Underwater target detection method and system based on multi-physical field detection fusion

Abstract

The embodiment of the invention provides an underwater target detection method and system based on multi-physical field detection fusion, and relates to the technical field of underwater target detection technologies. The method comprises the following steps: acquiring a multi-physical field signal of a detection node; preprocessing the multi-physical field signal to obtain first information; performing feature extraction on the first information to obtain signal features; performing data association processing according to the signal characteristics; and performing information fusion processing according to the data association processing result to obtain a target detection result. According to the invention, the problems that the signal detection capability of a single physical field is insufficient, the underwater target detection precision is low and the false alarm rate is high are solved, and the effect of improving the underwater target detection precision is achieved.

Description

Technical Field

[0001] The embodiments of the present invention relate to the technical field of underwater target detection, and in particular, to an underwater target detection method and system based on multi-physical field detection fusion. Background Art

[0002] Underwater target detection technology has important application value in the fields of marine resource development, marine security, national defense, etc. Traditional underwater target detection methods mainly rely on single physical field signals (such as acoustic field signals, electric field signals or magnetic field signals) for target detection and identification. These single physical field detection methods are often easily interfered by environmental noise, signal attenuation, multipath effects and other factors in complex underwater environments, resulting in reduced detection accuracy and reliability.

[0003] There is currently no better solution to the above problems. Summary of the invention

[0004] The embodiments of the present invention provide a method and system for underwater target detection based on multi-physical field detection fusion, so as to at least solve the problem of low accuracy of underwater target detection by a single physical field signal in the related art.

[0005] According to one embodiment of the present invention, a method for underwater target detection based on multi-physical field detection fusion is provided, comprising:

[0006] Acquire a multi-physical field signal of a detection node, wherein the multi-physical field signal includes an acoustic field signal, an electric field signal, and a magnetic field signal, and the detection node is provided with a plurality of them;

[0007] Preprocessing the multi-physical field signal to obtain first information;

[0008] Performing feature extraction on the first information to obtain signal features;

[0009] Performing data association processing according to the signal characteristics;

[0010] Information fusion processing is performed based on the data association processing results to obtain the target detection results.

[0011] In an exemplary embodiment, after extracting features from the first information to obtain signal features, the method further includes:

[0012] Based on the signal characteristics, determining a local detection result of each of the detection nodes;

[0013] Obtaining decision fusion rules;

[0014] According to the decision fusion rule, the local detection results are subjected to detection fusion processing to obtain the global detection results;

[0015] A first match is performed between the global detection result and the target detection result, and when the first matching result does not meet a first condition, it is determined that the target detection result is abnormal.

[0016] In an exemplary embodiment, after preprocessing the multi-physics field signal to obtain the first information, the method further includes:

[0017] constructing a first matrix based on the first information;

[0018] Performing information correlation calculation on the first matrix to obtain a correlation value;

[0019] When the correlation value does not meet the second condition, it is determined that the first information is abnormal.

[0020] In an exemplary embodiment, after preprocessing the multi-physics field signal to obtain the first information, the method includes:

[0021] constructing a characteristic distribution according to the first information, wherein the characteristic distribution includes electric field distribution, magnetic field distribution, and acoustic distribution;

[0022] performing a second association process on the feature distribution;

[0023] A chi-square test calculation is performed on the second association processing result. When the chi-square value is within a preset range, it is determined that the first information is normal; otherwise, it is determined to be abnormal.

[0024] According to another embodiment of the present invention, there is provided an underwater target detection system based on multi-physical field detection fusion, comprising:

[0025] An information acquisition module, used to obtain multi-physical field signals of a detection node, wherein the multi-physical field signals include acoustic field signals, electric field signals, and magnetic field signals, and the detection node is provided with multiple;

[0026] A preprocessing module, used for preprocessing the multi-physical field signal to obtain first information;

[0027] A feature extraction module, used to extract features from the first information to obtain signal features;

[0028] An association module, used for performing data association processing according to the signal characteristics;

[0029] The fusion module is used to perform information fusion processing according to the data association processing results to obtain the target detection results.

[0030] In an exemplary embodiment, it further includes:

[0031] A local detection module, configured to determine a local detection result of each detection node based on the signal feature after extracting the feature of the first information to obtain the signal feature;

[0032] A rule acquisition module is used to acquire decision fusion rules;

[0033] A detection fusion module, used to perform detection fusion processing on the local detection results according to the decision fusion rule to obtain a global detection result;

[0034] The first matching module is used to perform a first matching between the global detection result and the target detection result, and determine that the target detection result is abnormal if the first matching result does not meet a first condition.

[0035] In an exemplary embodiment, it further includes:

[0036] A matrix construction module, configured to construct a first matrix based on the first information after preprocessing the multi-physics field signal to obtain the first information;

[0037] A correlation calculation module, used for performing information correlation calculation on the first matrix to obtain a correlation value;

[0038] The abnormality judgment module is used to determine that the first information is abnormal when the correlation value does not meet the second condition.

[0039] In an exemplary embodiment, it further includes:

[0040] A characteristic distribution module, configured to construct a characteristic distribution according to the first information after preprocessing the multi-physical field signal to obtain the first information, wherein the characteristic distribution includes electric field distribution, magnetic field distribution, and acoustic distribution;

[0041] A second association module, used for performing a second association process on the feature distribution;

[0042] The chi-square detection module is used to perform a chi-square detection calculation on the second association processing result, and determine that the first information is normal when the chi-square value is within a preset range, otherwise it is determined to be abnormal.

[0043] According to yet another embodiment of the present invention, a computer-readable storage medium is provided, in which a computer program is stored, wherein the computer program is configured to execute the steps of any one of the above method embodiments when run.

[0044] According to yet another embodiment of the present invention, there is provided an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0045] Through the present invention, by fusing multiple physical field signals (including acoustic field signals, electric field signals and magnetic field signals), the limitations of a single physical field detection method are overcome, and the accuracy, reliability and environmental adaptability of underwater target detection are improved. Therefore, the problems of low underwater target detection accuracy and high false alarm rate of a single physical field signal can be solved, thereby achieving the effect of improving the underwater target detection accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 is a flow chart of an underwater target detection method based on multi-physical field detection fusion according to an embodiment of the present invention;

[0047] Figure 2 It is a schematic diagram of the principle of a specific embodiment of the present invention. Figure 1

[0048] Figure 3 It is a schematic diagram of the principle of a specific embodiment of the present invention. Figure 2 ;

[0049] Figure 4 It is a structural block diagram of an underwater target detection system based on multi-physical field detection fusion according to an embodiment of the present invention. DETAILED DESCRIPTION

[0050] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments.

[0051] In the following, the terms "first", "second", etc. are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first", "second", etc. may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0052] In addition, in the present application, directional terms such as "up", "down", "left" and "right" may be defined including but not limited to the orientation relative to the schematic placement of the components in the drawings. It should be understood that these directional terms may be relative concepts, which are used for relative description and clarification, and may change accordingly according to the change in the orientation of the components in the drawings.

[0053] In this application, unless otherwise specified or limited, the term "connection" should be understood in a broad sense. For example, "connection" can be a fixed connection, a detachable connection, or an integral connection; it can be a direct connection or an indirect connection through an intermediate medium. In addition, the term "coupling" can be a way of achieving electrical connection for signal transmission.

[0054] As used herein, "about," "substantially," or "approximately" includes the stated value and an average value that is within an acceptable range of variation from the particular value as determined by one of ordinary skill in the art taking into account the measurements in question and the errors associated with the measurement of the particular quantity (i.e., the limitations of the measurement system).

[0055] In this embodiment, a method for underwater target detection based on multi-physical field detection fusion is provided. Figure 1 is a flow chart of an underwater target detection method based on multi-physical field detection fusion according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0056] Step S11, obtaining a multi-physical field signal of a detection node, wherein the multi-physical field signal includes an acoustic field signal, an electric field signal, and a magnetic field signal, and the detection node is provided with a plurality of them;

[0057] In this embodiment, when performing underwater target detection, it is necessary to arrange multiple detection nodes, each detection node is equipped with multiple sensors to detect underwater targets from multiple positions, reducing the interference of water flow, partial signal delay, underwater terrain and other factors on data collection; similarly, collecting multiple signals including sound field signals, magnetic field signals, and electric field signals is also for detecting underwater targets from multiple dimensions, thereby avoiding data loss or errors caused by excessive interference of a single signal, and ensuring the accuracy of underwater target detection.

[0058] Among them, Figure 2 As shown, multiple detection nodes can be deployed in the detection area, and each node is equipped with an acoustic sensor, an electric field sensor, and a magnetic field sensor; each detection node synchronously collects acoustic field signals, electric field signals, and magnetic field signals, and records the collected signals by timestamp to ensure the temporal and spatial consistency of the data; the detection node transmits the data to the communication buoy through a unified underwater wiring node, and the communication buoy transmits the data to the control station. At this time, the control station sends it to the data center that needs to process the underwater target according to the demand, and then the data center processes the underwater target according to the settings.

[0059] For example, sonar or hydrophone can be used to collect acoustic field signals, electric field sensors (such as electrode arrays) can be used to collect electric field signals, and magnetometers or fluxgate sensors can be used to collect magnetic field signals. GPS or other synchronization technologies can then be used to ensure time synchronization of all detection nodes. When transmitting signals, in order to ensure accurate signal transmission, data link transmission can be used step by step.

[0060] It should be noted that, in order to ensure the accuracy of data collection, when arranging detection nodes, in addition to setting up data links for step-by-step transmission, the detection nodes corresponding to the data links can also be divided into detection sub-areas according to the detection area, such as Figure 3 As shown, under normal circumstances, the three detection nodes ABC form the first detection sub-area, and DEF forms the second detection sub-area. The two detection sub-areas exchange data through the transit link node AD, and the detection range of each detection node is certain; at this time, when a certain underwater target a is detected by the detection node of the first detection sub-area, its detection data will be obtained, and at the same time, the detection node of the second detection sub-area will also detect and obtain detection data. At this time, the relevant data are integrated through the two nodes AD to obtain accurate data about the underwater target a; and in order to further obtain accurate data of the underwater target a, the detection sub-area can be re-divided according to the integration result, for example, it is divided into a third detection sub-area composed of two detection nodes BD, and EF constitutes the fourth detection sub-area, AC constitutes The fifth detection sub-area is detected, and a new node is selected as a link communication node (for example, for the fourth detection sub-area, E is selected as a transit link node, and the communication link between F and D is cut off, and the communication link between AD or AB is cut off in the same way), so as to adjust the detection area, thereby reducing the interference of signal data of other communication nodes on the data of the two nodes BD, and so on; and the selection of the transit link node can be based on the integration result, and the node with the greatest impact on the detection data of the underwater target a, or the node with the greatest signal strength, the most signal connections, and the strongest data correlation is determined as the transit link node, for example, the node closest to the underwater target a and with the most / least associated nodes, the strongest signal, and the widest detection range is selected as the transit link node; of course, it can also be calculated by the following formula, which is not limited here:

[0061]

[0062] In the formula, s i The node score of node i, d i is the distance from node i to underwater target a, n i is the number of associated nodes, g i is the signal strength of node i, r iis the detection range area of ​​node i, and w is the weighted value of each factor; wherein, Formula 1 is one of the judgment methods and is not a limitation of this solution.

[0063] Step S12, preprocessing the multi-physical field signal to obtain first information;

[0064] In this embodiment, the preprocessing is mainly to remove noise and interference in the signal to ensure the accuracy of subsequent data processing; and to normalize the relevant data to normalize the signal amplitude to a uniform range to reduce the amount of data calculation.

[0065] Among them, a low-pass filter is used to remove high-frequency noise, a band-pass filter is used to retain the target signal frequency band, and a wavelet transform is used to remove mutation noise; the normalization processing is specifically to normalize the amplitude of the sound field signal, electric field signal and magnetic field signal to the range of [0,1] or [-1,1], and then align the data of different sensors according to the timestamp, and use the interpolation method to fill the missing data.

[0066] Step S13, performing feature extraction on the first information to obtain signal features;

[0067] In this embodiment, feature extraction mainly includes extracting features of the three types of acoustic and electromagnetic signals, and associating the extracted features to facilitate subsequent data analysis.

[0068] Among them, for acoustic feature extraction, it includes calculating the sound pressure level (RMS value), extracting frequency characteristics (such as main frequency, bandwidth), and calculating the harmonic distortion rate; for electric field signal feature extraction, the electric field strength (first amplitude) is calculated, the electric field change rate (first time derivative) is extracted, and the power spectral density of the electric field is calculated; the magnetic field strength (second amplitude) is calculated, the magnetic field change rate (second time derivative) is extracted, and the power spectral density of the magnetic field is calculated.

[0069] Step S14, performing data association processing according to the signal characteristics;

[0070] In this embodiment, when performing feature association, association may be performed from different dimensions to facilitate subsequent analysis of data from different dimensions.

[0071] For example, the acoustic, electric, and magnetic field characteristics can be correlated according to the position of the underwater target in space; or the acoustic, electric, and magnetic field characteristics can be correlated according to the temporal changes of the underwater target; and then the correlation between different characteristics, such as the correlation coefficient, can be calculated.

[0072] Specifically, the acoustic, electric field, and magnetic field characteristics can be spatially matched according to the geographical location of the detection node, and the spatial distribution map can be constructed using the interpolation method; at the same time, the acoustic, electric field, and magnetic field characteristics can be time-aligned according to the timestamp, and the sliding window method can be used to analyze the changes in the characteristics over time, and so on.

[0073] Step S15, performing information fusion processing according to the data association processing result to obtain the target detection result.

[0074] In this embodiment, the associated features are fused through a preset model, and the fusion results are identified and analyzed to obtain the final detection result.

[0075] The associated features are weighted and fused, and machine learning or deep learning models are used for target recognition, and the target detection results are output, including target location (such as longitude and latitude, depth), type (such as underwater target size, volume, shape, possible categories such as submarines, ships, animals and other underwater objects) and confidence (such as recognition probability).

[0076] Specifically, the weighted average method is used to fuse the acoustic, electric field, and magnetic field features, and the PCA dimensionality reduction method is used to remove redundant features. Then, the trained model is used to output the target detection results including information such as the target location.

[0077] Through the above steps, by fusing multiple physical field signals (including acoustic field signals, electric field signals and magnetic field signals), the limitations of the single physical field detection method are overcome, the accuracy, reliability and environmental adaptability of underwater target detection are improved, the problem of low accuracy of underwater target detection by a single physical field signal is solved, and the accuracy of underwater target detection is improved.

[0078] The execution subject of the above steps may be a base station, a terminal, etc., but is not limited thereto.

[0079] In an optional embodiment, after extracting features from the first information to obtain signal features, the method further includes:

[0080] Step S131, determining a local detection result of each detection node based on the signal characteristics;

[0081] In this embodiment, a decision threshold is set for each feature according to the statistical characteristics (such as mean, variance) of the feature or prior knowledge. For example, the amplitude threshold T of the sound field signal is set 声 , the intensity threshold of the electric field signal T 电 , the change rate threshold of the magnetic field signal T 磁 ; Local detection is performed in the following way:

[0082] For each detection node i, according to its feature F i (F i ={f 声,i ,f 电,i ,f 磁,i}) is compared with the threshold to determine whether the target exists; for example, if It is determined that an underwater target is detected, and then according to f 声,i 、f 电,i 、f 磁,i The speed, size, movement path, etc. of the underwater target can be judged based on its distribution, and its type, location coordinates and other information can be judged from this, and so on.

[0083] Step S132, obtaining decision fusion rules;

[0084] In this embodiment, the decision fusion rules may include the following rules:

[0085] A1, “AND” rule: The global detection result is “target exists” only when the local detection results of all nodes are “target exists”.

[0086] A2, “or” rule: the global detection result is “target exists” as long as the local detection result of one node is “target exists”.

[0087] A3, weighted voting method: assign different weights according to the reliability or importance of the nodes, calculate the weighted sum, and compare it with the preset threshold to determine the global detection result.

[0088] A4, Bayesian fusion rule: Based on Bayesian theory, it combines prior probability and likelihood function to calculate the probability of global detection results.

[0089] Among them, if the weighted voting method is used, the weight of each node needs to be recorded; if the Bayesian fusion rule is used, the parameters of the prior probability and likelihood function need to be recorded.

[0090] Step S133, performing detection fusion processing on the local detection results according to the decision fusion rule to obtain a global detection result;

[0091] In this embodiment, according to the selected fusion rule, the local detection results D of all detection nodes are i Fusion into the global detection result D 全局 , specifically:

[0092] A1, "AND" rule fusion:

[0093]

[0094] A2, "or" rule fusion:

[0095] D全局 =max(D 1 ,D 2 ,D 3 ...,D N )

[0096] (Formula 3)

[0097] A3, weighted voting fusion:

[0098]

[0099] Among them, T 融合 is the preset fusion threshold.

[0100] A4, Bayesian fusion:

[0101]

[0102] The calculated probability value is then compared with the preset threshold to determine the global detection result.

[0103] Step S134: performing a first match between the global detection result and the target detection result, and determining that the target detection result is abnormal if the first matching result does not meet the first condition.

[0104] In this embodiment, after the fusion is completed, if the global detection result is consistent with the target detection result, the target detection result is considered correct, otherwise it is judged to be abnormal.

[0105] In an optional embodiment, after preprocessing the multi-physical field signal to obtain the first information, the method further includes:

[0106] Step S121, constructing a first matrix based on the first information;

[0107] Step S122, performing information correlation calculation on the first matrix to obtain a correlation value;

[0108] Step S123: When the correlation value does not meet the second condition, it is determined that the first information is abnormal.

[0109] In this embodiment, in order to ensure the accuracy of the data, before data fusion, it is also possible to determine whether the multi-physical field signals are normal by calculating the correlation between the related data.

[0110] Specifically, the first information can be used as a matrix element to fill in the corresponding detection matrices according to the detection areas. These detection matrices together constitute a first matrix set. Then, the correlation value of the detection matrix of each detection area is calculated according to the Pearson correlation coefficient, and the similarity value of the detection matrices between different areas is calculated. When the correlation value and the similarity value are both within the preset range, the corresponding first information is judged to be normal, otherwise it is judged to be abnormal, and so on.

[0111] For example, the preprocessed acoustic field signal, electric field signal and magnetic field signal of the first detection sub-area are respectively expressed in vector form. Assume that the acoustic field signal collected by each detection node is The electric field signal is The magnetic field signal is The detection matrix M corresponding to the first detection area is formed as follows: Then the correlation between the columns in the detection matrix is ​​calculated, and the calculation formula of the correlation value R is:

[0112] R = corr(M)

[0113] (Formula 6)

[0114] In the formula, corr() represents the correlation coefficient calculation function, and the correlation value R is a 3×3 matrix, which represents the correlation between the three signals, and so on, which is not limited here.

[0115] In an optional embodiment, after preprocessing the multi-physical field signal to obtain the first information, the method includes:

[0116] Step S124, constructing a characteristic distribution according to the first information, wherein the characteristic distribution includes electric field distribution, magnetic field distribution, and acoustic distribution;

[0117] Step S125, performing a second association process on the feature distribution;

[0118] Step S126, performing a chi-square test calculation on the second association processing result, and determining that the first information is normal when the chi-square value is within a preset range, otherwise it is determined to be abnormal.

[0119] In this embodiment, in addition to judging the data by constructing a matrix, the independence between feature distributions can also be judged based on the distribution of the data and its chi-square test results. Generally, multi-physical field signals are detections of the same thing, so their independence should be lower. Therefore, if a higher independence appears, it means that the data may be abnormal.

[0120] Specifically, the electric field strength is organized into electric field distribution according to spatial position or time series, the magnetic field strength is organized into magnetic field distribution according to spatial position or time series, and the sound pressure level is organized into acoustic distribution according to spatial position or time series, and each distribution is discretized into several intervals (or "buckets") for chi-square detection. For example, the electric field strength is divided into k intervals, the magnetic field strength is divided into m intervals, and the sound pressure level is divided into n intervals, and then the joint distribution J = (E, B, P) of the electric field distribution, magnetic field distribution and acoustic distribution is calculated, and the marginal distribution of each distribution is calculated separately:

[0121] Edge distribution of electric field distribution Edge distribution of magnetic field distribution Edge distribution of acoustic distribution At this time, assuming that the three distributions are independent of each other, the joint distribution should be equal to the product of the marginal distributions:

[0122]

[0123] The chi-square test is then used to evaluate the difference between the actual joint distribution and the joint distribution under the independence assumption. If the difference is significant, it means that the data is abnormal. For example, if the chi-square value exceeds the preset critical value, it means that the aforementioned independence product is wrong, which means that the data is abnormal, and so on.

[0124] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0125] In this embodiment, an underwater target detection system based on multi-physical field detection fusion is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0126] Figure 4 is a structural block diagram of an underwater target detection system based on multi-physical field detection fusion according to an embodiment of the present invention. Figure 4 As shown, the system includes:

[0127] An information acquisition module 41 is used to obtain a multi-physical field signal of a detection node, wherein the multi-physical field signal includes an acoustic field signal, an electric field signal, and a magnetic field signal, and the detection node is provided with a plurality of them;

[0128] A preprocessing module 42, used for preprocessing the multi-physical field signal to obtain first information;

[0129] A feature extraction module 43, used to extract features from the first information to obtain signal features;

[0130] An association module 44, configured to perform data association processing according to the signal characteristics;

[0131] The fusion module 45 is used to perform information fusion processing according to the data association processing result to obtain the target detection result.

[0132] In an optional embodiment, it also includes:

[0133] A local detection module, configured to determine a local detection result of each detection node based on the signal feature after extracting the feature of the first information to obtain the signal feature;

[0134] A rule acquisition module is used to acquire decision fusion rules;

[0135] A detection fusion module, used to perform detection fusion processing on the local detection results according to the decision fusion rule to obtain a global detection result;

[0136] The first matching module is used to perform a first matching between the global detection result and the target detection result, and determine that the target detection result is abnormal if the first matching result does not meet a first condition.

[0137] In an optional embodiment, it also includes:

[0138] A matrix construction module, configured to construct a first matrix based on the first information after preprocessing the multi-physics field signal to obtain the first information;

[0139] A correlation calculation module, used for performing information correlation calculation on the first matrix to obtain a correlation value;

[0140] The abnormality judgment module is used to determine that the first information is abnormal when the correlation value does not meet the second condition.

[0141] In an optional embodiment, it also includes:

[0142] A characteristic distribution module, configured to construct a characteristic distribution according to the first information after preprocessing the multi-physical field signal to obtain the first information, wherein the characteristic distribution includes electric field distribution, magnetic field distribution, and acoustic distribution;

[0143] A second association module, used for performing a second association process on the feature distribution;

[0144] The chi-square detection module is used to perform a chi-square detection calculation on the second association processing result, and determine that the first information is normal when the chi-square value is within a preset range, otherwise it is determined to be abnormal.

[0145] It should be noted that the above modules can be implemented by software or hardware. For the latter, it can be implemented in the following ways, but not limited to: the above modules are all located in the same processor; or the above modules are located in different processors in any combination.

[0146] An embodiment of the present invention further provides a computer-readable storage medium, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when running.

[0147] In an exemplary embodiment, the computer-readable storage medium may include, but is not limited to, various media that can store computer programs, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0148] An embodiment of the present invention further provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0149] In an exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0150] Through the description of the above implementation methods, technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0151] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0152] The units described as separate components may or may not be physically separated, and the components shown as units may be one physical unit or multiple physical units, that is, they may be located in one place or distributed in multiple different places. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0153] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0154] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium, including several instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to perform all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program code.

[0155] The above contents are only specific implementation methods of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions within the technical scope disclosed in the present application shall be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. An underwater target detection method based on multi-physical field detection fusion, characterized in that: include: Acquire a multi-physical field signal of a detection node, wherein the multi-physical field signal includes an acoustic field signal, an electric field signal, and a magnetic field signal, and the detection node is provided with a plurality of them; Preprocessing the multi-physical field signal to obtain first information; Performing feature extraction on the first information to obtain signal features; Performing data association processing according to the signal characteristics; Information fusion processing is performed based on the data association processing results to obtain the target detection results.

2. The method according to claim 1, characterized in that After extracting features from the first information to obtain signal features, the method further includes: Based on the signal characteristics, determining a local detection result of each of the detection nodes; Obtaining decision fusion rules; According to the decision fusion rule, the local detection results are subjected to detection fusion processing to obtain the global detection results; A first match is performed between the global detection result and the target detection result, and when the first matching result does not meet a first condition, it is determined that the target detection result is abnormal.

3. The method according to claim 1, characterized in that After preprocessing the multi-physical field signal to obtain the first information, the method further includes: constructing a first matrix based on the first information; Performing information correlation calculation on the first matrix to obtain a correlation value; When the correlation value does not meet the second condition, it is determined that the first information is abnormal.

4. The method according to claim 1, characterized in that: After preprocessing the multi-physics field signal to obtain first information, the method includes: constructing a characteristic distribution according to the first information, wherein the characteristic distribution includes electric field distribution, magnetic field distribution, and acoustic distribution; performing a second association process on the feature distribution; A chi-square test calculation is performed on the second association processing result. When the chi-square value is within a preset range, it is determined that the first information is normal; otherwise, it is determined to be abnormal.

5. An underwater target detection system based on multi-physical field detection fusion, characterized in that: include: An information acquisition module, used to obtain multi-physical field signals of a detection node, wherein the multi-physical field signals include acoustic field signals, electric field signals, and magnetic field signals, and the detection node is provided with multiple; A preprocessing module, used for preprocessing the multi-physical field signal to obtain first information; A feature extraction module, used to extract features from the first information to obtain signal features; An association module, used for performing data association processing according to the signal characteristics; The fusion module is used to perform information fusion processing according to the data association processing results to obtain the target detection results.

6. The system according to claim 5, characterized in that Also includes: A local detection module, configured to determine a local detection result of each detection node based on the signal feature after extracting the feature of the first information to obtain the signal feature; A rule acquisition module is used to acquire decision fusion rules; A detection fusion module, used to perform detection fusion processing on the local detection results according to the decision fusion rule to obtain a global detection result; The first matching module is used to perform a first matching between the global detection result and the target detection result, and determine that the target detection result is abnormal if the first matching result does not meet a first condition.

7. The system according to claim 6, characterized in that Also includes: A matrix construction module, configured to construct a first matrix based on the first information after preprocessing the multi-physics field signal to obtain the first information; A correlation calculation module, used for performing information correlation calculation on the first matrix to obtain a correlation value; The abnormality judgment module is used to determine that the first information is abnormal when the correlation value does not meet the second condition.

8. The system according to claim 6, characterized in that Also includes: A characteristic distribution module, configured to construct a characteristic distribution according to the first information after preprocessing the multi-physical field signal to obtain the first information, wherein the characteristic distribution includes electric field distribution, magnetic field distribution, and acoustic distribution; A second association module, used for performing a second association process on the feature distribution; The chi-square detection module is used to perform a chi-square detection calculation on the second association processing result, and determine that the first information is normal when the chi-square value is within a preset range, otherwise it is determined to be abnormal.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program is configured to execute the method according to any one of claims 1 to 4 when executed.

10. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to run the computer program to perform the method according to any one of claims 1 to 4.

Images