CN115878982B - Underwater target identification method and system based on double-frequency echo signal characteristics - Google Patents
Underwater target identification method and system based on double-frequency echo signal characteristics Download PDFInfo
- Publication number
- CN115878982B CN115878982B CN202211571572.6A CN202211571572A CN115878982B CN 115878982 B CN115878982 B CN 115878982B CN 202211571572 A CN202211571572 A CN 202211571572A CN 115878982 B CN115878982 B CN 115878982B
- Authority
- CN
- China
- Prior art keywords
- frequency
- target
- echo
- underwater
- time
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/30—Assessment of water resources
Landscapes
- Measurement Of Velocity Or Position Using Acoustic Or Ultrasonic Waves (AREA)
Abstract
The invention discloses an underwater target identification method and system based on double-frequency echo signal characteristics. The method comprises the following steps: extracting time-frequency characteristics of each sample of the acquired underwater sound target echo signal data samples in different frequency bands; respectively placing the time-frequency characteristic diagrams of the two frequency bands of the same target echo into two channels for combination to form a time-frequency characteristic diagram of a double-frequency echo signal; taking the time-frequency characteristics of each sample as sample data, labeling the same label by the underwater acoustic echo data samples of the same target, and labeling different labels by the underwater acoustic echo data samples of different targets to form a training set; training by taking the training set as the input of the convolutional neural network to obtain an identification model based on the convolutional neural network; and carrying out target recognition on the underwater acoustic echo data subjected to the feature extraction by using the trained recognition model. The invention has high identification accuracy, simple network structure, less parameters and convenient application.
Description
Technical Field
The invention relates to the field of underwater acoustic signal processing, in particular to an underwater target recognition method and system based on double-frequency echo signal characteristics, and belongs to the field of underwater target echo signal recognition.
Background
Along with the rapid development of underwater sound technology, underwater target observation data is rapidly increased, and how to use the observation data for underwater sound target identification is always a research hot spot in the field of underwater safety. Today, underwater sound countermeasure technology is continuously developed, and the countermeasure environment is increasingly complex. A common countermeasure is to interfere with the opponent's target positioning by simulating the echo of the underwater target. Therefore, a target identification method is urgently needed to be found to cope with various underwater decoy interferences, and further, the underwater target identification under the complex environment is realized.
The traditional underwater target recognition method generally depends on shallow learning, such as a support vector machine model, a Gaussian mixture model and the like, is suitable for solving the problems of easiness in feature extraction and limitation of specific classification, and has poor data classification effect on difficult feature engineering. In addition, parameters of shallow learning cannot be self-adaptive, so that the self-correcting capability of the shallow learning system is poor. Meanwhile, the existing underwater target recognition method is based on target echo of a single frequency band, and the recognition effect is greatly affected under the interference of acoustic decoys due to the lack of characteristic information of a target body in different frequency bands.
It is therefore desirable to establish an underwater object identification scheme capable of identifying objects in complex underwater acoustic environments in response to the interference of acoustic decoys in such environments.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a method for realizing underwater target identification under the interference of acoustic decoys, which improves the identification effect.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
an underwater target recognition method based on double-frequency echo signal characteristics comprises the following steps:
(1) Extracting time-frequency characteristics of each sample of the acquired underwater sound target echo signal data samples in different frequency bands;
(2) Respectively placing the time-frequency characteristic diagrams of the two frequency bands of the same target echo into two channels for combination to form a time-frequency characteristic diagram of a double-frequency echo signal;
(3) Taking the time-frequency characteristics of each sample as sample data, labeling the same label by the underwater acoustic echo data samples of the same target, and labeling different labels by the underwater acoustic echo data samples of different targets to form a training set;
(4) Training by taking the training set as the input of the convolutional neural network to obtain an identification model based on the convolutional neural network;
(5) And carrying out target recognition on the underwater acoustic echo data subjected to the feature extraction by using the trained recognition model.
The invention also provides an underwater target recognition system based on the difference of the double-frequency echo signals, which comprises:
the time-frequency characteristic construction module of the double-frequency signal is used for extracting the time-frequency characteristic of the underwater acoustic echo data, combining the time-frequency characteristics under two frequency bands of the same target, and taking the combined characteristic as the time-frequency characteristic of the double-frequency signal;
the convolutional neural network recognition model training module is used for taking the time-frequency characteristic of each sample as sample data, labeling the same label by the underwater acoustic echo data samples of the same target, labeling different labels by the underwater acoustic echo data samples of different targets to form a training set, and training by taking the training set as the input of the convolutional neural network to obtain a recognition model based on the convolutional neural network;
and the target recognition module is used for taking the underwater acoustic echo data subjected to the feature extraction as the input of a recognition model to realize the classification recognition of the target.
The present invention also provides a computer device comprising: one or more processors; a memory; and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, which when executed by the processors implement the steps of the underwater target identification method based on dual frequency echo signal differences as described above.
The present invention also provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the underwater target identification method based on dual frequency echo signal differences as described above.
The invention provides an underwater target recognition method based on double-frequency echo signal characteristics, which is characterized in that the recognition effect is enhanced by combining echo signals of two different frequency bands and analyzing the characteristics, and is applied to the field of underwater sound recognition for the first time. The convolutional neural network model can break the dependence on priori knowledge and a feature extraction method in the existing underwater sound target recognition, well overcomes the defect of shallow learning self-adaption deficiency, can perform parameter self-adaption learning, can characterize high-dimensional complex parameters, and extracts deep features of the target. Experiments prove that the accuracy of the dual-frequency echo signal identification method provided by the invention is improved by 8.9% on a test set compared with that of the traditional single-frequency signal identification method, 84.6% is achieved, the network structure is simple, the parameters are few, a new thought is provided for the underwater sound target identification method in a complex environment, and the method has a wide application prospect.
Drawings
FIG. 1 is a schematic flow chart of the method of the present invention.
Fig. 2 is a diagram of a classification recognition confusion matrix for the method of the present invention.
Fig. 3 is a block diagram of a convolutional neural network of the present invention.
Detailed Description
The technical scheme of the invention is further described below with reference to the accompanying drawings.
The invention provides a realization method for underwater target recognition based on double-frequency echo signal characteristics, and referring to fig. 1, the method mainly comprises two stages: and constructing a time-frequency characteristic of the double-frequency signal and identifying a convolutional neural network. The time-frequency characteristics of the underwater acoustic echo data are extracted by the time-frequency characteristics part of the double-frequency signal, then the time-frequency characteristics of the same target under different frequency bands are combined, and the combined characteristics are regarded as the time-frequency characteristics of the double-frequency signal. The convolutional neural network recognition part takes the constructed time-frequency characteristics of the double-frequency signals as input samples, takes a linear rectification function as an activation function, and takes a binary cross entropy function as an objective function for training, so that the classification recognition of the input samples is realized. In the embodiment, after the underwater sound target echo signal is obtained, the underwater sound target echo signal is divided into a training sample and a test sample according to a certain proportion, and a training set and a test set are formed through feature extraction, double-frequency signal time-frequency feature construction and labeling; the training set is used as the input of the convolutional neural network to obtain an identification model based on the convolutional neural network, and the test set is used as the input of the identification model to verify the identification performance of the convolutional neural network.
The implementation method and the obtaining effect of the invention are specifically discussed below in conjunction with an on-lake test case. The method specifically comprises the following steps:
step 001, the test conditions of the present invention are: a cylindrical phantom of 55cm diameter and 4.2m length was selected as the target and a sound source was used to provide simulated echoes in place of the acoustic decoys. A lake with good hydrologic conditions is selected in the test field, the collected data can be ensured to be effective, and the test obtains echo data of the target body by transmitting a detection signal through a sound source. False echoes of the acoustic decoys are then sent by the acoustic source directly to the hydrophones. And respectively arranging the standard hydrophone, the transmitting transducer and the target body to the same depth, wherein the standard hydrophone is arranged between the transmitting transducer and the target body. The transmitting transducer is 3m away from the standard hydrophone, the standard hydrophone is 3m away from the target body, and the laying depth is 4m. The signal source is used for driving the transmitting transducer to transmit single-frequency pulse signals, the signal frequencies are respectively 20KHz and 50KHz, the pulse width is 0.5ms, the wave numbers are respectively 10 and 25, and the sampling points are 256000. And the steps are repeated after the target body rotates 45 degrees and 90 degrees respectively so as to acquire the echo characteristics of the target body under different postures.
And 002, the experimental data comprise two types of target body echo and non-target false echo, each type comprises two frequency bands of 20KHz and 50KHz, the pulse width of the detection signal is 1ms, and the number of samples of each frequency band is 1110, which is 4400 in total. And removing part of data with poor acquisition effect, manually removing blank segments left during acquisition from the rest of audio, filtering and denoising the audio, and carrying out data enhancement on part of data to solve the problem of small sound.
Step 003, performing a fast fourier transform on the data, extracting the time-frequency characteristics of each sample, and obtaining 1110 time-frequency diagrams with sizes (198, 138).
Step 004, the time-frequency characteristic diagrams of the two different frequency bands are put into different channels to form a new time-frequency characteristic diagram of the double-frequency signal of the two channels, each channel comprises the time-frequency characteristic of one frequency band, the combined image size is (198, 138,2), and 2 is the number of channels.
The double-frequency time-frequency characteristic is built based on the underwater acoustic echo bright spot model. A large number of theoretical analysis and experimental researches prove that the echo of any complex target is formed by superposition of a plurality of sub-waves, and each sub-wave can be regarded as a wave emitted from a certain scattering point, and the scattering point is a bright point. The target echo is generated by the target under the excitation of the incident sound wave, carries the characteristic information of the target and can be equivalent to the superposition of a series of scattering bright spots.
The echo is related to both the natural vibration characteristics of the target and the incident acoustic wave characteristics. Single-frequency wave with frequency omega alongThe direction of propagation onto the target, the transfer function of a single bright point can be generalized to:
wherein, the liquid crystal display device comprises a liquid crystal display device,is an amplitude reflection factor, usually a function of frequency, and can take a central frequency value for a narrowband signal; τ is the time delay, determined by the sound Cheng of the equivalent scattering center relative to a certain reference point, τ=2ζ/C, C is the speed of sound; />The phase jump during echo formation is determined by the nature of the bright spot, i.e. the shape of the target and the angle of incidence of the sound wave.
According to the linear superposition principle, the target can be regarded as a superposition of multiple bright spots, N represents the total number of target bright spots, and the total transfer function can be expressed as:
the object model being composed of a plurality of different orientationsThree parameters.
The single bright point echo signal can be expressed as:
wherein P is i (omega) is the detection signal, i.e. the input signal, P S (ω) is the echo signal,for far field correction, k is the wave number, j is the imaginary unit, and r is the propagation distance.
Because a large volume difference generally exists between the target body and the acoustic decoy, the characteristic difference contained in the underwater acoustic echo signals of different frequency bands is mainly reflected in far field correction and amplitude factors according to the parameter setting of the bright spot model. For targets of different structures and materials, the reflected intensities thereof differ for acoustic signals of different frequencies. In the invention, the amplitude factor and the amplitude reflection factor are the same meaning, and all represent correction coefficients for the amplitude, and reflection refers to the influence of the coefficients on echo generated by reflection. Wherein the amplitude factorFor some angular and edge bright spots and elastic bright spots, the signal frequency is dependent. Let the radius of the curved surface of the target body be R, the included angle between the incident signal and the target body be θ, and the amplitude factor can be expressed as:
according to the underwater target identification method, echo signals are analyzed through the underwater acoustic echo bright spot model, echo differences caused by incident signals in different frequency bands are clarified, and underwater targets are identified according to the characteristic differences of the double-frequency echo signals.
The final dual frequency time-frequency signature is a size (198, 138,2) image matrix.
And step 005, labeling samples according to the time-frequency characteristic diagrams of the double-frequency signals obtained in the steps 002-004. And labeling the same label on the underwater acoustic echo data samples of the same target, and labeling different labels on the underwater acoustic echo data samples of different targets to form a training set and a testing set. In the embodiment of the invention, according to 8:2 to divide the training set and the test set.
In step 006, the training set is used as an input of a convolutional neural network, and the convolutional neural network is configured as shown in fig. 3. In order to preserve as much as possible the double-frequency time-frequency characteristic information, the convolution operation must be avoided continuously, so the convolution neural network structure of this example is composed of two convolution layers, two pooling layers and two full connection layers, wherein the pooling method of the pooling layers is the maximum pooling. In addition, in the time-frequency diagram sample, most of information of the underwater target is hidden in the frequency band distribution and the amplitude of the frequency band distribution, and the boundary characteristics of the picture are not particularly critical, so that a padding layer is not added in the model. In order to avoid the overfitting problem caused by the increase of the network layer number, a Dropout method is introduced, and the Dropout coefficient is 0.6. According to the characteristics of the double-frequency echo signals, a linear rectification function (ReLU) is adopted as an activation function, a binary cross entropy function is adopted as an objective function for training, and a trained model is stored. The linear characteristic of the ReLU function when the ReLU function is larger than 0 can well solve the problem of gradient descent, so that the characteristic can be more efficient in the calculation process. The overall nonlinearity of which in turn is able to fit any complex continuous function in the neural network. The cross entropy loss function has the characteristics that the loss is small when the predicted value is close to the label value, the loss is large when the predicted value is far away from the label value, and the model learning is facilitated.
The specific parameters of the model are shown in table 1 below.
TABLE 1 neural network model parameters
And step 007, using the test set as the input of the training model, and verifying the identification performance of the convolutional neural network.
Referring to FIG. 2, a confusion matrix may be used to present a visual result of the performance of the algorithm, with the total number of columns each representing the number of data predicted to be of that class, each row representing the true home class of data, and the total number of data for each row representing the number of data instances for that class. The recognition method of the time-frequency characteristics of the double-frequency signals can be seen through the confusion matrix, and the recognition accuracy rate is close to that of the two types of signals. 482 out of 577 target volume echo signals are accurately identified as target volume echoes, and 95 are identified as simulated echoes of the target volume. 494 of the 577 target volume analog echoes are identified as target volume analog echoes, and 83 are identified as target volume echoes.
From the verification result of the test set, the method has good identification effect. In practical application, the actually collected underwater sound target echo data can be input into a model after feature extraction based on a trained recognition model, and target recognition can be performed.
Experiments prove that compared with the traditional single-frequency signal identification method, the accuracy of the double-frequency echo signal identification method provided by the invention is improved by 8.9%, 84.6% is achieved, the network structure is simple, the parameters are few, a new thought is provided for the underwater sound target identification method in a complex environment, and the method has a wide application prospect.
The invention also provides an underwater target recognition system based on the difference of the double-frequency echo signals, which comprises:
the time-frequency characteristic construction module of the double-frequency signal is used for extracting the time-frequency characteristic of the underwater acoustic echo data, combining the time-frequency characteristics under two frequency bands of the same target, and taking the combined characteristic as the time-frequency characteristic of the double-frequency signal;
the convolutional neural network recognition model training module is used for taking the time-frequency characteristic of each sample as sample data, labeling the same label by the underwater acoustic echo data samples of the same target, labeling different labels by the underwater acoustic echo data samples of different targets to form a training set, and training by taking the training set as the input of the convolutional neural network to obtain a recognition model based on the convolutional neural network;
and the target recognition module is used for taking the underwater acoustic echo data subjected to the feature extraction as the input of a recognition model to realize the classification recognition of the target.
It should be understood that the underwater target recognition system in the embodiment of the present invention may implement all the technical solutions in the above method embodiments, and the functions of each functional module may be implemented according to the methods in the above method embodiments, for example, the dual-frequency signal time-frequency feature building module may be implemented according to the descriptions of steps 001-004 during implementation, the convolutional neural network recognition model training module may be implemented according to the descriptions of steps 005-006, the target recognition module may be implemented according to the descriptions of step 007, and the specific implementation process may refer to the related descriptions in the above method embodiments, which are not repeated herein.
The present invention also provides a computer device comprising: one or more processors; a memory; and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, which when executed by the processors implement the steps of the underwater target identification method based on dual frequency echo signal differences as described above.
The present invention also provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the underwater target identification method based on dual frequency echo signal differences as described above.
The invention provides a method for realizing underwater target recognition based on double-frequency echo signal characteristics, and the method for realizing the technical scheme are numerous, and the method are only the preferred embodiments of the invention. It should be noted that modifications and adaptations to the present invention may occur to one skilled in the art without departing from the principles of the present invention and are intended to be comprehended within the scope of the present invention. The components not explicitly described in this embodiment can be implemented by using the prior art.
Claims (6)
1. An underwater target identification method based on double-frequency echo signal difference is characterized by comprising the following steps:
(1) Extracting time-frequency characteristics of each sample for the acquired underwater sound target echo signal data samples in different frequency bands, wherein the underwater sound target echo signal data samples are acquired by the following method: the standard hydrophone, the transmitting transducer and the target body are arranged to the same depth, the standard hydrophone is arranged between the transmitting transducer and the target body and is equal to the transmitting transducer and the target body in distance, the transmitting transducer is driven by a signal source to transmit a single-frequency pulse signal, the signal frequency comprises two frequency bands, the echo characteristics of the target body under different postures are acquired, the acquired data comprise two types of target body echo and non-target false echo, and each type comprises two frequency bands;
(2) The time-frequency characteristic diagrams of two frequency bands of the same target echo are respectively put into two channels to be combined to form a time-frequency characteristic diagram of a double-frequency echo signal, the difference between the time-frequency characteristics of the double-frequency echo signal comprises far field correction and amplitude factors, and the far field correction is as followsWhere k is the wave number, j is the imaginary unit, and r is the propagation distance of the incident wave; the amplitude factor is expressed as: />Wherein R is the radius of the curved surface of the target body, and theta is the included angle between the incident signal and the target body;
(3) Taking the time-frequency characteristics of each sample as sample data, labeling the same label by the underwater acoustic echo data samples of the same target, and labeling different labels by the underwater acoustic echo data samples of different targets to form a training set;
(4) Training by taking a training set as input of a convolutional neural network to obtain an identification model based on the convolutional neural network, wherein the convolutional neural network consists of two convolutional layers, two pooling layers and two full-connection layers, the pooling method of the pooling layers is maximum pooling, and a Dropout layer is arranged behind the maximum pooling layer;
(5) And carrying out target recognition on the underwater acoustic echo data subjected to the feature extraction by using the trained recognition model.
2. The method of claim 1, wherein the time-frequency characteristics of the samples are extracted using a fast fourier transform.
3. The method of claim 1, wherein training the convolutional neural network employs a linear rectification function ReLU as an activation function and a binary cross entropy function as a target loss function.
4. An underwater target recognition system based on the difference of double-frequency echo signals, which is characterized by comprising:
the time-frequency characteristic construction module of the double-frequency signal is used for extracting the time-frequency characteristic of the underwater sound echo data, combining the time-frequency characteristics of the same target under two frequency bands, and regarding the combined characteristic as the time-frequency characteristic of the double-frequency signal, wherein the underwater sound echo data is obtained by the following method: the standard hydrophone, the transmitting transducer and the target body are arranged to the same depth, the standard hydrophone is arranged between the transmitting transducer and the target body and is equal to the transmitting transducer and the target body in distance, the transmitting transducer is driven by a signal source to transmit a single-frequency pulse signal, the signal frequency comprises two frequency bands, the echo characteristics of the target body under different postures are acquired, the acquired data comprise two types of target body echo and non-target false echo, and each type comprises two frequency bands; the difference between the time-frequency characteristics of the double-frequency echo signals comprises far-field correction and an amplitude factor, wherein the far-field correction is thatWhere k is the wave number, j is the imaginary unit, and r is the propagation distance of the incident wave; the amplitude factor is expressed as: />Wherein R is the radius of the curved surface of the target body, and theta is the included angle between the incident signal and the target body;
the convolutional neural network recognition model training module is used for taking time-frequency characteristics of each sample as sample data, labeling the same label by the underwater acoustic echo data samples of the same target, labeling different labels by the underwater acoustic echo data samples of different targets to form a training set, taking the training set as input of the convolutional neural network for training to obtain a recognition model based on the convolutional neural network, wherein the convolutional neural network consists of two convolutional layers, two pooling layers and two fully-connected layers, the pooling method of the pooling layers is maximum pooling, and a Dropout layer is arranged behind the maximum pooling layer;
and the target recognition module is used for taking the underwater acoustic echo data subjected to the feature extraction as the input of a recognition model to realize the classification recognition of the target.
5. A computer device, comprising:
one or more processors;
a memory; and
one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, which when executed by the processors implement the steps of the dual frequency echo signal difference based underwater target identification method of any of claims 1-3.
6. A computer readable storage medium, on which a computer program is stored, which computer program, when being executed by a processor, implements the steps of the method for underwater target identification based on dual frequency echo signal differences as claimed in any one of claims 1-3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211571572.6A CN115878982B (en) | 2022-12-08 | 2022-12-08 | Underwater target identification method and system based on double-frequency echo signal characteristics |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211571572.6A CN115878982B (en) | 2022-12-08 | 2022-12-08 | Underwater target identification method and system based on double-frequency echo signal characteristics |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115878982A CN115878982A (en) | 2023-03-31 |
| CN115878982B true CN115878982B (en) | 2023-09-22 |
Family
ID=85766542
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211571572.6A Active CN115878982B (en) | 2022-12-08 | 2022-12-08 | Underwater target identification method and system based on double-frequency echo signal characteristics |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115878982B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB201201027D0 (en) * | 2011-01-25 | 2012-03-07 | Subsea Asset Location Tech Ltd | Identification, detection and positioning of underwater accoustic reflectors |
| CN104777474A (en) * | 2015-04-29 | 2015-07-15 | 中国科学院声学研究所 | Echo phase feature extracting method used for underwater target recognition |
| CN107748862A (en) * | 2017-09-21 | 2018-03-02 | 清华大学 | A kind of unmanned plane sorting technique and device based on dual-frequency radar signal time-frequency distributions |
| CN109100710A (en) * | 2018-06-26 | 2018-12-28 | 东南大学 | A kind of Underwater targets recognition based on convolutional neural networks |
| CN112257521A (en) * | 2020-09-30 | 2021-01-22 | 中国人民解放军军事科学院国防科技创新研究院 | CNN underwater acoustic signal target identification method based on data enhancement and time-frequency separation |
| CN112990082A (en) * | 2021-04-06 | 2021-06-18 | 舟山精卫智能科技有限公司 | Detection and identification method of underwater sound pulse signal |
| CN113435276A (en) * | 2021-06-16 | 2021-09-24 | 中国电子科技集团公司第五十四研究所 | Underwater sound target identification method based on antagonistic residual error network |
| CN113452637A (en) * | 2021-09-01 | 2021-09-28 | 中国海洋大学 | Underwater acoustic communication signal modulation identification method based on feature selection and support vector machine |
-
2022
- 2022-12-08 CN CN202211571572.6A patent/CN115878982B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB201201027D0 (en) * | 2011-01-25 | 2012-03-07 | Subsea Asset Location Tech Ltd | Identification, detection and positioning of underwater accoustic reflectors |
| CN104777474A (en) * | 2015-04-29 | 2015-07-15 | 中国科学院声学研究所 | Echo phase feature extracting method used for underwater target recognition |
| CN107748862A (en) * | 2017-09-21 | 2018-03-02 | 清华大学 | A kind of unmanned plane sorting technique and device based on dual-frequency radar signal time-frequency distributions |
| CN109100710A (en) * | 2018-06-26 | 2018-12-28 | 东南大学 | A kind of Underwater targets recognition based on convolutional neural networks |
| CN112257521A (en) * | 2020-09-30 | 2021-01-22 | 中国人民解放军军事科学院国防科技创新研究院 | CNN underwater acoustic signal target identification method based on data enhancement and time-frequency separation |
| CN112990082A (en) * | 2021-04-06 | 2021-06-18 | 舟山精卫智能科技有限公司 | Detection and identification method of underwater sound pulse signal |
| CN113435276A (en) * | 2021-06-16 | 2021-09-24 | 中国电子科技集团公司第五十四研究所 | Underwater sound target identification method based on antagonistic residual error network |
| CN113452637A (en) * | 2021-09-01 | 2021-09-28 | 中国海洋大学 | Underwater acoustic communication signal modulation identification method based on feature selection and support vector machine |
Non-Patent Citations (2)
| Title |
|---|
| Intelligent Recognition of Underwater Acoustic Target Noise on Underwater Glider Platform;Zhang Shao-Kang等;《2018 Chinese Automation Congress (CAC)》;第4189-4193页 * |
| 水下目标主动声呐回波信号特征研究;夏峙;《中国博士学位论文全文数据库工程科技Ⅱ辑》(第11期);第C028-9页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115878982A (en) | 2023-03-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107220606B (en) | Radar radiation source signal identification method based on one-dimensional convolutional neural network | |
| Sen et al. | Data-driven semi-supervised and supervised learning algorithms for health monitoring of pipes | |
| Thode et al. | Automated detection and localization of bowhead whale sounds in the presence of seismic airgun surveys | |
| CN107272005B (en) | Active positioning method based on target echo arrival time delay and arrival angle under reliable acoustic path | |
| CN104483049A (en) | Fiber bragg grating sensing dynamic load identification method based on AR model and mahalanobis distance | |
| CN111665489B (en) | Line spectrum extraction method based on target characteristics | |
| CN106772331A (en) | Target identification method and Target Identification Unit | |
| CN113673312B (en) | Deep learning-based radar signal intra-pulse modulation identification method | |
| CN106526563B (en) | A kind of penton product battle array multi-target DOA estimation method based on cross-correlation virtual array | |
| Kubicek et al. | Sonar target representation using two-dimensional Gabor wavelet features | |
| CN109100711A (en) | Active sonar low operand 3-D positioning method in single base under a kind of deep-marine-environment | |
| CN108919241A (en) | A kind of underwater signal time-frequency endpoint parameter estimation method based on CFAR detection | |
| CN111950438A (en) | Depth learning-based effective wave height inversion method for Tiangong No. two imaging altimeter | |
| CN113126099A (en) | Single-beam substrate classification method based on audio feature extraction | |
| CN115878982B (en) | Underwater target identification method and system based on double-frequency echo signal characteristics | |
| CN113253248B (en) | Small sample vertical array target distance estimation method based on transfer learning | |
| CN113109794A (en) | Deep sea sound source depth setting method based on deep neural network in strong noise environment | |
| Zeng et al. | Underwater sound classification based on Gammatone filter bank and Hilbert-Huang transform | |
| Klay et al. | Advanced methods for passive acoustic detection, classification, and localization of marine mammals | |
| CN115236620A (en) | Intermittent sampling type interference identification and anti-interference target detection method based on DCNN | |
| LeBien et al. | Species-level classification of beaked whale echolocation signals detected in the northern Gulf of Mexico | |
| CN113109760B (en) | Multi-line spectrum combined DOA estimation and clustering method and system based on group sparsity | |
| CN113109795B (en) | Deep sea direct sound zone target depth estimation method based on deep neural network | |
| CN114818113A (en) | Underwater target detection and identification simulation system and method | |
| Ashok et al. | Absorption of echo signal for underwater acoustic signal target system using hybrid of ensemble empirical mode with machine learning techniques |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |