Radar identification method for unknown space cone target

Abstract

The invention discloses a radar identification method for an unknown space cone target. The radar identification method for the unknown space cone target comprises the following steps: acquiring a to-be-detected HRRP sequence; extracting weighted physical features and deep features of the to-be-detected HRRP sequence; fusing the weighted physical features and the deep features to obtain fused features; inputting the fusion features into a pre-trained prototype network to obtain a plurality of to-be-tested embedded vectors based on the prototype network; unknown space cone target radar identification is carried out based on the prototype vector of each target type and the embedded vector to be measured; the target types comprise a space cone target, a light accompanying flying false target and a heavy accompanying flying false target. According to the unknown space cone target radar identification method provided by the invention, the universal problems of weak generalization ability of the space cone target and difficulty in zero sample identification in the existing identification method are solved.

Description

Technical Field

[0001] The invention belongs to the technical field of radar target recognition, and in particular relates to a radar recognition method for an unknown space cone target. Background Art

[0002] In modern military warfare, space cone targets have a long attack range and a fast strike speed, and have a strong strategic deterrent capability. However, during the flight of space cone targets, there are often a large number of accompanying false targets. Identifying space cone targets from many accompanying false targets is of great significance to anti-missile defense and national security.

[0003] In order to penetrate effectively, the space cone target and the accompanying false target usually maintain a small target distance when flying. Narrowband radar is limited by bandwidth and has low range resolution. Multiple targets may exist in the same range unit of the low-resolution range profile echo, resulting in the inability to distinguish different targets. However, broadband radar has a larger bandwidth and higher range resolution. Different targets are located in different range unit areas of the high-resolution range profile (HRRP) echo, which is conducive to the distinction between different targets and further judgment of the specific categories of space cone targets and accompanying false targets. In addition, the broadband radar HRRP can reflect the distribution information of the target scattering center in the direction of the radar line of sight, and contains richer target detail information than the narrowband echo. Therefore, the recognition of space cone targets based on broadband radar HRRP echo has important research significance and has received widespread attention.

[0004] Existing spatial cone target recognition methods based on radar HRRP sequences can be divided into two types: recognition methods based on artificial feature extraction and recognition methods based on deep learning. The spatial cone target recognition method based on artificial feature extraction first extracts statistical features such as the number of scattering points and energy entropy or transform domain features such as Doppler domain and time-frequency domain from the radar target HRRP echo data. On the basis of feature extraction, shallow recognition models such as k-nearest neighbor and random forest are used to realize the recognition of spatial cone targets. The spatial cone target recognition method based on deep learning can realize the approximation of complex functions between input radar target echoes and category labels through multi-layer nonlinear transformations, and complete end-to-end learning between input data and output categories.

[0005] The patent "A method for mid-course target recognition using HRRP sequence at low data rate" with publication number CN115932778A proposes a method for mid-course target recognition based on low data rate HRRP sequence. This method is based on the periodicity of the scattering center point in the HRRP sequence. The energy distribution of the signal along the time dimension is obtained through time-frequency analysis, and the target precession frequency is extracted. In addition, the number of target scattering points, target length, entropy and other features are extracted and spliced ​​with the precession frequency features. The classification of fused features is realized using a random forest classifier. The document "HRRP image recognition of mid-course targets based on DCNN System Engineering and Electronic Technology, 2020, 42(11): 2426-2433" proposes a spatial cone target HRRP image recognition method based on a deep convolutional neural network (DCNN). The specific steps of this method are: the first step is to use the HRRP visualization method to convert the one-dimensional HRRP into a 0-1 binary HRRP image; the second step is to use the DCNN combined with the L2 regularization constraint to extract the 0-1 binary HRRP image features layer by layer; the third step is to use the normalized exponential function based on the proposed features to realize the classification of spatial cone targets.

[0006] However, the existing HRRP recognition method for space cone target radar is limited to the category judgment of known space cone targets, light accompanying false targets, and heavy accompanying false targets that appeared in the training phase. However, with the continuous optimization and updating of equipment, there are usually new non-cooperative unknown targets in actual combat that have different parameters such as micro-motion and structure from the known targets in training. For unknown variable parameter targets that are not involved in training, the existing recognition methods have the general problem of weak generalization ability and difficulty in zero-sample recognition. Summary of the invention

[0007] In order to solve the above problems existing in the prior art, the present invention provides a radar recognition method for unknown spatial cone targets.

[0008] The technical problem to be solved by the present invention is achieved through the following technical solutions:

[0009] The present invention provides a method for radar recognition of an unknown space cone target, and the method comprises:

[0010] Obtain the HRRP sequence to be tested;

[0011] Extracting weighted physical features and deep features of the HRRP sequence to be tested;

[0012] fusing the weighted physical feature and the deep feature to obtain a fused feature;

[0013] Inputting the fused features into a pre-trained prototype network to obtain a plurality of embedding vectors to be tested based on the prototype network;

[0014] The unknown space cone target radar recognition is performed based on the prototype vector of each target type and the embedded vector to be tested; the target types include space cone targets, light accompanying false targets and heavy accompanying false targets.

[0015] Optionally, the method of extracting the weighted physical characteristics of the HRRP sequence to be measured includes:

[0016] Acquiring physical characteristics of the HRRP sequence to be tested;

[0017] The physical feature is subjected to nonlinear transformation and normalized exponential function to obtain a normalized physical feature weight vector;

[0018] The physical feature is weighted by using the normalized physical feature weight vector to obtain a weighted physical feature.

[0019] Optionally, the physical characteristics include micro-motion parameters, structural parameters, maximum radial dimension characteristics and energy entropy characteristics.

[0020] Optionally, the method for obtaining the maximum radial dimension feature includes:

[0021] Acquire energy distribution of the HRRP sequence to be measured;

[0022] Determine a HRRP sequence signal search area based on the energy distribution;

[0023] Determining the radial size of each HRRP echo in the HRRP sequence to be measured based on the HRRP sequence signal search area;

[0024] The largest radial dimension is selected as the maximum radial dimension feature.

[0025] Optionally, the radial size of each HRRP echo in the HRRP sequence to be measured is calculated as follows:

[0026]

[0027] Among them, L i represents the radial size of the i-th HRRP echo in the HRRP sequence to be measured; M represents the number of HRRP echoes in the HRRP sequence to be measured; ρ r Indicates radar range resolution; Indicates the number of range units occupied by the radial size of the target in the i-th HRRP echo.

[0028] Optionally, the energy entropy feature is obtained by:

[0029] Acquire energy distribution of the HRRP sequence to be measured;

[0030] Normalizing the energy distribution to obtain an energy probability distribution;

[0031] The information entropy of the energy probability distribution is calculated to obtain the energy entropy feature.

[0032] Optionally, the energy entropy feature is calculated as follows:

[0033]

[0034] Wherein, f7 represents the energy entropy characteristic; p r represents the rth element of the energy probability distribution, r=1, ..., R; R represents the number of distance units of the HRRP echo in the HRRP sequence to be measured.

[0035] Optionally, the calculation method of the prototype vector includes:

[0036] Obtain multiple sample HRRP sequences under each target type;

[0037] Extract sample weighted physical features and sample deep features of sample HRRP sequences under each target type;

[0038] For the sample HRRP sequence under each target type, the sample weighted physical features and sample deep features of the sample HRRP sequence are fused to obtain the sample fusion features under the target type;

[0039] Inputting the sample fusion features under each target type into the prototype network to obtain multiple embedded sample vectors under each target type based on the prototype network;

[0040] For each target type, the average value of multiple embedded sample vectors under the target type is calculated to obtain the prototype vector under the target type.

[0041] The present invention provides a radar recognition method for unknown spatial cone targets. The method characterizes the HRRP sequence to be tested by fusing weighted physical features with deep features, thereby solving the problems of incomplete feature representation and poor inter-class separability in the spatial cone target radar HRRP recognition method in the prior art which only uses shallow features or pure data-driven deep features, and provides a good feature basis for subsequent recognition. In addition, the pre-trained prototype network used in the present invention can more accurately summarize class-general characteristics from known targets through pre-training, and has a stronger generalization ability for similar heterogeneous targets, thereby solving the general problems of weak generalization ability and difficult zero-sample recognition for unknown new spatial cone targets that have not appeared in the training stage in the existing spatial cone target radar HRRP recognition method, and improving the accuracy of unknown spatial cone target radar recognition.

[0042] The present invention will be further described in detail below with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 It is a flow chart of a method for radar identification of unknown space cone targets provided by an embodiment of the present invention;

[0044] Figure 2 is a schematic diagram of energy distribution of a HRRP sequence to be tested provided by an embodiment of the present invention;

[0045] Figure 3 It is a schematic diagram of the number of range units occupied by a single HRRP echo target provided by an embodiment of the present invention;

[0046] Figure 4 is a schematic diagram of the structure of a weight learning network provided by an embodiment of the present invention;

[0047] Figure 5 It is a structural schematic diagram of a deep feature extraction model based on a convolutional neural network provided in an embodiment of the present invention;

[0048] Figure 6 is a schematic diagram of the structure of an adaptive weighted network provided by an embodiment of the present invention;

[0049] Figure 7 It is a comparison diagram of the recognition accuracy confusion matrix of different recognition methods;

[0050] Figure 8 It is a t-SNE visualization diagram of the features proposed by different recognition methods and the classification interface learned;

[0051] Fig. 9 It is a statistical diagram of the average values ​​of the seven-dimensional physical feature weights of all test samples of various types of targets;

[0052] Fig.10It is a schematic diagram of correctly classifying corresponding samples of a radar recognition method for an unknown spatial cone target provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0053] 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.

[0054] In order to solve the technical problems of weak generalization ability and difficulty in zero-sample recognition in the existing space cone target radar HRRP recognition method, the embodiment of the present invention provides an unknown space cone target radar recognition method, see Figure 1 , Figure 1 1 is a flow chart of a method for radar identification of an unknown space cone target provided by an embodiment of the present invention, which specifically includes the following steps:

[0055] Step S101: Acquire a HRRP sequence to be tested.

[0056] In an embodiment of the present invention, a radar system can be used to detect a target to be detected, by transmitting a broadband signal and receiving an echo signal reflected by the target to be detected, and then a series of signal processing steps are performed to extract a HRRP sequence to be detected that reflects the structural characteristics of the target. The HRRP sequence to be detected includes multiple HRRP echoes.

[0057] Step S102: extracting weighted physical features and deep features of the HRRP sequence to be tested.

[0058] In an embodiment of the present invention, the weighted physical characteristics of the HRRP sequence to be measured are obtained by weighting the physical characteristics of the HRRP sequence to be measured. First, the physical characteristics of the HRRP sequence to be measured are described. The physical characteristics of the HRRP sequence to be measured include micro-motion parameters, structural parameters, maximum radial size characteristics and energy entropy characteristics. Among them, the micro-motion parameters include precession frequency f1 and precession angle f2. The structural parameters include cone height f3, cone bottom radius f4 and cone generatrix length f5.

[0059] The micro-motion parameters and structural parameters can be obtained by extracting the scattering point macro-distance curve from the HRRP sequence diagram, and then solving the extracted scattering point macro-distance curve and the scattering point theoretical macro-distance equation. For details, please refer to the prior art, which will not be described in detail here.

[0060] In one implementation, the method for obtaining the maximum radial dimension feature includes:

[0061] Obtaining energy distribution of the HRRP sequence to be measured;

[0062] Determine the HRRP sequence signal search area based on the energy distribution;

[0063] Determine the radial size of each HRRP echo in the HRRP sequence to be measured based on the HRRP sequence signal search area;

[0064] Select the largest radial dimension as the maximum radial dimension feature.

[0065] In the embodiment of the present invention, firstly, all HRRP echoes in the HRRP sequence to be measured are accumulated to obtain the energy distribution of the HRRP sequence to be measured, see Figure 2 , Figure 2 This is a schematic diagram of the energy distribution of the HRRP sequence to be tested provided by an embodiment of the present invention. Then, the mean value of the energy distribution of the HRRP sequence to be tested is used as a threshold, and the HRRP sequence area to be tested within the distance units on the left and right ends greater than the threshold is used as the HRRP sequence signal search area. For each HRRP echo in the HRRP sequence signal search area, all peak points whose amplitude is greater than the mean value of the echo amplitude and greater than the echo amplitude of two adjacent distance units in the HRRP echo are searched, and the distance unit indexes of all peak points are determined. The maximum index value minus the minimum index value is the number of distance units occupied by the radial size of the target in the HRRP echo. See also Figure 3 , Figure 3 Schematic diagram of the number of distance units occupied by a single HRRP echo target provided by an embodiment of the present invention. Taking the 32nd HRRP echo as an example, peak point 1 corresponds to the minimum index k1, peak point 2 corresponds to the maximum index k2, and the number of distance units occupied by the radial size of the target in the 32nd HRRP echo w opt =k2-k1.

[0066] The radial size of the target in the HRRP echo is further calculated:

[0067]

[0068] Among them, L i represents the radial size of the i-th HRRP echo in the HRRP sequence to be measured, M represents the number of HRRP echoes in the HRRP sequence to be measured, and ρ r Indicates the radar range resolution.

[0069] Finally, the maximum radial dimension f6 of the HRRP sequence to be measured is the maximum radial length of all HRRP echoes in the sequence.

[0070] In one implementation, the energy entropy feature is obtained by:

[0071] Obtaining energy distribution of the HRRP sequence to be measured;

[0072] Normalizing the energy distribution to obtain the energy probability distribution;

[0073] The information entropy of energy probability distribution is calculated to obtain the energy entropy characteristics.

[0074] In the embodiment of the present invention, the energy distribution of the HRRP sequence to be measured is normalized to obtain the energy probability distribution p, and the information entropy of the energy probability distribution p is calculated to obtain the energy entropy feature f7 of the HRRP sequence. The calculation method of f7 is:

[0075]

[0076] Among them, p r represents the rth element of the energy probability distribution p, where r=1,…,R; and R represents the number of range units of the HRRP echo in the HRRP sequence to be measured.

[0077] Finally, the above-mentioned 7-dimensional physical features are concatenated to obtain the physical feature f1 = [f1, f2, ..., f7] of the HRRP sequence to be tested.

[0078] In one implementation, the method of extracting the weighted physical characteristics of the HRRP sequence to be measured includes:

[0079] Acquiring physical characteristics of the HRRP sequence to be tested;

[0080] The physical features are subjected to nonlinear transformation and normalized exponential function to obtain a normalized physical feature weight vector;

[0081] The physical features are weighted using the normalized physical feature weight vector to obtain weighted physical features.

[0082] In the embodiment of the present invention, the physical feature f1=[f1, f2, ..., f7] is first input into the weight learning network g composed of a multi-layer fully connected network, see Figure 4 , Figure 4 It is a structural diagram of the weight learning network provided by an embodiment of the present invention. After two layers of nonlinear transformation and normalized exponential function, the normalized physical feature weight vector ω=[ω1,ω2,…,ω7] is obtained, and then the physical feature is weighted to obtain the weighted physical feature f1′=[ω1f1,ω2f2,…,ω7f7].

[0083] In the embodiment of the present invention, the nonlinear transformation is expressed as:

[0084] f l+1 =R(a l+1 f l +b l+1 );

[0085] Where R(·) represents the linear rectification function; f l represents the input of the lth layer of nonlinear transformation; f l+1represents the output of the lth layer nonlinear transformation, l = 1, 2, and f 1 =f1;a l+1 represents the weight of the nonlinear transformation of the lth layer; b l+1 Represents the bias of the nonlinear transformation of the lth layer.

[0086] In the embodiment of the present invention, the normalized exponential function is expressed as:

[0087]

[0088] Among them, x i represents the i-th element of the vector obtained by two layers of nonlinear transformation of f1; x k represents the kth element of the vector obtained by two layers of nonlinear transformation of f1; ω i Represents the i-th element of the normalized physical feature weight vector.

[0089] In the embodiment of the present invention, the extraction of deep features of the HRRP sequence to be measured can be implemented by using a deep feature extraction model based on a convolutional neural network (CNN), as follows:

[0090] The HRRP sequence to be tested is normalized, and then the normalized HRRP sequence to be tested is convolved using multiple convolution kernels to obtain a multi-channel feature map; then the multi-channel feature map is subjected to a channel attention operation to obtain a weighted feature map, see Figure 5 , Figure 5 It is a structural diagram of a deep feature extraction model based on a convolutional neural network provided by an embodiment of the present invention. The specific process is: a multi-channel feature map is subjected to global average pooling to obtain a feature vector, and then the feature vector is subjected to two layers of nonlinear transformation to obtain a feature map weight vector, and then the multi-channel feature map is weighted according to the feature map weight vector to obtain a weighted feature map; finally, the weighted feature map is subjected to activation and pooling operations to obtain the first layer of features; the first layer of features is subjected to a set of "convolution-channel attention-activation-pooling" operations in sequence to obtain the second layer of features; the second layer of features is subjected to a set of "convolution-channel attention-activation-pooling" operations to obtain the third layer of features, and the third layer of features is input into a fully connected network with a three-layer nonlinear mapping structure for feature dimensionality reduction to obtain the deep features f2 of the HRRP sequence to be tested. The convolutional neural network in the embodiment of the present invention uses a convolution kernel size of 3×3, the stride of the convolution operation is 1×1, and the pooling window size is 2×2.

[0091] Step S103, fusing the weighted physical features and the deep features to obtain fused features.

[0092] In the embodiment of the present invention, the weighted physical feature f1′ and the deep feature f2 are first concatenated and input into an adaptive weighted network g′ composed of a multi-layer fully connected network. Figure 6 , Figure 6 It is a structural diagram of the adaptive weighted network provided in an embodiment of the present invention. After two layers of nonlinear transformation and normalized exponential function, a normalized two-dimensional weight vector [λ1,λ2] is obtained, and then the weighted physical features and deep features of the HRRP sequence to be tested are weightedly spliced ​​to obtain a fusion feature d=[λ1f1′,λ2f2].

[0093] Step S104: input the fused features into the pre-trained prototype network to obtain a plurality of embedding vectors to be tested based on the prototype network.

[0094] In the embodiment of the present invention, the prototype network has a two-layer nonlinear mapping structure. The prototype network is a model for few-sample learning, which performs classification by learning the "prototype" of each category, that is, the average representation of the samples of this category in the feature space. Specifically, the training method of the prototype network is as follows:

[0095] Obtain the fusion features of known space cone targets, light accompanying false targets, and heavy accompanying false targets. The acquisition method of the fusion features of these three types of targets can be referred to the above steps and will not be repeated here.

[0096] Then, the fusion features of the known space cone target, light accompanying false target, and heavy accompanying false target are input into the prototype network to obtain multiple embedded sample vectors for each target type. Then, for each target type, the average value of multiple embedded sample vectors for this target type is calculated to obtain the prototype vector for this target type, which is recorded as the prototype vector c under the known space cone target. 1 , prototype vector c under light accompanying false target 2 , prototype vector c under heavy accompanying false target 3 .

[0097] Assume that after feature fusion, the embedded sample vector corresponding to the HRRP sequence of the i-th sample of the spatial cone target is The embedded sample vector corresponding to the jth sample HRRP sequence of the light accompanying false target is The embedded sample vector corresponding to the kth sample HRRP sequence of the heavy accompanying false target is Then the loss function L of the prototype network is proto It can be expressed as:

[0098]

[0099] Among them, N1 represents the total number of sample HRRP sequences of spatial cone targets; N2 represents the total number of sample HRRP sequences of light accompanying false targets; N3 represents the total number of sample HRRP sequences of heavy accompanying false targets; dis(x,y) represents the cosine similarity between vectors x and y, and the specific calculation method is:

[0100]

[0101] Among them, xy T represents the inner product of two row vectors, the superscript T represents the transpose operation of the vector; |x||y| represents the module multiplication of the vectors; vectors x and y represent any two vectors of the same latitude; during the training phase, the convolutional neural network, physical feature weight learning network, adaptive weighted network, and prototype network are optimized simultaneously, and the optimal parameters of the network are obtained by minimizing the loss function of the prototype network.

[0102] At this point, a trained prototype network is obtained, and then the fusion features of the HRRP sequence to be tested are input into the pre-trained prototype network, and multiple embedding vectors to be tested can be obtained based on the prototype network.

[0103] Step S105, performing radar recognition of unknown space cone targets based on the prototype vectors of each target type and the embedded vector to be tested; the target types include space cone targets, light accompanying false targets and heavy accompanying false targets.

[0104] In the embodiment of the present invention, the prototype vector of each target type mentioned above refers to a representative vector of each target type in the feature space, representing the central feature of the target type. The embedded vector to be tested refers to the embedded vector generated by mapping the HRRP sequence to be tested to the feature space through feature extraction, reflecting the feature representation of the HRRP sequence to be tested.

[0105] By calculating the distance between the embedding vector to be tested and the prototype vectors of each known category, the category with the closest distance is found, thereby completing target recognition. Specifically, by measuring the similarity between each embedding vector to be tested and each type of prototype, the HRRP sequence to be tested is judged as the target type with the greatest similarity, and the number of HRRP sequences to be tested assigned to each known category is counted, and the target of the HRRP sequence to be tested is judged as the category corresponding to the known category with the largest number of assigned categories. Among them, the similarity calculation method is the same as the aforementioned cosine similarity calculation formula, which will not be repeated here.

[0106] In an embodiment of the present invention, the HRRP sequence to be tested is characterized by fusing weighted physical features with deep features, thereby solving the problems of incomplete feature representation and poor inter-class separability in the prior art spatial cone target radar HRRP recognition method that only uses shallow features or pure data-driven deep features, and providing a good feature basis for subsequent recognition. In addition, the pre-trained prototype network used in the embodiment of the present invention can more accurately summarize class-general characteristics from known targets through pre-training, and has a stronger generalization ability for similar heterogeneous targets, thereby solving the general problems of weak generalization ability and difficult zero-sample recognition for unknown new spatial cone targets that have not appeared in the training stage in the existing spatial cone target radar HRRP recognition method, and improving the accuracy of radar recognition of unknown spatial cone targets.

[0107] The simulation experiment of applying a radar identification method for an unknown space cone target provided by an embodiment of the present invention is as follows: the radar echo of the training known target and the radar echo of the test unknown target used in this simulation experiment are three types of HRRP sequence samples of "space cone target", "light accompanying false target" and "heavy accompanying false target" obtained by electromagnetic simulation. Among them, the radar parameters are set as follows: operating frequency 10GHz, operating bandwidth 1.3GHz, signal frequency range 9.35GHz~10.65GHz, frequency interval 0.01GHz, radar line of sight angle range 52°~56°, repetition rate 100Hz, sampling time 2s, Gaussian white noise added to the echo signal, and signal-to-noise ratio 20dB. The micro-motion and structural parameter settings of various training known targets are shown in Table 1. In the simulation experiment, the parameter settings of the same type of targets are not fixed, and multiple values ​​are set for each micro-motion and structural parameter. Considering that the height of the cone target is usually greater than the diameter, different parameter settings are combined to form multiple targets of the same type. In the experiment, each of the three known classes contains 64 targets, each target contains 25 HRRP sequence samples, and the three known classes have a total of 4800 samples.

[0108] Table 1

[0109]

[0110] The settings of the micro-motion and structural parameters of the unknown target test are different from those of the known target. The settings of the micro-motion and structural parameters of various unknown target tests are shown in Table 2. In the experiment, the three unknown classes each contain 30 targets, each target contains 20 HRRP sequence samples, and the three known classes have a total of 1800 samples.

[0111] Table 2

[0112]

[0113] After the training process obtains the optimal parameters of each network by minimizing the prototype contrast loss, all the embedding vectors of each type output by the prototype network are averaged to obtain various prototype vectors. In the test phase, the three types of HRRP sequence samples of unknown targets to be tested are generated based on the above simulation conditions, and input into the trained recognition network. After multi-dimensional physical feature extraction and deep feature extraction, physical feature selection, feature fusion and prototype network, the embedding vectors of the HRRP samples to be tested are obtained, and the target type is determined by measuring the similarity between the embedding vector to be tested and various prototypes. The average recognition accuracy calculation formula of the three types of targets defined in the embodiment of the present invention is as follows:

[0114]

[0115] Among them, n i Indicates the number of correctly identified samples of the i-th category, N i Represents the total number of samples of the i-th category target.

[0116] According to the above recognition accuracy calculation formula, the average recognition rate of the three types of targets of the method proposed in the embodiment of the present invention is calculated, and compared with the recognition rates of four comparison methods, namely, the method using only physical features and using the prototype network as a classifier (method 1), the method using only weighted physical features and using the prototype network as a classifier (method 2), the method using only deep features and using the prototype network as a classifier (method 3), and the method using fusion features based on an adaptive weighted network and using a traditional normalized index classifier (method 4). The normalized index classifier in method 4 refers to the classification score prediction after a layer of nonlinear transformation of the fusion features through a normalized exponential function. The comparison methods of different features in the simulation experiment are shown in Table 3:

[0117] Table 3

[0118]

[0119]

[0120] The above methods were compared with the test set samples of unknown space cone targets (UA), unknown light accompanying false targets (UB), and unknown heavy accompanying false targets (UC). The average recognition accuracy of the three types of targets of each method is shown in Table 3. In order to quantitatively analyze the separability between different targets, the confusion matrix of different methods is given below. Figure 7 As shown, Figure 7 This is a comparison diagram of the recognition accuracy confusion matrix of different recognition methods. Figure 7 (a) is a schematic diagram of the recognition accuracy confusion matrix of method 1. Figure 7 (b) is a schematic diagram of the recognition accuracy confusion matrix of method 2. Figure 7(c) is a schematic diagram of the recognition accuracy confusion matrix of method 3. Figure 7 (d) is a schematic diagram of the recognition accuracy confusion matrix of method 4. Figure 7 (e) is a schematic diagram of the confusion matrix of the recognition accuracy of the unknown spatial cone target radar recognition method provided by an embodiment of the present invention. Figure 7 In the confusion matrix, the vertical axis is the true labels of the three types of test samples, "UA", "UB", and "UC", respectively representing "space cone target", "light accompanying false target", and "heavy accompanying false target", and the horizontal axis is the category predicted by the recognition model.

[0121] From Table 3 and Figure 7 It can be seen from the figure that: Method 1 and Method 2 are easy to distinguish heavy accompanying false targets, and their misclassified samples are mainly concentrated between space cone targets and light accompanying false targets. The recognition rate of Method 2 is improved by 1.83% compared with Method 1, which verifies the effectiveness of physical feature selection; Method 3 is more separable from space cone targets and light accompanying false targets than Method 2, and its misclassified samples are concentrated between light accompanying false targets and heavy accompanying false targets; the method proposed in the embodiment of the present invention combines the advantages of physical features and deep features, and can significantly improve the overall recognition performance of space cone targets, light accompanying false targets and heavy accompanying false targets. The recognition accuracy rates are improved by 6.89% and 11.17% compared with those of Method 2 and Method 3, respectively, which verifies the effectiveness of the feature fusion method based on adaptive weighted network proposed in the embodiment of the present invention; the recognition rate is improved by 3.01% compared with Method 4. The method proposed in the present invention adopts prototype network as classifier, which has stronger generalization for unknown targets.

[0122] See also Figure 8 , Figure 8 This is a t-SNE visualization diagram of the features proposed by different recognition methods and the classification interface learned. Figure 8 The t-SNE visualization of the features proposed by different methods and the learned classification interface in Table 3 is given to further qualitatively illustrate the recognition performance of different methods, where t-SNE is a nonlinear dimensionality reduction technique. Figure 8 (a) is the t-SNE visualization diagram of method 1. Figure 8 (b) is the t-SNE visualization diagram of method 2. Figure 8 (c) is the t-SNE visualization diagram of method 3. Figure 8 (d) is the t-SNE visualization diagram of method 4. Figure 8 (e) is a t-SNE visualization diagram of the unknown spatial cone target radar recognition method provided by an embodiment of the present invention. Figure 8In the figure, the red, green and black dots represent the features of unknown space cone targets, light accompanying false targets and heavy accompanying false targets respectively. The blue, pink and yellow five-pointed stars represent the space cone target prototype, light accompanying false target prototype and heavy accompanying false target prototype respectively learned in the training phase.

[0123] from Figure 8 It can be seen that the unknown heavy accompanying false target features proposed by Method 1 and Method 2 are significantly different from the other two types of unknown target features compared with Method 3, which further illustrates the advantages of physical features in the identification of heavy accompanying false targets; the aliasing degree of the unknown spatial cone target and the unknown light accompanying false target features learned by Method 3 is weaker than that of Method 1 and Method 2, which further illustrates the advantages of deep features in the identification of spatial cone targets and light accompanying false targets. The feature separability of the three types of targets in the method proposed in the present invention is significantly enhanced, which once again verifies the effectiveness of the feature fusion method based on adaptive weighted network proposed in the present invention in extracting separable features. In addition, by comparing Figure 8 (d) and Figure 8 It can be seen from (e) that, for the same fusion features, the classification interface learned by the classifier used in method 4 is significantly less accurate than the classification interface learned by the classifier used in the present invention, which further illustrates the superiority of the prototype network-based radar target recognition framework proposed in the present invention in recognizing unknown targets that have not appeared in the training phase.

[0124] To verify the rationality of the physical feature weight learning network, see Fig. 9 , Fig. 9 It is a statistical diagram of the average value of the seven-dimensional physical feature weights of all test samples of various targets. Fig. 9 (a) is a statistical diagram of the average value of the seven-dimensional physical feature weights of all test samples of the spatial cone target. Fig. 9 (b) is a statistical diagram of the average value of the seven-dimensional physical feature weights of all test samples of light accompanying decoy targets. Fig. 9 (c) is a statistical diagram of the average value of the seven-dimensional physical feature weights of all test samples of heavy accompanying decoy targets. Fig. 9 It can be seen that the weights of the size and structure-related features of the heavy accompanying false targets are larger, while the weights of the micro-motion features of the space cone targets and light accompanying false targets are larger, indicating that the physical features mainly rely on size and structure features to distinguish heavy accompanying false targets, and rely on micro-motion features to distinguish space cone targets and light accompanying false targets. This is consistent with the setting in Table 2 that the unknown heavy accompanying false targets and space cone targets / light accompanying false targets have large differences in structural parameters, and the space cone targets and light accompanying false targets have small differences in structural parameters but relatively large differences in micro-motion parameters, which verifies the rationality of the physical feature weight learning network.

[0125] To further verify the rationality of deep features in alleviating the misclassification of space cone targets and light accompanying false targets, see Table 4 and Fig.10 Table 4 is an example table of misclassified sample parameters for method 2. Fig.10 This is a schematic diagram of correctly classifying corresponding samples of a method for identifying an unknown spatial cone target by radar provided by an embodiment of the present invention. Fig.10 (a) is a schematic diagram of the sample corresponding to the correct classification of the spatial cone target in Example 1. Fig.10 (b) is a schematic diagram of the sample corresponding to the correct classification of the light accompanying false target in Example 1. Fig.10 (c) is a schematic diagram of the sample corresponding to the correct classification of the spatial cone target in Example 2. Fig.10 (d) in Example 2 is a schematic diagram of the correct classification of the light accompanying false target, Table 4 and Fig.10 The corresponding samples correctly classified by the proposed method are given respectively. The parameter setting examples of the space cone target and the light accompanying false target that can be correctly distinguished by the proposed method in the embodiment of the present invention but misclassified by method 2 are given respectively, as well as the corresponding HRRP sequence examples. It can be seen from Table 4 that since method 2 mainly relies on micro-motion parameter features to distinguish between space cone targets and light accompanying false targets, when the micro-motion parameter difference between the two is small, method 2 is easy to make mistakes. However, small micro-motion parameter differences may produce obvious changes in the HRRP sequence data, such as Fig.10 The number of sinusoidal curve cycles shown is significantly different. Therefore, it is meaningful to effectively distinguish between space cone targets and light accompanying false targets by fusing the deep features of HRRP echo data.

[0126] Table 4

[0127]

[0128] It should be noted that the terms "first", "second", etc. are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchangeable where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention.

[0129] 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.

[0130] Although the present invention is described herein in conjunction with various embodiments, in the process of implementing the claimed invention, those skilled in the art can understand and implement other changes to the disclosed embodiments by viewing the drawings and the disclosed content. In the description of the present invention, the term "comprising" does not exclude other components or steps, "one" or "an" does not exclude multiple situations, and "multiple" means two or more, unless otherwise clearly and specifically limited. In addition, certain measures are recorded in different embodiments, but this does not mean that these measures cannot be combined to produce good results.

[0131] 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 radar recognition method for unknown spatial cone targets, characterized in that: The unknown space cone target radar recognition method comprises: Obtain the HRRP sequence to be tested; Extracting weighted physical features and deep features of the HRRP sequence to be tested; fusing the weighted physical feature and the deep feature to obtain a fused feature; Inputting the fused features into a pre-trained prototype network to obtain a plurality of embedding vectors to be tested based on the prototype network; The unknown space cone target radar recognition is performed based on the prototype vector of each target type and the embedded vector to be tested; the target types include space cone targets, light accompanying false targets and heavy accompanying false targets.

2. The unknown space cone target radar recognition method according to claim 1 is characterized in that: The method of extracting the weighted physical characteristics of the HRRP sequence to be measured includes: Acquiring physical characteristics of the HRRP sequence to be tested; The physical feature is subjected to nonlinear transformation and normalized exponential function to obtain a normalized physical feature weight vector; The physical feature is weighted by using the normalized physical feature weight vector to obtain a weighted physical feature.

3. The unknown space cone target radar recognition method according to claim 2 is characterized in that: The physical characteristics include micro-motion parameters, structural parameters, maximum radial size characteristics and energy entropy characteristics.

4. The unknown space cone target radar recognition method according to claim 3 is characterized in that: The method for obtaining the maximum radial dimension feature includes: Acquire energy distribution of the HRRP sequence to be measured; Determine a HRRP sequence signal search area based on the energy distribution; Determining the radial size of each HRRP echo in the HRRP sequence to be measured based on the HRRP sequence signal search area; The largest radial dimension is selected as the maximum radial dimension feature.

5. The unknown space cone target radar recognition method according to claim 4 is characterized in that: The radial size of each HRRP echo in the HRRP sequence to be measured is calculated as follows: Among them, L i represents the radial size of the i-th HRRP echo in the HRRP sequence to be measured; M represents the number of HRRP echoes in the HRRP sequence to be measured; ρ r Indicates radar range resolution; Indicates the number of range units occupied by the radial size of the target in the i-th HRRP echo.

6. The unknown space cone target radar recognition method according to claim 3 is characterized in that: The energy entropy feature is obtained by: Acquire energy distribution of the HRRP sequence to be measured; Normalizing the energy distribution to obtain an energy probability distribution; The information entropy of the energy probability distribution is calculated to obtain the energy entropy feature.

7. The unknown space cone target radar recognition method according to claim 6 is characterized in that: The energy entropy characteristic is calculated as follows: Wherein, f7 represents the energy entropy characteristic; p r represents the rth element of the energy probability distribution, r=1, ..., R; R represents the number of distance units of the HRRP echo in the HRRP sequence to be measured.

8. The unknown space cone target radar recognition method according to claim 1 is characterized in that: The calculation method of the prototype vector includes: Obtain multiple sample HRRP sequences under each target type; Extract sample weighted physical features and sample deep features of sample HRRP sequences under each target type; For the sample HRRP sequence under each target type, the sample weighted physical features and sample deep features of the sample HRRP sequence are fused to obtain the sample fusion features under the target type; Inputting the sample fusion features under each target type into the prototype network to obtain multiple embedded sample vectors under each target type based on the prototype network; For each target type, the average value of multiple embedded sample vectors under the target type is calculated to obtain the prototype vector under the target type.

Images