A sea surface weak target detection method based on weighted difference visibility map features

Abstract

The application discloses a sea surface weak target detection method based on a weighted difference visibility graph feature, and comprises the following steps: collecting a sea surface echo amplitude sequence, converting the sea surface echo amplitude sequence into a phase difference sequence after dividing the sea surface echo amplitude sequence into subsequences, and performing normalization processing on the phase difference sequence; constructing a weighted difference visibility graph network by using the normalized phase difference sequence; extracting features from the weighted difference visibility graph network corresponding to each subsequence, and constructing a sea clutter map feature vector of the subsequence by using the extracted features; taking each sea clutter map feature vector as a training sample point to construct a training sample set; training a target detector by using the training sample set; for a sea surface echo amplitude sequence to be detected, taking a sea clutter map feature vector corresponding to the sequence as a to-be-detected sample point, and determining whether there is a target in the sea surface echo amplitude sequence to be detected by a relative position relationship between the to-be-detected sample point and the target detector.

Description

Technical Field

[0001] The present invention belongs to the technical field of radar target detection, and specifically relates to a method for detecting faint targets on the sea surface based on weighted difference visibility map features. The method is suitable for target detection under low signal-to-clutter ratio conditions and improves the detection performance of radar for faint targets on the sea surface. Background Art

[0002] Detection of weak targets in complex sea clutter background is a major challenge for radar remote sensing. 2 ) are small, have low speeds, and at low grazing angles, sea spikes resemble target radar echoes. This causes sea clutter to overlap with weak targets and even obscure them, severely limiting the target detection performance of maritime radars. Existing target detection methods based on feature theory distinguish between sea clutter and target echoes by studying their differences in the transform domain. However, single features extracted in the transform domain often require long observation times and have limited ability to capture sea surface echo information when dealing with diverse sea conditions. This significantly impacts the separability of targets and sea clutter in feature space. Summary of the Invention

[0003] In view of the complexity of the impact of sea clutter on radar target detection, the present invention provides a method for detecting faint targets on the sea surface based on weighted difference visibility map features. This method solves the problem of faint target detection in the sea clutter background from the perspective of combining multi-dimensional features in the image domain, and extracts weighted difference visibility map features between sea clutter and target echoes to achieve effective target detection.

[0004] In order to achieve the above tasks, the present invention adopts the following technical solutions:

[0005] A method for detecting faint targets on the sea surface based on weighted difference visibility map features, comprising:

[0006] Acquire a sea surface echo amplitude sequence, divide the sea surface echo amplitude sequence into subsequences and convert it into a phase difference sequence, and perform normalization on the phase difference sequence;

[0007] The normalized phase difference sequence is used to construct a weighted difference visibility graph network;

[0008] Feature extraction is performed on the weighted difference visibility graph network corresponding to each subsequence, and the sea clutter map feature vector of the subsequence is constructed using the extracted features;

[0009] Each sea clutter map feature vector is used as a training sample point to construct a training sample set; the training sample set is used to train the target detector;

[0010] For the sea surface echo amplitude sequence to be detected, the sea clutter map eigenvector corresponding to the sequence is used as the sample point to be tested. The relative position relationship between the sample point to be tested and the target detector is used to determine whether there is a target in the sea surface echo amplitude sequence to be detected.

[0011] Furthermore, the converting of the sea surface echo amplitude sequence into a phase difference sequence after dividing the sea surface echo amplitude sequence into subsequences includes:

[0012] The sea surface echo amplitude sequence received by the radar is divided into subsequences of length N. After division, the m-th subsequence x at the nth moment is obtained. m (n) The phase difference sequence is calculated as follows:

[0013]

[0014] Where τ represents the time interval, the superscript * represents the complex conjugate, and arg(·) represents the phase of the complex variable.

[0015] Furthermore, the method of constructing a weighted difference visibility graph network using the normalized phase difference sequence includes:

[0016] Step 2.1, build visibility graph network VG

[0017] Based on visibility graph theory, the visibility criterion for the phase difference sequence x(n), n = 1, 2, ..., N is defined as follows:

[0018] x(k)<x(j)+(x(i)-x(j))(ik) / (ji),i<k<j

[0019] Where i, k, and j represent the data points in the phase difference sequence, and x(i), x(j), and x(k) represent the amplitudes at the corresponding data points in the sequence;

[0020] For any two data points i and j in the sequence, if any point k between them and its amplitude satisfy the above formula, then the data points i and j are regarded as two mutually visible nodes in the visibility graph network, and there is an edge between the two nodes;

[0021] The normalized phase difference sequence of each subsequence is converted into a visibility graph network, where each data point in the phase difference sequence is a node in the network;

[0022] Step 2.2, build the horizontal visibility graph network HVG

[0023] Two data points i and j are considered as two connected nodes in the horizontal visibility graph network if the following geometric criteria are met in the sequence x(a):

[0024] x(i),x(j)>x(k) (for all k,i<k<j)

[0025] According to the above definition, the visibility map network established for the phase difference sequence is converted into a horizontal visibility map network network;

[0026] Step 2.3, construct the difference visibility graph network DVG

[0027] The difference visibility graph network is defined as follows:

[0028] E(DVG)=E(VG) / E(HVG), V(DVG)=V(VG)=V(HVG)

[0029] Where E(DVG), E(VG) and E(HVG) represent the sets of edges of the DVG network, VG network and HVG network respectively, and V(DVG), V(VG) and V(HVG) represent the sets of nodes of the DVG network, VG network and HVG network respectively;

[0030] Through the above formula, based on the VG network and HVG network, the phase difference sequence is represented by the DVG network;

[0031] Step 2.4, construct the weighted difference visibility graph network WDVG

[0032] Based on the DVG network, the arctan function is used to assign weights to the edges between two nodes with a connection relationship in the DVG network to characterize the changes between the quantity data points with a link relationship in the phase difference sequence, thereby obtaining a weighted difference visibility graph network; the weight is defined as follows:

[0033] W ij =arctan(x(j)-x(i)) / (ji)

[0034] Among them, W ij Represents the weight of the edge between node i and node j in the DVG network; the weighted adjacency matrix WA is defined as follows:

[0035]

[0036] Among them, W ij represents the element in row i and column j of the adjacency matrix; if W ij =W ji ≠0, indicating that node i is connected to node j, and the edge weight is W ij If W ij =W ji =0, indicating that there is no edge between the two nodes.

[0037] Furthermore, the feature extraction of the weighted difference visibility graph network corresponding to each subsequence includes:

[0038] (1) Weighted graph weight peak height (WPH)

[0039] WPH=max(W ij )

[0040] Among them, W ij represents the element in the i-th row and j-th column of the weighted adjacency matrix WA;

[0041] (2) Weighted Graph Complexity (WGC)

[0042] WGC=4κ(1-κ)

[0043] κ=λ max -2cos(π / (N+1)) / N-1-2cos(π / (N+1))

[0044] Among them, λ max represents the maximum eigenvalue of the weighted adjacency matrix WA;

[0045] (3) Weighted Graph Entropy (WGE)

[0046]

[0047] Among them, k i represents the degree of node i in WDVG, and p(k) represents the distribution of the degree.

[0048] Furthermore, the extracted features are used to construct the sea clutter map feature vector of the subsequence, specifically:

[0049] ρ m =[ρ1(x m ),ρ2(x m ),ρ3(x m )] T

[0050] Among them, x m represents the mth sea surface echo subsequence, ρ1(x m ),ρ2(x m ),ρ3(x m ) represents the subsequence x m The vector composed of the WPH features extracted from the corresponding WDVG, the vector composed of the WGC features extracted, and the vector composed of the WGE features extracted. The superscript T represents the transposition operation.

[0051] Furthermore, each sea clutter image feature vector is used as a training sample point to construct a training sample set; and the target detector is trained using the training sample set, including:

[0052] Step 5.1: construct a training sample set ρ. Each training sample point in the training sample set is a sea clutter map feature vector ρ constructed for the subsequence. m ; and calculate the original convex hull S containing all sea clutter map feature vectors based on the training sample points n ;

[0053] Step 5.2: Use the training samples to convex hull S n Specifically, the internal segmentation operation is performed by finding the redundant local space and its corresponding triangulation surface in the convex hull, and selecting the training samples as the internal segmentation points;

[0054] Step 5.3, when performing the internal sectioning, it may cause the internal training sample points contained in the convex hull area to appear in S after the internal sectioning operation. n In the external case, such training sample points are called external points; after the internal segmentation operation is completed, S n To perform external operations:

[0055] To S n The subdivision surface is found, the subdivision surface closest to the external point is found, and a new external subdivision surface is constructed with the three edges of the external point and the subdivision surface to surround all training sample points; finally, the redundant subdivision surface is deleted to complete the update;

[0056] Step 5.4: Set the number of iterations and repeat step 5.3 to obtain the final concave hull decision region Ω.

[0057] Step 5.5, delete a specified number of training sample points on the generated concave hull decision area surface;

[0058] Step 5.6: When the specified false alarm rate requirement is met, stop the iteration and convert the concave hull decision area Ω fina as an object detector.

[0059] Furthermore, the selection criteria of the inner section point are as follows: find the section plane with the largest perimeter △ max and the longest side, and then find the corresponding training sample point as the inline point P o , and then use P o Construct 4 new subdivision surfaces and add them to S n , and delete △ max To update S n , complete S n The internal section.

[0060] Furthermore, the specified number of training sample points on the generated concave hull decision area surface are deleted as follows:

[0061] Step 5.5.1: Based on the number Q of training sample points in the training sample set ρ and the preset false alarm rate Pf , calculate the number of false alarm points: N f =Q×P f ;

[0062] In step 5.5.2, based on the principle of maximizing the volume loss of the concave hull decision area, delete one training sample point at a time from all training sample points that satisfy the minimum concave hull decision area; based on the training sample set after deleting the training sample points, iteratively repeat steps 5.1 to 5.5 to complete the update of the training sample set and the concave hull decision area.

[0063] Furthermore, for the sea surface echo amplitude sequence to be detected, the sea clutter map feature vector corresponding to the sequence is used as a sample point to be detected, and whether a target exists in the sea surface echo amplitude sequence to be detected is determined based on the relative position relationship between the sample point to be detected and the target detector, including:

[0064] For the sea surface echo amplitude sequence to be detected, subsequence division, phase difference sequence conversion, normalization processing, weighted difference visibility map network construction, feature extraction, sea clutter map feature vector construction are carried out in sequence and used as the sample point to be tested;

[0065] If the ratio of the sample points to be tested that fall outside the concave hull decision area to all the sample points to be tested is greater than a preset value, it is considered that there is a target in the sea surface echo amplitude sequence to be detected.

[0066] A terminal device includes a processor, a memory, and a computer program stored in the memory; when the processor is executed by a computer, the method for detecting faint targets on the sea surface based on weighted difference visibility map features is implemented.

[0067] A computer-readable storage medium stores a computer program; when the computer program is executed by a processor, the method for detecting faint targets on the sea surface based on weighted difference visibility map features is implemented.

[0068] Compared with the prior art, the present invention has the following technical features:

[0069] This paper proposes a method for detecting weak targets on the sea surface based on weighted difference visibility graph features. By constructing a weighted difference visibility graph of radar received echo signals, the underlying dynamic characteristics of the echo data sequence are analyzed. Three features, WPH, WGC, and WGE, are extracted from the graph domain. A target detector with controllable false alarms is constructed using a concave hull learning algorithm to detect weak targets on the sea surface. Verification using the IPIX radar measured data set demonstrates that the difference graph features extracted by this invention exhibit good separability in feature space. Compared to existing feature joint detection algorithms, the proposed algorithm still exhibits superior detection performance under low signal-to-noise ratio conditions, effectively enabling detection of weak targets on the sea surface. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] Figure 1 Schematic diagram of the overall process of the method of the present invention;

[0071] Figure 2 The distribution of clutter feature sample points, concave hull decision area and sample points of the unit to be measured are obtained by extracting the sea clutter data measured by IPIX;

[0072] Figure 3 10 sets of IPIX measured sea clutter data at a false alarm rate of 1e -3 Under these conditions, the detection performance of the method of the present invention is compared with that of the existing feature detection methods. DETAILED DESCRIPTION

[0073] To improve target detection performance in complex sea environments, some scholars have proposed the comprehensive utilization of multidimensional information, integrating and utilizing high-dimensional refined information to provide a more refined description of complex sea surface echoes. Many studies have extracted joint features from different domains, including multifractal, phase, speckle, and polarization features for target detection. Due to the complexity of the impact of sea clutter on radar detection, in order to fully exploit the differences between sea clutter signals and target signals, detection methods are developing in the direction of absorbing emerging disciplines and technologies and mining information from different transformation fields. Network theory has demonstrated significant advantages in analyzing the dynamic characteristics of time series and has been widely used in discrete signal processing, computer biology, the internet industry, and other fields in recent years.

[0074] Based on the above ideas, this paper analyzes the visibility graph (VG) and its variants in complex network theory, proposes a feature extraction method combined with the weighted different visibility graph (WDVG), designs a false alarm controllable concave hull detector to construct the sea clutter decision region, and thus improves the faint target detection performance under low signal-to-noise ratio conditions.

[0075] See also Figure 1 The present invention proposes a method for detecting faint targets on the sea surface based on weighted difference visibility map features, comprising the following steps:

[0076] Step 1: Collect the sea surface echo amplitude sequence for target detector training and preprocess each sea surface echo amplitude sequence; the specific steps are as follows:

[0077] Step 1.1: Divide the sea surface echo amplitude sequence received by the radar into subsequences of length N. After division, the m-th subsequence x at the nth moment is obtained. m (n) The phase difference sequence is calculated as follows:

[0078]

[0079] Where τ represents the time interval, the superscript “*” represents the complex conjugate, arg(·) represents the phase of the complex variable, and N is the subsequence length, that is, the time corresponding to the subsequence. Each moment n corresponds to a data point.

[0080] Step 1.2: Normalize the phase difference sequence and map the data between [0, 1] to reduce the difference between the data. The preprocessed phase difference sequence is obtained. The specific formula is as follows:

[0081]

[0082] Among them, x(n) represents the normalized phase difference sequence, φ mmax represents the maximum value in the phase difference sequence, φ mmin Indicates the minimum value in the phase difference sequence.

[0083] Step 2: Use the normalized phase difference sequence to construct a weighted difference visibility graph network.

[0084] Step 2.1, build the visibility graph network (VG network).

[0085] Based on visibility graph theory, the visibility criterion for the phase difference sequence x(n), n = 1, 2, ..., N is defined as follows:

[0086] x(k)<x(j)+(x(i)-x(j))(ik) / (ji),i<k<j

[0087] Where i, k, and j represent the data points in the phase difference sequence, and x(i), x(j), and x(k) represent the amplitudes at the corresponding data points in the sequence.

[0088] For any two data points i and j in the sequence, if any point k between them and its amplitude satisfy the above formula, then the data points i and j are regarded as two mutually visible nodes in the visibility graph network, and there is an edge between the two nodes; traverse all data points in the sequence to obtain the adjacency matrix A:

[0089]

[0090] Among them, A ij Represents the element in row i and column j of the adjacency matrix; if A ij =A ji =1, indicating that node i is connected to node j; if A ij =A ji =0, indicating that there is no edge between the two nodes.

[0091] The normalized phase difference sequence of each subsequence is converted into a visibility graph network according to the above definition, where each data point in the phase difference sequence is a node in the network; the resulting VG network is denoted by G(V,E), where V represents the node set corresponding to the amplitude of the original signal sequence; E represents the set of edges between nodes.

[0092] Step 2.2: Construct the horizontal visibility graph network (HVG network). The horizontal visibility graph (HVG) is an improved version of VG. It is computationally faster than VG, easier to process, and allows for analysis. The HVG is defined as follows:

[0093] If the following geometric criteria are met in the sequence x(a), two data points i and j are regarded as two connected nodes in the HVG network:

[0094] x(i),x(j)>x(k) (for all k,i<k<j)

[0095] According to the above definition, the VG network established for the phase difference sequence is converted into an HVG network.

[0096] Step 2.3, construct the Differential Visibility Graph Network (DVG Network).

[0097] In this scheme, the behavior difference sequence is finally represented by the Differential Visibility Graph (DVG) network. The DVG network is an extension of the VG network and the HVG network, emphasizing the analysis of the differences between sequence data. The definition of DVG is as follows:

[0098] E(DVG)=E(VG) / E(HVG), V(DVG)=V(VG)=V(HVG)

[0099] Among them, E(DVG), E(VG) and E(HVG) represent the sets of edges of the DVG network, VG network and HVG network respectively, and V(DVG), V(VG) and V(HVG) represent the sets of nodes of the DVG network, VG network and HVG network respectively.

[0100] Through the above formula, the phase difference sequence can be expressed by the DVG network based on the VG network and the HVG network.

[0101] Step 2.4, construct the weighted difference visibility graph network WDVG.

[0102] The DVG network constructed in step 2.3 is a binary network that only provides information about the existence or non-existence of a link between two nodes. However, the weighted graph that assigns edge weights based on the link strength of the edges in the DVG network retains the weight information in the network topology and can obtain more robust results.

[0103] Based on the DVG network, the present invention uses the arctan function to assign weights to the edges between two nodes with a connection relationship in the DVG network to characterize the changes between the quantitative data points with a link relationship in the phase difference sequence, thereby obtaining a weighted difference visibility graph network; the weight is defined as follows:

[0104] W ij =arctan(x(j)-x(i)) / (ji)

[0105] Among them, W ij Represents the weight of the edge between node i and node j in the DVG network; the weighted adjacency matrix WA is defined as follows:

[0106]

[0107] Among them, W ij represents the element in row i and column j of the adjacency matrix; if W ij =W ji ≠0, indicating that node i is connected to node j, and the edge weight is W ij If W ij =W ji =0, indicating that there is no edge between the two nodes.

[0108] Step 3: Perform feature extraction on the weighted difference visibility graph network.

[0109] Step 2 has obtained the weighted difference visibility graph network corresponding to each subsequence of the sea surface echo amplitude sequence; for the weighted difference visibility graph network corresponding to each subsequence, the following feature extraction is performed:

[0110] (1) Weighted graph weight peak height (WPH)

[0111] The weight information of the weighted graph edge plays an important role in distinguishing the strength of the WDVG edge link relationship, that is, the criticality. Therefore, WPH is defined as:

[0112] WPH=max(W ij )

[0113] Among them, W ij Represents the element in the i-th row and j-th column of the weighted adjacency matrix WA.

[0114] (2) Weighted Graph Complexity (WGC)

[0115] The graph complexity (GC) represents the global complexity of the graph structure and adjacency matrix. In WDVG, the edge weights are considered in the calculation of WGC. It is defined as follows:

[0116] WGC=4κ(1-κ)

[0117] κ=λ max -2cos(π / (N+1)) / N-1-2cos(π / (N+1))

[0118] Among them, λ max Represents the maximum eigenvalue of the weighted adjacency matrix WA.

[0119] (3) Weighted Graph Complexity (WGE)

[0120] Graph entropy is a metric used to describe the complexity of a graph, reflecting the nonlinear dynamic characteristics of the system and is effective even in low SCR conditions. It is defined as follows:

[0121]

[0122] Among them, k i represents the degree of node i in WDVG, p(k) represents the distribution of degree; the degree k of node i in WDVG i Refers to the number of edges associated with node i. The larger the degree, the more important the role the node usually plays in the network.

[0123] Step 4: Based on the extracted WPH, WGC and WGE features, construct the sea clutter feature vector ρ of the subsequence m , expressed as:

[0124] ρ m =[ρ1(x m ),ρ2(x m ),ρ3(x m )] T

[0125] Among them, x m represents the mth sea surface echo subsequence, ρ1(x m ),ρ2(x m ),ρ3(x m ) represents the subsequence x mThe vector composed of the WPH features extracted from the corresponding WDVG, the vector composed of the WGC features extracted, and the vector composed of the WGE features extracted. The superscript T represents the transposition operation.

[0126] Step 5: Build the target detector.

[0127] Traditional fast convex hull learning detection methods suffer from decision space redundancy, which is caused by the uneven and non-convex distribution of features in space. To address these shortcomings, the present invention designs a concave hull detector with controllable false alarms based on a fast convex hull learning algorithm. The specific steps are as follows:

[0128] Step 5.1: construct a training sample set ρ. Each training sample point in the training sample set is a sea clutter map feature vector ρ constructed for the subsequence. m ; and calculate the original convex hull S containing all sea clutter map feature vectors based on the training sample points n .

[0129] Step 5.2: Use the training samples to convex hull S n Specifically, by finding the redundant local space and its corresponding triangulation surface (denoted by △) in the convex hull, and selecting appropriate internal training samples as internal segmentation points for internal segmentation, the spatial redundancy can be reduced.

[0130] The selection criteria for the internal sectioning point are as follows: find the sectioning surface with the largest perimeter △ max and the longest side ridge, and then find the corresponding training sample point as the inline point P o , and then use P o Construct 4 new subdivision surfaces and add them to S n , and delete △ max To update S n , complete S n The internal section.

[0131] Step 5.3, after the internal section operation S n The shape of is more consistent with the eigenvector distribution. However, when performing the introjection, in order to reduce the spatial redundancy, it is possible that the internal training sample points contained in the convex hull area will appear in the updated S after the introjection operation. n In the external case, such training sample points are called external points; therefore, after the internal section operation is completed, it is necessary to n To perform external operations:

[0132] To S n The dividing surface △ k , find the subdivision surface closest to the external point, and construct a new external subdivision surface with the three edges of the external point and the subdivision surface to surround all training sample points; finally, delete the redundant subdivision surface to complete the update.

[0133] Step 5.4: Set the number of iterations and repeat step 5.3 to obtain the final concave hull decision region Ω.

[0134] In step 5.5, after the convex hull is converted to the concave hull decision region Ω, in order to meet the requirement of constant false alarm rate, it is necessary to delete a specified number of training sample points on the surface of the generated concave hull decision region, as follows:

[0135] Step 5.5.1: Based on the number Q of training sample points in the training sample set ρ and the preset false alarm rate P f , calculate the number of false alarm points: N f =Q×P f ;

[0136] In step 5.5.2, based on the principle of maximizing the volume loss of the concave hull decision area, delete one training sample point at a time from all training sample points (false alarm points) that satisfy the minimum concave hull decision area; based on the training sample set after deleting the training sample points, iteratively repeat steps 5.1 to 5.5 to complete the update of the training sample set and the concave hull decision area.

[0137] Step 5.6: When the specified false alarm rate (such as P fa =0.001) when the requirement is met, the iteration is stopped and the concave hull decision area Ω is set. fina as an object detector.

[0138] Step 6: Process the sea surface echo amplitude sequence to be detected according to the method of steps 1 to 4 to obtain the sea clutter map feature vector corresponding to each subsequence of the sequence;

[0139] Each sea clutter map feature vector is used as a sample point to be tested, and the sample point to be tested is detected to see if it is in the concave hull decision area Ω of the target detector. fina To determine whether there is a target outside the concave hull decision area Ω fina If the ratio of the sample points to be tested to all the sample points to be tested is greater than a preset value, it is considered that there is a target in the sea surface echo amplitude sequence to be detected.

[0140] Figure 3 10 sets of IPIX radar measured sea clutter data are shown with a false alarm rate of 1e -3 , performance comparison of the proposed detector under HV polarization conditions with the original three-feature detector and the detector based on graph connectivity density. Figure 3 It can be seen that the target detection performance of the proposed detector is better than that of the comparison method under the condition of shorter observation time (0.256s).

[0141] The above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit the same. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be included in the scope of protection of the claims of the present invention.

Claims

1. A method for detecting faint targets on the sea surface based on weighted difference visibility map features, characterized in that: include: Acquire a sea surface echo amplitude sequence, divide the sea surface echo amplitude sequence into subsequences and convert it into a phase difference sequence, and perform normalization on the phase difference sequence; The normalized phase difference sequence is used to construct a weighted difference visibility graph network; Feature extraction is performed on the weighted difference visibility graph network corresponding to each subsequence, including: (1) Weighted graph weight peak height WPH: in, The weighted adjacency matrix of the weighted difference visibility graph network is represented by i Row, No. j Elements of the column; (2) Weighted Graph Complexity (WGC): in, represents the maximum eigenvalue of the weighted adjacency matrix, N Indicates the length of the subsequence; (3) Weighted Graph Entropy WGE: in, Represents nodes in a weighted differential visibility graph network i The degree, represents the distribution of degrees; Using the extracted features, construct the sea clutter map feature vector of the subsequence; Each sea clutter map feature vector is used as a training sample point to construct a training sample set; the training sample set is used to train the target detector; For the sea surface echo amplitude sequence to be detected, the sea clutter map eigenvector corresponding to the sequence is used as the sample point to be tested. The relative position relationship between the sample point to be tested and the target detector is used to determine whether there is a target in the sea surface echo amplitude sequence to be detected.

2. The method for detecting faint targets on the sea surface based on weighted difference visibility map features according to claim 1, characterized in that: The step of dividing the sea surface echo amplitude sequence into subsequences and converting the subsequences into a phase difference sequence includes: The sea surface echo amplitude sequence received by the radar is divided into N After partitioning, we get the subsequence n Moment m Segment sequence The phase difference sequence is calculated as follows: in, τ represents the time interval, the superscript * represents the complex conjugate, represents the phase of a complex variable.

3. The method for detecting faint targets on the sea surface based on weighted difference visibility map features according to claim 1, characterized in that: The method of constructing a weighted difference visibility graph network using the normalized phase difference sequence includes: Step 2.1, build visibility graph network VG Based on visibility graph theory, for phase difference sequence The visibility criteria are defined as follows: in i 、 k 、 j represents a data point in the phase difference sequence, 、 and Indicates the amplitude of the corresponding data point of the sequence; For any two data points in the sequence i, j , if any point between them k and its amplitude satisfies the above formula, then the data point i 、 j As two nodes that are visible to each other in the visibility graph network, there is an edge between the two nodes; The normalized phase difference sequence of each subsequence is converted into a visibility graph network, where each data point in the phase difference sequence is a node in the network; Step 2.2, build the horizontal visibility graph network HVG If in the sequence If the following geometric criteria are met, the two data points i, j As two connected nodes in a horizontal visibility graph network: According to the above definition, the visibility map network established for the phase difference sequence is converted into a horizontal visibility map network network; Step 2.3, construct the difference visibility graph network DVG The difference visibility graph network is defined as follows: in, 、 as well as Represent the sets of edges of DVG network, VG network and HVG network respectively, 、 as well as Represent the set of nodes of DVG network, VG network and HVG network respectively; Through the above formula, based on the VG network and HVG network, the phase difference sequence is represented by the DVG network; Step 2.4, construct the weighted difference visibility graph network WDVG Based on the DVG network, the inverse tangent function is used arctan Assign weights to the edges between two nodes with a connection relationship in the DVG network to characterize the changes between the quantity data points with a link relationship in the phase difference sequence, thereby obtaining a weighted difference visibility graph network; the weight is defined as follows: in, Represents a node in the DVG network i and nodes j The weights of the edges between them; weighted adjacency matrix The definition is as follows: in, Indicates the adjacency matrix i Row, No. j The elements of the column; if , representing a node i With node j Connected, the edge weight is ;like , indicating that there is no edge between the two nodes.

4. The method for detecting faint targets on the sea surface based on weighted difference visibility map features according to claim 1, characterized in that: The extracted features are used to construct the sea clutter map feature vector of the subsequence, specifically: in, Indicates the m sea ​​surface echo subsequences, For subsequence The vector composed of the WPH features extracted from the corresponding WDVG, the vector composed of the WGC features extracted, and the vector composed of the WGE features extracted. The superscript T represents the transposition operation.

5. The method for detecting faint targets on the sea surface based on weighted difference visibility map features according to claim 1, characterized in that: Each sea clutter image feature vector is used as a training sample point to construct a training sample set; Use the training sample set to train the target detector, including: Step 5.1: Construct a training sample set , each training sample point in the training sample set is the sea clutter map feature vector constructed for the subsequence ; and calculate the original convex hull containing all sea clutter map feature vectors based on the training sample points S n ; Step 5.2, use the training samples to convex hull S n Specifically, the internal segmentation operation is performed by finding the redundant local space and its corresponding triangulation surface in the convex hull, and selecting the training samples as the internal segmentation points; Step 5.3, when performing the internal sectioning, it may cause the internal training sample points contained in the convex hull area to appear in the S n In the case of external points, such training sample points are called external points; after the internal segmentation operation is completed, S n To perform external operations: right S n The subdivision surface is found, the subdivision surface closest to the external point is found, and a new external subdivision surface is constructed with the three edges of the external point and the subdivision surface to surround all training sample points; finally, the redundant subdivision surface is deleted to complete the update; Step 5.4: Set the number of iterations and repeat step 5.3 to obtain the final concave hull decision region Ω. Step 5.5, delete a specified number of training sample points on the generated concave hull decision area surface; Step 5.6: When the specified false alarm rate requirement is met, stop the iteration and convert the concave hull decision area Ω fina as an object detector.

6. The method for detecting faint targets on the sea surface based on weighted difference visibility map features according to claim 5, characterized in that: The selection criteria for the internal sectioning points are as follows: find the sectioning surface with the largest perimeter △ max and the longest side, and then find the corresponding training sample point as the inline point P o , reuse P o 4 new subdivision surfaces are added to S n , and delete △ max To update S n ,Finish S n The internal section.

7. The method for detecting faint targets on the sea surface based on weighted difference visibility map features according to claim 5, characterized in that: The specific method for deleting a specified number of training sample points on the surface of the generated concave hull decision region is as follows: Step 5.5.1, based on the training sample set The number of training sample points in Q And the preset false alarm rate , calculate the number of false alarm points: ; Step 5.5.2: Based on the principle of maximizing the volume loss of the concave hull decision region, delete one training sample point at a time from all training sample points that satisfy the minimum concave hull decision region; According to the training sample set after deleting the training sample points, iteratively repeat steps 5.1 to 5.5 to complete the update of the training sample set and the concave hull decision area.

8. The method for detecting faint targets on the sea surface based on weighted difference visibility map features according to claim 1, characterized in that: The method comprises: taking a sea clutter map feature vector corresponding to a sea surface echo amplitude sequence to be detected as a sample point to be detected, and determining whether a target exists in the sea surface echo amplitude sequence to be detected based on a relative position relationship between the sample point to be detected and a target detector. For the sea surface echo amplitude sequence to be detected, subsequence division, phase difference sequence conversion, normalization processing, weighted difference visibility map network construction, feature extraction, sea clutter map feature vector construction are carried out in sequence and used as the sample point to be tested; If the ratio of the sample points to be tested that fall outside the concave hull decision area to all the sample points to be tested is greater than a preset value, it is considered that there is a target in the sea surface echo amplitude sequence to be detected.

9. A computer-readable storage medium storing a computer program; wherein: When the computer program is executed by a processor, the method for detecting faint targets on the sea surface based on weighted difference visibility map features according to any one of claims 1 to 8 is implemented.

Images