Satellite-borne SAR (Synthetic Aperture Radar) working mode identification method and equipment based on multi-scale network

Abstract

The invention discloses a satellite-borne SAR working mode recognition method and device based on a multi-scale network, and the method comprises the steps: obtaining a multivariate reconnaissance parameter sequence of a to-be-recognized satellite-borne synthetic aperture radar reconnaissance signal, extracting the semantic information of a synthetic aperture radar, obtaining a synthetic aperture radar semantic sequence, carrying out the normalization processing, and obtaining a recognition result; a normalized synthetic aperture radar semantic sequence is obtained; calculating the mean value of the normalized synthetic aperture radar semantic sequence to obtain the mean value of the synthetic aperture radar semantic sequence; extracting an amplitude sequence, and normalizing the amplitude sequence to obtain a normalized amplitude sequence; and processing the mean value of the semantic sequence of the synthetic aperture radar and the normalized amplitude sequence by adopting the trained satellite-borne synthetic aperture radar working mode recognition network to obtain a working mode corresponding to the multivariate reconnaissance parameter sequence. According to the invention, the working mode identification accuracy of the spaceborne synthetic aperture radar can be improved.

Description

Technical Field

[0001] The invention belongs to the technical field of synthetic aperture radar reconnaissance signal processing, and in particular relates to a method and a device for identifying a spaceborne SAR working mode based on a multi-scale network. Background Art

[0002] Synthetic Aperture Radar (SAR) is a microwave remote sensing radar with the advantages of long distance and wide coverage. It can work all day and all weather in bad weather environments such as clouds and rain. It is widely used in ocean observation, geological mapping, information collection and other fields. SAR is mainly divided into airborne SAR and satellite SAR. Among them, satellite SAR has become a hot research topic with its advantages such as global observation. However, when using satellite SAR to scout the opponent's scene, the key areas of one's own side will also be exposed to the detection of the opponent's satellite SAR. Therefore, it is necessary to take corresponding measures to disrupt the normal operation of the opponent's satellite SAR. A typical method is to interfere with the satellite SAR to prevent the opponent from obtaining one's own information. Whether the waveform parameters, working mode and other information of the opponent can be accurately obtained before the interference is implemented on the satellite SAR will have an important impact on the effectiveness of the interference. Therefore, the research on the precise processing method of satellite SAR reconnaissance signals has an important role in promoting the efficient implementation of satellite SAR interference.

[0003] As spaceborne SAR systems have developed from low-resolution, single-mode to high-resolution, multi-mode, etc., multi-mode SAR with higher flexibility has been widely used and deployed, bringing severe challenges to the accurate identification of spaceborne SAR working modes. In recent years, many scholars have actively explored the problem of SAR working mode recognition. Tang Xiaoming et al. constructed an error square sum array based on theory and intercepted data, and used iterative search to infer the SAR working mode and observation range. In addition, a genetic algorithm was used to speed up the search speed, and a multi-station measurement method was proposed to improve the reliability of the algorithm. Wang Zhetao et al. used a binary tree support vector machine to realize the recognition of spaceborne SAR imaging mode, and used a genetic algorithm to optimize the parameters in the model. He Jun et al. proposed a method for identifying SAR working modes based on CGRU-SVM and one-dimensional convolutional neural network, respectively taking the I / Q data and amplitude of the pulse peak as the input of the two networks to achieve rapid identification of spaceborne SAR working modes. Although the above methods have studied the problem of SAR working mode recognition, they still have the problems of long time consumption, poor versatility, and low recognition accuracy in complex scenes. Summary of the invention

[0004] In order to solve the above problems existing in the prior art, the present invention provides a method and device for identifying the working mode of a spaceborne SAR based on a multi-scale network. The technical problem to be solved by the present invention is achieved through the following technical solutions: In a first aspect, the present invention provides a method for identifying a spaceborne SAR working mode based on a multi-scale network, comprising: Acquire a multi-element reconnaissance parameter sequence of a spaceborne synthetic aperture radar reconnaissance signal to be identified; Extracting synthetic aperture radar semantic information from the multivariate reconnaissance parameter sequence to obtain a synthetic aperture radar semantic sequence; normalizing the synthetic aperture radar semantic sequence to obtain a normalized synthetic aperture radar semantic sequence; calculating the mean of the normalized synthetic aperture radar semantic sequence to obtain the mean of the synthetic aperture radar semantic sequence; Extracting the amplitude sequence in the multivariate reconnaissance parameter sequence to obtain the amplitude sequence, normalizing the amplitude sequence to obtain a normalized amplitude sequence; The trained spaceborne synthetic aperture radar working mode recognition network is used to process the mean value of the synthetic aperture radar semantic sequence and the normalized amplitude sequence to obtain the working mode corresponding to the multivariate reconnaissance parameter sequence. Among them, the trained spaceborne synthetic aperture radar working mode recognition network uses preset category data as training data set to train the initial spaceborne synthetic aperture radar working mode recognition network. During the training process, the preset category data is used as a verification data set to perform model selection and hyperparameter tuning on the spaceborne synthetic aperture radar working mode recognition network.

[0005] In a second aspect, the present invention further provides a spaceborne SAR working mode recognition device based on a multi-scale network, comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; Memory, used to store computer programs; The processor is used to implement the above-mentioned multi-scale network-based spaceborne SAR working mode recognition method when executing the program stored in the memory.

[0006] Beneficial effects of the present invention: The present invention provides a method and device for identifying a spaceborne SAR working mode based on a multi-scale network, which improves the network's ability to recognize different working modes under non-ideal conditions by introducing synthetic aperture radar semantic information such as duty cycle and range resolution that are tightly coupled with the synthetic aperture radar working mode. The multi-scale information of the mean of the synthetic aperture radar semantic sequence and the normalized amplitude sequence is fully integrated through the trained spaceborne synthetic aperture radar working mode recognition network, thereby improving the distinction between different working modes of the spaceborne synthetic aperture radar in the high-dimensional latent feature space, thereby improving the accuracy of the spaceborne synthetic aperture radar working mode recognition. In addition, experiments in complex scenarios with a high proportion of missed pulses and false pulses show that compared with the existing spaceborne synthetic aperture radar working mode recognition method, the spaceborne synthetic aperture radar working mode recognition method based on the knowledge-assisted multi-scale information fusion network has good recognition accuracy and robustness.

[0007] The present invention will be further described in detail below with reference to the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1 It is a flow chart of a method for identifying a spaceborne SAR working mode based on a multi-scale network provided by an embodiment of the present invention; Figure 2 It is a schematic diagram of a trained spaceborne synthetic aperture radar working mode recognition network provided by an embodiment of the present invention; Figure 3 It is a schematic diagram of result curves of different satellite-borne synthetic aperture radar working mode recognition methods in the process of increasing the false pulse ratio from 5% to 20% provided by the embodiment of the present invention; Figure 4 It is a schematic diagram of result curves of different satellite-borne synthetic aperture radar working mode recognition methods when the leakage pulse ratio provided by the embodiment of the present invention increases from 5% to 20%. DETAILED DESCRIPTION

[0009] The present invention is further described in detail below with reference to specific embodiments, but the embodiments of the present invention are not limited thereto.

[0010] See also Figure 1 , Figure 1 1 is a flow chart of a method for identifying a spaceborne SAR working mode based on a multi-scale network provided by an embodiment of the present invention. The method for identifying a spaceborne SAR working mode based on a multi-scale network provided by the present invention comprises: S101. Acquire a multivariate reconnaissance parameter sequence of a spaceborne synthetic aperture radar reconnaissance signal to be identified.

[0011] Specifically, in this embodiment, the multi-element reconnaissance parameter sequence of the spaceborne synthetic aperture radar reconnaissance signal to be identified may be a parameter sequence obtained by measuring the parameters of the signal emitted by the spaceborne synthetic aperture radar when the reconnaissance receiver collects the signal.

[0012] S102, extracting synthetic aperture radar semantic information from the multivariate reconnaissance parameter sequence to obtain a synthetic aperture radar semantic sequence; normalizing the synthetic aperture radar semantic sequence to obtain a normalized synthetic aperture radar semantic sequence; calculating a mean of the normalized synthetic aperture radar semantic sequence to obtain a mean of the synthetic aperture radar semantic sequence.

[0013] In this embodiment, the synthetic aperture radar semantic sequence includes a duty cycle sequence and a range resolution sequence.

[0014] Specifically, considering that the range resolution and duty cycle are closely related to the quality of the spaceborne synthetic aperture radar image, in this embodiment, the range resolution and duty cycle are used as important feature quantities, wherein the range resolution is determined by the signal bandwidth (Bandwidth, BW), and the duty cycle is related to the pulse width (Pulse Width, PW) and the pulse repetition interval (Pulse Repetition Interval, PRI). In the actual working process of the spaceborne SAR, BW, PW and PRI will be appropriately adjusted according to different task requirements. Since the range resolution and duty cycle are features tightly coupled with the characteristics of the spaceborne SAR working mode, they can reflect the joint changes of the signal BW, PW and PRI. Therefore, the range resolution and duty cycle features can be extracted from the multivariate reconnaissance parameter sequence detected by the reconnaissance receiver to assist in the subsequent identification of the SAR working mode.

[0015] Specifically, for a spaceborne synthetic aperture radar system that transmits a linear frequency modulation signal, the larger the signal bandwidth, the higher the distance resolution capability of the spaceborne synthetic aperture radar. Usually, different working modes of the spaceborne synthetic aperture radar system perform specific imaging tasks by selecting different signal bandwidths. The spaceborne synthetic aperture radar system selects a suitable duty cycle according to the imaging characteristics of different working modes; for example, in the scanning mode, in order to reduce the distance ambiguity and reduce the overlap of pulse echoes, a lower duty cycle is generally used; while in the beamforming mode, a higher duty cycle is generally used to improve the signal-to-noise ratio, thereby obtaining a better synthetic aperture radar image. It can be seen that the distance resolution and duty cycle are tightly coupled with the working mode of the spaceborne synthetic aperture radar system, and can be extracted as synthetic aperture radar semantic information to improve the discrimination of the working mode of the spaceborne synthetic aperture radar.

[0016] Get the distance resolution sequence and duty cycle sequence, their expressions are: ; ; in, represents the range resolution sequence, represents the speed of light, represents the signal bandwidth sequence in the multivariate reconnaissance parameter sequence, Represents the duty cycle sequence. In actual operation, the spaceborne synthetic aperture radar selects the appropriate duty cycle according to the imaging characteristics of different working modes. represents the pulse width sequence in the multivariate reconnaissance parameter sequence, Represents the pulse repetition period sequence in the multivariate reconnaissance parameter sequence.

[0017] The distance resolution sequence and duty cycle sequence are normalized respectively to obtain the normalized distance resolution sequence and the normalized duty cycle sequence , whose expression is: ; in, represents the normalized threshold of the distance resolution sequence, represents the normalized threshold of the duty cycle sequence, function The expression is: ; in, express or ; Calculate the mean of the normalized distance resolution sequence and the mean of the normalized duty cycle sequence, and their expressions are: ; ; in, represents the mean of the normalized distance resolution sequence, represents the number of elements in the normalized distance resolution sequence, represents the first in the normalized distance resolution sequence elements, represents the mean of the normalized duty cycle sequence, represents the first in the normalized duty cycle sequence elements, Represents a sum operation.

[0018] S103, extracting the amplitude sequence in the multivariate reconnaissance parameter sequence to obtain an amplitude sequence, and normalizing the amplitude sequence to obtain a normalized amplitude sequence.

[0019] Specifically, in this embodiment, the maximum and minimum normalization method is used to normalize the amplitude sequence to a value between [0, 1] to avoid the influence of different variable dimensions during the processing.

[0020] The expression of the normalized amplitude sequence is: ; in, represents the amplitude sequence in the multivariate reconnaissance parameter sequence of the spaceborne synthetic aperture radar reconnaissance signal to be identified, represents the minimum value function, represents the maximum value function, Represents the normalized amplitude sequence.

[0021] S104. Using the trained spaceborne synthetic aperture radar working mode recognition network, process the mean value and normalized amplitude sequence of the synthetic aperture radar semantic sequence to obtain the working mode corresponding to the multivariate reconnaissance parameter sequence.

[0022] Among them, the trained spaceborne synthetic aperture radar working mode recognition network uses preset category data as training data set to train the initial spaceborne synthetic aperture radar working mode recognition network. During the training process, the preset category data is used as a verification data set to perform model selection and hyperparameter tuning on the spaceborne synthetic aperture radar working mode recognition network.

[0023] Specifically, see Figure 2 , Figure 2 1 is a schematic diagram of a trained spaceborne synthetic aperture radar working mode recognition network provided by an embodiment of the present invention. In this embodiment, the trained spaceborne synthetic aperture radar working mode recognition network includes a trained feature embedding network, a trained feature extraction network and a trained classifier. The trained feature embedding network includes a trained amplitude sequence feature embedding network and a trained synthetic aperture radar semantic feature embedding network. The trained spaceborne synthetic aperture radar working mode recognition network is used to process the mean of the synthetic aperture radar semantic sequence and the normalized amplitude sequence to obtain the working mode corresponding to the multivariate reconnaissance parameter sequence, including: The trained synthetic aperture radar semantic feature embedding network is used to process the mean of the synthetic aperture radar semantic sequence to obtain semantic embedding vectors of different scales; the trained amplitude sequence feature embedding network is used to process the normalized amplitude sequence, and the patch processing is performed with different patch lengths to obtain patch sequences of different scales, and according to the patch sequences of different scales, amplitude sequence embedding vectors of different scales are obtained; the semantic embedding vector and the amplitude sequence embedding vector of the same scale are cascaded to obtain cascaded embedding vectors of different scales; The trained feature extraction network is used to extract features from cascade embedding vectors of different scales to obtain deep latent features; The trained classifier is used to classify the deep latent features and identify the working mode corresponding to the multivariate reconnaissance parameter sequence.

[0024] In this embodiment, the trained synthetic aperture radar semantic feature embedding network includes a first fully connected layer, an activation layer, and a second fully connected layer; The synthetic aperture radar semantic feature embedding network is used to process the mean of the synthetic aperture radar semantic sequence, the dimension of the mean of the synthetic aperture radar semantic sequence is transformed through the first fully connected layer to obtain a feature vector after dimension expansion, an activation layer is used to increase the nonlinear representation ability of the feature vector after dimension expansion to obtain an activated feature vector, and a second fully connected layer is used to transform the dimension of the activated feature vector to obtain a deep semantic embedding vector; the deep semantic embedding vector is rearranged according to different scales to obtain semantic embedding vectors of different scales.

[0025] It should be noted that the fully connected layer is used to transform the feature dimension, and the activation layer is a Tanh activation layer, which is used to increase the nonlinear representation ability of the network.

[0026] In this embodiment, the trained amplitude sequence feature embedding network includes a multi-scale processing layer, a first linear mapping layer, a second linear mapping layer, a third linear mapping layer and a first normalization layer; the first linear mapping layer, the second linear mapping layer and the third linear mapping layer all include a third fully connected layer and a position encoding layer; it should be noted that the parameters of the third fully connected layer and the position encoding layer included in the first linear mapping layer, the second linear mapping layer and the third linear mapping layer are different; A multi-scale processing layer is used to process the normalized amplitude sequence to obtain a sequence of patches of different scales. The first linear mapping layer, the second linear mapping layer and the third linear mapping layer are used to process the patch sequences of different scales respectively, and the patch sequences of different scales are embedded into the embedding vectors of the patch sequences of different scales through the third fully connected layer, and the encoding vectors of different scales are generated through the position encoding layer; Add the embedding vectors of the patch sequences of different scales to the corresponding encoding vectors of the same scale to obtain amplitude vectors of different scales; The first normalization layer is used to normalize the amplitude vectors of different scales to obtain the amplitude sequence embedding vectors of different scales.

[0027] It should be noted that the multi-scale processing layer is used to process the normalized amplitude sequence into multi-scale sub-sequences, the position encoding layer is used to record the distribution of timing information in the sample sequence, and the layer normalization layer is used to normalize the feature vector to improve the network convergence speed.

[0028] In this embodiment, the trained feature extraction network includes a first encoder, a first segmentation block (patch) sequence merging layer, a second encoder, a second segmentation block (patch) sequence merging layer and a third encoder; the first encoder, the second encoder and the third encoder all include multiple layers of second normalization layers, feedforward layers and multi-head attention mechanism layers, the parameters of the multiple layers of second normalization layers are different, and the first segmentation block (patch) sequence merging layer and the second segmentation block (patch) sequence merging layer both include a merging layer, a third normalization layer and a fourth fully connected layer; Using a first encoder to process a first-scale concatenated embedding vector among concatenated embedding vectors of different scales, to obtain a deep implicit feature of the first scale; The deep implicit features of the first scale are processed by a first segmentation block (patch) sequence merging layer to obtain a first merged deep implicit feature, and the cascade embedding vector of the second scale in the cascade embedding vectors of different scales is added to the first merged deep implicit feature to obtain a first feature to be processed; The first feature to be processed is processed by a second encoder to obtain a deep latent feature of a second scale; The second scale deep implicit features are processed by a second patch sequence merging layer to obtain a second merged deep implicit feature, and the concatenated embedding vector of the third scale in the concatenated embedding vectors of different scales is added to the second merged deep implicit feature to obtain a second feature to be processed; The third encoder is used to process the second feature to be processed to obtain a deep latent feature.

[0029] It should be noted that the first encoder, the second encoder and the third encoder are all encoders in the Transformer network. The first patch sequence merging layer and the second patch sequence merging layer are used to merge feature vectors. The multi-head attention mechanism layer is used to calculate the attention weights between different patches in the patch sequence to capture the dependencies within the sequence.

[0030] In this embodiment, the trained classifier includes an activation layer, a fifth fully connected layer, a sixth fully connected layer, and an activation function layer; The activation layer is used to process the deep implicit features to improve the nonlinear expression ability of the network. The fifth and sixth fully connected layers are used to compress the feature vector information. The feature vector output by the fully connected layer is represented in the form of working mode category probability through the activation function layer.

[0031] In this embodiment, the training process of the trained spaceborne synthetic aperture radar working mode recognition network includes: Get data for multiple preset categories; Extracting synthetic aperture radar semantic information from data of a preset category to obtain a training synthetic aperture radar semantic sequence; normalizing the training synthetic aperture radar semantic sequence to obtain a normalized training synthetic aperture radar semantic sequence; calculating a mean of the normalized training synthetic aperture radar semantic sequence to obtain a mean of the training synthetic aperture radar semantic sequence; Extracting the amplitude sequence in the data of the preset category to obtain a training amplitude sequence, normalizing the training amplitude sequence to obtain a normalized training amplitude sequence; Will The mean of the training synthetic aperture radar semantic sequence corresponding to the preset categories of data and the normalized training amplitude sequence are used as samples in the training data set. The mean of the training synthetic aperture radar semantic sequence corresponding to the preset category of data and the normalized training amplitude sequence are used as samples in the verification data set; at the same time, the true labels of the samples in the training data set and the verification data set are obtained; and is a positive integer greater than 0; Input some samples in the training data set into the The spaceborne synthetic aperture radar working mode recognition network to be trained is trained to obtain the first The prediction results output by the classifier during the training process; According to The prediction results output by the classifier during the training process are consistent with the The real labels of the samples of the spaceborne synthetic aperture radar working mode recognition network to be trained are used to calculate the classification loss and serve as the first The classification loss of the training process; According to The classification loss of the first training process is back-propagated to update the The network parameters of the spaceborne synthetic aperture radar working mode recognition network to be trained are obtained. The spaceborne synthetic aperture radar working mode recognition network to be trained is trained times; at the same time, a preset verification interval value is set for each interval, for example, 20 training times is used as the preset verification interval value, and the samples in the verification data set are input into the spaceborne synthetic aperture radar working mode recognition network to be trained, and the prediction results output by the classifier are obtained. Combined with the real labels of the samples in the verification data set, model selection and hyperparameter tuning are performed, and this is iterated until the number of training times or the degree of convergence meets the preset conditions, and a trained spaceborne synthetic aperture radar working mode recognition network is obtained.

[0032] In summary, the present invention provides a method for identifying the working mode of a spaceborne SAR based on a multi-scale network, which improves the network's ability to recognize different working modes under non-ideal conditions by introducing synthetic aperture radar semantic information such as duty cycle and range resolution that are tightly coupled with the working mode of the synthetic aperture radar. The multi-scale information of the mean of the synthetic aperture radar semantic sequence and the normalized amplitude sequence is fully integrated through the trained spaceborne synthetic aperture radar working mode recognition network, thereby improving the distinction between different working modes of the spaceborne synthetic aperture radar in the high-dimensional latent feature space, thereby improving the accuracy of the recognition of the working mode of the spaceborne synthetic aperture radar. In addition, experiments in complex scenarios with a high proportion of missed pulses and false pulses show that compared with the existing spaceborne synthetic aperture radar working mode recognition method, the spaceborne synthetic aperture radar working mode recognition method based on the knowledge-assisted multi-scale information fusion network has good recognition accuracy and robustness.

[0033] In an optional embodiment of the present invention, the spaceborne synthetic aperture radar working mode recognition of the present invention is implemented through the following process, specifically: S201. Acquire a multivariate reconnaissance parameter sequence of a satellite-borne synthetic aperture radar reconnaissance signal.

[0034] S202. According to synthetic aperture radar expert knowledge, synthetic aperture radar semantic information such as a range resolution sequence and a duty cycle sequence that are tightly coupled with a spaceborne synthetic aperture radar working mode are extracted from a multivariate reconnaissance parameter sequence to obtain a synthetic aperture radar semantic sequence, and the synthetic aperture radar semantic sequence is normalized to obtain a normalized synthetic aperture radar semantic sequence, which are a normalized range resolution sequence and a normalized duty cycle sequence.

[0035] S203, calculating the means of the normalized range resolution sequence and the normalized duty cycle sequence to obtain the mean of the synthetic aperture radar semantic sequence, which are the means of the range resolution sequence and the means of the duty cycle sequence respectively.

[0036] S204, extracting an amplitude sequence from the multivariate reconnaissance parameter sequence, and normalizing the amplitude sequence using a maximum-minimum normalization method to obtain a normalized amplitude sequence.

[0037] S205, constructing multiple samples, each sample including a normalized amplitude sequence and a mean of a synthetic aperture radar semantic sequence; dividing the multiple samples into a training data set, a validation data set, and a test data set; and at the same time, marking the true labels of the working modes corresponding to the samples in the training data set and the validation data set.

[0038] Optionally, the number of samples in the training data set, the validation data set, and the test data set may be determined according to actual conditions, and the present invention does not make any specific limitation thereto.

[0039] S206. Construct a satellite-borne synthetic aperture radar working mode recognition network.

[0040] Please continue to see Figure 2 ,The space-borne synthetic aperture radar working mode recognition network includes feature embedding network, feature extraction network and classifier.

[0041] Among them, the feature embedding network includes an amplitude sequence feature embedding network and a synthetic aperture radar semantic feature embedding network; the synthetic aperture radar semantic feature embedding network includes a first fully connected layer, an activation layer and a second fully connected layer; the amplitude sequence feature embedding network includes a multi-scale processing layer, a first linear mapping layer, a second linear mapping layer, a third linear mapping layer and a first normalization layer; the first linear mapping layer, the second linear mapping layer and the third linear mapping layer all include a third fully connected layer and a position encoding layer; it should be noted that the parameters of the third fully connected layer and the position encoding layer included in the first linear mapping layer, the second linear mapping layer and the third linear mapping layer are different.

[0042] The feature extraction network includes a first encoder, a first patch sequence merging layer, a second encoder, a second patch sequence merging layer and a third encoder; the first encoder, the second encoder and the third encoder all include multiple layers of second normalization layers, feedforward layers and multi-head attention mechanism layers, the parameters of the multiple layers of second normalization layers are different, the first patch sequence merging layer and the second patch sequence merging layer both include a merging layer, a third normalization layer and a fourth fully connected layer.

[0043] The classifier includes an activation layer, a fifth fully connected layer, a sixth fully connected layer and an activation function layer; the classifier is used to establish a mapping relationship between deep latent features and corresponding spaceborne synthetic aperture radar working mode categories.

[0044] It should be noted that at this time, the network parameters of the spaceborne synthetic aperture radar working mode recognition network have not been determined.

[0045] S207, initialize the spaceborne synthetic aperture radar working mode recognition network, input the training data set and the verification data set into the initial spaceborne synthetic aperture radar working mode recognition network, train the spaceborne synthetic aperture radar working mode recognition network with samples in the training data set, and iteratively optimize the network parameters under the guidance of the loss function until convergence, and perform model selection and hyperparameter tuning on the samples in the verification data set during the training process to obtain a trained spaceborne synthetic aperture radar working mode recognition network.

[0046] S208, inputting the samples in the test data set into the trained spaceborne synthetic aperture radar working mode recognition network to identify the working mode category corresponding to the samples in the test data set.

[0047] S2081. Input the samples in the test data set into the trained feature embedding network, and output semantic embedding vectors of different scales and amplitude sequence embedding vectors of different scales respectively.

[0048] S2082. Concatenate the semantic embedding vector and the amplitude sequence embedding vector of the same scale to obtain concatenated embedding vectors of different scales.

[0049] S2083. Input the cascade embedding vectors of different scales into the trained feature extraction network for processing to obtain deep latent features.

[0050] S2084. Input the deep latent features into the trained classifier for processing to obtain the working mode corresponding to the samples in the test data set.

[0051] In an optional embodiment of the present invention, the effect of the spaceborne SAR working mode recognition method based on the multi-scale network provided in the above embodiment is verified by simulation experiments, specifically: 1. Simulation conditions The simulation experiment conditions of this embodiment are as follows: the data of the four working modes of the spaceborne synthetic aperture radar, namely, strip, beam, sliding beam and scanning, are simulated. The range of simulation parameter values ​​of different working modes of the spaceborne synthetic aperture radar is shown in Table 1. Among them, 1000 samples are generated in each working mode, and the total number of samples is 4000. 70% of the total number of samples are randomly selected to construct a training data set, 10% to construct a verification data set, and 20% to construct a test data set. At the same time, in order to test the adaptability of the method proposed in the present invention in a complex environment containing leaky pulses and false pulses, the proportions of leaky pulses and false pulses are set between 0% and 20%, respectively.

[0052] Table 1 Simulation parameter values ​​of different working modes of spaceborne synthetic aperture radar

[0053] 2. Simulation content and results analysis Please refer to Table 2, batch size is the number of samples used to update the model parameters in each iteration, epoch is the number of times the model is fully trained using all training samples, initial learning rate is the initial learning rate, optimizer is the optimizer, V_dim is the dimension of the hidden layer feature vector, N_heads is the number of heads in the multi-head attention mechanism, d ff is the dimension of the fully connected layer, and layers is the number of Transformer encoders. 70% of all samples are randomly selected for training, 10% for validation, and the remaining 20% ​​for testing. The validation dataset is used to verify the performance of the trained spaceborne synthetic aperture radar working mode recognition network in some iterations, and the test dataset is used to test the performance of the overall trained spaceborne synthetic aperture radar working mode recognition network.

[0054] Table 2 Parameters of the spaceborne synthetic aperture radar working mode recognition network

[0055] The performance of the method proposed in the present invention was tested under different proportions of leaked pulses and false pulses. The results show that as the proportion of false pulses and leaked pulses gradually increases, the performance of the algorithm gradually decreases. This is because the existence of false pulses and leaked pulses will destroy the timing laws and joint feature laws of each working mode data, and the higher the proportion, the more serious the degree of destruction of the data law, which makes it difficult for the network to extract highly distinguishable features. It is worth noting that the spaceborne SAR working mode recognition method based on a multi-scale network of the present invention can still maintain the highest recognition accuracy when the proportion of leaked pulses or false pulses is as high as 20%. This is due to the introduction of synthetic aperture radar semantic information that is tightly coupled with the working mode of the spaceborne synthetic aperture radar, which reduces the impact of outliers on the network; and the use of multi-scale information fusion, which effectively improves the recognition accuracy of the spaceborne synthetic aperture radar working mode under non-ideal conditions containing leaked pulses and false pulses.

[0056] See also Figure 3 , Figure 3 is a schematic diagram of result curves of different satellite-borne synthetic aperture radar working mode recognition methods when the false pulse ratio provided by the embodiment of the present invention increases from 5% to 20%. Figure 3 It is the accuracy curve, the horizontal axis represents the proportion of added false pulses, the vertical axis represents the accuracy, the curve with squares is the experimental result of the method proposed in the present invention, the curve with circles is the experimental result of the CNN method, the curve with five-pointed stars is the experimental result of the Transformer method, and the curve with triangles is the experimental result of the TCN method. It can be seen that with the gradual increase in the proportion of false pulses, the experimental results of all methods have declined to varying degrees. However, the method proposed in the present invention always maintains the highest accuracy in this process. This result shows that the method proposed in the present invention has good adaptability under non-ideal conditions.

[0057] See also Figure 4 , Figure 4 is a schematic diagram of result curves of different satellite-borne synthetic aperture radar working mode recognition methods when the leakage pulse ratio provided by the embodiment of the present invention increases from 5% to 20%, Figure 4It is the accuracy curve, the horizontal axis represents the proportion of added leakage pulses, and the vertical axis represents the accuracy. The curve with squares in the figure is the experimental result of the method proposed in the present invention, the curve with circles is the experimental result of the CNN method, the curve with five-pointed stars is the experimental result of the Transformer method, and the curve with triangles is the experimental result of the TCN method. It can be seen that with the gradual increase in the proportion of leakage pulses, the experimental results of all methods have declined to varying degrees. However, the method proposed in the present invention always maintains the highest accuracy in this process. This result shows that the method proposed in the present invention has good adaptability under non-ideal conditions.

[0058] The proposed method introduces semantic information of SAR such as range resolution and duty cycle, which are tightly coupled with the working mode of spaceborne SAR, into the working mode recognition task of spaceborne SAR according to the SAR expert knowledge, thus enriching the representation of the working mode. On this basis, in order to solve the problem of low accuracy of the working mode recognition of spaceborne SAR in complex non-ideal scenarios with high proportion of missed pulses and false pulses, a working mode recognition network of spaceborne SAR is constructed. The network uses a feature extraction module to fully fuse the cascaded embedding vectors of different scales based on the cascaded multi-scale amplitude sequence embedding vectors and semantic embedding vectors, effectively improving the discrimination of different working modes of spaceborne SAR in high-dimensional latent feature space, thereby effectively improving the accuracy of the working mode recognition of spaceborne SAR.

[0059] Based on the same inventive concept, the present invention also provides a spaceborne SAR working mode recognition device based on a multi-scale network, including a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; Memory, used to store computer programs; The processor is used to implement the above-mentioned multi-scale network-based spaceborne SAR working mode recognition method when executing the program stored in the memory.

[0060] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations. Moreover, the term "include", "comprise" or any other variant is intended to cover non-exclusive inclusion, so that the article or device including a series of elements includes not only those elements, but also other elements that are not explicitly listed. In the absence of more restrictions, the elements defined by the sentence "including one..." do not exclude the existence of other identical elements in the article or device including the elements. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. The orientation or position relationship indicated by "up", "down", "left", "right", etc. is based on the orientation or position relationship shown in the accompanying drawings, which is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation of the present invention.

[0061] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification.

[0062] The above contents are further detailed descriptions of the present invention in combination with specific preferred embodiments, and it cannot be determined that the specific implementation of the present invention is limited to these descriptions. For ordinary technicians in the technical field to which the present invention belongs, several simple deductions or substitutions can be made without departing from the concept of the present invention, which should be regarded as falling within the protection scope of the present invention.

Claims

1. A method for identifying spaceborne SAR working modes based on multi-scale networks, characterized in that: include: Acquire a multi-element reconnaissance parameter sequence of a spaceborne synthetic aperture radar reconnaissance signal to be identified; Extracting synthetic aperture radar semantic information from the multivariate reconnaissance parameter sequence to obtain a synthetic aperture radar semantic sequence; normalizing the synthetic aperture radar semantic sequence to obtain a normalized synthetic aperture radar semantic sequence; calculating a mean of the normalized synthetic aperture radar semantic sequence to obtain a mean of the synthetic aperture radar semantic sequence; Extracting the amplitude sequence in the multivariate reconnaissance parameter sequence to obtain an amplitude sequence, and normalizing the amplitude sequence to obtain a normalized amplitude sequence; Using a trained spaceborne synthetic aperture radar working mode recognition network, the mean of the synthetic aperture radar semantic sequence and the normalized amplitude sequence are processed to obtain the working mode corresponding to the multivariate reconnaissance parameter sequence; The trained spaceborne synthetic aperture radar working mode recognition network uses preset category data as a training data set to train the initial spaceborne synthetic aperture radar working mode recognition network, and during the training process, the preset category data is used as a verification data set to perform model selection and hyperparameter tuning on the spaceborne synthetic aperture radar working mode recognition network.

2. The method for identifying spaceborne SAR working modes based on multi-scale networks according to claim 1, characterized in that: The trained spaceborne synthetic aperture radar working mode recognition network includes a trained feature embedding network, a trained feature extraction network and a trained classifier, and the trained feature embedding network includes a trained amplitude sequence feature embedding network and a trained synthetic aperture radar semantic feature embedding network; The method uses a trained spaceborne synthetic aperture radar working mode recognition network to process the mean of the synthetic aperture radar semantic sequence and the normalized amplitude sequence to obtain the working mode corresponding to the multivariate reconnaissance parameter sequence, including: The trained synthetic aperture radar semantic feature embedding network is used to process the mean of the synthetic aperture radar semantic sequence to obtain semantic embedding vectors of different scales; the trained amplitude sequence feature embedding network is used to process the normalized amplitude sequence, and segmentation block processing is performed with different segmentation block lengths to obtain segmentation block sequences of different scales, and amplitude sequence embedding vectors of different scales are obtained according to the segmentation block sequences of different scales; the semantic embedding vector and the amplitude sequence embedding vector of the same scale are cascaded to obtain cascaded embedding vectors of different scales; Using the trained feature extraction network to extract features from the cascade embedding vectors of different scales to obtain deep hidden features; The trained classifier is used to classify the deep latent features and identify the working mode corresponding to the multivariate reconnaissance parameter sequence.

3. The method for identifying spaceborne SAR working modes based on multi-scale networks according to claim 2, characterized in that: The trained synthetic aperture radar semantic feature embedding network includes a first fully connected layer, an activation layer, and a second fully connected layer; The synthetic aperture radar semantic feature embedding network is used to process the mean of the synthetic aperture radar semantic sequence, the first fully connected layer is used to transform the dimension of the mean of the synthetic aperture radar semantic sequence to obtain a dimensionally expanded feature vector, the activation layer is used to increase the nonlinear representation ability of the dimensionally expanded feature vector to obtain an activated feature vector, the second fully connected layer is used to transform the dimension of the activated feature vector to obtain a deep semantic embedding vector; the deep semantic embedding vector is rearranged according to different scales to obtain semantic embedding vectors of different scales.

4. The method for identifying spaceborne SAR working modes based on multi-scale networks according to claim 2, characterized in that: The trained amplitude sequence feature embedding network includes a multi-scale processing layer, a first linear mapping layer, a second linear mapping layer, a third linear mapping layer and a first normalization layer; the first linear mapping layer, the second linear mapping layer and the third linear mapping layer all include a third fully connected layer and a position encoding layer; The normalized amplitude sequence is processed by the multi-scale processing layer to obtain a sequence of segmented blocks of different scales; The first linear mapping layer, the second linear mapping layer and the third linear mapping layer are used to process the segmented block sequences of different scales respectively, and the segmented block sequences of different scales are embedded into embedding vectors of the segmented block sequences of different scales through the third fully connected layer, and the encoding vectors of different scales are generated through the position encoding layer; Adding the embedding vectors of the segmented block sequences of different scales to the corresponding encoding vectors of the same scale to obtain amplitude vectors of different scales; The first normalization layer is used to normalize the amplitude vectors of different scales to obtain amplitude sequence embedding vectors of different scales.

5. The method for identifying spaceborne SAR working modes based on multi-scale networks according to claim 2, characterized in that: The trained feature extraction network includes a first encoder, a first segmentation block sequence merging layer, a second encoder, a second segmentation block sequence merging layer and a third encoder; the first encoder, the second encoder and the third encoder all include a multi-layer second normalization layer, a feedforward layer and a multi-head attention mechanism layer, and the first segmentation block sequence merging layer and the second segmentation block sequence merging layer all include a merging layer, a third normalization layer and a fourth fully connected layer; Using the first encoder to process the concatenated embedding vector of a first scale among the concatenated embedding vectors of different scales to obtain a deep implicit feature of the first scale; Using the first segmentation block sequence merging layer to process the deep implicit features of the first scale to obtain a first merged deep implicit feature, adding the cascade embedding vector of the second scale in the cascade embedding vectors of different scales to the first merged deep implicit feature to obtain a first feature to be processed; Using the second encoder to process the first feature to be processed to obtain a deep latent feature of a second scale; The second segmentation block sequence merging layer is used to process the second scale deep implicit features to obtain second merged deep implicit features, and the cascade embedding vector of the third scale in the cascade embedding vectors of different scales is added to the second merged deep implicit features to obtain a second feature to be processed; The third encoder is used to process the second feature to be processed to obtain a deep latent feature.

6. The method for identifying spaceborne SAR working modes based on multi-scale networks according to claim 1, characterized in that: The synthetic aperture radar semantic sequence includes a duty cycle sequence and a range resolution sequence.

7. The method for identifying spaceborne SAR working modes based on multi-scale networks according to claim 6, characterized in that: The step of extracting the synthetic aperture radar semantic information from the multivariate reconnaissance parameter sequence to obtain a synthetic aperture radar semantic sequence; and normalizing the synthetic aperture radar semantic sequence to obtain a normalized synthetic aperture radar semantic sequence; Calculating the mean of the normalized synthetic aperture radar semantic sequence to obtain the mean of the synthetic aperture radar semantic sequence includes: Get the distance resolution sequence and duty cycle sequence, their expressions are: ； ； in, represents the range resolution sequence, represents the speed of light, represents the signal bandwidth sequence in the multivariate reconnaissance parameter sequence, represents the duty cycle sequence, represents the pulse width sequence in the multivariate reconnaissance parameter sequence, represents the pulse repetition period sequence in the multivariate reconnaissance parameter sequence; The distance resolution sequence and the duty cycle sequence are normalized to obtain a normalized distance resolution sequence. and the normalized duty cycle sequence , whose expression is: ； in, represents the normalized threshold of the distance resolution sequence, represents the normalized threshold of the duty cycle sequence, function The expression is: ； in, express or ; The mean of the normalized distance resolution sequence and the mean of the normalized duty cycle sequence are calculated, and their expressions are: ； ； in, represents the mean of the normalized distance resolution sequence, represents the number of elements in the normalized distance resolution sequence, represents the normalized distance resolution sequence elements, represents the mean of the normalized duty cycle sequence, represents the first in the normalized duty cycle sequence elements, Represents a sum operation.

8. The method for identifying spaceborne SAR working modes based on multi-scale networks according to claim 1, characterized in that: The expression of the normalized amplitude sequence is: ； in, represents the amplitude sequence in the multivariate reconnaissance parameter sequence, represents the minimum value function, represents the maximum value function, Represents the normalized amplitude sequence.

9. The method for identifying spaceborne SAR working modes based on multi-scale networks according to claim 1, characterized in that: The training process of the trained spaceborne synthetic aperture radar working mode recognition network includes: Acquire data of a plurality of preset categories; Extracting synthetic aperture radar semantic information from the preset category of data to obtain a training synthetic aperture radar semantic sequence; normalizing the training synthetic aperture radar semantic sequence to obtain a normalized training synthetic aperture radar semantic sequence; calculating a mean of the normalized training synthetic aperture radar semantic sequence to obtain a mean of the training synthetic aperture radar semantic sequence; Extracting an amplitude sequence from the preset category of data to obtain a training amplitude sequence, and normalizing the training amplitude sequence to obtain a normalized training amplitude sequence; Will The mean of the training synthetic aperture radar semantic sequence corresponding to the preset category of data and the normalized training amplitude sequence are used as samples in the training data set. The mean of the training synthetic aperture radar semantic sequence corresponding to the preset category of data and the normalized training amplitude sequence are used as samples in the verification data set; at the same time, the true labels of the samples in the training data set and the verification data set are obtained; and is a positive integer greater than 0; Input some samples in the training data set into the The spaceborne synthetic aperture radar working mode recognition network to be trained is trained to obtain the first The prediction results output by the classifier during the training process; According to The prediction results output by the classifier during the training process are consistent with the The real labels of the samples of the spaceborne synthetic aperture radar working mode recognition network to be trained are used to calculate the classification loss and serve as the first The classification loss of the training process; According to The classification loss of the first training process is back-propagated to update the The network parameters of the spaceborne synthetic aperture radar working mode recognition network to be trained are obtained. The satellite-borne synthetic aperture radar working mode recognition network to be trained is inputted with the samples in the verification data set into the satellite-borne synthetic aperture radar working mode recognition network to be trained at each preset verification interval value, and the prediction result output by the classifier is obtained. The model selection and hyperparameter tuning are performed in combination with the real labels of the samples in the verification data set, and the training is iterated until the number of training times or the degree of convergence meets the preset conditions, thereby obtaining the trained satellite-borne synthetic aperture radar working mode recognition network.

10. A spaceborne SAR working mode recognition device based on a multi-scale network, comprising a processor, a communication interface, a memory and a communication bus, characterized in that: The processor, the communication interface and the memory communicate with each other via the communication bus; The memory is used to store computer programs; The processor, when used to execute the program stored in the memory, implements the method according to any one of claims 1 to 9.

Images