Unmanned ship multi-beam sonar detection method, system, device, product and medium

Abstract

The present application relates to the field of sonar signal processing, and provides an unmanned vehicle multi-beam sonar detection method, system, equipment, product and medium, comprising obtaining a side-scan sonar and a multi-beam sonar, scanning the seabed topography using the side-scan sonar and the multi-beam sonar, obtaining a multi-beam scanning signal and a side-scan signal; performing Kalman filtering to obtain a first filtered signal, filtering the first filtered signal through an adaptive filtering threshold to obtain a second filtered signal; constructing a minimum energy function, obtaining an optimized filtered signal through the minimum energy function and iterating the optimized filtered signal to obtain a first topography signal; constructing a generative adversarial network using a generator and a discriminator, reconstructing the topography of the first topography signal through the generative adversarial network to obtain a second topography signal; correcting the second topography signal through a sound velocity measuring device to obtain a target topography signal, and constructing an underwater topography scanning map according to the target topography signal.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of sonar signal processing, and in particular to an unmanned vehicle multi-beam sonar detection method, system, device, product and medium. BACKGROUND

[0002] An unmanned surface vehicle is a kind of unmanned ship with the characteristics of autonomous navigation and autonomous control. It has wide application value in the fields of ocean exploration, ocean environment monitoring and marine rescue. Multi-beam sonar is a kind of high-precision underwater detection equipment that can provide underwater target position, seabed topography and ocean depth information. Loading multi-beam sonar on unmanned surface vehicle can realize the measurement and mapping of seabed topography. It provides support for the safe navigation of surface ships and submarines, and also helps to detect seabed resources. These ocean measurement unmanned vehicles can be widely used in ocean observation and research, and provide important data support for the development of ocean science and related fields.

[0003] How to reconstruct seabed topography information from existing multi-beam sonar data is the key and difficulty. However, due to the complex and changeable motion state of the unmanned surface vehicle and the underwater environment, the detection data of the multi-beam sonar has noise, error and deviation, which needs to be filtered, optimized and fused. In addition, the density of seawater at different depths is different, which leads to different sound speeds in seawater, which will also have a certain impact on the detection results of the sonar. SUMMARY

[0004] The present application aims to at least solve one of the technical problems in the related art. To this end, the present application provides an unmanned vehicle multi-beam sonar detection method, system, device, product and medium, which realizes the construction of high-precision underwater topographic scanning map.

[0005] The present application provides an unmanned vehicle multi-beam sonar detection method, comprising:

[0006] S1: acquiring a side-scan sonar and a multi-beam sonar, using the side-scan sonar and the multi-beam sonar to scan the seabed topography, and obtaining multi-beam scanning signals and side-scan signals;

[0007] S2: Kalman filtering the multi-beam scanning signals and the side-scan signals to obtain a first filtered signal, calculating an adaptive filtering threshold, filtering the first filtered signal through the adaptive filtering threshold to obtain a second filtered signal;

[0008] S3: calculating an edge weight using the second filtered signal, constructing a minimum energy function through the edge weight and the second filtered signal, obtaining an optimized filtered signal through the minimum energy function, and iterating the optimized filtered signal to obtain a first topographic signal;

[0009] S4: acquire the generator and the discriminator, construct a generative adversarial network using the generator and the discriminator, perform terrain reconstruction on the first terrain signal through the generative adversarial network, and obtain a second terrain signal;

[0010] S5: acquire a sound velocity measuring device, correct the second terrain signal through the sound velocity measuring device to obtain a target terrain signal, and construct an underwater terrain scanning map according to the target terrain signal.

[0011] According to the unmanned ship multi-beam sonar detection method provided by the application, in step S1, a side scan sonar and a multi-beam sonar are acquired, the side scan sonar is placed in water through a drag bracket, a multi-beam signal is obtained by scanning using the multi-beam sonar, and a side scan signal is obtained by scanning using the side scan sonar.

[0012] According to the unmanned ship multi-beam sonar detection method provided by the application, in step S2, after the first filtered signal is obtained, an adaptive coefficient is determined, a local scan signal is obtained from the first filtered signal, a local standard variance of the local scan signal is calculated, and the adaptive filtering threshold is calculated according to the local standard variance and the adaptive coefficient.

[0013] According to the unmanned ship multi-beam sonar detection method provided by the application, step S3 further comprises:

[0014] S31: determine a scale parameter, and calculate an edge weight using the scale parameter and the second filtered signal;

[0015] S32: determine a regularization parameter, and construct the minimum energy function through the regularization parameter, the second filtered signal and the edge weight;

[0016] S33: determine an iteration stop condition, select an optimization algorithm, substitute the minimum energy function into the optimization algorithm, thereby obtaining the optimized filtered signal and iterating the optimized filtered signal until the iteration stop condition is met, and take the iterated optimized filtered signal as the first terrain signal.

[0017] According to the unmanned ship multi-beam sonar detection method provided by the application, in step S4, the noise distribution of the first terrain signal is determined, the first terrain signal distribution is determined according to the first terrain signal, the generative adversarial network is constructed using the noise distribution, the first terrain signal distribution, the generator and the discriminator, the generator and the discriminator are updated, the first terrain signal is reconstructed through the updated generator, and the second terrain signal is obtained.

[0018] According to the unmanned ship multi-beam sonar detection method provided by the application, step S5 further comprises:

[0019] S51: Obtain a sound velocity measuring device including a sound velocity profiler and a surface sound velocity instrument, and install the sound velocity profiler at a mounting position of the multi-beam sonar and lower the surface sound velocity instrument into water;

[0020] S52: Obtain a first correction parameter by the sound velocity profiler, obtain a second correction parameter by the surface sound velocity instrument, correct the second terrain signal according to the first correction parameter and the second correction parameter to obtain a target terrain signal, and construct an underwater terrain scanning map according to the target terrain signal.

[0021] The application further provides an unmanned ship multi-beam sonar detection system, comprising:

[0022] The sonar scanning module is used to obtain a side scan sonar and a multi-beam sonar, scan the seabed terrain by using the side scan sonar and the multi-beam sonar, and obtain a multi-beam scanning signal and a side scanning signal.

[0023] The second filtering signal module is used to perform Kalman filtering on the multi-beam scanning signal and the side scanning signal to obtain a first filtering signal, calculate an adaptive filtering threshold, and perform filtering on the first filtering signal by using the adaptive filtering threshold to obtain a second filtering signal.

[0024] The first terrain signal module is used to calculate an edge weight by using the second filtering signal, construct a minimum energy function by using the edge weight and the second filtering signal, obtain an optimized filtering signal by using the minimum energy function, and perform iteration on the optimized filtering signal to obtain a first terrain signal.

[0025] The second terrain signal module is used to obtain a generator and a discriminator, construct a generative adversarial network by using the generator and the discriminator, and perform terrain reconstruction on the first terrain signal by using the generative adversarial network to obtain a second terrain signal.

[0026] The underwater terrain scanning map module is used to obtain a sound velocity measuring device, correct the second terrain signal by using the sound velocity measuring device to obtain a target terrain signal, and construct an underwater terrain scanning map according to the target terrain signal.

[0027] The application further provides an electronic device, which comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the unmanned ship multi-beam sonar detection method according to any one of the above embodiments when executing the computer program.

[0028] The application further provides a non-transitory computer readable storage medium, which stores a computer program, and the computer program implements the steps of the unmanned ship multi-beam sonar detection method according to any one of the above embodiments when executed by a processor.

[0029] The application further provides a computer program product, which comprises a computer program stored on a non-transitory computer-readable storage medium, and the computer program comprises program instructions, when the program instructions are executed by a computer, the computer can execute the steps of the unmanned ship multi-beam sonar detection method according to any one of the above.

[0030] The one or more technical solutions described above in the embodiments of the application have at least one of the following technical effects.

[0031] The unmanned ship multi-beam sonar detection method, system, device, product and medium provided by the application have good adaptability and robustness, can realize high-precision and high-reliability depth data measurement, and can improve the precision and efficiency of seabed topography measurement of the ocean measurement unmanned ship carrying the multi-beam sonar.

[0032] Additional aspects and advantages of the application will be described in the following description, will become apparent from the following description, or will be learned by practice of the application. BRIEF DESCRIPTION OF DRAWINGS

[0033] In order to more clearly illustrate the technical solutions in the application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description are some embodiments of the application, and those skilled in the art can also obtain other drawings according to these drawings without creative labor.

[0034] Figure 1 is a flowchart of the unmanned ship multi-beam sonar detection method provided by the application.

[0035] Figure 2 is an underwater topography scanning diagram of the unmanned ship multi-beam sonar detection method provided by the application.

[0036] Figure 3 is a structural schematic diagram of the unmanned ship multi-beam sonar detection system provided by the application.

[0037] Figure 4 is a structural schematic diagram of the unmanned ship multi-beam sonar detection device provided by the application.

[0038] Reference signs:

[0039] 100, sonar scanning module; 200, second filtered signal module; 300, first terrain signal module; 400, second terrain signal module; 500, underwater terrain scanning map module; 810, processor; 820, communication interface; 830, memory; 840, communication bus. DETAILED DESCRIPTION

[0040] In order to make the objects, technical solutions and advantages of the present application clearer, the technical solutions in the present application will be clearly and completely described below. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all the other embodiments obtained by those skilled in the art without creative work fall within the protection scope of the present application. The following embodiments are used to illustrate the present application, but cannot be used to limit the scope of the present application.

[0041] In the description of the embodiments of the present application, it should be noted that the terms "center", "longitudinal", "transverse", "upper", "lower", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer" and the like indicate the orientation or positional relationship shown in the drawings, and are only used to facilitate the description of the embodiments of the present application and simplify the description, and do not indicate or imply that the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the embodiments of the present application. In addition, the terms "first", "second", "third" are only used for description purposes, and cannot be understood as indicating or implying relative importance.

[0042] In the description of the embodiments of the present application, it should be noted that unless otherwise explicitly specified and limited, the terms "connected", "connected" should be understood in a broad sense, for example, it can be fixedly connected, or it can be detachably connected, or integrally connected; it can be mechanically connected, or it can be electrically connected; it can be directly connected, or it can be indirectly connected through an intermediate medium. For those skilled in the art, the specific meaning of the above terms in the embodiments of the present application can be understood according to the specific circumstances.

[0043] In the description of the present specification, the description of the terms "one embodiment", "some embodiments", "an example", "a specific example", or "some examples" and the like means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the present specification, the illustrative description of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any appropriate manner in any one or more embodiments or examples. In addition, the person skilled in the art can combine and combine the different embodiments or examples described in the present specification and the features of the different embodiments or examples without contradiction.

[0044] The following will be described in combination with Figures 1 to 4 a specific embodiment of the present application is described, Figure 1 is the flowchart of the unmanned surface vehicle multi-beam sonar detection method provided by the present application, comprising:

[0045] S1: obtaining a side-scan sonar and a multi-beam sonar, using the side-scan sonar and the multi-beam sonar to scan the seafloor topography to obtain a multi-beam scanning signal and a side scanning signal;

[0046] Further, the purpose of this stage is to use the side-scan sonar and the multi-beam sonar to scan the seafloor topography to obtain a multi-beam scanning signal and a side scanning signal. Specifically, in step S1, the side-scan sonar and the multi-beam sonar are obtained, the side-scan sonar is placed in the water through the towing bracket, the multi-beam sonar is used for scanning to obtain a multi-beam signal, and the side-scan sonar is used for scanning to obtain a side scanning signal.

[0047] For the above steps, the specific embodiments in the present embodiment are as follows:

[0048] First, the side-scan sonar and the multi-beam sonar are obtained, and a moon pool and a flange structure are arranged at the front of the unmanned surface vehicle, so that the multi-beam sonar is installed in the flange structure, which can reduce the influence of the cavitation generated during the navigation of the unmanned surface vehicle on the multi-beam sonar. In addition, the side of the unmanned surface vehicle is also provided with a towing bracket and a matching winch, the side-scan sonar is connected with the cable of the winch and the cable is arranged on the towing bracket, so that the side-scan sonar can be controlled by the winch to be put into the water. Then, the multi-beam sonar is used to scan the seafloor topography, and a multi-beam scanning signal can be obtained. The side-scan sonar is used to scan the same piece of seafloor topography, and a side scanning signal can be obtained.

[0049] S2: Kalman filtering is performed on the multi-beam scanning signal and the side scanning signal to obtain a first filtered signal, an adaptive filtering threshold is calculated, and the first filtered signal is filtered through the adaptive filtering threshold to obtain a second filtered signal;

[0050] Furthermore, the objective of this stage is to perform dual filtering on the multi-beam scanning signal and the side-scanning signal to obtain a second filtered signal. Specifically, in step S2, after obtaining the first filtered signal, adaptive coefficients are determined, a local scanning signal is obtained from the first filtered signal, the local standard deviation of the local scanning signal is calculated, and the adaptive filtering threshold is calculated based on the local standard deviation and the adaptive coefficients.

[0051] The specific implementation method for the above steps in this embodiment is as follows:

[0052] First, Kalman filtering is required on both the multibeam scanning signal and the side-scan signal to perform the first layer of filtering in a dual-filtering process. After Kalman filtering, the first filtered signal is obtained. Next, a second filtering process is needed on the first filtered signal. Here, the adaptive coefficient α needs to be determined first. The adaptive coefficient is determined based on experience and the hydrological environment of the sea area. If the hydrological environment is highly polluted or the water depth is deep, the adaptive coefficient can be appropriately increased to enhance the filtering strength; otherwise, the adaptive coefficient can be appropriately decreased.

[0053] Subsequently, the local scan signal is obtained from the first filtered signal. The local scan signal is obtained by determining a reasonable sampling radius based on the complexity of the seabed topography. Then, using the sampling radius as the radius, one of the scanning points from the multibeam scanning signal and the side scanning signal is selected as the center of a sphere, thus obtaining a sphere. All scanning points within the sphere are taken as the local scan signal in the k-th scanning region. The local standard deviation of the k-th scanning region is obtained by calculating its standard deviation. Then, the adaptive filtering threshold for the k-th scan region can be calculated based on the local standard deviation and adaptive coefficients. :

[0054]

[0055] The first filtered signal is then filtered using an adaptive filtering threshold. Specifically, the absolute value of the difference between a scanned point in the scanning area and the mean value of all scanned points in the scanning area is calculated, and this value is compared with the adaptive filtering threshold. If the difference is greater than the threshold, the scanned point is considered abnormal and should be replaced with the mean value of all scanned points in the scanning area; otherwise, the scanned point is considered acceptable. This completes the filtering process. Applying this method to all scanned areas in the seabed topography yields the second filtered signal.

[0056] S3: calculating edge weights using the second filtered signal, constructing a minimization energy function by the edge weights and the second filtered signal, obtaining an optimized filtered signal by minimizing the energy function, and iterating the optimized filtered signal to obtain the first terrain signal;

[0057] Further, the purpose of this stage is to construct a minimization energy function by the edge weights and the second filtered signal, so as to obtain an optimized filtered signal and iterate, and finally obtain the first terrain signal. Specifically, step S3 further comprises:

[0058] S31: determining a scale parameter, and calculating edge weights using the scale parameter and the second filtered signal;

[0059] S32: determining a regularization parameter, and constructing the minimization energy function by the regularization parameter, the second filtered signal and the edge weights;

[0060] S33: determining an iteration stopping condition, selecting an optimization algorithm, substituting the minimization energy function into the optimization algorithm, so as to obtain the optimized filtered signal and iterate the optimized filtered signal until the iteration stopping condition is met, and taking the iterated optimized filtered signal as the first terrain signal.

[0061] For the above steps, the specific implementation in this embodiment is as follows:

[0062] First, the scale parameter for calculating the edge weights needs to be determined according to experience , then the second filtered signal data of the i th scanning point from the multi-beam scanning signal in the second filtered signal and the second filtered signal data of the j th scanning point from the side scanning signal in the second filtered signal are extracted from the second filtered signal, so that the edge weight between them can be calculated :

[0063]

[0064] wherein exp() represents an exponential operation on the content in the parentheses, represents the calculation of the Euclidean distance between the parameters inside. The edge weights between all scanning points from the multi-beam scanning signal and scanning points from the side scanning signal in the second filtered signal are calculated.

[0065] Then the regularization parameter is determined , and then the minimization energy function constructed by the regularization parameter, the second filtered signal and the edge weights is constructed :

[0066]

[0067] wherein X is a set of optimized filtered signals, is the i-th optimized filtered signal, i.e. the optimized filtered signal from the i-th scan point in the multi-beam scan signal in the last iteration, and if the optimized filtered signal has not been iterated before, it takes the value of the second filtered signal data from the i-th scan point in the multi-beam scan signal, is the j-th optimized filtered signal, i.e. the optimized filtered signal from the j-th scan point in the side scan signal in the last iteration, and if the optimized filtered signal has not been iterated before, it takes the value of the second filtered signal data from the j-th scan point in the side scan signal.

[0068] Subsequently, the minimized energy function is substituted into an optimization algorithm such as simulated annealing algorithm, particle swarm optimization, etc., so that the value of the minimized energy function is as small as possible, i.e. a new optimized filtered signal is obtained. The new optimized filtered signal is input into the minimized energy function to obtain a new minimized energy function for circulation, so as to realize iteration of the optimized filtered signal. Then, an iteration stopping condition is determined, for example, when a predetermined number of iterations is reached, at this time the value of the minimized energy function is small enough, i.e. the iteration can be stopped, and the optimized filtered signal after iteration is taken as the first terrain signal.

[0069] S4: obtaining a generator and a discriminator, constructing a generative adversarial network using the generator and the discriminator, and performing terrain reconstruction on the first terrain signal through the generative adversarial network to obtain a second terrain signal;

[0070] Further, the purpose of this stage is to construct a generative adversarial network using the generator and the discriminator, so as to perform terrain reconstruction on the first terrain signal to obtain a second terrain signal. Specifically, in step S4, the noise distribution of the first terrain signal is determined, the first terrain signal distribution is determined according to the first terrain signal, the generative adversarial network is constructed using the noise distribution, the first terrain signal distribution, the generator and the discriminator, and the generator and the discriminator are updated, the first terrain signal is terrain reconstructed through the updated generator to obtain the second terrain signal.

[0071] For the above steps, the specific implementation in this embodiment is as follows:

[0072] First, the noise distribution of the first terrain signal is determined according to experience , i.e. the mathematical expectation function of the noise of the first terrain signal, the first terrain signal distribution is determined according to the first terrain signal , i.e. the mathematical expectation function of the first terrain signal, the generator G and the discriminator D are obtained, and the generative adversarial network is constructed using the noise distribution, the first terrain signal distribution, the generator and the discriminator:

[0073]

[0074] wherein, is a value function of a min-max game target of the discriminator and the generator, is a discriminator network function, G() is a generator network function, represents that the probability value of the generator output is minimized, represents that the probability value of the discriminator output is maximized, z is noise of the first terrain signal, is a first terrain signal, through the min-max game of the generative adversarial network, the generator and the discriminator in the generative adversarial network are trained, so that the trained generator can perform terrain reconstruction on the first terrain signal according to the first terrain signal distribution, and generate a second terrain signal close to the real situation and excluding noise interference.

[0075] S5: obtaining a sound velocity measuring device, correcting the second terrain signal through the sound velocity measuring device to obtain a target terrain signal, and constructing an underwater terrain scanning map according to the target terrain signal.

[0076] Further, the purpose of this stage is to correct the second terrain signal through the sound velocity measuring device, so as to construct the underwater terrain scanning map. Specifically, step S5 further comprises:

[0077] S51: obtaining a sound velocity measuring device comprising a sound velocity profiler and a surface sound velocity instrument, and installing the sound velocity profiler at the installation position of the multi-beam sonar, and lowering the surface sound velocity instrument into the water;

[0078] S52: obtaining a first correction parameter through the sound velocity profiler, obtaining a second correction parameter through the surface sound velocity instrument, correcting the second terrain signal according to the first correction parameter and the second correction parameter to obtain a target terrain signal, and constructing an underwater terrain scanning map according to the target terrain signal.

[0079] For the above steps, the specific implementation in this embodiment is as follows:

[0080] Firstly, a sound velocity measuring device comprising a sound velocity profiler and a surface sound velocity instrument needs to be obtained, and the sound velocity profiler needs to be installed at the installation position of the multi-beam sonar, that is, inside the flange structure. The surface sound velocity instrument needs to be lowered into the water below the water surface unmanned boat through the moon pool on the water surface unmanned boat, and the surface sound velocity instrument is connected with the winch, so that it can be retracted and extended through the winch to measure the sound velocity of the water at different depths.

[0081] Then, the sound speed profiler can measure the sound speed at the installation position of the multi-beam sonar, so as to obtain a first correction parameter according to the sound speed at the installation position of the multi-beam sonar. Similarly, the surface sound speed profiler can measure the sound speed at different depths of the water, so as to obtain a second correction parameter according to the sound speed at different depths of the water. The first correction parameter and the second correction parameter can correct the second terrain signal to correct the influence of the change of the sound speed on the second terrain signal, so that a target terrain signal can be obtained, and finally an underwater terrain scanning map can be constructed according to the target terrain signal, as shown in Figure 2 .

[0082] The present application can effectively realize high-precision and high-reliability depth data measurement, eliminate the influence of sound speed, and generate a high-precision underwater terrain scanning map.

[0083] The unmanned ship multi-beam sonar detection device provided by the present application is described below, and the unmanned ship multi-beam sonar detection device described below can be correspondingly referred to the unmanned ship multi-beam sonar detection method described above.

[0084] Figure 3 The structure diagram of the unmanned ship multi-beam sonar detection system is shown in Figure 3 , which is used to execute the unmanned ship multi-beam sonar detection method as described above, and includes:

[0085] The sonar scanning module 100 is used to acquire the side scan sonar and the multi-beam sonar, scan the seabed terrain using the side scan sonar and the multi-beam sonar, and obtain the multi-beam scanning signal and the side scanning signal.

[0086] The second filtering signal module 200 is used to perform Kalman filtering on the multi-beam scanning signal and the side scanning signal to obtain a first filtering signal, calculate an adaptive filtering threshold, and filter the first filtering signal through the adaptive filtering threshold to obtain a second filtering signal.

[0087] The first terrain signal module 300 is used to calculate an edge weight using the second filtering signal, construct a minimum energy function through the edge weight and the second filtering signal, obtain an optimized filtering signal through the minimum energy function, and iterate the optimized filtering signal to obtain a first terrain signal.

[0088] The second terrain signal module 400 is used to acquire a generator and a discriminator, construct a generative adversarial network using the generator and the discriminator, perform terrain reconstruction on the first terrain signal through the generative adversarial network, and obtain a second terrain signal.

[0089] The underwater terrain scanning map module 500 is used to acquire a sound speed measuring device, correct the second terrain signal through the sound speed measuring device to obtain a target terrain signal, and construct an underwater terrain scanning map according to the target terrain signal.

[0090] Figure 4 An example of a schematic diagram of the physical structure of an electronic device is shown in Figure 4 The electronic device can include a processor 810, a communications interface 820, a memory 830, and a communications bus 840, wherein the processor 810, the communications interface 820, and the memory 830 communicate with each other through the communications bus 840. The processor 810 can invoke a computer program in the memory 830 to execute an unmanned surface vehicle multi-beam sonar detection method, which includes:

[0091] S1: Obtain a side-scan sonar and a multi-beam sonar, use the side-scan sonar and the multi-beam sonar to scan the seafloor topography, and obtain a multi-beam scanning signal and a side-scan signal;

[0092] S2: Perform Kalman filtering on the multi-beam scanning signal and the side-scan signal to obtain a first filtered signal, calculate an adaptive filtering threshold, filter the first filtered signal through the adaptive filtering threshold, and obtain a second filtered signal;

[0093] S3: Calculate an edge weight using the second filtered signal, construct a minimum energy function through the edge weight and the second filtered signal, obtain an optimized filtered signal through the minimum energy function, and iterate the optimized filtered signal to obtain a first topographic signal;

[0094] S4: Obtain a generator and a discriminator, construct a generative adversarial network using the generator and the discriminator, perform topographic reconstruction on the first topographic signal through the generative adversarial network, and obtain a second topographic signal;

[0095] S5: Obtain a sound velocity measuring device, correct the second topographic signal through the sound velocity measuring device to obtain a target topographic signal, and construct an underwater topographic scan map according to the target topographic signal.

[0096] Further, the computer program in the above-mentioned memory 830 can be realized in the form of a software functional unit and sold or used as an independent product, which can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or partially contribute to the prior art, or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, including a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0097] In another aspect, the present application also provides a computer program product, which comprises a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions which, when executed by a computer, enable the computer to perform the unmanned surface vehicle multi-beam sonar detection method provided by the above-mentioned methods, the method comprising:

[0098] S1: obtaining a side scan sonar and a multi-beam sonar, using the side scan sonar and the multi-beam sonar to scan the seafloor topography, obtaining a multi-beam scanning signal and a side scanning signal;

[0099] S2: Kalman filtering the multi-beam scanning signal and the side scanning signal to obtain a first filtered signal, calculating an adaptive filtering threshold, filtering the first filtered signal through the adaptive filtering threshold to obtain a second filtered signal;

[0100] S3: calculating an edge weight using the second filtered signal, constructing a minimum energy function through the edge weight and the second filtered signal, obtaining an optimized filtered signal through the minimum energy function, and iterating the optimized filtered signal to obtain a first topographic signal;

[0101] S4: obtaining a generator and a discriminator, constructing a generative adversarial network using the generator and the discriminator, and reconstructing the topography of the first topographic signal through the generative adversarial network to obtain a second topographic signal;

[0102] S5: obtaining a sound velocity measuring device, correcting the second topographic signal through the sound velocity measuring device to obtain a target topographic signal, and constructing an underwater topographic scanning map according to the target topographic signal.

[0103] In yet another aspect, the present application also provides a non-transitory computer-readable storage medium having stored thereon a computer program, which, when executed by a processor, implements the unmanned surface vehicle multi-beam sonar detection method provided above, and the method comprises:

[0104] S1: Obtain a side scan sonar and a multi-beam sonar, use the side scan sonar and the multi-beam sonar to scan a seabed terrain, and obtain a multi-beam scanning signal and a side scanning signal;

[0105] S2: Perform Kalman filtering on the multi-beam scanning signal and the side scanning signal to obtain a first filtered signal, calculate an adaptive filtering threshold, filter the first filtered signal through the adaptive filtering threshold to obtain a second filtered signal;

[0106] S3: Calculate an edge weight using the second filtered signal, construct a minimum energy function through the edge weight and the second filtered signal, obtain an optimized filtered signal through the minimum energy function, and iterate the optimized filtered signal to obtain a first terrain signal;

[0107] S4: Obtain a generator and a discriminator, construct a generative adversarial network using the generator and the discriminator, perform terrain reconstruction on the first terrain signal through the generative adversarial network to obtain a second terrain signal;

[0108] S5: Obtain a sound velocity measuring device, correct the second terrain signal through the sound velocity measuring device to obtain a target terrain signal, and construct an underwater terrain scanning map according to the target terrain signal.

[0109] The device embodiments described above are only schematic, wherein the units shown as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, i.e., can be located in one place, or can be distributed on multiple network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the present embodiment scheme. Those skilled in the art can understand and implement without creative labor.

[0110] From the above description of the embodiments, those skilled in the art can clearly understand that the embodiments can be realized by means of software plus necessary general hardware platforms, and of course can also be realized by hardware. Based on such understanding, the above technical solutions, essentially or in other words, the part that contributes to the prior art, can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, etc., and includes a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods described in each embodiment or some parts of the embodiments.

[0111] It should be pointed out finally that the above embodiments are only used to illustrate the technical solutions of the present application, but not to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that the technical solutions recorded in the foregoing embodiments can still be modified, or some technical features therein can be replaced equivalently; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A multi-beam sonar detection method for unmanned surface vessels, characterized in that, include: S1: Acquire side-scan sonar and multibeam sonar, use side-scan sonar and multibeam sonar to scan the seabed topography, and obtain multibeam scanning signal and side-scan signal; S2: Perform Kalman filtering on the multi-beam scanning signal and the side-scanning signal to obtain the first filtered signal. Calculate the adaptive filtering threshold and filter the first filtered signal using the adaptive filtering threshold to obtain the second filtered signal. S3: Calculate the edge weights using the second filtered signal, construct a minimized energy function using the edge weights and the second filtered signal, obtain the optimized filtered signal by minimizing the energy function, and iterate the optimized filtered signal to obtain the first terrain signal; S4: Obtain the generator and discriminator, use the generator and discriminator to construct a generative adversarial network, and use the generative adversarial network to reconstruct the terrain from the first terrain signal to obtain the second terrain signal; S5: Acquire sound velocity measurement equipment, correct the second terrain signal using sound velocity measurement equipment to obtain the target terrain signal, and construct an underwater terrain scanning map based on the target terrain signal.

2. The unmanned surface vessel multibeam sonar detection method according to claim 1, characterized in that, In step S1, the side-scan sonar and multi-beam sonar are acquired. The side-scan sonar is placed in the water by a towing bracket. The multi-beam sonar is used to scan and obtain the multi-beam signal. The side-scan sonar is used to scan and obtain the side-scan signal.

3. The unmanned surface vessel multibeam sonar detection method according to claim 1, characterized in that, In step S2, after obtaining the first filtered signal, the adaptive coefficient is determined, the local scan signal is obtained from the first filtered signal, the local standard deviation of the local scan signal is calculated, and the adaptive filtering threshold is calculated based on the local standard deviation and the adaptive coefficient.

4. The unmanned surface vessel multibeam sonar detection method according to claim 1, characterized in that, Step S3 further includes: S31: Determine the scale parameters, and use the scale parameters and the second filtered signal to calculate the edge weights; S32: Determine the regularization parameter, and construct the minimum energy function using the regularization parameter, the second filtered signal, and the edge weights; S33: Determine the iteration stopping condition, select an optimization algorithm, substitute the minimized energy function into the optimization algorithm to obtain the optimized filtered signal, and iterate the optimized filtered signal until the iteration stopping condition is met, and use the iterated optimized filtered signal as the first terrain signal.

5. The multi-beam sonar detection method for unmanned surface vessels according to claim 1, characterized in that, In step S4, the noise distribution of the first terrain signal is determined, the first terrain signal distribution is determined based on the first terrain signal, a generative adversarial network is constructed using the noise distribution, the first terrain signal distribution, the generator, and the discriminator, and the generator and the discriminator are updated. The updated generator is used to reconstruct the terrain of the first terrain signal to obtain the second terrain signal.

6. The unmanned surface vessel multibeam sonar detection method according to claim 1, characterized in that, Step S5 further includes: S51: Obtain a sound velocity measuring device including a sound velocity profiler and a surface sound velocity meter, install the sound velocity profiler at the mounting location of the multibeam sonar, and suspend the surface sound velocity meter in the water; S52: Obtain a first correction parameter through the sound velocity profiler, obtain a second correction parameter through the surface sound velocity meter, correct the second terrain signal according to the first correction parameter and the second correction parameter to obtain the target terrain signal, and construct an underwater terrain scanning map according to the target terrain signal.

7. An unmanned surface vessel (USV) multibeam sonar detection system, used to perform the USV multibeam sonar detection method as described in any one of claims 1 to 6, characterized in that, include: Sonar scanning module: used to acquire side-scan sonar and multibeam sonar, and use side-scan sonar and multibeam sonar to scan the seabed topography to obtain multibeam scanning signals and side-scan signals; The second filtering signal module is used to perform Kalman filtering on the multi-beam scanning signal and the side-scanning signal to obtain the first filtered signal, calculate the adaptive filtering threshold, and filter the first filtered signal through the adaptive filtering threshold to obtain the second filtered signal. First terrain signal module: used to calculate edge weights using the second filtered signal, construct a minimized energy function using the edge weights and the second filtered signal, obtain an optimized filtered signal by minimizing the energy function, and iterate the optimized filtered signal to obtain the first terrain signal; Second terrain signal module: used to acquire generator and discriminator, use generator and discriminator to construct generative adversarial network, and use generative adversarial network to reconstruct terrain from first terrain signal to obtain second terrain signal; Underwater topography scanning map module: used to acquire sound velocity measurement equipment, correct the second topography signal through sound velocity measurement equipment to obtain the target topography signal, and construct an underwater topography scanning map based on the target topography signal.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the unmanned surface vessel multibeam sonar detection method as described in any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the unmanned surface vessel multibeam sonar detection method as described in any one of claims 1 to 6.

10. A computer program product comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions, characterized in that, When the program instructions are executed by the computer, the computer is able to perform the steps of the unmanned surface vessel multibeam sonar detection method as described in any one of claims 1 to 6.

Images