Sea surface target identification method applying time domain multi-scale permutation entropy features

Abstract

The invention relates to a sea surface target identification method applying time domain multi-scale permutation entropy features, and belongs to the technical field of radar signal processing. Comprising the following steps: 1) caching target echo data; 2) target multi-scale permutation entropy feature extraction; 3) feature optimization; and 4) performing target identification by using the multi-scale permutation entropy features. The objective of the invention is to identify a sea surface target under the condition that target identification is difficult to effectively perform through traditional target features.

Description

Technical Field

[0001] The invention relates to a sea surface target recognition method using time domain multi-scale arrangement entropy features, and belongs to the technical field of radar signal processing. Background Art

[0002] The ocean is vast and the environment is changeable. Due to the differences in longitude and latitude and the distance from the land, the temperature, salinity and meteorological conditions will form different ocean environments. There are many types of sea surface targets with different characteristics, including major ship targets such as merchant ships, civilian ships and warships, as well as offshore operating platforms, marine aquaculture farms, channel buoys, floating ice, etc. In the process of sailing at sea, implementing production and operation activities and maritime law enforcement, there is an urgent need to identify sea surface targets in complex ocean environments. High-resolution range profile (HRRP) is the main feature source for radar target identification at present. The features mainly focus on the energy, size, shape, etc. of the target. Due to the complex material composition of different targets and the diverse scene existence modes, the target features are unstable under different observation angles, different natural environments, different radar working conditions, etc., and there is a problem that the features between targets are difficult to distinguish with high similarity, which makes it easy for radar to make identification errors and difficult to adapt to the complex and changeable ocean environment. Summary of the invention

[0003] The purpose of the present invention is to solve the shortcomings of the above-mentioned prior art and propose a sea surface target recognition method using time domain multi-scale arrangement entropy features, aiming to identify sea surface targets when traditional target features are difficult to effectively perform target recognition.

[0004] The present invention provides a method for identifying sea surface targets using time domain multi-scale permutation entropy features, which is special in that it comprises the following steps:

[0005] Step 1: Target echo data buffer

[0006] The target detection is completed by using the echo data after pulse compression processing. According to the target distance unit information, the target time domain echo sequence is intercepted and cached;

[0007] Step 2: Target multi-scale permutation entropy feature extraction

[0008] The target time domain echo sequence is segmented, the permutation entropy value of each data segment is calculated, the data segments are coarse-grained at different time scales, the permutation entropy values ​​of the corresponding scales are calculated, the obtained entropy value information is integrated, the multi-scale permutation entropy feature vector of each data segment is obtained, and the target feature matrix is ​​formed;

[0009] Step 3: Feature Optimization

[0010] For various parameters that appear when calculating multi-scale permutation entropy, including the embedding dimension m of the phase space reconstruction matrix, the time coarse-grained scale s, and the number of pulses N in each segment of data, the appropriate parameter range is determined according to the degree of influence on the separability of the two types of targets under different parameter settings to achieve feature optimization and improve recognition performance;

[0011] Step 4: Utilize multi-scale permutation entropy features for target recognition

[0012] The classification algorithm is used to complete the recognition of two types of targets and the recognition performance is tested. The support vector machine method is used to divide the feature matrix composed of multiple targets into training set and test set, and the model hyperparameters are optimized, including the penalty factor c and the RBF kernel function parameter gamma, to obtain better recognition effect. Finally, the feature vector of the test set is input into the model for testing to obtain the target recognition result.

[0013] Preferably, the specific steps of step 1 are as follows:

[0014] The radar receives echo data in tracking mode. After pulse compression, clutter suppression, target detection and tracking processing, a total of J targets are detected in the current scene. The distance unit where the strongest scattering point of the target is located is selected and its pulse echo data sequence is cached. For the jth target, it is expressed as {z j (1),z j (2),…,z j (L)}, L represents the coherent pulse train length.

[0015] Preferably, the specific steps of step 2 are:

[0016] For a target echo sequence z detected in step 1 j (n), and it is segmented and intercepted. The number of pulses in each segment of data is N. After interception, I subsequences can be obtained, which are expressed as {x1(n), x2(n), ..., x I (n)1≤n≤N}, where

[0017] For the i-th data segment x extracted above i (n), in order to obtain more feature information at different time scales, it is first coarsened, and the process is as follows:

[0018]

[0019] in, is the echo sequence after coarse-graining, s is the coarse-graining scale, β is a positive integer, and after coarse-graining, the sequence length is Q, where

[0020] For coherent radar, the target pulse echo data sequence is a complex number. In order to compare the size in the subsequent permutation entropy calculation, the absolute value of each data point should be taken, that is, let y s (β) = x s (β), define the phase space reconstruction matrix Y as:

[0021]

[0022] Where m is the embedding dimension, a is the number of delayed pulses, K = Q-(m-1), the dimension of the phase space reconstruction matrix Y is K×m, and the pulse repetition interval of the radar is expressed as T r , then the corresponding delay time t is expressed asT r , arrange the elements of each row in the matrix Y in ascending order, and obtain a set of symbol sequences consisting of the indexes of the positions of each element in the row vector, expressed as S(l). There are k kinds of arrangement modes, namely:

[0023] S(l)={γ1,γ2,…,γ m}, l = 1, 2, ..., k, and k ≤ m! (3)

[0024] There are m! different symbol sequences mapped in the m-dimensional phase space, where ! represents the factorial operator. The frequency of each arrangement order in the reconstructed sequence is counted, and the probability sequence {P1, P2, …, P k}, then the multi-scale permutation entropy H s The calculation formula is:

[0025]

[0026] Normalize the multi-scale permutation entropy, that is:

[0027]

[0028] After normalization, its value range is [0,1];

[0029] According to the above process, we get the i-th data segment x i (n) Permutation entropy value H at scale s s , select different coarse-grained scales s, that is, let s = [s1, s2, …, s λ ], and obtain the permutation entropy values ​​at different coarse-grained scales, which form a feature vector with a dimension of λ;

[0030] Process each data segment of the current target echo sequence in turn to obtain its multi-scale permutation entropy feature matrix Φ, which is expressed as:

[0031]

[0032] The number of rows of the matrix Φ is related to the number of data segments I, and the number of columns is related to the number of coarse-grained scales λ;

[0033] For all target echo sequences detected in step 1), using the above feature extraction method, each target can extract I feature vectors corresponding to it, and these feature vectors are integrated to obtain the feature matrix of the target.

[0034] Preferably, the specific steps of step 3 are:

[0035] The Bhattacharyya distance (B-distance), which can measure the similarity of two types of samples, is used as an indicator to quantitatively analyze the separability between the ship target sample space S1 and the floating target sample space S2 in the feature space. The appropriate parameter range is selected through analysis and optimization. The Bhattacharyya distance estimation method is as follows:

[0036] Calculate the mean vector μ and covariance matrix C of the two sample spaces:

[0037] μ1=mean(S1),C1=cov(S1) (7)

[0038] μ2=mean(S2),C2=cov(S2) (8)

[0039] In the formula, mean and cov represent the mean and covariance operators respectively, and Bhattacharyya distance d B The estimated value of is obtained by the following formula:

[0040]

[0041] In the formula, C = (C1 + C2) / 2, d μ =(μ1-μ2) / chol(C), where det represents the determinant operator and chol represents the Cholesky decomposition operator.

[0042] The beneficial effects of the present invention are as follows:

[0043] (1) The method proposed in the present invention uses the multi-scale permutation entropy of the target as a feature and obtains more target feature information through multiple time scales. It can study the mutation and randomness characteristics of the echo signal and solve the problem of relying on traditional target features but being difficult to achieve identification.

[0044] (2) Taking the Bhattacharyya distance as a quantitative indicator to measure the similarity between the two types of target samples, the feature extraction parameters were optimized to improve the feature separability of the two types of samples.

[0045] (3) Under the existing data conditions, the average accuracy of the method proposed in this patent for identifying ship targets and floating targets is 93.49% in an observation time of 0.5s, which is 39.17% higher than the existing methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 : It is a comparison diagram of Bhattacharyya distance between two types of target samples under different embedding dimensions m;

[0047] Figure 2 : is the comparison diagram of Bhattacharyya distance between two types of target samples under different coarse-grained scales s;

[0048] Figure 3 : The comparison diagram of Bhattacharyya distance between two types of target samples under different pulse numbers N;

[0049] Figure 4 : Scatter envelope diagram of two-dimensional multi-scale permutation entropy features of two types of targets before and after feature optimization. DETAILED DESCRIPTION

[0050] The specific implementation of the present invention is further described below in conjunction with the accompanying drawings and technical solutions.

[0051] A method for identifying sea surface targets using time domain multi-scale permutation entropy features in this embodiment is described in detail in the attached Figure 1-4 , including the following steps:

[0052] 1) Target echo data cache

[0053] The radar receives echo data in tracking mode. After pulse compression, clutter suppression, target detection and tracking processing, a total of J targets are detected in the current scene. The distance unit where the strongest scattering point of the target is located is selected and its pulse echo data sequence is cached. For the jth target, it is expressed as {z j (1),z j (2),...,z j (L)}, L represents the coherent pulse train length;

[0054] 2) Target multi-scale permutation entropy feature extraction

[0055] For a target echo sequence z detected in step 1) j (n), and it is segmented and intercepted. The number of pulses in each segment of data is N. After interception, I subsequences can be obtained, which are expressed as {x1(n), x2(n), ..., x I (n)|1≤n≤N}, where

[0056] For the i-th data segment x extracted above i(n), in order to obtain more feature information at different time scales, it is first coarsened, and the process is as follows:

[0057]

[0058] in, is the echo sequence after coarse-graining, s is the coarse-graining scale, β is a positive integer, and after coarse-graining, the sequence length is Q, where

[0059] For coherent radar, the target pulse echo data sequence is a complex number. In order to compare the size in the subsequent permutation entropy calculation, the absolute value of each data point should be taken, that is, let y s (β) = x s (β). Define the phase space reconstruction matrix Y as:

[0060]

[0061] Where m is the embedding dimension, a is the number of delayed pulses, K = Q-(m-1), and the dimension of the phase space reconstruction matrix Y is K×m. The pulse repetition interval of the radar is represented as T r , then the corresponding delay time t is expressed asT r By arranging the elements of each row in the matrix Y in ascending order, we can obtain a set of symbol sequences consisting of the indexes of the positions of each element in the row vector, expressed as S(l), that is,

[0062] S(l)={γ1,γ2,…,γ m}, l = 1, 2, ..., k, and k ≤ m! (3)

[0063] There are m! different symbol sequences mapped in the m-dimensional phase space, where ! represents the factorial operator. By counting the frequency of each arrangement order in the reconstructed sequence, we can get the probability sequence {P1, P2, …, P k}, then the multi-scale permutation entropy H s The calculation formula is:

[0064]

[0065] Normalize the multi-scale permutation entropy, that is:

[0066]

[0067] After normalization, its value range is [0,1].

[0068] According to the above process, the i-th data segment x can be obtained i (n) Permutation entropy value H at scale s s, select different coarse-grained scales s, that is, let s = [s1, s2, …, s λ ], we can get the permutation entropy values ​​at different coarse-grained scales, and these values ​​form a feature vector with dimension λ. For example, when λ = 3, for the i-th data segment, we can get a three-dimensional feature vector, expressed as

[0069] Process each data segment of the current target echo sequence in turn to obtain its multi-scale permutation entropy feature matrix Φ, which is expressed as:

[0070]

[0071] The number of rows of the matrix Φ is related to the number of data segments I, and the number of columns is related to the number of coarse-grained scales λ.

[0072] For all target echo sequences detected in step 1), the above feature extraction method is used to extract I feature vectors corresponding to each target, and these feature vectors are integrated to obtain the feature matrix of the target. For example, if two targets are detected in the echo data, the number of data segments obtained after the interception of each target echo data is A, and the number of coarse-grained scales is λ=B, then the multi-scale permutation entropy feature matrices Φ1 and Φ2 of the target can be obtained, and the matrix dimensions are both A×B.

[0073] 3) Feature Optimization

[0074] In step 2), many parameters are involved in the feature extraction process, including the embedding dimension m of the phase space reconstruction matrix Y, the number of delayed pulses a, the coarse-grained scale s, and the number of pulses N in each data segment. Among them, the number of delayed pulses a is usually 1 to ensure the continuity of the target information features in the time domain. The selection of the other three parameters should be optimized in combination with the impact on the separability of different targets, so as to achieve feature optimization.

[0075] The Bhattacharyya distance (B-distance), which can measure the similarity of two types of samples, is used as an indicator to quantitatively analyze the separability between the ship target sample space S1 and the floating target sample space S2 in the feature space, and the appropriate parameter range is selected through analysis and optimization. The Bhattacharyya distance estimation method is as follows:

[0076] Calculate the mean vector μ and covariance matrix C of the two sample spaces

[0077] μ1=mean(S1),C1=cov(S1) (7)

[0078] μ2=mean(S2),C2=cov(S2) (8)

[0079] In the formula, mean and cov represent the mean and covariance operators respectively, and Bhattacharyya distance d B The estimated value of is obtained by the following formula:

[0080]

[0081] In the formula, C = (C1 + C2) / 2, d μ =(μ1-μ2) / chol(C). Here det represents the determinant operator, chol represents the Cholesky decomposition operator;

[0082] The following uses measured data to study the effects of the three parameters on the separability of the two types of targets in order to determine the appropriate parameter range.

[0083] (1) The embedding dimension m of the phase space reconstruction matrix Y

[0084] m determines the number of columns of the phase space reconstruction matrix Y. The larger the value of m, the more symbol sequences are formed by the position index of each element when the elements of each row of the matrix are arranged in ascending order, and the higher the accuracy of sorting the elements. The comparison of the Bhattacharyya distances of the two types of target samples obtained from the measured data under different embedding dimensions m is as follows: Figure 1 As shown. Obviously, when the embedding dimension m is 2, the separability of the features is poor. When m is 3, the feature separability is generally good. When m is 4, 5, and 6, the feature separability is close, but slightly worse than when m is 3.

[0085] (2) Coarse-grained scale s

[0086] s determines the length of the time series after coarse-graining. Different s values ​​represent different time scales for observing target features. The Bhattacharyya distance comparison of the two types of target samples obtained from the measured data at different coarse-graining scales s is shown in Figure 2. Figure 2 As shown. Obviously, when the coarse-grained scale s is 2 and 3, the difference in sea surface target features is better. When the s value continues to increase, the feature separability becomes worse. This is because too many data points will cover up the target's feature information when averaged, making it impossible to achieve a good distinction effect. In the feature extraction process, the multi-scale permutation entropy of each data segment with a coarse-grained scale of 2 and 3 is calculated, and these two values ​​are used to form a feature vector of a data segment.

[0087] (3) Number of pulses per segment of data N

[0088] N determines the amount of data required for an entropy calculation when processing echo signals. The comparison of the Bhattacharyya distances of two types of target samples obtained from measured data under different pulse numbers N is shown in Figure 2. Figure 3Obviously, the more pulses there are, the better the separability of the multi-scale permutation entropy features of the two types of targets is. However, it is necessary to consider the need for target recognition in an actual radar system and to make a compromise between recognition accuracy and real-time performance to achieve better performance.

[0089] After feature optimization, the appropriate parameter range is selected to increase the Bhattacharyya distance between the two types of samples and improve the feature separability. The comparison of the extracted two-dimensional features before and after optimization is shown in Figure 2. Figure 4 As shown, Figure 4 (a) Select any two sets of feature parameters to form a two-dimensional feature, and the feature envelope areas of the two types of targets overlap. Figure 4 In (b), two sets of optimized feature parameters are selected, and the overlap of the two types of target features is significantly reduced. It can be seen that feature optimization is of great help to the subsequent target recognition work.

[0090] 4) Using multi-scale permutation entropy features for target recognition

[0091] In step 3), the optimized feature vector set of all targets is obtained, and the classification algorithms in machine learning and deep learning are used to complete the recognition of two types of targets, and the recognition performance is tested. The classification algorithms include decision tree, support vector machine, naive Bayes, convex hull algorithm, and convolutional neural network.

[0092] Three sets of measured data were used for feature extraction, and their basic information is shown in Table 1. The echo data were segmented, with 1024 pulses in each segment, corresponding to a duration of about 0.5 s. A total of 128 feature vectors could be extracted from each target, and a total of 256 feature vectors related to the two types of targets could be obtained from each set of data to form a feature matrix.

[0093] Table 1 Introduction to measured data

[0094]

[0095] During recognition, first, each feature vector label value is assigned, for example, a ship target is 1 and a floating target is 2, and the feature matrix is ​​divided into a training set and a test set. The recognition process is explained using the support vector machine method as an example. The SVM classifier model is constructed using the training set, and the hyperparameters in the SVM are optimized using a loop iteration method, including the penalty factor c and the RBF kernel function parameter gamma. The range of both parameters is from the minimum value 2 -8 Start, maximum value 2 8 End, the loop step is exponentially increased by one, and a five-fold cross-validation is performed on the model under each set of parameters. The parameters with the best recognition effect are selected to obtain the classifier model. Then the test set data is input into the model for recognition. The following four situations will appear in the test results:

[0096] ① True Positive (TP): The model correctly predicts a sample that is actually a ship target as a ship target;

[0097] ②False Negative (FN): The model mistakenly predicts samples that are actually ship targets as floating targets;

[0098] ③False Positive (FP): The model mistakenly predicts a sample that is actually a floating target as a ship target;

[0099] ④True Negative (TN): The model correctly predicts a sample that is actually a floating target as a floating target.

[0100] Table 2 Statistics of target recognition results of multi-scale permutation entropy features in time domain

[0101]

[0102] Table 3 Statistics of target recognition results based on waveform entropy features in the time domain

[0103]

[0104] The recognition results are statistically analyzed, and the results are shown in Table 2. For the sake of comparison, the recognition results using time domain waveform entropy as a feature are given in Table 3. It can be seen that the average recognition accuracy that the existing methods can achieve is 54.32%, while the average accuracy of the method proposed in this patent is 93.49%. Under the existing data conditions, the recognition accuracy is improved by 39.17% compared with the existing methods.

Claims

1. A method for sea surface target recognition using multi-scale permutation entropy features in the time domain, characterized in that The following steps are involved: Step 1: Target echo data buffer The target detection is completed by using the echo data after pulse compression processing. According to the target distance unit information, the target time domain echo sequence is intercepted and cached; Step 2: Target multi-scale permutation entropy feature extraction The target time domain echo sequence is segmented, the permutation entropy value of each data segment is calculated, the data segments are coarse-grained at different time scales, the permutation entropy values ​​of the corresponding scales are calculated, the obtained entropy value information is integrated, the multi-scale permutation entropy feature vector of each data segment is obtained, and the target feature matrix is ​​formed; Step 3: Feature Optimization For various parameters that appear when calculating multi-scale permutation entropy, including the embedding dimension m of the phase space reconstruction matrix, the time coarse-grained scale s, and the number of pulses N in each segment of data, the appropriate parameter range is determined according to the degree of influence on the separability of the two types of targets under different parameter settings to achieve feature optimization and improve recognition performance; Step 4: Utilize multi-scale permutation entropy features for target recognition The classification algorithm is used to complete the recognition of two types of targets and test the recognition performance. The support vector machine method is used to divide the feature matrix composed of multiple targets into training set and test set, and the hyperparameters of the model are optimized, including the penalty factor c and the RBF kernel function parameter gamma, to obtain better recognition effect. Finally, the feature vector of the test set is input into the model for testing to obtain the target recognition result.

2. A method for identifying sea surface targets using time domain multi-scale permutation entropy features according to claim 1, characterized in that The specific steps of step 1 are as follows: The radar receives echo data in tracking mode. After pulse compression, clutter suppression, target detection and tracking processing, a total of J targets are detected in the current scene. The distance unit where the strongest scattering point of the target is located is selected and its pulse echo data sequence is cached. For the jth target, it is expressed as {z j (1),z j (2),…,z j (L)}, L represents the coherent pulse train length.

3. A method for identifying sea surface targets using time domain multi-scale permutation entropy features according to claim 2, characterized in that The specific steps of step 2 are: For a target echo sequence z detected in step 1 j (n), and it is segmented and intercepted. The number of pulses in each segment of data is N. After interception, I subsequences can be obtained, which are expressed as {x1(n), x2(n), ..., x I (n)|1≤n≤N}, where For the i-th data segment x extracted above i (n), in order to obtain more feature information at different time scales, it is first coarsened, and the process is as follows: in, is the echo sequence after coarse-graining, s is the coarse-graining scale, β is a positive integer, and after coarse-graining, the sequence length is Q, where For coherent radar, the target pulse echo data sequence is a complex number. In order to compare the size in the subsequent permutation entropy calculation, the absolute value of each data point should be taken, that is, let y s (β)=|x s (β)|, define the phase space reconstruction matrix Y as: Where m is the embedding dimension, a is the number of delayed pulses, K = Q-(m-1), the dimension of the phase space reconstruction matrix Y is K×m, and the pulse repetition interval of the radar is expressed as T r , then the corresponding delay time t is expressed asT r , arrange the elements of each row in the matrix Y in ascending order, and obtain a set of symbol sequences consisting of the indexes of the positions of each element in the row vector, denoted as S(l). There are k kinds of arrangement modes, namely: S(l) = {γ1, γ2, …, γ m}, l = 1, 2, …, k, and k ≤ m! (3) There are m! different symbol sequences mapped in the m-dimensional phase space, where ! represents the factorial operator. The frequency of each arrangement order in the reconstructed sequence is counted, and the probability sequence {P1, P2, …, P k }, then the multi-scale permutation entropy H s The calculation formula is: The multi-scale permutation entropy is normalized, that is: After normalization, its value range is [0,1]; According to the above process, we get the i-th data segment x i (n) Permutation entropy value H at scale s s , select different coarse-grained scales s, that is, let s = [s1, s2, …, s λ ], and obtain the permutation entropy values ​​at different coarse-grained scales, which form a feature vector with a dimension of λ; Process each data segment of the current target echo sequence in turn to obtain its multi-scale permutation entropy feature matrix Φ, which is expressed as: The number of rows of the matrix Φ is related to the number of data segments I, and the number of columns is related to the number of coarse-grained scales λ; For all target echo sequences detected in step 1), using the above feature extraction method, each target can extract I feature vectors corresponding to it, and these feature vectors are integrated to obtain the feature matrix of the target.

4. A method for identifying sea surface targets using time domain multi-scale permutation entropy features according to claim 1, characterized in that The specific steps of step 3 are: The Bhattacharyya distance, which can measure the similarity of two types of samples, is used as an indicator to quantitatively analyze the separability between the ship target sample space S1 and the floating target sample space S2 in the feature space. The appropriate parameter range is selected through analysis and optimization. The Bhattacharyya distance estimation method is as follows: Calculate the mean vector μ and covariance matrix C of the two sample spaces: μ1=mean(S1),C1=cov(S1) (7) μ2=mean(S2),C2=cov(S2) (8) In the formula, mean and cov represent the mean and covariance operators respectively, and Bhattacharyya distance d B The estimated value of is obtained by the following formula: In the formula, C = (C1 + C2) / 2, d μ =(μ1-μ2) / chol(C), where det represents the determinant operator and chol represents the Cholesky decomposition operator.

Images