Image denoising method, device, processor and storage medium

Abstract

The embodiment of the present application provides a method, device, processor and storage medium for image processing. The method includes: obtaining an image to be denoised, the image to be denoised is generated by at least one optical fiber sensing data detected by an optical fiber sensor; determining the time series and spatial direction of the optical fiber sensing data; processing the image to be denoised according to the time series and spatial direction to obtain the processed target image features; and determining the target image after denoising the image to be denoised according to the target image features. The optical fiber sensing data can be processed to filter out the background noise in the image to be denoised, thereby effectively identifying the effective information in the optical fiber sensing.

Description

Technical Field

[0001] The present application relates to the field of optical fiber sensing technology, and in particular to an image denoising method, device, processor and storage medium. Background Art

[0002] The data generated by fiber optic sensing is displayed in the image as multi-channel time series data. If it is affected by external environment or threats, such as sound, temperature and strain, the vibration data generated is a non-stationary data feature. In the prior art, the original spectrum feature analysis methods such as Fourier transform have limited suppression of background noise in noisy areas of the image, thus affecting the ability to extract relevant features. Summary of the invention

[0003] The purpose of the embodiments of the present application is to provide a method, device, processor and storage medium for image denoising.

[0004] In order to achieve the above-mentioned object, the first aspect of the present application provides an image denoising method, comprising: acquiring an image to be denoised, where the image to be denoised is generated by at least one optical fiber sensing data detected by an optical fiber sensor;

[0005] Determine the time series and spatial orientation of fiber optic sensing data;

[0006] The denoised image is processed according to the time series and the spatial direction to obtain the processed target image features;

[0007] The target image after denoising the image to be denoised is determined according to the target image features.

[0008] In an embodiment of the present application, the denoised image is processed according to a time series and a spatial direction to obtain features of a target image after processing, including: determining a plurality of one-dimensional image features corresponding to the denoised image according to a time series; splicing the plurality of one-dimensional image features to obtain a spliced ​​two-dimensional image; and decomposing the two-dimensional image according to a spatial direction to obtain features of a target image.

[0009] In an embodiment of the present application, determining multiple one-dimensional image features corresponding to the image to be denoised according to a time series includes: decomposing the image to be denoised according to the time series to obtain multiple local images corresponding to the image to be denoised; determining the maximum points and minimum points of multiple pixel points contained in each local image; for each local image, determining the one-dimensional image features of the local image according to the maximum points and the minimum points; and determining multiple one-dimensional image features corresponding to the image to be denoised according to the multiple one-dimensional image features corresponding to the multiple local images.

[0010] In an embodiment of the present application, for each local image, determining the one-dimensional image features of the local image based on the maximum points and the minimum points includes: for each local image, interpolating the maximum points and the minimum points to obtain the mean envelope surface of each image to be denoised, the mean envelope surface including multiple pixel points; for each local image, determining the local image features and standard deviation of the local image based on the mean envelope surface; for each local image, when the standard deviation is less than or equal to a preset threshold, determining the local image features as the one-dimensional image features of the local image; for each local image, when the standard deviation is greater than the preset threshold, determining the maximum points and the minimum points of the multiple pixel points contained in the local image based on the mean envelope surface, so that the standard deviation is less than or equal to the preset threshold.

[0011] In an embodiment of the present application, for each local image, interpolating the maximum point and the minimum point to obtain the mean envelope surface of the image to be denoised includes: calculating the mean envelope surface according to the following formula (1):

[0012]

[0013] Among them, M ij (x, y) refers to the pixel value of the pixel point with coordinates (x, y) contained in the corresponding mean envelope surface in each local image, i refers to the i-th component obtained by decomposition, j refers to the number of decomposition cycles, and U max (x, y) refers to the pixel value of the pixel point contained in the upper envelope of the image to be denoised, L min (x, y) refers to the pixel value of the pixel point contained in the lower envelope of the image to be denoised.

[0014] In an embodiment of the present application, for each local image, determining the local image feature and standard deviation of the local image according to the mean envelope surface includes: calculating the local image feature according to the following formula (2):

[0015] h i(j+1) (x, y) = h ij (x, y)-M ij (x, y) (2)

[0016] Among them, h i(j+1) (x, y) refers to the pixel value of the pixel point with coordinates (x, y) in the local image corresponding to the jth number of cycles of the i-th component decomposition, h ij (x, y) refers to the pixel value of the pixel point with coordinates (x, y) in the local image corresponding to the jth number of decomposition cycles of the i-th component, i refers to the i-th component obtained by decomposition, and j refers to the number of decomposition cycles.

[0017] In an embodiment of the present application, for each local image, determining the local image features and the standard deviation of the local image according to the mean envelope surface includes: calculating the standard deviation according to the following formula (3):

[0018]

[0019] Among them, SD refers to the standard deviation of each local image, m refers to the maximum value of the horizontal coordinate of each local image, n refers to the maximum value of the vertical coordinate of each local image, and h i(j+1) (x, y) refers to the pixel value of the pixel point with coordinates (x, y) in the local image corresponding to the jth number of cycles of the i-th component decomposition, h ij (x, y) refers to the pixel value of the pixel point with coordinates (x, y) in the local image corresponding to the jth number of decomposition cycles of the i-th component, i refers to the i-th component obtained by decomposition, and j refers to the number of decomposition cycles.

[0020] A second aspect of the present application provides a processor configured to execute the above-mentioned image denoising method.

[0021] A third aspect of the present application provides an image denoising device, comprising a processor configured to execute the above-mentioned image denoising method.

[0022] A fourth aspect of the present application provides a machine-readable storage medium having instructions stored thereon, which, when executed by a processor, configure the processor to execute the above-mentioned image denoising method.

[0023] Through the above technical solution, by acquiring the image to be denoised, the image to be denoised is generated by at least one optical fiber sensing data detected by the optical fiber sensor; determining the time series and spatial direction of the optical fiber sensing data; processing the image to be denoised according to the time series and spatial direction to obtain the processed target image features; and determining the target image after denoising the image to be denoised according to the target image features. The optical fiber sensing data can be processed to filter out the background noise in the image to be denoised, thereby effectively identifying the effective information in the optical fiber sensing.

[0024] Other features and advantages of the embodiments of the present application will be described in detail in the subsequent specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present application, but do not constitute a limitation on the embodiments of the present application. In the accompanying drawings:

[0026] Figure 1The following is a schematic diagram showing a flow chart of an image denoising method according to an embodiment of the present application;

[0027] Figure 2 A schematic diagram schematically shows a denoised image according to an embodiment of the present application;

[0028] Figure 3 The structure block diagram of the device for image denoising according to an embodiment of the present application is schematically shown;

[0029] Figure 4 The internal structure diagram of a computer device according to an embodiment of the present application is schematically shown. DETAILED DESCRIPTION

[0030] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the specific implementation methods described herein are only used to illustrate and explain the embodiments of the present application, and are not used to limit the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0031] Figure 1 The flowchart of the method for image denoising according to an embodiment of the present application is schematically shown. Figure 1 As shown, in one embodiment of the present application, a method for image denoising is provided, comprising the following steps:

[0032] Step 102: Acquire an image to be denoised, where the image to be denoised is generated from at least one optical fiber sensing data detected by the optical fiber sensor.

[0033] Step 104, determining the time sequence and spatial direction of the optical fiber sensing data.

[0034] Step 106, processing the image to be denoised according to the time series and the spatial direction to obtain the processed target image features.

[0035] Step 108, determining a target image after denoising the image to be denoised according to the target image features.

[0036] Optical fiber sensing includes two functions: sensing and transmitting external signals (measured objects). Optical fiber sensors can measure measured objects to obtain optical fiber sensing data related to the measured objects. Optical fiber sensing data refers to the optical fiber sensor using the light transmission characteristics of optical fibers to convert the relevant data of the measured object into data of light characteristics, such as intensity, phase, polarization state, frequency, wavelength, etc. The image to be denoised is generated by at least one optical fiber sensing data detected by the optical fiber sensor. The optical fiber sensing data generated by optical fiber sensing is displayed in the image as multi-channel time series data. The vibration data generated by the external environment or threats, such as sound, temperature and strain, has non-stationary data characteristics. The processor can determine the time series and spatial direction of the optical fiber sensing data. Among them, the time series refers to the time sequence of the optical fiber sensing data. The spatial direction refers to the spatial coordinates of the optical fiber sensing data. The processor can process the image to be denoised according to the time series and spatial direction to obtain the processed target image features. The target image feature refers to the effective information extracted from the image after the image to be denoised is processed. By processing the optical fiber sensing data through the time series and spatial direction of the optical fiber sensing data, the background noise in the image to be denoised can be filtered out, thereby identifying the target image features in the optical fiber sensing. The processor can obtain the target image after denoising the image to be denoised according to the target image features.

[0037] In one embodiment, the denoised image is processed according to a time series and a spatial direction to obtain features of a processed target image, including: determining a plurality of one-dimensional image features corresponding to the denoised image according to a time series; splicing the plurality of one-dimensional image features to obtain a spliced ​​two-dimensional image; and decomposing the two-dimensional image according to a spatial direction to obtain features of a target image.

[0038] The processor can process the denoised image according to the time series and the spatial direction. Specifically, the denoised image can be decomposed by the EMD algorithm. Among them, the EMD algorithm refers to the empirical mode decomposition algorithm (empirical mode decomposition-EMD). The processor can determine the time series and spatial direction of the optical fiber sensing data in the image to be denoised. More specifically, the ordinate of the image to be denoised is the time coordinate in the time series direction, and the abscissa is the spatial coordinate in the spatial direction. When the image is decomposed by the traditional EMD algorithm, it is easy to cause the basis function selection to be inappropriate due to the inconsistency of the modes in the two directions. Therefore, according to the data characteristics of light sensing, based on the EMD algorithm, according to the time series of the optical fiber sensing data, the processor can decompose the image to be denoised to obtain multiple one-dimensional image features. The one-dimensional image feature refers to the local feature data corresponding to the time feature scale of the image to be denoised. Further, the processor can splice multiple one-dimensional image features to obtain a spliced ​​two-dimensional image. Specifically, the processor can reversely decompose each one-dimensional image feature by the EMD algorithm, so that the sequence of the one-dimensional image features changes. Then, the processor can concatenate the one-dimensional image features according to the time series to obtain a two-dimensional image, and then decompose the two-dimensional image according to the spatial direction to obtain the target image feature. The target image feature refers to the local feature data corresponding to the spatial feature scale of the two-dimensional image. Figure 2 , by decomposing the image to be denoised into one-dimensional image features corresponding to the time series, and then performing EMD decomposition on each one-dimensional image feature, and then splicing them into a two-dimensional image, and then performing one-dimensional decomposition of the two-dimensional image according to the spatial direction. Not only does it reduce the amount of calculation, but it also achieves excellent noise reduction effects, and the background noise is greatly suppressed.

[0039] In one embodiment, determining multiple one-dimensional image features corresponding to the image to be denoised based on a time series includes: decomposing the image to be denoised based on the time series to obtain multiple local images corresponding to the image to be denoised; determining the maximum points and minimum points of multiple pixel points contained in each local image, and for each local image, determining the one-dimensional image features of the local image based on the maximum points and the minimum points; and determining multiple one-dimensional image features corresponding to the image to be denoised based on the multiple one-dimensional image features corresponding to the multiple local images.

[0040] The processor can decompose the image to be denoised according to the time series to obtain multiple local images corresponding to the image to be denoised. The local image refers to an area in the image to be denoised corresponding to the time characteristic scale of the image to be denoised. Each local image contains multiple pixels, and the processor can determine the maximum points and minimum points of the multiple pixels contained in each local image. For each local image, the processor can determine the one-dimensional image features of the local image according to the maximum points and the minimum points. The local time domain characteristics of the one-dimensional image features of the optical fiber sensing data in the image to be denoised are determined by the time scale between the extreme points. Then, the processor can determine the multiple one-dimensional image features corresponding to the image to be denoised according to the multiple one-dimensional image features corresponding to the multiple local images. In this way, all vibration modes contained in the signal can be identified through the characteristic time scale, thereby identifying the noise information.

[0041] In one embodiment, for each local image, determining the one-dimensional image features of the local image based on the maximum points and the minimum points includes: for each local image, interpolating the maximum points and the minimum points to obtain the mean envelope surface of the image to be denoised, the mean envelope surface including multiple pixel points; for each local image, determining the local image features and standard deviation of the local image based on the mean envelope surface; for each local image, when the standard deviation is less than or equal to a preset threshold, determining the local image features as the one-dimensional image features of the local image; for each local image, when the standard deviation is greater than the preset threshold, determining the maximum points and the minimum points of the multiple pixel points contained in the local image based on the mean envelope surface, so that the standard deviation is less than or equal to the preset threshold.

[0042] Based on the EMD algorithm, for each local image, the processor can interpolate between the maximum point and the minimum point to obtain the mean envelope surface of each local image. The mean envelope surface refers to the pixel points corresponding to the average value between the maximum point and the minimum point of the local image, and is composed of multiple pixel points corresponding to the average value corresponding to multiple local images. Then, the processor can determine the local image features and standard deviation of each local image based on the mean envelope surface. The local image feature is a high-frequency component with high energy in the local image, which represents the main characteristics of the local image. For each local image, when the standard deviation is less than or equal to the preset threshold, the processor can determine the local image feature as a one-dimensional image feature of the local image. When the standard deviation is greater than the preset threshold, the processor re-determines the maximum and minimum points of the multiple pixel points contained in the local image based on the pixel points contained in the mean envelope surface, so as to re-determine the mean envelope surface based on the new maximum and minimum points, until the standard deviation calculated based on the new mean envelope surface is less than or equal to the preset threshold. Among them, the preset threshold refers to the preset threshold of the standard deviation, which is the stop condition for determining whether to redefine the maximum and minimum points. Through the above scheme, based on the EMD algorithm, the scale components of the fiber optic sensor data in the image to be denoised are continuously extracted from high frequency to low frequency, and the order of the decomposed characteristic mode functions is arranged from high to low frequency, that is, the highest frequency component is obtained first, then the second high frequency, and finally a residual component with a frequency close to 0 is obtained. For the data that is continuously decomposed, the high-frequency component with large energy always represents the main characteristics of the original data and is the most important component, so that the key modal characteristics of the fiber optic sensor data can be extracted.

[0043] In one embodiment, for each local image, interpolating the maximum value points and the minimum value points to obtain the mean envelope surface of the image to be denoised includes: calculating the mean envelope surface according to the following formula (1):

[0044]

[0045] Among them, M ij (x, y) refers to the pixel value of the pixel point with coordinates (x, y) contained in the corresponding mean envelope surface in each local image, i refers to the i-th component obtained by decomposition, j refers to the number of decomposition cycles, and U max (x, y) refers to the pixel value of the pixel point contained in the upper envelope of the image to be denoised, L min (x, y) refers to the pixel value of the pixel point contained in the lower envelope of the image to be denoised.

[0046] In one embodiment, for each local image, determining the local image feature and the standard deviation of the local image according to the mean envelope surface includes: calculating the local image feature according to the following formula (2):

[0047] h i(j+1) (x, y) = h ij (x, y)-M ij (x, y) (2)

[0048] Among them, h i(j+1) (x, y) refers to the pixel value of the pixel point with coordinates (x, y) in the local image corresponding to the jth number of cycles of the i-th component decomposition, h ij (x, y) refers to the pixel value of the pixel point with coordinates (x, y) in the local image corresponding to the jth number of decomposition cycles of the i-th component, i refers to the i-th component obtained by decomposition, and j refers to the number of decomposition cycles.

[0049] In one embodiment, for each local image, determining the local image features and standard deviation of the local image according to the mean envelope surface includes: calculating the standard deviation according to the following formula (3):

[0050]

[0051] Among them, SD refers to the standard deviation of each local image, m refers to the maximum value of the horizontal coordinate of each local image, n refers to the maximum value of the vertical coordinate of each local image, and h i(j+1) (x, y) refers to the pixel value of the pixel point with coordinates (x, y) in the local image corresponding to the jth number of cycles of the i-th component decomposition, h ij (x, y) refers to the pixel value of the pixel point with coordinates (x, y) in the local image corresponding to the jth number of decomposition cycles of the i-th component, i refers to the i-th component obtained by decomposition, and j refers to the number of decomposition cycles.

[0052] Determine h i(j+1) Whether (x, y) satisfies the two-dimensional intrinsic mode function can be determined by the standard deviation StandardDeviation (SD). According to experience, the preset threshold of SD is 0.2-0.3.

[0053] In a specific embodiment, after performing EMD decomposition on the image to be denoised, it can be expressed in the following form:

[0054]

[0055] Among them, f(x,y) refers to the pixel value of any pixel point in the image to be denoised, c i (x, y) represents the i-th component of the image to be denoised decomposed along the time series, r n (x,y) refers to the residual or trend term after decomposition.

[0056] Through the above technical scheme, by obtaining the image to be denoised, the image to be denoised is generated by at least one optical fiber sensing data detected by the optical fiber sensor; determining the time series and spatial direction of the optical fiber sensing data; processing the image to be denoised according to the time series and spatial direction to obtain the processed target image features; and determining the target image after denoising the image to be denoised according to the target image features. The optical fiber sensing data can be processed to filter out the background noise in the image to be denoised. The amount of calculation is reduced, and an excellent noise reduction effect is achieved. The background noise is greatly suppressed, and the effective information in the optical fiber sensing is effectively identified.

[0057] Figure 1 FIG. 1 is a flow chart of a method for image denoising in one embodiment. It should be understood that although Figure 1 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 1 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0058] In one embodiment, Figure 4 As shown, a device for image denoising is provided, comprising an image acquisition module, an image processing module and a target image determination module, wherein:

[0059] The image acquisition module 302 is used to acquire the image to be denoised, where the image to be denoised is generated from at least one optical fiber sensing data detected by the optical fiber sensor.

[0060] The image processing module 304 is used to determine the time sequence and spatial direction of the optical fiber sensing data, and process the image to be denoised according to the time sequence and spatial direction to obtain the processed target image features.

[0061] The target image determination module 306 is used to determine the target image after the denoising of the image to be denoised according to the target image features.

[0062] In one embodiment, the image processing module 304 is further used to determine multiple one-dimensional image features corresponding to the image to be denoised based on a time series; splice the multiple one-dimensional image features to obtain a spliced ​​two-dimensional image; and decompose the two-dimensional image according to a spatial direction to obtain a target image feature.

[0063] In one embodiment, the image processing module 304 is further used to decompose the image to be denoised according to a time series to obtain a plurality of local images corresponding to the image to be denoised; determine the maximum points and minimum points of a plurality of pixel points contained in each local image; for each local image, determine the one-dimensional image features of the local image according to the maximum points and the minimum points; and determine a plurality of one-dimensional image features corresponding to the image to be denoised according to a plurality of one-dimensional image features corresponding to a plurality of local images.

[0064] In one embodiment, the image processing module 304 is also used to interpolate the maximum points and the minimum points for each local image to obtain a mean envelope surface for each image to be denoised, wherein the mean envelope surface includes multiple pixel points; for each local image, the local image features and the standard deviation of the local image are determined according to the mean envelope surface; for each local image, when the standard deviation is less than or equal to a preset threshold, the local image features are determined as one-dimensional image features of the local image; for each local image, when the standard deviation is greater than a preset threshold, the maximum points and the minimum points of the multiple pixel points contained in the local image are determined according to the mean envelope surface, so that the standard deviation is less than or equal to the preset threshold.

[0065] In one embodiment, the image processing module 304 is further configured to calculate the mean envelope surface according to the following formula (1):

[0066]

[0067] Among them, M ij (x, y) refers to the pixel value of the pixel point with coordinates (x, y) contained in the corresponding mean envelope surface in each local image, i refers to the i-th component obtained by decomposition, j refers to the number of decomposition cycles, and U max (x, y) refers to the pixel value of the pixel point contained in the upper envelope of the image to be denoised, L min (x, y) refers to the pixel value of the pixel point contained in the lower envelope of the image to be denoised.

[0068] In one embodiment, the image processing module 304 is further configured to calculate the local image feature according to the following formula (2):

[0069] h i(j+1) (x, y) = h ij (x, y)-M ij (x, y) (2)

[0070] Among them, h i(j+1) (x, y) refers to the pixel value of the pixel point with coordinates (x, y) in the local image corresponding to the jth number of cycles of the i-th component decomposition, h ij(x, y) refers to the pixel value of the pixel point with coordinates (x, y) in the local image corresponding to the jth number of decomposition cycles of the i-th component, i refers to the i-th component obtained by decomposition, and j refers to the number of decomposition cycles.

[0071] In one embodiment, the image processing module 304 is further configured to calculate the standard deviation according to the following formula (3):

[0072]

[0073] Among them, SD refers to the standard deviation of each local image, m refers to the maximum value of the horizontal coordinate of each local image, n refers to the maximum value of the vertical coordinate of each local image, and h i(j+1) (x, y) refers to the pixel value of the pixel point with coordinates (x, y) in the local image corresponding to the jth number of cycles of the i-th component decomposition, h ij (x, y) refers to the pixel value of the pixel point with coordinates (x, y) in the local image corresponding to the jth number of decomposition cycles of the i-th component, i refers to the i-th component obtained by decomposition, and j refers to the number of decomposition cycles.

[0074] The image denoising device includes a processor and a memory. The image acquisition module, image processing module and target image determination module are all stored in the memory as program units. The processor executes the program modules stored in the memory to implement corresponding functions.

[0075] The processor includes a kernel, which calls the corresponding program unit from the memory. One or more kernels can be set, and the method of image denoising is implemented by adjusting kernel parameters.

[0076] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0077] An embodiment of the present application provides a storage medium on which a program is stored. When the program is executed by a processor, the above-mentioned image denoising method is implemented.

[0078] An embodiment of the present application provides a processor, which is used to run a program, wherein the above-mentioned image denoising method is executed when the program is run.

[0079] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 4As shown. The computer device includes a processor A01, a network interface A02, a memory (not shown in the figure) and a database (not shown in the figure) connected through a system bus. Among them, the processor A01 of the computer device is used to provide computing and control capabilities. The memory of the computer device includes an internal memory A03 and a non-volatile storage medium A04. The non-volatile storage medium A04 stores an operating system B01, a computer program B02 and a database (not shown in the figure). The internal memory A03 provides an environment for the operation of the operating system B01 and the computer program B02 in the non-volatile storage medium A04. The database of the computer device is used to store image processing data. The network interface A02 of the computer device is used to communicate with an external terminal through a network connection. When the computer program B02 is executed by the processor A01, a method of image processing is implemented.

[0080] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0081] The embodiment of the present application provides a device, which includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, the following steps are implemented:

[0082] Acquire an image to be denoised, where the image to be denoised is generated by at least one optical fiber sensing data detected by the optical fiber sensor; determine the time series and spatial direction of the optical fiber sensing data; process the image to be denoised according to the time series and spatial direction to obtain features of a processed target image; and determine a target image after denoising the image to be denoised according to the features of the target image.

[0083] In one embodiment, the denoised image is processed according to a time series and a spatial direction to obtain features of a processed target image, including: determining a plurality of one-dimensional image features corresponding to the denoised image according to a time series; splicing the plurality of one-dimensional image features to obtain a spliced ​​two-dimensional image; and decomposing the two-dimensional image according to a spatial direction to obtain features of a target image.

[0084] In one embodiment, determining multiple one-dimensional image features corresponding to the image to be denoised based on a time series includes: decomposing the image to be denoised based on the time series to obtain multiple local images corresponding to the image to be denoised; determining the maximum points and minimum points of multiple pixel points contained in each local image; for each local image, determining the one-dimensional image features of the local image based on the maximum points and the minimum points; and determining multiple one-dimensional image features corresponding to the image to be denoised based on the multiple one-dimensional image features corresponding to the multiple local images.

[0085] In one embodiment, for each local image, determining the one-dimensional image features of the local image based on the maximum points and the minimum points includes: for each local image, interpolating the maximum points and the minimum points to obtain the mean envelope surface of each image to be denoised, the mean envelope surface including multiple pixel points; for each local image, determining the local image features and standard deviation of the local image based on the mean envelope surface; for each local image, when the standard deviation is less than or equal to a preset threshold, determining the local image features as the one-dimensional image features of the local image; for each local image, when the standard deviation is greater than the preset threshold, determining the maximum points and the minimum points of the multiple pixel points contained in the local image based on the mean envelope surface, so that the standard deviation is less than or equal to the preset threshold.

[0086] In one embodiment, for each local image, interpolating the maximum value points and the minimum value points to obtain the mean envelope surface of the image to be denoised includes: calculating the mean envelope surface according to the following formula (1):

[0087]

[0088] Among them, M ij (x, y) refers to the pixel value of the pixel point with coordinates (x, y) contained in the corresponding mean envelope surface in each local image, i refers to the i-th component obtained by decomposition, j refers to the number of decomposition cycles, and U max (x, y) refers to the pixel value of the pixel point contained in the upper envelope of the image to be denoised, L min (x, y) refers to the pixel value of the pixel point contained in the lower envelope of the image to be denoised.

[0089] In one embodiment, for each local image, determining the local image feature and the standard deviation of the local image according to the mean envelope surface includes: calculating the local image feature according to the following formula (2):

[0090] h i(j+1) (x,y)=h ij (x, y)-M ij (x, y) (2)

[0091] Among them, h i(j+1)(x, y) refers to the pixel value of the pixel point with coordinates (x, y) in the local image corresponding to the jth number of cycles of the i-th component decomposition, h ij (x, y) refers to the pixel value of the pixel point with coordinates (x, y) in the local image corresponding to the jth number of decomposition cycles of the i-th component, i refers to the i-th component obtained by decomposition, and j refers to the number of decomposition cycles.

[0092] In one embodiment, for each local image, determining the local image features and standard deviation of the local image according to the mean envelope surface includes: calculating the standard deviation according to the following formula (3):

[0093]

[0094] Among them, SD refers to the standard deviation of each local image, m refers to the maximum value of the horizontal coordinate of each local image, n refers to the maximum value of the vertical coordinate of each local image, and h i(j+1) (x, y) refers to the pixel value of the pixel point with coordinates (x, y) in the local image corresponding to the jth number of cycles of the i-th component decomposition, h ij (x, y) refers to the pixel value of the pixel point with coordinates (x, y) in the local image corresponding to the jth number of decomposition cycles of the i-th component, i refers to the i-th component obtained by decomposition, and j refers to the number of decomposition cycles.

[0095] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program for initializing the following method steps:

[0096] Acquire an image to be denoised, where the image to be denoised is generated by at least one optical fiber sensing data detected by the optical fiber sensor; determine the time series and spatial direction of the optical fiber sensing data; process the image to be denoised according to the time series and spatial direction to obtain features of a processed target image; and determine a target image after denoising the image to be denoised according to the features of the target image.

[0097] In one embodiment, the denoised image is processed according to a time series and a spatial direction to obtain features of a processed target image, including: determining a plurality of one-dimensional image features corresponding to the denoised image according to a time series; splicing the plurality of one-dimensional image features to obtain a spliced ​​two-dimensional image; and decomposing the two-dimensional image according to a spatial direction to obtain features of a target image.

[0098] In one embodiment, determining multiple one-dimensional image features corresponding to the image to be denoised based on a time series includes: decomposing the image to be denoised based on the time series to obtain multiple local images corresponding to the image to be denoised; determining the maximum points and minimum points of multiple pixel points contained in each local image; for each local image, determining the one-dimensional image features of the local image based on the maximum points and the minimum points; and determining multiple one-dimensional image features corresponding to the image to be denoised based on the multiple one-dimensional image features corresponding to the multiple local images.

[0099] In one embodiment, for each local image, determining the one-dimensional image features of the local image based on the maximum points and the minimum points includes: for each local image, interpolating the maximum points and the minimum points to obtain the mean envelope surface of each image to be denoised, the mean envelope surface including multiple pixel points; for each local image, determining the local image features and standard deviation of the local image based on the mean envelope surface; for each local image, when the standard deviation is less than or equal to a preset threshold, determining the local image features as the one-dimensional image features of the local image; for each local image, when the standard deviation is greater than the preset threshold, determining the maximum points and the minimum points of the multiple pixel points contained in the local image based on the mean envelope surface, so that the standard deviation is less than or equal to the preset threshold.

[0100] In one embodiment, for each local image, interpolating the maximum value points and the minimum value points to obtain the mean envelope surface of the image to be denoised includes: calculating the mean envelope surface according to the following formula (1):

[0101]

[0102] Among them, M ij (x, y) refers to the pixel value of the pixel point with coordinates (x, y) contained in the corresponding mean envelope surface in each local image, i refers to the i-th component obtained by decomposition, j refers to the number of decomposition cycles, and U max (x, y) refers to the pixel value of the pixel point contained in the upper envelope of the image to be denoised, L min (x, y) refers to the pixel value of the pixel point contained in the lower envelope of the image to be denoised.

[0103] In one embodiment, for each local image, determining the local image feature and the standard deviation of the local image according to the mean envelope surface includes: calculating the local image feature according to the following formula (2):

[0104] h i(j+1) (x,y)=h ij (x, y)-M ij (x, y) (2)

[0105] Among them, h i(j+1)(x, y) refers to the pixel value of the pixel point with coordinates (x, y) in the local image corresponding to the jth number of cycles of the i-th component decomposition, h ij (x, y) refers to the pixel value of the pixel point with coordinates (x, y) in the local image corresponding to the jth number of decomposition cycles of the i-th component, i refers to the i-th component obtained by decomposition, and j refers to the number of decomposition cycles.

[0106] In one embodiment, for each local image, determining the local image features and standard deviation of the local image according to the mean envelope surface includes: calculating the standard deviation according to the following formula (3):

[0107]

[0108] Among them, SD refers to the standard deviation of each local image, m refers to the maximum value of the horizontal coordinate of each local image, n refers to the maximum value of the vertical coordinate of each local image, and h i(j+1) (x, y) refers to the pixel value of the pixel point with coordinates (x, y) in the local image corresponding to the jth number of cycles of the i-th component decomposition, h ij (x, y) refers to the pixel value of the pixel point with coordinates (x, y) in the local image corresponding to the jth number of decomposition cycles of the i-th component, i refers to the i-th component obtained by decomposition, and j refers to the number of decomposition cycles.

[0109] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0110] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0111] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0112] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0113] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0114] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0115] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0116] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0117] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for image denoising, characterized in that: The method comprises: Acquire an image to be denoised, where the image to be denoised is generated by at least one optical fiber sensing data detected by the optical fiber sensor; Determining the time series and spatial direction of the optical fiber sensing data; Processing the image to be denoised according to the time series and the spatial direction to obtain processed target image features includes: Determine a plurality of one-dimensional image features corresponding to the image to be denoised according to the time series, wherein the one-dimensional image features refer to local feature data corresponding to the time feature scale of the image to be denoised; splicing the multiple one-dimensional image features to obtain a spliced ​​two-dimensional image; Decomposing the two-dimensional image according to the spatial direction to obtain the target image feature; A target image after denoising the image to be denoised is determined according to the target image features.

2. The image denoising method according to claim 1, characterized in that: Determining the plurality of one-dimensional image features corresponding to the image to be denoised according to the time series comprises: Decomposing the image to be denoised according to the time series to obtain a plurality of local images corresponding to the image to be denoised; Determine the maximum and minimum points of multiple pixel points contained in each local image; For each local image, determining a one-dimensional image feature of the local image according to the maximum point and the minimum point; A plurality of one-dimensional image features corresponding to the image to be denoised are determined according to the plurality of one-dimensional image features corresponding to the plurality of local images.

3. The method for image denoising according to claim 2, characterized in that: For each local image, determining the one-dimensional image feature of the local image according to the maximum point and the minimum point comprises: For each local image, interpolate the maximum value point and the minimum value point to obtain a mean envelope surface of the image to be denoised, wherein the mean envelope surface includes a plurality of pixel points; For each local image, determining the local image features and standard deviation of the local image according to the mean envelope surface; For each local image, when the standard deviation is less than or equal to a preset threshold, determining the local image feature as a one-dimensional image feature of the local image; For each local image, when the standard deviation is greater than a preset threshold, the maximum points and minimum points of multiple pixel points contained in the local image are determined according to the mean envelope surface so that the standard deviation is less than or equal to the preset threshold.

4. The method for image denoising according to claim 3, characterized in that: For each local image, interpolating the maximum value point and the minimum value point to obtain the mean envelope surface of the image to be denoised includes: The mean envelope surface is calculated according to the following formula (1): （1） in, It means that the coordinates of the corresponding mean envelope surface in each local image are The pixel value of the pixel point, i refers to the i-th component obtained by decomposition, and j refers to the number of decomposition cycles It refers to the pixel value of the pixel point contained in the upper envelope surface of the image to be denoised, .

5. The method for image denoising according to claim 3, characterized in that: The step of determining the local image features and the standard deviation of each local image according to the mean envelope surface comprises: The local image feature is calculated according to the following formula (2): （2） in, It means that the coordinates in the local image corresponding to the number of cycles of decomposition of the i-th component is j are The pixel value of the pixel point, It means that the coordinates in the local image corresponding to the number of cycles of decomposition of the i-th component is j are The pixel value of the pixel point, i refers to the i-th component obtained by decomposition, and j refers to the number of decomposition cycles.

6. The method for image denoising according to claim 3, characterized in that: The step of determining the local image features and the standard deviation of each local image according to the mean envelope surface comprises: The standard deviation is calculated according to the following formula (3): （3） in, refers to the standard deviation of each local image, m refers to the maximum value of the horizontal coordinate of each local image, and n refers to the maximum value of the vertical coordinate of each local image. It means that the coordinates in the local image corresponding to the number of cycles of decomposition of the i-th component is j are The pixel value of the pixel point, It means that the coordinates in the local image corresponding to the number of cycles of decomposition of the i-th component is j are The pixel value of the pixel point, i refers to the i-th component obtained by decomposition, and j refers to the number of decomposition cycles.

7. A computer device, characterized in that: The invention comprises a processor, a memory and a program stored in the memory and executable on the processor, wherein the processor implements the image denoising method according to any one of claims 1 to 6 when executing the program.

8. An image denoising device, characterized in that: include: An image acquisition module, used for acquiring an image to be denoised, wherein the image to be denoised is generated by at least one optical fiber sensing data detected by the optical fiber sensor; An image processing module is used to determine the time sequence and spatial direction of the optical fiber sensing data, and process the image to be denoised according to the time sequence and the spatial direction to obtain the processed target image features, including: determining a plurality of one-dimensional image features corresponding to the image to be denoised according to the time sequence, splicing the plurality of one-dimensional image features to obtain a spliced ​​two-dimensional image; decomposing the two-dimensional image according to the spatial direction to obtain the target image features, wherein the one-dimensional image features refer to local feature data corresponding to the time feature scale of the image to be denoised; The target image determination module is used to determine the target image after the denoising of the image to be denoised according to the target image features.

9. A machine-readable storage medium having instructions stored thereon, characterized in that: When the instruction is executed by a processor, the processor is configured to perform the image denoising method according to any one of claims 1 to 6.

Images