ISAR image compensation method under low signal-to-noise ratio condition

Abstract

The invention relates to the technical field of ISAR image processing, and discloses an ISAR image compensation method and system under a low signal-to-noise ratio condition. Comprising the following steps: S1, data acquisition; step S2, collecting ISAR data; s3, extracting translation information; s4, establishing an adaptive compensation model; step S5, implementing self-adaptive translation compensation; s6, training a neural network; step S7, evaluating and optimizing; and step S8, iterative optimization: extracting translation information by preprocessing data, then establishing an adaptive compensation model, performing motion compensation through a neural network, and adjusting parameters of the adaptive compensation model according to image quality indexes, thereby solving the problems of poor visualization and distinguishable effects of the ISAR image under the condition of low signal-to-noise ratio, and high resolution of the ISAR image under the condition of low signal-to-noise ratio. And the morphological structure of the observation target is difficult to distinguish.

Description

Technical Field

[0001] The invention relates to the technical field of ISAR image processing, and in particular to an ISAR image compensation method under low signal-to-noise ratio conditions. Background Art

[0002] Inverse Synthetic Aperture Radar (ISAR) has the ability to perform high-resolution two-dimensional imaging of non-cooperative targets at all times, in all weather conditions, and at long distances, and can obtain information such as the morphological structure of the observed target. As the ISAR observation distance increases, the signal-to-noise ratio of the echo decreases, and the existing ISAR imaging translation compensation method is difficult to accurately estimate and compensate for the translation component, and thus cannot obtain the focused imaging results of the observed target. At the same time, the visualization and distinguishability of ISAR images under low signal-to-noise ratio conditions are poor, and it is difficult to distinguish the morphological structure of the observed target.

[0003] The signal-to-noise ratio is the ratio of signal to noise, and a low signal-to-noise ratio (SNR) indicates a weak signal or high interference. In radar applications, a low signal-to-noise ratio may be caused by the long distance, small cross-sectional area, or weak scattering characteristics of the target. A low signal-to-noise ratio leads to a degradation of the image quality and makes it difficult to identify the target. In ISAR, the signal-to-noise ratio may be reduced, especially when the target is moving at high speed. Doppler shift and blurring effects occur in the ISAR imaging process due to the motion of the target and / or radar platform. In order to obtain clear ISAR images, these movements need to be compensated. Motion compensation adjusts the received echo data to offset the effects caused by the motion of the target and platform. This can be achieved by knowing the motion parameters of the target or platform and then processing the echo data accordingly. Motion compensation is essential to obtain high-quality ISAR images.

[0004] Existing ISAR translation compensation methods usually divide the translation compensation into two steps: envelope alignment and self-focusing. Under low signal-to-noise ratio conditions, the target envelope is equivalent to or even submerged in the noise, and the envelope alignment performance is reduced, which makes it difficult for self-focusing to accurately estimate and compensate the initial phase error, and it is impossible to obtain focused imaging results. In order to solve the ISAR image compensation under low signal-to-noise ratio conditions, it is necessary to provide an ISAR image compensation method under low signal-to-noise ratio conditions to solve the problem that the ISAR image under low signal-to-noise ratio conditions has poor visualization and distinguishability, and it is difficult to distinguish the morphological structure of the observed target. Summary of the invention

[0005] In order to solve the problems raised in the above background technology, the present invention provides an ISAR image compensation method under low signal-to-noise ratio conditions. In order to solve the problem that the existing ISAR translation compensation method is difficult to achieve accurate estimation and compensation of the initial phase error due to self-focusing, and cannot obtain focused imaging, firstly, the translation information is extracted by preprocessing the data, and then an adaptive compensation model is established, motion compensation is performed through a neural network, and the parameters of the adaptive compensation model are adjusted according to the image quality index.

[0006] To achieve the above object, the first aspect of the present invention provides an ISAR image compensation method under low signal-to-noise ratio conditions, comprising:

[0007] Step S1, data acquisition: collecting ISAR data, including radar echo data, translational data, and system and environmental information;

[0008] Step S2, data preprocessing: performing denoising and / or interference removal processing on radar echo data;

[0009] Step S3, extracting translation information: extracting translation data of the target, including velocity, acceleration and position, through radar echo data;

[0010] Step S4, establishing an adaptive compensation model: establishing an adaptive translation compensation model according to the target motion model and the actual translation information, taking the ISAR preprocessed radar echo data, translation data, system and environment information as input, and taking the corresponding adjusted translation parameters as target output;

[0011] Step S5, implementing adaptive translation compensation: determining the loss function and neural network architecture of adaptive translation compensation, and using the difference between the neural network output and the actual translation parameter as compensation;

[0012] Step S6, training the neural network: inputting data into the neural network, adjusting the weights and biases of the neural network so that the network can approximate the mapping relationship between input and output;

[0013] Step S7, evaluation and tuning: evaluating the compensation effect and adjusting the adaptive compensation model parameters according to the image quality index;

[0014] Step S8, iterative optimization: perform iterative optimization according to real-time feedback from the system, improve the adaptive rules, and improve the effect of translation compensation through different filter parameter combinations.

[0015] As a further description of the above technical solution: Step S1 includes: radar echo and translation data are acquired according to the following steps:

[0016] Step S101, the radar echo data in the three-dimensional time domain is:

[0017] x(t)=A(t)e jφ(t) +n(t) (1)

[0018] Where: A(t) is the complex amplitude of the radar signal changing with time, j is the imaginary unit j 2 = -1, φ(t) is the phase of the radar signal that varies with time, and n(t) is the noise of the radar signal that varies with time;

[0019] Step S102, the three-dimensional translation data is:

[0020]

[0021] in: is the three-dimensional position vector, is the three-dimensional velocity vector, is the three-dimensional acceleration vector, r 0 is the initial position vector, v 0 is the initial velocity vector, a is the acceleration vector;

[0022] Step S103, including the time domain signal data of the three-dimensional time domain radar echo data of the translation:

[0023] x(t)=A(t)e jφ(t) s(t-τ(t))+n(t) (3)

[0024] Where: s(t-τ(t)) is the time delay caused by target motion, and τ(t) is the time delay.

[0025] As a further description of the above technical solution: Step S2 includes: radar echo data is subjected to denoising according to the following steps:

[0026] Step S201, denoising the radar echo data by time domain filtering:

[0027] x denoised (t)=Filter(x(t)) (4)

[0028] Wherein, Filter(x(t)) is a filter, which is one of mean filtering, median filtering, and Gaussian filtering;

[0029] Step S202, denoising the radar echo data by frequency domain filtering:

[0030] X(f)=F(x(t)) (5)

[0031] X denoised (f)=Filter(X(f)) (6)

[0032] x denoised (t) = F -1(X denoised (f)) (7)

[0033] Where F is the Fourier transform, X(f) is the spectrum of the signal, and Filter(X(f)) is the frequency domain filter spectrum, which is one of the mean filter, median filter, and Gaussian filter.

[0034] As a further description of the above technical solution: Step S2 includes: the radar echo data is subjected to interference removal processing according to the following steps:

[0035] Step S203, removing interference from radar echo data by time domain filtering:

[0036] x clean (t)=x(t)-Interference(t) (8)

[0037] Among them, Interference(t) is the identified interference part;

[0038] Step S204, removing interference from radar echo data by frequency domain filtering:

[0039] X clean (f)=X(f)-Interference(f) (9)

[0040] x clean (t) = F -1 (X clean (f)) (10)

[0041] Among them, Interference(f) is the frequency domain part of the identified interference.

[0042] As a further description of the above technical solution: in step S4, the adaptive compensation model is established as follows:

[0043]

[0044] Among them, α, β, γ are weight parameters, MotionEstimate(t) is the real-time estimation of translation information, EnvironmentInfo(t) is the environmental information,

[0045]

[0046] Here, τ(t) is the time delay caused by the target motion.

[0047] As a further description of the above technical solution: the step S4, taking the radar echo data, translational data, system and environmental information preprocessed by ISAR as input and taking the corresponding adjusted translational parameters as target output, further comprises the following steps:

[0048] Step S401, the input can be expressed as:

[0049] X=[X radar ,X motion ,X system / env ] (13)

[0050] Among them, X radar is the feature vector of radar echo data, X motion is the eigenvector of the translational data, X system / env is the feature vector of system and environment information;

[0051] Step S402, the output can be expressed as:

[0052] Y=[y 1 ,y 2 ,y 3 ] (14)

[0053] Among them, y 1 is the target position information that needs to be adjusted, y 2 is the target speed information that needs to be adjusted, y 3 is the target acceleration information that needs to be adjusted;

[0054] As a further description of the above technical solution: the step S5, using the difference between the neural network output and the actual translation parameter as compensation, also includes the following steps:

[0055] Step S501, using the complex image I of ISAR as the input X of the neural network mapping function, the image size of the complex image I is h×w×2, where h is the image height, w is the image width, 2 is the number of channels, and the real part and the imaginary part each occupy one channel;

[0056] Step S502, construct a feature extraction module, including convolution blocks Conv_block1 and Conv_block2, and maximum pooling layers Max_pool1 and Max_pool2, wherein Conv_block1 includes two convolution layers Conv1 and Conv2 with activation function ReLU, the convolution kernel size is 3×3, and the ISAR image I is used as input, and the output feature map I with a size of h×w×64 is 0 , using the maximum pooling layer Max_pool1 to reduce the dimension, the output size is h 1 × 1 ×64 feature map I 1 , where h 1 =h / 2,w 1 =w / 2,

[0057]

[0058] Conv_block2 includes two convolutional layers Conv3 and Conv4 with activation function ReLU, the convolution kernel size is 3×3, and Conv_block2 is based on feature map I 1 As input, the output size is h 1 × 1 ×128 Feature Map I 2 , using the maximum pooling layer Max_pool2 to reduce the dimension, the output size is h 2 × 2 ×256 feature map I 3 , where h 2 =h 1 / 2,w 2 =w 1 / 2,

[0059]

[0060] The feature extraction module outputs the feature map I 3 As the input of the feature encoding module;

[0061] Step S503, construct a feature encoding module, including two self-attention networks Transformer1 and Transformer2, and a batch normalization layer BN5 and a convolution layer Conv5, wherein Transformer1 includes batch normalization BN1, window-based multi-head self-attention W-MSA, batch normalization BN2 and multi-layer perceptron MLP1, wherein the input of BN1 is residually connected to the output of W-MSA, the input of BN2 is residually connected to the output of MLP1, and Transformer1 is based on feature mapping I 3 As input, output feature map I" 3 ,

[0062]

[0063] Among them, I' 3 For the intermediate output feature map, Transformer2 includes batch normalization BN3, multi-head self-attention SW-MSA based on shift window, deep convolution DWConv, batch normalization BN4 and multi-layer perceptron MLP2, where the input of BN3 is residually connected to the output of SW-MSA, the input and output of DWConv are residually connected, and the input of BN4 is residually connected to the output of MLP2. Transformer2 uses feature map I" 3 As input, output feature map I" 4 ,

[0064]

[0065] Among them, I 4 and I' 4 is the intermediate output feature map. The kernel size of the last convolutional layer Conv5 of the feature encoding module is 3×3, and the final output size of the feature encoding module is h 2 × 2 ×256 feature map I 5 ,

[0066] I 5 =Conv5[BN5(I 4 ”)]+I 3 (19)

[0067] The feature encoding module outputs the feature map I 5 As the input of the feature decoding module;

[0068] Step S504, construct a feature decoding module, which includes two convolution blocks Conv_block3 and Conv_block4, two sub-pixel convolution layers SP_Conv1 and SP_Conv2, and a convolution 1×1Conv with a kernel size of 1, and outputs a feature map I 5 As input, the sub-pixel convolution layer SP_Conv1 is used to achieve upsampling, and the size of the output feature map is h 1 × 1 ×128, and then add pixel by pixel to the feature map I 2 Perform integration, the output size is h 1 × 1 ×256 feature map I 6 ,

[0069] I 6 =SP_Conv1(I 5 )+I 2 (20)

[0070] And as the input of Conv_block3, Conv_block3 includes 2 convolutional layers Conv6 and Conv7 with activation function ReLU, convolution kernel size is 3×3, and output size is h 1 × 1 ×128 feature map I 7 ,

[0071] I 7 =Conv7[Conv6(I 6 ) ReLU ] ReLU (twenty one)

[0072] The sub-pixel convolution layer SP_Conv2 is used to implement upsampling, and the output feature map of size h×w×64 is added pixel by pixel to the feature map I 0 Integrate and output feature map I with size h×w×128 8 ,

[0073] I 8 =SP_Conv2(I 7 )+I 0 (twenty two)

[0074] And as the input of Conv_block4, Conv_block4 includes 2 convolutional layers Conv8 and Conv9 with activation function ReLU, the convolution kernel size is 3×3, and Conv_block4 uses feature map I 8 As input, the output feature map I of size h×w×64 9 ,

[0075] I 9 =Conv9[Conv8(I 8 ) ReLU ] ReLU (twenty three)

[0076] Reuse the convolution Conv with a kernel size of 1 1×1 Transform and finally output feature map I 10 ,

[0077] I 10 =Conv 1×1 (I 9 ) (twenty four)

[0078] The size is h×w×2, with feature map I 10 As output Y.

[0079] As a further description of the above technical solution: the step S6, adjusting the weight and bias of the neural network is as follows:

[0080] Step S601, input layer to hidden layer:

[0081] H 1 =σ(W 1 X+b 1 ) (25)

[0082] Among them, H 1 is the output of the hidden layer, σ is the activation function, which is a nonlinear function such as ReLU (Rectified Linear Unit) or Sigmoid, W 1 is the weight matrix from the input layer to the hidden layer, b 1is the bias vector from the input layer to the hidden layer;

[0083] Step S602, hidden layer to output layer:

[0084] Y=σ(W 2 H 1 +b 2 ) (26)

[0085] Among them, W 2 is the weight matrix from the hidden layer to the output layer, b 2 is the bias vector from the hidden layer to the output layer;

[0086] Step S603, using a gradient descent algorithm with momentum to update the parameters of the neural network, initializing the weights, biases and momentum terms of the neural network, wherein the momentum term is used to record the direction and magnitude of the previous parameter update;

[0087] Step S604, randomly select a batch of samples from the training data set, calculate the average values ​​dW and db of the gradients obtained by differentiating the selected samples with respect to the neural network parameters during the back propagation process of the current batch, and calculate the new momentum term v according to the current average gradient and the momentum term of the previous parameter update. dW and v db , and use the new momentum term to update the neural network parameters, weights W and bias b,

[0088]

[0089] Among them, α is the learning rate and β is the hyperparameter;

[0090] Step S606, repeating steps S604 to S605 until the preset number of training rounds epochs is reached, and the loss function L(W,b) is expressed as follows:

[0091]

[0092] Among them, N is the number of samples, M is the number of output features, and Y ij Output the predicted value for the network, is the true value of the label, the optimization goal is to minimize the loss function value, and the neural network parameters are trained as compensation parameters.

[0093] As a further description of the above technical solution: Step S7, adjusting the adaptive compensation model parameters according to the image quality index, the adjusted image index includes one or more of peak signal-to-noise ratio, contrast, image standard deviation, and image average gradient, is implemented by one or more of the following steps:

[0094] Step S701, peak signal-to-noise ratio:

[0095]

[0096] Among them, PSNR represents the ratio between the energy of the maximum signal in the image and the background noise, I, K, M, N represent that the image size of the current image I and the reference image K is M×N, MAX 1 is the highest grayscale value, usually 255;

[0097] Step S702, contrast:

[0098]

[0099] Among them, δ(i,j)=|ij| represents the grayscale difference between adjacent pixels, P δ (i, j) represents the distribution probability of pixels with grayscale difference between adjacent pixels;

[0100] Step S703, image standard deviation:

[0101]

[0102] Among them, f(i,j) is the image pixel value, μ is the image mean;

[0103] Step S704, image average gradient value:

[0104]

[0105] Among them, G x and G y The gradient values ​​of the image in the horizontal and vertical directions.

[0106] The second aspect of the present invention is an ISAR image compensation system under low signal-to-noise ratio conditions, characterized in that it is used for an ISAR image compensation method under low signal-to-noise ratio conditions as described above, comprising: a data acquisition module, a data recording system, a data preprocessing module, a translational information extraction module, an adaptive compensation model establishment module, a neural network training platform, an evaluation and tuning module, and an iterative optimization module. The data acquisition module comprises an ISAR radar system, a translational data collector, and an environmental monitoring sensor. The radar system, the translational data collector, and the environmental monitoring sensor are connected to the data recording system through a communication interface, and then connected in sequence to the data preprocessing module, the translational information extraction module, the adaptive compensation model establishment module, the neural network training platform, the evaluation and tuning module, and the iterative optimization module through a data interface.

[0107] Preferably, the data preprocessing module, translation information extraction module, adaptive compensation model building module, evaluation and tuning module, and iterative optimization module are high-performance computing servers or data analysis workstations.

[0108] Preferably, the neural network training platform is a deep learning workstation.

[0109] The present invention provides an ISAR image compensation method under low signal-to-noise ratio conditions, which solves the problem that the existing ISAR translation compensation method is difficult to achieve accurate estimation and compensation of initial phase errors through self-focusing and cannot obtain focused imaging. Firstly, translation information is extracted by preprocessing data, and then an adaptive compensation model is established. Motion compensation is performed through a neural network, and the parameters of the adaptive compensation model are adjusted according to image quality indicators. BRIEF DESCRIPTION OF THE DRAWINGS

[0110] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0111] Figure 1 Flow chart of an ISAR image compensation method under low signal-to-noise ratio conditions proposed by the present invention DETAILED DESCRIPTION

[0112] The present invention is further described in detail below by specific embodiments in conjunction with the accompanying drawings. In the following embodiments, many detailed descriptions are intended to enable the present application to be better understood. However, those skilled in the art can effortlessly recognize that some of the features can be omitted in different situations, or can be replaced by other elements, materials, and methods. In some cases, some operations related to the present application are not shown or described in the specification, in order to avoid the core part of the present application being overwhelmed by too much description, and for those skilled in the art, it is not necessary to describe these related operations in detail, and they can fully understand the related operations according to the description in the specification and the general technical knowledge in the art.

[0113] In addition, the features, operations or characteristics described in the specification can be combined in any appropriate manner to form various implementations. At the same time, the steps or actions in the method description can also be interchanged or adjusted in a manner that is obvious to those skilled in the art. Therefore, the various sequences in the specification and the drawings are only for the purpose of clearly describing a certain embodiment and are not meant to be a required sequence, unless otherwise specified that a certain sequence must be followed.

[0114] The serial numbers assigned to the components in this article, such as "first", "second", etc., are only used to distinguish the objects described and do not have any order or technical meaning. Specific implementation method 1

[0116] A first aspect of the present invention provides an ISAR image compensation method under low signal-to-noise ratio conditions, comprising:

[0117] Step S1, data acquisition: collecting ISAR data, including radar echo data, translational data, and system and environmental information;

[0118] Step S2, data preprocessing: performing denoising and / or interference removal processing on radar echo data;

[0119] Step S3, extracting translation information: extracting translation data of the target, including velocity, acceleration and position, through radar echo data;

[0120] Step S4, establishing an adaptive compensation model: establishing an adaptive translation compensation model according to the target motion model and the actual translation information, taking the radar echo data, translation data, system and environmental information preprocessed by ISAR as input, and taking the corresponding adjusted translation parameters as target output, further comprising the following steps:

[0121] Step S401, the input can be expressed as:

[0122] X=[X radar ,X motion ,X system / env ] (33)

[0123] Among them, X radar is the feature vector of radar echo data, X motion is the eigenvector of the translational data, X system / env is the feature vector of system and environment information;

[0124] Step S402, the output can be expressed as:

[0125] Y=[y 1 ,y 2 ,y 3 ] (34)

[0126] Among them, y 1 is the target position information that needs to be adjusted, y 2 is the target speed information that needs to be adjusted, y 3 is the target acceleration information that needs to be adjusted;

[0127] Step S5, implementing adaptive translation compensation: determining the loss function and neural network architecture of adaptive translation compensation, using the difference between the neural network output and the actual translation parameter as compensation, and further comprising the following steps:

[0128] Step S501, using the complex image I of ISAR as the input X of the neural network mapping function, the image size of the complex image I is h×w×2, where h is the image height, w is the image width, 2 is the number of channels, and the real part and the imaginary part each occupy one channel;

[0129] Step S502, construct a feature extraction module, including convolution blocks Conv_block1 and Conv_block2, and maximum pooling layers Max_pool1 and Max_pool2, wherein Conv_block1 includes two convolution layers Conv1 and Conv2 with activation function ReLU, the convolution kernel size is 3×3, and the ISAR image I is used as input, and the output feature map I with a size of h×w×64 is 0 , using the maximum pooling layer Max_pool1 to reduce the dimension, the output size is h 1 × 1 ×64 feature map I 1 , where h 1 =h / 2,w 1 =w / 2,

[0130]

[0131] Conv_block2 includes two convolutional layers Conv3 and Conv4 with activation function ReLU, the convolution kernel size is 3×3, and Conv_block2 is based on feature map I 1 As input, the output size is h 1 × 1 ×128 Feature Map I 2 , using the maximum pooling layer Max_pool2 to reduce the dimension, the output size is h 2 × 2 ×256 feature map I 3 , where h 2 =h 1 / 2,w 2 =w 1 / 2,

[0132]

[0133] The feature extraction module outputs the feature map I 3 As the input of the feature encoding module;

[0134] Step S503, construct a feature encoding module, including two self-attention networks Transformer1 and Transformer2, and a batch normalization layer BN5 and a convolution layer Conv5, wherein Transformer1 includes batch normalization BN1, window-based multi-head self-attention W-MSA, batch normalization BN2 and multi-layer perceptron MLP1, wherein the input of BN1 is residually connected to the output of W-MSA, the input of BN2 is residually connected to the output of MLP1, and Transformer1 is based on feature mapping I 3 As input, output feature map I" 3,

[0135]

[0136] Among them, I' 3 For the intermediate output feature map, Transformer2 includes batch normalization BN3, multi-head self-attention SW-MSA based on shift window, deep convolution DWConv, batch normalization BN4 and multi-layer perceptron MLP2, where the input of BN3 is residually connected to the output of SW-MSA, the input and output of DWConv are residually connected, and the input of BN4 is residually connected to the output of MLP2. Transformer2 uses feature map I" 3 As input, output feature map I" 4 ,

[0137]

[0138] Among them, I 4 and I' 4 is the intermediate output feature map. The kernel size of the last convolutional layer Conv5 of the feature encoding module is 3×3, and the final output size of the feature encoding module is h 2 × 2 ×256 feature map I 5 ,

[0139] I 5 =Conv5[BN5(I 4 ”)]+I 3 (39)

[0140] The feature encoding module outputs the feature map I 5 As the input of the feature decoding module;

[0141] Step S504, construct a feature decoding module, which includes two convolution blocks Conv_block3 and Conv_block4, two sub-pixel convolution layers SP_Conv1 and SP_Conv2, and a convolution 1×1Conv with a kernel size of 1, and outputs a feature map I 5 As input, the sub-pixel convolution layer SP_Conv1 is used to achieve upsampling, and the size of the output feature map is h 1 × 1 ×128, and then add pixel by pixel to the feature map I 2 Perform integration, the output size is h 1 × 1 ×256 feature map I 6 ,

[0142] I 6=SP_Conv1(I 5 )+I 2 (40)

[0143] And as the input of Conv_block3, Conv_block3 includes 2 convolutional layers Conv6 and Conv7 with activation function ReLU, convolution kernel size is 3×3, and output size is h 1 × 1 ×128 feature map I 7 ,

[0144] I 7 =Conv7[Conv6(I 6 ) ReLU ] ReLU (41)

[0145] The sub-pixel convolution layer SP_Conv2 is used to implement upsampling, and the output feature map of size h×w×64 is added pixel by pixel to the feature map I 0 Integrate and output feature map I with size h×w×128 8 ,

[0146] I 8 =SP_Conv2(I 7 )+I 0 (42)

[0147] And as the input of Conv_block4, Conv_block4 includes 2 convolutional layers Conv8 and Conv9 with activation function ReLU, the convolution kernel size is 3×3, and Conv_block4 uses feature map I 8 As input, the output feature map I of size h×w×64 9 ,

[0148] I 9 =Conv9[Conv8(I 8 ) ReLU ] ReLU (43)

[0149] Reuse the convolution Conv with a kernel size of 1 1×1 Transform and finally output feature map I 10 ,

[0150] I 10 =Conv 1×1 (I 9 ) (44)

[0151] The size is h×w×2, with feature map I 10 As output Y.

[0152] Step S6, training the neural network: inputting data into the neural network, adjusting the weights and biases of the neural network so that the network can approximate the mapping relationship between input and output, and further comprising the following steps:

[0153] Step S601, input layer to hidden layer:

[0154] H 1 =σ(W 1 X+b 1 ) (45)

[0155] Among them, H 1 is the output of the hidden layer, σ is the activation function, which is a nonlinear function such as ReLU (Rectified Linear Unit) or Sigmoid, W 1 is the weight matrix from the input layer to the hidden layer, b 1 is the bias vector from the input layer to the hidden layer;

[0156] Step S602, hidden layer to output layer:

[0157] Y=σ(W 2 H 1 +b 2 ) (46)

[0158] Among them, W 2 is the weight matrix from the hidden layer to the output layer, b 2 is the bias vector from the hidden layer to the output layer;

[0159] Step S603, using a gradient descent algorithm with momentum to update the parameters of the neural network, initializing the weights, biases and momentum terms of the neural network, wherein the momentum term is used to record the direction and magnitude of the previous parameter update;

[0160] Step S604, randomly select a batch of samples from the training data set, calculate the average values ​​dW and db of the gradients obtained by differentiating the selected samples with respect to the neural network parameters during the back propagation process of the current batch, and calculate the new momentum term v according to the current average gradient and the momentum term of the previous parameter update. dW and v db , and use the new momentum term to update the neural network parameters, weights W and bias b,

[0161]

[0162] Among them, α is the learning rate and β is the hyperparameter;

[0163] Step S605, repeating steps S604 to S605 until a preset number of training rounds epochs is reached, and the loss function L(W,b) is expressed as follows:

[0164]

[0165] Among them, N is the number of samples, M is the number of output features, and Y ij Output the predicted value for the network, is the true value of the label, the optimization goal is to minimize the loss function value, and the neural network parameters are trained as compensation parameters.

[0166] Step S7, evaluation and tuning: evaluating the compensation effect and adjusting the adaptive compensation model parameters according to the image quality index;

[0167] Step S8, iterative optimization: perform iterative optimization according to real-time feedback from the system, improve the adaptive rules, and improve the effect of translation compensation through different filter parameter combinations. Specific implementation method 2

[0169] The second aspect of the present invention provides an ISAR image compensation system under low signal-to-noise ratio conditions, including: a data acquisition module, a data recording system, a data preprocessing module, a translational information extraction module, an adaptive compensation model establishment module, a neural network training platform, an evaluation and tuning module, and an iterative optimization module. The data acquisition module includes an ISAR radar system, a translational data collector, and an environmental monitoring sensor. The radar system, the translational data collector, and the environmental monitoring sensor are connected to the data recording system through a communication interface, and then connected in sequence to the data preprocessing module, the translational information extraction module, the adaptive compensation model establishment module, the neural network training platform, the evaluation and tuning module, and the iterative optimization module through a data interface.

[0170] The radar system collects radar echo data, the translation data collector obtains the translation data of the target including speed, acceleration and position, the environmental monitoring sensor collects environmental information including temperature and humidity, and transmits the collected data to the data recording system through the communication interface. The data recording system stores the collected radar echo data, translation data and environmental information. The data preprocessing module receives the preprocessed data storage information from the data recording system, executes specific denoising algorithms and interference removal operations to denoise and interfere with the data, the translation information extraction module receives the preprocessed data from the data preprocessing module, extracts translation information such as speed, acceleration and position, and transmits the extracted translation data to the adaptive compensation model establishment module. The adaptive compensation model establishment module establishes an adaptive translation compensation model, and transmits the compensation model and related data to the neural network training platform. The neural network training platform trains the neural network, adjusts the model weights and biases, and transmits the training results to the evaluation and tuning module. The evaluation and tuning module evaluates the compensation effect, adjusts the model parameters according to the image quality indicators, and transmits the evaluation results and adjustment suggestions to the iterative optimization module. The iterative optimization module optimizes the compensation effect according to the real-time feedback, and transmits the optimization results and adjustment schemes back to the adaptive compensation model establishment module for adjustment.

[0171] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

[0172] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned wireless terminal can refer to the corresponding process in the above-mentioned method embodiment, and will not be repeated here.

[0173] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0174] In the embodiments provided by the present invention, it should be understood that the disclosed system / terminal device and method can be implemented in other ways. For example, the system / terminal device embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the system or unit can be electrical, mechanical or other forms.

[0175] The units described as separate components may or may not be physically separated, and the components described as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0176] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for compensating ISAR images under low signal-to-noise ratio conditions, characterized in that: The following steps are involved: Step S1, data acquisition: collecting ISAR data, including radar echo data, translational data, and system and environmental information; Step S2, data preprocessing: performing denoising and / or interference removal processing on radar echo data; Step S3, extracting translation information: extracting translation data of the target, including velocity, acceleration and position, through radar echo data; Step S4, establishing an adaptive compensation model: establishing an adaptive translation compensation model according to the target motion model and the actual translation information, taking the ISAR preprocessed radar echo data, translation data, system and environment information as input, and taking the corresponding adjusted translation parameters as target output; Step S5, implementing adaptive translation compensation: determining the loss function and neural network architecture of adaptive translation compensation, and using the difference between the neural network output and the actual translation parameter as compensation; Step S6, training the neural network: inputting data into the neural network, adjusting the weights and biases of the neural network so that the network can approximate the mapping relationship between input and output; Step S7, evaluation and tuning: evaluating the compensation effect and adjusting the adaptive compensation model parameters according to the image quality index; Step S8, iterative optimization: perform iterative optimization according to real-time feedback from the system, improve the adaptive rules, and improve the effect of translation compensation through different filter parameter combinations.

2. The ISAR image compensation method under low signal-to-noise ratio conditions according to claim 1, characterized in that: The radar echo and translation data in step S1 are obtained according to the following steps: Step S101, the radar echo data in the three-dimensional time domain is: x(t)=A(t)e jφ(t) +n(t) (1) Where: A(t) is the complex amplitude of the radar signal changing with time, j is the imaginary unit j 2 = -1, φ(t) is the phase of the radar signal that varies with time, and n(t) is the noise of the radar signal that varies with time; Step S102, the three-dimensional translation data is: in: is the three-dimensional position vector, is the three-dimensional velocity vector, is the three-dimensional acceleration vector, r0 is the initial position vector, v0 is the initial velocity vector, and a is the acceleration vector; Step S103, including the time domain signal data of the three-dimensional time domain radar echo data of the translation: x(t)=A(t)e jφ(t) s(t-τ(t))+n(t) (3) Where: s(t-τ(t)) is the time delay caused by target motion, and τ(t) is the time delay.

3. The ISAR image compensation method under low signal-to-noise ratio conditions according to claim 1, characterized in that: In step S2, the radar echo data is subjected to denoising according to the following steps: Step S201, denoising the radar echo data by time domain filtering: x denoised (t)=Filter(x(t)) (4) Wherein, Filter(x(t)) is a filter, which is one of mean filtering, median filtering, and Gaussian filtering; Step S202, denoising the radar echo data by frequency domain filtering: X(f)=F(x(t)) (5) X denoised (f)=Filter(X(f)) (6) x denoised (t)=F -1 (X denoised (f)) (7) Where F is the Fourier transform, X(f) is the spectrum of the signal, and Filter(X(f)) is the frequency domain filter spectrum, which is one of the mean filter, median filter, and Gaussian filter. Step S203, removing interference from radar echo data by time domain filtering: x clean (t)=x(t)-Interference(t) (8) Among them, Interference(t) is the identified interference part; Step S204, removing interference from radar echo data by frequency domain filtering: X clean (f)=X(f)-Interference(f) (9) x clean (t)=F -1 (X clean (f)) (10) Among them, Interference(f) is the frequency domain part of the identified interference.

4. The ISAR image compensation method under low signal-to-noise ratio conditions according to claim 1, characterized in that: The step S4 is performed according to the following steps: Step S401, establishing an adaptive compensation model: Among them, α, β, γ are weight parameters, MotionEstimate(t) is the real-time estimation of translation information, EnvironmentInfo(t) is the environmental information, Among them, τ(t) is the time delay caused by the target motion; Step S402, using the radar echo data, translational data, system and environment information preprocessed by ISAR as input, the input can be expressed as: X=[X radar ,X motion ,X system / env ] (13) Among them, X radar is the feature vector of radar echo data, X motion is the eigenvector of the translational data, X system / env is the feature vector of system and environment information; Step S403, the output can be expressed as: Y=[y1,y2,y3] (14) Among them, y1 is the target position information that needs to be adjusted, y2 is the target speed information that needs to be adjusted, and y3 is the target acceleration information that needs to be adjusted.

5. The ISAR image compensation method under low signal-to-noise ratio conditions according to claim 1, characterized in that: According to the difference between the neural network output and the actual translation parameters as compensation, the following steps are also included: Step S501, using the complex image I of ISAR as the input X of the neural network mapping function, the image size of the complex image I is h×w×2, where h is the image height, w is the image width, 2 is the number of channels, and the real part and the imaginary part each occupy one channel; Step S502, construct a feature extraction module, including convolution blocks Conv_block1 and Conv_block2, and maximum pooling layers Max_pool1 and Max_pool2, wherein Conv_block1 includes two convolution layers Conv1 and Conv2 with activation function ReLU, the convolution kernel size is 3×3, and the ISAR image I is used as input to output a feature map I0 with a size of h×w×64. The maximum pooling layer Max_pool1 is used for dimensionality reduction to output a feature map I1 with a size of h1×w1×64, wherein h1=h / 2, w1=w / 2, Conv_block2 includes two convolutional layers Conv3 and Conv4 with activation function ReLU. The convolution kernel size is 3×3. Conv_block2 takes feature map I1 as input and outputs feature map I2 with size h1×w1×128. It uses the maximum pooling layer Max_pool2 to reduce the dimension and outputs feature map I3 with size h2×w2×256, where h2=h1 / 2, w2=w1 / 2. The feature map I3 output by the feature extraction module is used as the input of the feature encoding module; Step S503, construct a feature encoding module, including two self-attention networks Transformer1 and Transformer2, and a batch normalization layer BN5 and a convolution layer Conv5, wherein Transformer1 includes batch normalization BN1, window-based multi-head self-attention W-MSA, batch normalization BN2 and multi-layer perceptron MLP1, wherein the input of BN1 is residually connected to the output of W-MSA, and the input of BN2 is residually connected to the output of MLP1, and Transformer1 takes feature map I3 as input and outputs feature map I"3, Among them, I'3 is the intermediate output feature map, Transformer2 includes batch normalization BN3, multi-head self-attention SW-MSA based on shift window, deep convolution DWConv, batch normalization BN4 and multi-layer perceptron MLP2, among which the input of BN3 is residually connected to the output of SW-MSA, the input and output of DWConv are residually connected, the input of BN4 is residually connected to the output of MLP2, Transformer2 takes feature map I"3 as input and outputs feature map I"4, Among them, I4 and I'4 are intermediate output feature maps, the kernel size of the last convolution layer Conv5 of the feature encoding module is 3×3, and the final output size of the feature encoding module is the feature map I5 of h2×w2×256. I5=Conv5[BN5(I”4)]+I3 (19) The feature encoding module outputs the feature map I5 as the input of the feature decoding module; Step S504, construct a feature decoding module, which includes two convolution blocks Conv_block3 and Conv_block4, two sub-pixel convolution layers SP_Conv1 and SP_Conv2, and a convolution 1×1Conv with a kernel size of 1. The feature encoding module outputs the feature map I5 as input, and the sub-pixel convolution layer SP_Conv1 is used to implement upsampling. The size of the output feature map is h1×w1×128, and then it is integrated with the feature map I2 by pixel-by-pixel addition. The output feature map I6 has a size of h1×w1×256. I6=SP_Conv1(I5)+I2 (20) And as the input of Conv_block3, Conv_block3 includes 2 convolutional layers Conv6 and Conv7 with activation function ReLU, convolution kernel size is 3×3, and output feature map I7 with size h1×w1×128, I7=Conv7[Conv6(I6) ReLU ] ReLU (21) The sub-pixel convolution layer SP_Conv2 is used to achieve upsampling, and the output feature map with a size of h×w×64 is integrated with the feature map I0 by pixel-by-pixel addition, and the output feature map I8 with a size of h×w×128 is output. I8=SP_Conv2(I7)+I0 (22) And as the input of Conv_block4, Conv_block4 includes 2 convolutional layers Conv8 and Conv9 with activation function ReLU, the convolution kernel size is 3×3, Conv_block4 takes feature map I8 as input and outputs feature map I9 with size h×w×64. I9=Conv9[Conv8(I8) ReLU ] ReLU (23) Reuse the convolution Conv with a kernel size of 1 1×1 Transform and finally output feature map I 10 , I 10 =Conv 1×1 (I9) (24) The size is h×w×2, with feature map I 10 As output Y.

6. The ISAR image compensation method under low signal-to-noise ratio conditions according to claim 1, characterized in that: The step S6, adjusting the weight and bias of the neural network is as follows: Step S601, input layer to hidden layer: H 1 =σ(W 1 X+b 1 ) (25) Among them, H 1 is the output of the hidden layer, σ is the activation function, which is a nonlinear function such as ReLU (Rectified Linear Unit) or Sigmoid, W 1 is the weight matrix from the input layer to the hidden layer, b 1 is the bias vector from the input layer to the hidden layer; Step S602, hidden layer to output layer: Y=σ(W 2 H 1 +b 2 ) (26) Among them, W 2 is the weight matrix from the hidden layer to the output layer, b 2 is the bias vector from the hidden layer to the output layer; Step S603, using a gradient descent algorithm with momentum to update the parameters of the neural network, initializing the weights, biases and momentum terms of the neural network, wherein the momentum term is used to record the direction and magnitude of the previous parameter update; Step S604, randomly select a batch of samples from the training data set, calculate the average values ​​dW and db of the gradients obtained by differentiating the selected samples with respect to the neural network parameters during the back propagation process of the current batch, and calculate the new momentum term v according to the current average gradient and the momentum term of the previous parameter update. dW and v db , and use the new momentum term to update the neural network parameters, weights W and bias b, Among them, α is the learning rate and β is the hyperparameter; Step S606, repeating steps S604 to S605 until the preset number of training rounds epochs is reached, and the loss function L(W,b) is expressed as follows: Among them, N is the number of samples, M is the number of output features, and Y ij Output the predicted value for the network, is the true value of the label, the optimization goal is to minimize the loss function value, and the neural network parameters are trained as compensation parameters.

7. The ISAR image compensation method under low signal-to-noise ratio conditions according to claim 1, characterized in that: The step S7, adjusting the adaptive compensation model parameters according to the image quality index, includes one or more of peak signal-to-noise ratio, contrast, image standard deviation, and image average gradient, and is implemented by one or more of the following steps: Step S701, peak signal-to-noise ratio: Among them, PSNR represents the ratio between the energy of the maximum signal in the image and the background noise, I, K, M, N represent that the image size of the current image I and the reference image K is M×N, MAX1 is the highest grayscale value, usually 255; Step S702, contrast: Among them, δ(i,j)=|ij| represents the grayscale difference between adjacent pixels, P δ (i, j) represents the distribution probability of pixels with grayscale difference between adjacent pixels; Step S703, image standard deviation: Among them, f(i,j) is the image pixel value, μ is the image mean; Step S704, image average gradient value: Among them, G x and G y The gradient values ​​of the image in the horizontal and vertical directions.

8. An ISAR image compensation system under low signal-to-noise ratio conditions, used to implement the method according to any one of claims 1 to 9, characterized in that: include: A data acquisition module, a data recording system, a data preprocessing module, a translational information extraction module, an adaptive compensation model establishment module, a neural network training platform, an evaluation and tuning module, and an iterative optimization module. The data acquisition module includes an ISAR radar system, a translational data collector, and an environmental monitoring sensor. The radar system, the translational data collector, and the environmental monitoring sensor are connected to the data recording system through a communication interface, and then connected in sequence to the data preprocessing module, the translational information extraction module, the adaptive compensation model establishment module, the neural network training platform, the evaluation and tuning module, and the iterative optimization module through a data interface.

9. The ISAR image compensation system under low signal-to-noise ratio conditions according to claim 8, characterized in that: The data preprocessing module, translation information extraction module, adaptive compensation model establishment module, evaluation and tuning module, and iterative optimization module are high-performance computing servers or data analysis workstations.

10. The ISAR image compensation system under low signal-to-noise ratio conditions according to claim 8, characterized in that: The neural network training platform is a deep learning workstation.

Images