is a schematic diagram of the reconstruction effect of the range Doppler domain reconstruction method provided by the present invention.

[0041] Figure 5 It is a structural schematic diagram of the range Doppler domain reconstruction device provided by the present invention.

[0042] Figure 6It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0043] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0044] It should be noted that all actions of acquiring signals, information or data in the present invention are performed in compliance with the corresponding local data protection laws and policies and with authorization from the corresponding device owner.

[0045] The non-uniform pulse emission mode can, to a certain extent, avoid the spectrum aliasing caused by the decrease in pulse repetition frequency. However, it does not specifically optimize the RD domain reconstruction algorithm, resulting in the reconstruction algorithm being unable to fully utilize the anti-aliasing capability of the non-uniform emission mode, which in turn reduces the RD domain reconstruction performance and accuracy to a certain extent.

[0046] In order to overcome the problem of inability to fully remove spectral aliasing due to the complete decoupling of the existing PD radar RD reconstruction algorithm and the non-uniform emission pattern design, the present invention proposes a joint optimization strategy that combines a learnable pulse emission pattern with the RD reconstruction algorithm for joint data-driven optimization to obtain high-quality RD reconstruction results, which can improve the quality of RD reconstruction while achieving the maximum unambiguous detection range extension.

[0047] Figure 1 This is one of the flow charts of the range Doppler domain reconstruction method provided by the present invention. Figure 2 This is the second flow chart of the range Doppler domain reconstruction method provided by the present invention, as shown in FIG. Figure 1 and Figure 2 As shown, the present invention provides a range Doppler domain reconstruction method, including steps S100 to S200.

[0048] Step S100 involves performing pulse transmission based on a predetermined pulse transmission time and collecting non-uniform echo signals. The pulse transmission time is the optimal pulse transmission time determined during the RD reconstruction network training process. Based on this pulse transmission time, a pulse transmission sequence is determined. A pulse transmission sequence is a set of instantaneous pulse signals transmitted in a regular, sequential order. Non-uniform echo signals refer to the non-uniform pulse echo data obtained by the PD radar after pulse transmission and echo collection according to the pulse transmission time.

[0049] Step S200: inputting the non-uniform echo signal into a pre-trained range Doppler domain RD reconstruction network to obtain an RD reconstruction result.

[0050] Among them, the training process of the RD reconstruction network includes generating non-uniform echo signal samples based on pulse emission time samples, obtaining a reconstructed image based on the non-uniform echo signal samples and a preset reconstruction network, constructing a loss function based on the pulse emission time samples and the reconstructed image, adjusting the respective parameters of the pulse emission time samples and the reconstruction network according to the loss function, and repeating the training steps until the preset convergence condition is reached.

[0051] The repeated training step refers to returning to and executing the step of generating non-uniform echo signal samples according to the pulse emission time samples. After reaching the preset convergence condition, the pulse emission time samples are used as the optimal pulse emission time, and the reconstructed network is used as the RD reconstruction network.

[0052] The method provided by the present invention includes a training process and an application process. The training process refers to the training process of the RD reconstruction network to determine the optimal pulse transmission sequence and the matching RD reconstruction algorithm. The training refers to steps S100 and S200, in which the trained pulse transmission sequence is used to transmit pulses and collect echoes. After collecting non-uniform pulse echo data, the trained RD reconstruction network is used to obtain the final reconstruction result.

[0053] It can be understood that the present invention combines the pulse emission time and RD reconstruction technology, so that the parameters of the RD reconstruction technology can fully combine the characteristics of the specific non-uniform pulse emission mode, and perform targeted optimization of the RD reconstruction algorithm, which can fully resist aliasing and improve the RD reconstruction quality while achieving the maximum unambiguous detection distance extension.

[0054] Based on the above embodiment, as an optional embodiment, the generating of non-uniform echo signal samples according to pulse emission time samples includes the following steps.

[0055] Step S011 , substituting preset system parameters of the PD radar, preset simulation scenarios, and pulse emission time samples into an echo simulation model to obtain simulated non-uniform echo signal samples.

[0056] The pulse emission time sample includes fixed parameters and random parameters. In the embodiment of the present invention, the random parameter part of the pulse emission time sample is used as a learnable variable.

[0057] It is understandable that the present invention uses the random parameter part in the pulse emission time as a learnable variable, which can increase the randomness and robustness of the non-uniform sequence and improve the anti-aliasing performance.

[0058] Based on the above embodiment, as an optional embodiment, obtaining a reconstructed image according to the non-uniform echo signal samples and a preset reconstruction network includes the following steps.

[0059] Step S021: performing range-matched filtering on the non-uniform echo signal samples. Range-matched filtering is also called fast time-domain matched filtering.

[0060] Step S022 : performing linear reconstruction and nonlinear filtering for a preset number of iterations on the filtered non-uniform echo signal samples based on the reconstruction network to obtain the reconstructed image.

[0061] Optionally, performing linear reconstruction and nonlinear filtering for a preset number of iterations on the filtered non-uniform echo signal samples based on the reconstruction network to obtain the reconstructed image includes the following steps.

[0062] Step S0221: Using the zero matrix as an initialization to reconstruct the image.

[0063] Step S0222: Determine a non-uniform inverse Fourier transform matrix and a non-uniform Fourier transform matrix based on the filtered non-uniform echo signal samples. The non-uniform inverse Fourier transform matrix is ​​a slow-time domain non-uniform inverse Fourier transform matrix, and the non-uniform Fourier transform matrix is ​​a slow-time domain non-uniform Fourier transform matrix.

[0064] Step S0223: input the initialized reconstructed image, the non-uniform inverse Fourier transform matrix and the non-uniform Fourier transform matrix into the reconstruction network to obtain the reconstructed image output by the reconstruction network.

[0065] The reconstruction network is used to determine the linear reconstruction result of the current iteration during each iteration based on the non-uniform inverse Fourier transform matrix, the non-uniform Fourier transform matrix, the filtered non-uniform echo signal samples, and the initialized reconstructed image / reconstruction result of the previous iteration, perform nonlinear filtering on the linear reconstruction result of the current iteration to obtain the reconstruction result of the current iteration, and repeat the preset number of iterations to obtain the reconstructed image.

[0066] Optionally, performing nonlinear filtering on the linear reconstruction result of the current iteration to obtain the reconstruction result of the current iteration includes: performing nonlinear filtering on the linear reconstruction result of the current iteration based on a soft threshold iterative function to obtain the reconstruction result of the current iteration.

[0067] It can be understood that the present invention provides an expanded RD reconstruction algorithm based on the depth of approximate observation, which can greatly reduce the time complexity of the algorithm, and solves the problem that the existing RD reconstruction algorithm for achieving maximum unambiguous detection distance extension only designs a non-uniform pulse emission mode and simply concatenates the RD reconstruction algorithm based on compressed sensing to obtain the reconstruction result, without considering the spectrum aliasing caused by a specific emission mode for targeted design.

[0068] Based on the above embodiment, as an optional embodiment, constructing a loss function according to the pulse emission time samples and the reconstructed image includes the following steps.

[0069] Step S031 : constructing the loss function according to the gap between the reconstructed image and the real image and the minimum value constraint of the samples at the pulse emission moment.

[0070] Specifically, the expression of the loss function is as follows:

[0071] ;

[0072] in, is the loss function, For the n The reconstructed image corresponding to the sample at the time of pulse emission, N is the total number of samples, For the n The real image corresponding to the sample at the moment of pulse emission, is the mth value of the sample vector at the pulse emission time, and M is the total number of values ​​of the sample vector at the pulse emission time.

[0073] It can be understood that the present invention constructs a loss function through the pulse emission time samples and the reconstructed image, and determines a joint optimization target, so as to simultaneously optimize the pulse emission time and the learnable parameters in the RD reconstruction algorithm, obtain the optimal pulse emission time and the matching RD reconstruction algorithm, and improve the quality of RD reconstruction while achieving the maximum unambiguous detection distance extension.

[0074] Based on the above embodiment, as an optional embodiment, adjusting the parameters of the pulse emission time sample and the reconstruction network according to the loss function includes the following steps.

[0075] Step S041: Generate a set of mask sequences corresponding to the pulse emission time samples based on a random parameter freezing strategy. Each element of the mask sequence is a random variable that obeys a Bernoulli distribution.

[0076] Step S042: multiplying the gradient of the loss function with respect to the sample at the pulse emission moment by the mask sequence to achieve random zeroing.

[0077] Step S043 , updating the random part parameters of the pulse emission time samples and the parameters of the reconstruction network according to the gradient of the loss function after random zeroing of the pulse emission time samples.

[0078] It is understandable that the present invention introduces a random parameter freezing strategy during back propagation, by randomly setting some elements in the updated gradient of the parameters at the pulse emission moment to zero, so as to increase the randomness and robustness of the non-uniform sequence and improve the anti-aliasing performance.

[0079] Figure 3 Schematic diagram of the training process of the RD reconstruction network provided by the present invention, such as Figure 3 As shown, the training input parameters of the RD reconstruction network include the PD simulation scene X, which is , PD system parameters and the number of iterations (The present invention is set to 11).

[0080] The training process of the RD reconstruction network specifically includes the following steps:

[0081] Step 1: According to PD system parameters and simulated scene X to generate simulated non-uniform echo signal Y.

[0082] Step 2: Perform range-matched filtering on the echo signal Y:

[0083] ;

[0084] ;

[0085] in, is the intermediate result after distance matching filtering, is the distance matched filter function, is the distance sampling frequency, is the range frequency modulation, FFT is the Fourier transform, and IFFT is the inverse Fourier transform.

[0086] Step 3: Initialize RD reconstruction results is a zero matrix.

[0087] Step 4: The reconstruction network includes 11 reconstruction network units, each of which includes a linear module and a nonlinear module.

[0088] Linear module: Using the slow-time domain non-uniform inverse Fourier transform matrix Get the matrix after approximate distance matching filtering , calculate the approximate echo matrix and the true range after matched filtering The difference between them is then used to obtain the approximate reconstruction result of the residual according to the slow time domain non-uniform Fourier transform matrix, which is added to the imaging result of the previous round. On the top, we get the reconstruction result of the linear module, that is, .

[0089] Step 5: Nonlinear module: Use soft threshold iterative function to filter out noise, that is , is the soft threshold iterative function.

[0090] Step 6: Repeat steps 4 and 5 for a total of times, and obtain the final reconstructed image .

[0091] Step 7: Calculate the loss function: The loss function is mainly divided into two parts. The former is the main optimization target of the joint optimization, that is, the gap between the final RD reconstruction result and the label. The latter is the minimum value constraint for the pulse emission interval. The expression is as follows:

[0092] ;

[0093] in, is the loss function, For the n The reconstructed image corresponding to the sample at the time of pulse emission, N is the total number of samples, For the n The real image corresponding to the sample at the moment of pulse emission, is the mth value of the sample vector at the pulse emission time, and M is the total number of values ​​of the sample vector at the pulse emission time.

[0094] Step 8: Use the random parameter freezing strategy to randomly generate a set of mask sequences with the same length as the pulse emission time , where each element is a random variable that obeys the Bernoulli distribution. The mask sequence and the Loss function are combined to determine the pulse emission time. Multiply the gradient of , in order to achieve the purpose of random zeroing.

[0095] Step 9: Update the parameters according to the gradient and repeat steps 1-9 until convergence to obtain the final optimized pulse emission time and matching RD reconstruction algorithm.

[0096] Figure 4a This is a schematic diagram of the reconstruction effect of the existing range Doppler domain reconstruction method. Figure 4bThe figure is a schematic diagram of the reconstruction effect of the range Doppler domain reconstruction method provided by the present invention. The table below is a comparison table of the reconstruction result indicators of the present invention and the prior art. According to the figures and the table, it can be seen that the present invention greatly improves the reconstruction accuracy in the range Doppler domain.

[0097]

[0098] In summary, the present invention proposes a data-driven joint optimization method that combines a learnable pulse emission pattern with an RD reconstruction algorithm, with the final RD reconstruction result as the optimization target. Through joint optimization of the two, the parameters of the reconstruction algorithm are fully integrated with the characteristics of the specific non-uniform pulse emission pattern, achieving maximum unambiguous detection range extension while improving RD reconstruction quality. On the one hand, the random portion of the pulse emission pattern is used as a learnable variable, and a random parameter freezing strategy is introduced during backpropagation. By randomly setting a portion of the elements in the updated gradient of the pulse emission sequence parameters to zero, the randomness and robustness of the non-uniform sequence are increased, thereby improving anti-aliasing performance. On the other hand, the algorithm's time complexity can be greatly reduced, which is expected to enable PD radar speed measurement to achieve a longer detection range and higher accuracy.

[0099] The range Doppler domain reconstruction device provided by the present invention is described below. The range Doppler domain reconstruction device described below and the range Doppler domain reconstruction method described above can be referenced to each other.

[0100] Figure 5 FIG. 1 is a schematic diagram of the structure of the range Doppler domain reconstruction device provided by the present invention. Figure 5 As shown, the present invention also provides a range Doppler domain reconstruction device, which includes the following modules.

[0101] A training module 510 is configured to generate non-uniform echo signal samples based on pulse emission time samples, obtain a reconstructed image based on the non-uniform echo signal samples and a preset reconstruction network, construct a loss function based on the pulse emission time samples and the reconstructed image, adjust parameters of the pulse emission time samples and the reconstruction network based on the loss function, and repeat the training steps until a preset convergence condition is reached;

[0102] An acquisition module 520 is configured to perform pulse transmission based on a predetermined pulse transmission time to acquire a non-uniform echo signal;

[0103] The reconstruction module 530 is configured to input the non-uniform echo signal into a pre-trained range Doppler domain RD reconstruction network to obtain an RD reconstruction result.

[0104] As an embodiment, the training module 510 is further configured to:

[0105] performing range-matched filtering on the non-uniform echo signal samples;

[0106] Based on the reconstruction network, linear reconstruction and nonlinear filtering are performed for a preset number of iterations on the filtered non-uniform echo signal samples to obtain the reconstructed image.

[0107] As an embodiment, the training module 510 is further configured to:

[0108] Use the zero matrix as the initialization to reconstruct the image;

[0109] Determine a non-uniform inverse Fourier transform matrix and a non-uniform Fourier transform matrix according to the filtered non-uniform echo signal samples;

[0110] Inputting the initialized reconstructed image, the non-uniform inverse Fourier transform matrix and the non-uniform Fourier transform matrix into the reconstruction network to obtain the reconstructed image output by the reconstruction network;

[0111] The reconstruction network is used to determine the linear reconstruction result of the current iteration during each iteration based on the non-uniform inverse Fourier transform matrix, the non-uniform Fourier transform matrix, the filtered non-uniform echo signal samples, and the initialized reconstructed image / reconstruction result of the previous iteration, perform nonlinear filtering on the linear reconstruction result of the current iteration to obtain the reconstruction result of the current iteration, and repeat the preset number of iterations to obtain the reconstructed image.

[0112] As an embodiment, the training module 510 is further configured to:

[0113] The linear reconstruction result of the current iteration is nonlinearly filtered based on the soft threshold iterative function to obtain the reconstruction result of the current iteration.

[0114] As an embodiment, the training module 510 is further configured to:

[0115] The loss function is constructed according to the gap between the reconstructed image and the real image and the minimum value constraint of the samples at the pulse emission moment.

[0116] As an embodiment, the loss function is expressed as follows:

[0117] ;

[0118] in, is the loss function, For the n The reconstructed image corresponding to the sample at the time of pulse emission, N is the total number of samples, For the n The real image corresponding to the sample at the moment of pulse emission, is the mth value of the sample vector at the pulse emission time, and M is the total number of values ​​of the sample vector at the pulse emission time.

[0119] As an embodiment, the training module 510 is further configured to:

[0120] generating a set of mask sequences corresponding to the pulse emission time samples based on a random parameter freezing strategy;

[0121] Multiplying the gradient of the loss function with respect to the pulse emission time sample by the mask sequence to achieve random zeroing;

[0122] According to the gradient of the loss function after random zeroing of the pulse emission time sample, the random part parameters of the pulse emission time sample and the parameters of the reconstruction network are updated.

[0123] It should be noted that the range Doppler domain reconstruction device provided by the present invention can execute the range Doppler domain reconstruction method described in any of the above embodiments during specific operation, and has the technical effects corresponding to the method, which will not be described in detail in this embodiment.

[0124] Figure 6 An example of a physical structure diagram of an electronic device is shown below. Figure 6 As shown, the electronic device may include: a processor 610, a communications interface 620, a memory 630, and a communications bus 640, wherein the processor 610, the communications interface 620, and the memory 630 communicate with each other via the communications bus 640. The processor 610 may call logic instructions in the memory 630 to execute a range Doppler domain reconstruction method, which includes: performing pulse transmission based on a predetermined pulse transmission time to collect non-uniform echo signals; inputting the non-uniform echo signals into a pre-trained range Doppler domain RD reconstruction network to obtain RD reconstruction results; wherein the training process of the RD reconstruction network includes generating non-uniform echo signal samples based on pulse transmission time samples, obtaining a reconstructed image based on the non-uniform echo signal samples and a preset reconstruction network, constructing a loss function based on the pulse transmission time samples and the reconstructed image, adjusting the parameters of the pulse transmission time samples and the reconstruction network based on the loss function, and repeating the training steps until a preset convergence condition is reached.

[0125] Furthermore, the logic instructions in the aforementioned memory 630 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0126] On the other hand, the present invention also provides a computer program product, which includes a computer program, which can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the range Doppler domain reconstruction method provided by the above methods, the method including: performing pulse transmission based on a predetermined pulse transmission time to collect non-uniform echo signals; inputting the non-uniform echo signals into a pre-trained range Doppler domain RD reconstruction network to obtain RD reconstruction results; wherein the training process of the RD reconstruction network includes generating non-uniform echo signal samples based on pulse transmission time samples, obtaining a reconstructed image based on the non-uniform echo signal samples and a preset reconstruction network, constructing a loss function based on the pulse transmission time samples and the reconstructed image, adjusting the respective parameters of the pulse transmission time samples and the reconstruction network according to the loss function, and repeating the training steps until a preset convergence condition is reached.

[0127] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the range Doppler domain reconstruction method provided by the above-mentioned methods, the method comprising: performing pulse emission based on a predetermined pulse emission time to collect a non-uniform echo signal; inputting the non-uniform echo signal into a pre-trained range Doppler domain RD reconstruction network to obtain an RD reconstruction result; wherein the training process of the RD reconstruction network comprises generating non-uniform echo signal samples based on pulse emission time samples, obtaining a reconstructed image based on the non-uniform echo signal samples and a preset reconstruction network, constructing a loss function based on the pulse emission time samples and the reconstructed image, adjusting the respective parameters of the pulse emission time samples and the reconstruction network according to the loss function, and repeating the training steps until a preset convergence condition is reached.

[0128] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0129] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods described in each embodiment or certain portions of the embodiments.

[0130] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A range Doppler domain reconstruction method, characterized in that: include: Performing pulse transmission based on a predetermined pulse transmission time to collect non-uniform echo signals; Inputting the non-uniform echo signal into a pre-trained range-Doppler domain RD reconstruction network to obtain an RD reconstruction result; The training process of the RD reconstruction network includes generating non-uniform echo signal samples according to pulse emission time samples, obtaining a reconstructed image according to the non-uniform echo signal samples and a preset reconstruction network, constructing a loss function according to the pulse emission time samples and the reconstructed image, adjusting the parameters of the pulse emission time samples and the reconstruction network according to the loss function, and repeating the training steps until a preset convergence condition is reached; The reconstructed image is determined based on the following steps: performing range-matched filtering on the non-uniform echo signal samples; Use the zero matrix as the initialization to reconstruct the image; Determine a non-uniform inverse Fourier transform matrix and a non-uniform Fourier transform matrix according to the filtered non-uniform echo signal samples; Inputting the initialized reconstructed image, the non-uniform inverse Fourier transform matrix and the non-uniform Fourier transform matrix into the reconstruction network to obtain the reconstructed image output by the reconstruction network; The reconstruction network is used to determine the linear reconstruction result of the current iteration during each iteration based on the non-uniform inverse Fourier transform matrix, the non-uniform Fourier transform matrix, the filtered non-uniform echo signal samples, and the initialized reconstructed image / reconstruction result of the previous iteration, perform nonlinear filtering on the linear reconstruction result of the current iteration to obtain the reconstruction result of the current iteration, and repeat the preset number of iterations to obtain the reconstructed image.

2. The range Doppler domain reconstruction method according to claim 1, wherein: The performing nonlinear filtering on the linear reconstruction result of the current iteration to obtain the reconstruction result of the current iteration includes: The linear reconstruction result of the current iteration is nonlinearly filtered based on the soft threshold iterative function to obtain the reconstruction result of the current iteration.

3. The range Doppler domain reconstruction method according to claim 1, wherein: The constructing of a loss function according to the pulse emission time samples and the reconstructed image includes: The loss function is constructed according to the gap between the reconstructed image and the real image and the minimum value constraint of the samples at the pulse emission moment.

4. The range Doppler domain reconstruction method according to claim 3, wherein: The expression of the loss function is as follows: in, is the loss function, is the reconstructed image corresponding to the sample at the time of the nth pulse emission, N is the total number of samples, GT n is the real image corresponding to the sample at the time of the nth pulse emission, d m is the mth value of the sample vector at the pulse emission time, and M is the total number of values ​​of the sample vector at the pulse emission time.

5. The range Doppler domain reconstruction method according to claim 1 or 4, characterized in that: The adjusting the parameters of the pulse emission time sample and the reconstruction network according to the loss function includes: generating a set of mask sequences corresponding to the pulse emission time samples based on a random parameter freezing strategy; Multiplying the gradient of the loss function with respect to the pulse emission time sample by the mask sequence to achieve random zeroing; According to the gradient of the loss function after random zeroing of the pulse emission time sample, the random part parameters of the pulse emission time sample and the parameters of the reconstruction network are updated.

6. A range Doppler domain reconstruction device, characterized in that: include: a training module, configured to generate non-uniform echo signal samples based on pulse emission time samples, obtain a reconstructed image based on the non-uniform echo signal samples and a preset reconstruction network, construct a loss function based on the pulse emission time samples and the reconstructed image, adjust parameters of the pulse emission time samples and the reconstruction network based on the loss function, and repeat the training steps until a preset convergence condition is reached; An acquisition module, configured to perform pulse emission based on a predetermined pulse emission time and acquire a non-uniform echo signal; A reconstruction module, configured to input the non-uniform echo signal into a pre-trained range Doppler domain RD reconstruction network to obtain an RD reconstruction result; The reconstructed image is determined based on the following steps: performing range-matched filtering on the non-uniform echo signal samples; Use the zero matrix as the initialization to reconstruct the image; Determine a non-uniform inverse Fourier transform matrix and a non-uniform Fourier transform matrix according to the filtered non-uniform echo signal samples; Inputting the initialized reconstructed image, the non-uniform inverse Fourier transform matrix and the non-uniform Fourier transform matrix into the reconstruction network to obtain the reconstructed image output by the reconstruction network; The reconstruction network is used to determine the linear reconstruction result of the current iteration during each iteration based on the non-uniform inverse Fourier transform matrix, the non-uniform Fourier transform matrix, the filtered non-uniform echo signal samples, and the initialized reconstructed image / reconstruction result of the previous iteration, perform nonlinear filtering on the linear reconstruction result of the current iteration to obtain the reconstruction result of the current iteration, and repeat the preset number of iterations to obtain the reconstructed image.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the range-Doppler domain reconstruction method according to any one of claims 1 to 5 is implemented.

8. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the range-Doppler domain reconstruction method according to any one of claims 1 to 5 is implemented.

Images