Acoustic image processing method, apparatus, and electronic device

Abstract

The application relates to the technical field of acoustic imaging, and discloses an acoustic image processing method, an acoustic image processing device and electronic equipment.The method comprises the following steps: acquiring an initial acoustic image output by an acoustic field imaging device; acquiring image parameters of the initial acoustic image, and constructing an initial mask matched with the initial acoustic image according to the image parameters; acquiring an imaging frequency band energy value of the initial acoustic image, and performing weighted processing on the initial mask based on the imaging frequency band energy value to obtain a noise suppression mask; and performing noise reduction processing on the initial acoustic image based on the noise suppression mask to generate an acoustic imaging image.The application can solve the problems of fixed noise suppression parameters, inflexible adjustment and poor dynamic adaptability by constructing a noise suppression mask capable of adapting to different frequency band signal characteristics to perform noise reduction processing on the acoustic image, thereby improving the noise suppression effect of the acoustic image and improving the imaging clarity and positioning accuracy of the acoustic image.

Description

Technical Field

[0001] This invention relates to the field of acoustic imaging technology, and in particular to an acoustic image processing method, apparatus, and electronic device. Background Technology

[0002] Acoustic field imaging technology is a technique that visualizes sound field characteristics by acquiring and analyzing the distribution of sound waves in space. It is widely used in industrial inspection, equipment maintenance, security monitoring, and other fields. The basic principle of acoustic field imaging technology is to use a microphone array to acquire sound signals and reconstruct acoustic images through algorithms to achieve the visual localization of spatial sound sources.

[0003] Under conditions of low signal-to-noise ratio or excessively high system sensitivity, if the microphone array parameters or system threshold settings are improper, non-realistic centrosymmetric noise will appear in the central region of the acoustic image. For example, it may appear as circular bright spots or symmetrical textures in the image. This noise can mislead the identification of the sound source or obscure the real target.

[0004] In existing image processing techniques, noise suppression is typically achieved using specific threshold filtering and edge enhancement techniques. However, existing noise suppression methods suffer from the following problems: system thresholds and other parameters are fixed and inflexible in adjustment, and they cannot be dynamically adapted to the characteristics of the imaging frequency band, resulting in unstable noise suppression effects or over-suppression, which affects the imaging quality of acoustic images. Summary of the Invention

[0005] To address the aforementioned problems, this invention provides an acoustic image processing method, apparatus, and electronic device. By constructing a noise suppression mask that can adapt to the signal characteristics of different frequency bands, the method performs noise reduction processing on acoustic images, thereby solving the problems of fixed parameters, inflexible adjustment, and poor dynamic adaptability in existing image processing technologies, and improving the noise suppression effect of acoustic images.

[0006] According to one aspect of the present invention, an acoustic image processing method is provided, comprising: acquiring an initial acoustic image output by a sound field imaging device; acquiring image parameters of the initial acoustic image, and constructing an initial mask matching the initial acoustic image based on the image parameters; wherein the initial mask satisfies the following conditions: the size of the initial mask is the same as the size of the initial acoustic image, and the weight attenuation degree of the noise region of the initial acoustic image is higher than the weight attenuation degree of the non-noise region of the initial acoustic image; acquiring the imaging frequency band energy value of the initial acoustic image, and performing weighted processing on the initial mask based on the imaging frequency band energy value to obtain a noise suppression mask; and performing noise reduction processing on the initial acoustic image based on the noise suppression mask to generate an acoustic imaging map.

[0007] Optionally, when the noise region is the central region of the initial acoustic image, the step of obtaining the image parameters of the initial acoustic image and constructing an initial mask matching the initial acoustic image based on the image parameters includes: obtaining the center coordinates and preset standard deviation of the initial acoustic image; and constructing the initial mask based on the center coordinates and the preset standard deviation.

[0008] Optionally, the mathematical expression for the initial mask satisfies the following equation:

[0009] ;

[0010] in, The initial mask represents the Gaussian function; i represents the row index of the pixel in the initial acoustic image; j represents the column index of the pixel in the initial acoustic image. This represents the preset standard deviation of the Gaussian function; The x-coordinate of the center point of the initial acoustic image; The vertical coordinate represents the center point of the initial acoustic image.

[0011] Optionally, the preset standard deviation is any value greater than or equal to 0.25 and less than or equal to 0.75.

[0012] Optionally, the step of obtaining the imaging frequency band energy value of the initial acoustic image and performing weighted processing on the initial mask based on the imaging frequency band energy value to obtain a noise suppression mask includes: obtaining the maximum output energy value of the sound field imaging device; establishing weighting coefficients based on the imaging frequency band energy value and the maximum output energy value; and normalizing the initial mask based on the weighting coefficients to obtain the noise suppression mask.

[0013] Optionally, the expression for the noise suppression mask satisfies the following equation: ;in, G represents the noise suppression mask; e represents the initial mask; and E represents the imaging frequency band energy value.

[0014] Optionally, the step of denoising the initial acoustic image based on the noise suppression mask to generate an acoustic imaging map includes: pixel overlay of the initial acoustic image and the noise suppression mask, and generating the acoustic imaging map based on the pixel overlay result.

[0015] Optionally, the initial acoustic image is a sound source localization map or an acoustic holographic image.

[0016] According to another aspect of the present invention, an acoustic image processing apparatus is provided, comprising: an image acquisition module for acquiring an initial acoustic image output by a sound field imaging device; a mask creation module for acquiring image parameters of the initial acoustic image and constructing an initial mask matching the initial acoustic image based on the image parameters; wherein the initial mask satisfies the following: the size of the initial mask is the same as the size of the initial acoustic image, and the weight attenuation degree of the noise region of the initial acoustic image is higher than the weight attenuation degree of the non-noise region of the initial acoustic image; a mask optimization module for acquiring the imaging frequency band energy value of the initial acoustic image and performing weighted processing on the initial mask based on the imaging frequency band energy value to obtain a noise suppression mask; and an image processing module for performing noise reduction processing on the initial acoustic image based on the noise suppression mask to generate an acoustic imaging image.

[0017] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the above-described acoustic image processing method.

[0018] The technical solution of this invention constructs an initial mask that matches the initial acoustic image output by the acoustic field imaging device, and adaptively weights the initial mask according to the imaging frequency band energy value of the initial acoustic image. The weighted noise suppression mask is then used to denoise the initial acoustic image. This solves the problems of fixed noise suppression parameters, inflexible adjustment, and poor dynamic adaptability in existing noise suppression methods. It can adapt to the characteristics of different frequency band signals, suppress noise generated in the acoustic image due to improper parameter settings, improve the noise suppression effect of the acoustic image, and improve the imaging clarity and positioning accuracy of the acoustic image.

[0019] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 A flowchart of an acoustic image processing method provided in an embodiment of the present invention;

[0022] Figure 2 A flowchart of another acoustic image processing method provided in an embodiment of the present invention;

[0023] Figure 3 This is a schematic diagram of a noise suppression mask and acoustic images before and after noise reduction processing, provided in an embodiment of the present invention.

[0024] Figure 4 This is a schematic diagram of the structure of an acoustic image processing device provided in an embodiment of the present invention;

[0025] Figure 5 A schematic diagram of the structure of an electronic device for implementing the acoustic image processing method of this invention. Detailed Implementation

[0026] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0027] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0028] Figure 1 This is a flowchart illustrating an acoustic image processing method provided in an embodiment of the present invention. This embodiment is applicable to application scenarios such as acoustic holographic imaging and array sound source localization. The method can be executed by an acoustic image processing device, which can be implemented in hardware and / or software. This acoustic image processing device can be configured within an acoustic imaging system or a separate electronic device. Figure 1 As shown, the acoustic image processing method of the present invention specifically includes the following steps:

[0029] S1: Acquire the initial acoustic image output by the sound field imaging device.

[0030] In this context, a sound field imaging device can be understood as a device used to acquire spatial sound signals and output a sound field image. Typically, a sound field imaging device includes a microphone array.

[0031] The initial acoustic image can be understood as a spatial sound field image reconstructed by an algorithm from a sound field imaging device. Optionally, the initial acoustic image can be a sound source localization map or a sound holographic image.

[0032] For example, the sound field imaging device may employ a 128-channel planar microphone array; the image size of the initial acoustic image output by the sound field imaging device may be denoted as: M×N=640×480.

[0033] It should be noted that when the sound source is in the center of the image, the noise at the center of the array will cause a strong energy concentration phenomenon in the central region of the image. In other words, in a microphone array imaging system, the noise interference intensity is greatest in the central region of the image.

[0034] S2: Obtain the image parameters of the initial acoustic image and construct an initial mask that matches the initial acoustic image based on the image parameters.

[0035] Image parameters can be understood as parameters characterizing image properties such as image size and coordinates of the initial acoustic image. Typically, image parameters include at least one of the following: image size, image center coordinates, row index, and column index of pixels in the image.

[0036] The initial mask can be understood as a weight map used to suppress image noise. The initial mask of the present invention satisfies the following conditions: the size of the initial mask is the same as the size of the initial acoustic image, and the weight attenuation degree of the noise region of the initial acoustic image is higher than the weight attenuation degree of the non-noise region of the initial acoustic image.

[0037] For example, taking an initial acoustic image with an image size of M×N=640×480 and the noise region as the central region of the initial acoustic image, a two-dimensional Gaussian weight map can be constructed at the center point (320, 240) of the initial acoustic image to ensure that the weight decays rapidly in the center of the image, thereby enhancing the suppression effect on the central noise.

[0038] S3: Obtain the imaging frequency band energy value of the initial acoustic image, and perform weighted processing on the initial mask based on the imaging frequency band energy value to obtain the noise suppression mask.

[0039] The imaging frequency band energy value can be understood as the spatial distribution intensity of the acoustic energy radiated by the sound source within the imaging frequency band range of the initial acoustic image. In this embodiment, the energy value can be obtained through Fourier transform.

[0040] A noise suppression mask can be understood as a normalized weighted map. It is used to suppress high-energy noise in noisy regions while preserving the image features of the original acoustic image.

[0041] Specifically, the mask peak value can be calculated by the ratio of the imaging frequency band energy value to the maximum output energy value of the sound field imaging device, and the weighted scaling ratio can be determined based on the mask peak value. If the imaging frequency band energy value of the initial acoustic image is denoted as e, and the maximum output energy value of the sound field imaging device is denoted as E, then the mask peak value of the initial mask can be denoted as e / E. Further, the weighted scaling ratio can be set to e / E, or e / 2E.

[0042] S4: Denoise the initial acoustic image based on a noise suppression mask to generate an acoustic imaging map.

[0043] Specifically, the final acoustic image can be generated by superimposing the noise suppression mask onto the initial acoustic image pixel by pixel.

[0044] Therefore, the technical solution of the present invention constructs an initial mask that matches the initial acoustic image output by the acoustic field imaging device, and adaptively weights the mask peak value of the initial mask according to the imaging frequency band energy value of the initial acoustic image. The weighted noise suppression mask is then used to denoise the initial acoustic image, solving the problems of fixed noise suppression parameters, inflexible adjustment, and poor dynamic adaptability in existing noise suppression methods. It can adapt to the signal characteristics of different frequency bands, suppress noise generated in the acoustic image due to improper parameter settings, improve the noise suppression effect of the acoustic image, and improve the imaging clarity and positioning accuracy of the acoustic image.

[0045] Figure 2 A flowchart illustrating another acoustic image processing method provided in an embodiment of the present invention. Figure 2 In the embodiment shown, the noise region is the central region of the initial acoustic image, and the noise suppression mask is used to suppress centrally symmetric noise interference.

[0046] See Figure 2 As shown, when the noise region is the central region of the initial acoustic image, the image parameters of the initial acoustic image are obtained, and an initial mask matching the initial acoustic image is constructed based on the image parameters. Specifically, this includes the following steps:

[0047] S201: Obtain the center coordinates and preset standard deviation of the initial acoustic image.

[0048] Here, the center coordinates can be understood as the coordinates of the center point of the initial acoustic image. For example, if the initial acoustic image size is defined as M×N, with units of pixels, then the center coordinates can be expressed as: .

[0049] The preset standard deviation can be understood as the standard deviation of a Gaussian function, used to control the magnitude of weight changes. When the preset standard deviation is small (e.g., any real number greater than 0 and less than 1), the value of the two-dimensional Gaussian function changes very rapidly near the center, and the pixel weights are concentrated near the center point; conversely, the change is slow. Optionally, the preset standard deviation of this invention can be set to any value greater than or equal to 0.25 and less than or equal to 0.75. Preferably, the preset standard deviation of this invention can be set to 0.5, which can ensure that the weights decay rapidly in the central region of the initial acoustic image, enhancing the suppression effect on central noise.

[0050] S202: Construct the initial mask based on the center coordinates and the preset standard deviation.

[0051] In some alternative embodiments, the initial mask may be a two-dimensional Gaussian weighted map. Specifically, a two-dimensional Gaussian function is constructed using the center coordinates of the initial acoustic image and a preset standard deviation.

[0052] Optionally, the mathematical expression for the initial mask of the present invention satisfies the following formula:

[0053] (Formula 1)

[0054] in, The initial mask represents the Gaussian function; i represents the row index of the pixel in the initial acoustic image; j represents the column index of the pixel in the initial acoustic image. This represents the preset standard deviation of the Gaussian function; The x-coordinate of the center point of the initial acoustic image, for example, ; The ordinate of the center point of the initial acoustic image, for example, .

[0055] Therefore, the technical solution of the present invention uses a Gaussian function to construct an initial mask that matches the image. This initial mask uses the decay characteristics of the Gaussian function to assign different weights to pixels or regions at different locations, thereby achieving adaptive processing of acoustic images.

[0056] See Figure 2 As shown, the imaging frequency band energy value of the initial acoustic image is obtained, and the mask peak value of the initial mask is weighted based on the imaging frequency band energy value to obtain a noise suppression mask, including the following steps:

[0057] S301: Obtain the maximum output energy value of the acoustic field imaging device and the imaging frequency band energy value of the initial acoustic image.

[0058] The maximum output energy value can be understood as the theoretical maximum value of the energy that the sound field imaging device can output in different frequency bands. For example, for a sound field imaging device configured with a 12-bit analog-to-digital converter, the maximum output energy value is equal to 2 to the power of 12.

[0059] In this embodiment, the imaging frequency band energy value and the maximum output energy value of the initial acoustic image can also be normalized and converted. For example, the maximum output energy value is recorded as 1, and the imaging frequency band energy value of the initial acoustic image is recorded as 0.85.

[0060] S302: Establish weighting coefficients based on the energy values ​​of the imaging frequency band and the maximum output energy value, and normalize the initial mask based on the weighting coefficients to obtain the noise suppression mask.

[0061] The weighting coefficient can be understood as a scaling factor established based on the ratio of the imaging frequency band energy value to the maximum output energy value.

[0062] Optionally, the expression for the noise suppression mask of the present invention satisfies the following Formula 2:

[0063] (Formula 2)

[0064] in, G represents the noise suppression mask; e represents the initial mask; e represents the energy value of the imaging frequency band; and E represents the maximum output energy value.

[0065] Specifically, by substituting the values ​​of the maximum output energy value E and the imaging frequency band energy value e into Formula 2 above, the normalized weighted Gaussian weight map can be obtained, which is the noise suppression mask required to suppress centrally symmetric noise. Adaptive weighting of the mask by the imaging frequency band energy level, and using the weighted mask to denoise the acoustic image, can adapt to the characteristics of sound source signals in different frequency bands, simplifying the algorithm.

[0066] See also Figure 2 As shown, the initial acoustic image is denoised using a noise suppression mask to generate an acoustic imaging map. The specific steps include:

[0067] S401: Pixel overlay of the initial acoustic image and the noise suppression mask, and generation of an acoustic imaging map based on the pixel overlay result.

[0068] Specifically, pixel superposition of the initial acoustic image and the noise suppression mask can be achieved by subtracting corresponding pixels in the initial acoustic image and the noise suppression mask. For example, if the initial acoustic image is defined as P, and the noise suppression mask is... The acoustic image obtained by pixel stacking is denoted as Then the acoustic imaging map Noise suppression mask The initial acoustic image P satisfies the following formula:

[0069] (Formula 3)

[0070] in, The acoustic image after suppressing centrally symmetric noise is the final acoustic image output by the system.

[0071] For example, Figure 3 This is a schematic diagram of a noise suppression mask and acoustic images before and after noise reduction processing, provided as an embodiment of the present invention. See also... Figure 3 As shown, Ⅰ represents the acoustic image before noise reduction, i.e., the initial acoustic image; Ⅱ represents the noise suppression mask; and Ⅲ represents the acoustic image after suppressing centrally symmetric noise. Figure 3 As shown, after noise suppression masking, noise interference (i.e., the central spot) in the central region of the acoustic image is effectively suppressed, which can effectively improve the robustness and clarity of the sound source localization image.

[0072] Based on the same inventive concept as the above embodiments, the present invention also provides an acoustic image processing device. The acoustic image processing device provided by the present invention can execute the acoustic image processing method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of executing the method.

[0073] Figure 4 This is a schematic diagram of the structure of an acoustic image processing device provided in an embodiment of the present invention. Figure 4 As shown, the acoustic image processing device includes: an image acquisition module 101, a mask creation module 102, a mask optimization module 103, and an image processing module 104.

[0074] The image acquisition module 101 is used to acquire the initial acoustic image output by the sound field imaging device; the mask creation module 102 is used to acquire the image parameters of the initial acoustic image and construct an initial mask matching the initial acoustic image based on the image parameters; wherein, the initial mask satisfies the following: the size of the initial mask is the same as the size of the initial acoustic image, and the weight attenuation degree of the noise region of the initial acoustic image is higher than the weight attenuation degree of the non-noise region of the initial acoustic image; the mask optimization module 103 is used to acquire the imaging frequency band energy value of the initial acoustic image and perform weighted processing on the mask peak of the initial mask based on the imaging frequency band energy value to obtain a noise suppression mask; the image processing module 104 is used to perform noise reduction processing on the initial acoustic image based on the noise suppression mask to generate an acoustic imaging map.

[0075] Optionally, the mask creation module 102 of the present invention is configured to: when the noise region is the central region of the initial acoustic image, obtain the center coordinates and preset standard deviation of the initial acoustic image, and construct an initial mask based on the center coordinates and preset standard deviation.

[0076] Optionally, the mathematical expression for the initial mask satisfies the following equation:

[0077] ;

[0078] in, The initial mask represents the Gaussian function; i represents the row index of the pixel in the initial acoustic image; j represents the column index of the pixel in the initial acoustic image. This represents the preset standard deviation of the Gaussian function; The x-coordinate of the center point of the initial acoustic image; The ordinate represents the center point of the initial acoustic image.

[0079] Preferably, the preset standard deviation of the present invention is any value that is greater than or equal to 0.25 and less than or equal to 0.75.

[0080] Optionally, the mask optimization module 103 of the present invention is configured to: obtain the maximum output energy value of the acoustic field imaging device and the imaging frequency band energy value of the initial acoustic image; establish weighting coefficients based on the imaging frequency band energy value and the maximum output energy value; and normalize the initial mask based on the weighting coefficients to obtain a noise suppression mask.

[0081] Optionally, the expression for the noise suppression mask satisfies the following equation: ;in, G represents the noise suppression mask; e represents the initial mask; e represents the energy value of the imaging frequency band; and E represents the maximum output energy value.

[0082] Optionally, the image processing module 104 of the present invention is configured to: superimpose pixels of the initial acoustic image and the noise suppression mask, and generate an acoustic imaging map based on the pixel superposition result.

[0083] Optionally, the initial acoustic image is a sound source localization map or an acoustic hologram.

[0084] Based on the above embodiments, the present invention also provides an electronic device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the above-described acoustic image processing method.

[0085] Figure 5This is a schematic diagram of the structure of an electronic device for implementing the acoustic image processing method of an embodiment of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0086] like Figure 5 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0087] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0088] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the acoustic image processing methods described above.

[0089] In some embodiments, the acoustic image processing method described above can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the acoustic image processing method described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the acoustic image processing method described above by any other suitable means (e.g., by means of firmware).

[0090] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0091] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0092] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0093] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0094] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0095] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0096] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0097] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. An acoustic image processing method, characterized in that, include: Acquire the initial acoustic image output by the acoustic field imaging device; Obtain the image parameters of the initial acoustic image, and construct an initial mask that matches the initial acoustic image based on the image parameters; wherein the initial mask satisfies the following: the size of the initial mask is the same as the size of the initial acoustic image, and the weight attenuation degree of the noise region of the initial acoustic image is higher than the weight attenuation degree of the non-noise region of the initial acoustic image; The imaging frequency band energy value of the initial acoustic image is obtained, and the initial mask is weighted based on the imaging frequency band energy value to obtain a noise suppression mask; The initial acoustic image is denoised based on the noise suppression mask to generate an acoustic imaging map; When the noise region is the central region of the initial acoustic image, the step of acquiring the image parameters of the initial acoustic image and constructing an initial mask matching the initial acoustic image based on the image parameters includes: Obtain the center coordinates and preset standard deviation of the initial acoustic image; The initial mask is constructed based on the center coordinates and the preset standard deviation. The mathematical expression for the initial mask satisfies the following equation: ； in, The initial mask represents the Gaussian function; i represents the row index of the pixel in the initial acoustic image; j represents the column index of the pixel in the initial acoustic image. This represents the preset standard deviation of the Gaussian function; The x-coordinate of the center point of the initial acoustic image; The vertical coordinate represents the center point of the initial acoustic image.

2. The acoustic image processing method according to claim 1, characterized in that, The preset standard deviation is any value greater than or equal to 0.25 and less than or equal to 0.

75.

3. The acoustic image processing method of claim 1, wherein, The step of acquiring the imaging frequency band energy value of the initial acoustic image and performing weighted processing on the initial mask based on the imaging frequency band energy value to obtain a noise suppression mask includes: Obtain the maximum output energy value of the acoustic field imaging device and the imaging frequency band energy value of the initial acoustic image; A weighting coefficient is established based on the energy value of the imaging frequency band and the maximum output energy value, and the initial mask is normalized based on the weighting coefficient to obtain the noise suppression mask.

4. The acoustic image processing method according to claim 3, characterized in that, The expression for the noise suppression mask satisfies the following equation: ； in, G represents the noise suppression mask; e represents the initial mask; and E represents the imaging frequency band energy value.

5. The acoustic image processing method according to claim 1, characterized in that, The step of denoising the initial acoustic image based on the noise suppression mask to generate an acoustic imaging map includes: The initial acoustic image and the noise suppression mask are pixel-overlayed, and the acoustic imaging map is generated based on the pixel overlay result.

6. The acoustic image processing method according to any one of claims 1-5, characterized in that, The initial acoustic image is a sound source localization map or an acoustic holographic image.

7. An acoustic image processing apparatus for implementing the acoustic image processing method as described in claim 1, characterized in that, include: The image acquisition module is used to acquire the initial acoustic image output by the sound field imaging device; A mask creation module is used to obtain image parameters of the initial acoustic image and construct an initial mask that matches the initial acoustic image based on the image parameters; wherein, the initial mask satisfies the following: the size of the initial mask is the same as the size of the initial acoustic image, and the weight attenuation degree of the noise region of the initial acoustic image is higher than the weight attenuation degree of the non-noise region of the initial acoustic image; A mask optimization module is used to obtain the imaging frequency band energy value of the initial acoustic image, and to perform weighted processing on the initial mask based on the imaging frequency band energy value to obtain a noise suppression mask; An image processing module is used to perform noise reduction processing on the initial acoustic image based on the noise suppression mask to generate an acoustic imaging map.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the acoustic image processing method according to any one of claims 1-6.

Images