Hologram generation method for coal mine degradation images

Abstract

The present application proposes a method, device, electronic device and storage medium for generating a hologram of a degraded image of a coal mine. The method includes: classifying degraded images of a coal mine to obtain image types of degraded images of a coal mine, enhancing the degraded images of a coal mine according to the image types to obtain target enhanced images of a coal mine, determining a hologram generation algorithm corresponding to the application scenario according to the application scenario corresponding to the target enhanced image of a coal mine, processing the target enhanced image of a coal mine according to the hologram generation algorithm, and generating a hologram of the target enhanced image of a coal mine in the application scenario, thereby enhancing the image quality of degraded images of different types and generating a hologram according to the hologram generation algorithm corresponding to the degraded image in different application scenarios, thereby obtaining a high-quality hologram of the degraded image of a coal mine.

Description

Technical Field

[0001] The present application relates to the technical field of digital image processing, and in particular to a method, device, electronic device and storage medium for generating a hologram of a coal mine degradation image. Background Art

[0002] At present, due to the poor quality of images collected by video surveillance equipment in coal mines, there are usually dust, mist, low illumination, blur, defocus, smear, noise and other problems, resulting in poor quality of image data collected by monitoring equipment, which is not conducive to safe production. Therefore, for the degraded images in coal mines, a high-quality hologram generation method for degraded images of coal mines is urgently needed. Summary of the invention

[0003] The present application proposes a method, device, electronic device and storage medium for generating a hologram of a coal mine degradation image.

[0004] The first aspect of the present application proposes a method for generating a hologram of a degraded coal mine image, the method comprising: classifying the degraded coal mine image to obtain the image type of the degraded coal mine image; performing image enhancement on the degraded coal mine image according to the image type to obtain an enhanced target coal mine enhanced image; determining a hologram generation algorithm corresponding to the application scenario according to the application scenario corresponding to the target coal mine enhanced image; processing the target coal mine enhanced image according to the hologram generation algorithm to generate a hologram of the target coal mine enhanced image in the application scenario.

[0005] In one embodiment of the present application, classifying the coal mine degraded image to obtain the image type of the coal mine degraded image includes: inputting the coal mine degraded image into a pre-trained classification model to obtain the image type of the coal mine degraded image through the classification model.

[0006] In one embodiment of the present application, the image enhancement is performed on the degraded coal mine image according to the image type to obtain an enhanced target coal mine enhanced image, including: acquiring an image enhancement algorithm corresponding to the image type; and performing image enhancement on the degraded coal mine image according to the image enhancement algorithm to obtain an enhanced target coal mine enhanced image.

[0007] In one embodiment of the present application, when the image enhancement algorithm is a dark channel enhancement algorithm, the image enhancement is performed on the degraded coal mine image according to the image enhancement algorithm to obtain an enhanced target coal mine enhanced image, including: acquiring image parameters of the degraded coal mine image; inputting the image parameters into the dark channel enhancement algorithm for calculation to obtain a dark channel image and a transmittance map of the degraded coal mine image; estimating the atmospheric light intensity corresponding to the degraded coal mine image according to the dark channel image of the degraded coal mine image; optimizing the edge values ​​in the transmittance map to obtain a target transmittance map with a preset lower limit value; determining a fog-free image of the degraded coal mine image based on the atmospheric light intensity corresponding to the degraded coal mine image, the dark channel image and the target transmittance; and using the fog-free image as the enhanced target coal mine enhanced image.

[0008] In one embodiment of the present application, the hologram generation algorithm is an angular spectrum diffraction algorithm or an adaptive weighted Geisberg-Saxon GS algorithm.

[0009] In one embodiment of the present application, when the hologram generation algorithm is an adaptive weighted GS algorithm, the target coal mine enhanced image is processed according to the hologram generation algorithm to generate a hologram of the target coal mine enhanced image in the application scenario, including: obtaining the plane wave constant amplitude and the initialization random phase of the target coal mine enhanced image; determining the current hologram of the target coal mine enhanced image according to the plane wave constant amplitude and the initialization random phase; iteratively processing the current hologram according to the adaptive weighted GS algorithm to obtain the initial hologram of the target coal mine enhanced image; using the initial hologram as the input for the next iterative processing until the number of iterations of the current hologram is equal to a preset iteration number threshold; using the target hologram obtained when the number of iterations is equal to the iteration number threshold as the hologram of the target coal mine enhanced image in the application scenario.

[0010] In one embodiment of the present application, the target coal mine enhanced image is iteratively processed according to the adaptive weighted GS algorithm to obtain an initial hologram of the target coal mine enhanced image, including: forward diffracting the current hologram onto an image plane to obtain a complex amplitude of the image plane; determining the spatial constraint amplitude of the image plane according to the amplitude in the complex amplitude of the image plane; determining the target complex amplitude of the image plane according to the spatial constraint amplitude and a random phase corresponding to the current hologram; and reversely diffracting the target complex amplitude to obtain an initial hologram of the target coal mine enhanced image.

[0011] The present application proposes a hologram generation method for coal mine degraded images, classifies the coal mine degraded images to obtain the image type of the coal mine degraded images, performs image enhancement on the coal mine degraded images according to the image type to obtain the enhanced target coal mine enhanced images, determines the hologram generation algorithm corresponding to the application scenario according to the application scenario corresponding to the target coal mine enhanced image, processes the target coal mine enhanced image according to the hologram generation algorithm, and generates a hologram of the target coal mine enhanced image in the application scenario. Thus, based on image enhancement of different types of degraded images and generating holograms according to the hologram generation algorithms corresponding to the degraded images in different application scenarios, the image quality of the coal mine degraded images is enhanced and a high-quality hologram of the coal mine degraded images is obtained.

[0012] The second aspect of the present application proposes a hologram generation device for a coal mine degraded image, the device comprising: a classification module, used to classify the coal mine degraded image to obtain the image type of the coal mine degraded image; an enhancement module, used to perform image enhancement on the coal mine degraded image according to the image type to obtain an enhanced target coal mine enhanced image; a determination module, used to determine the hologram generation algorithm corresponding to the application scenario according to the application scenario corresponding to the target coal mine enhanced image; a generation module, used to process the target coal mine enhanced image according to the hologram generation algorithm to generate a hologram of the target coal mine enhanced image in the application scenario.

[0013] In one embodiment of the present application, the classification module is specifically used to: input the coal mine degraded image into a pre-trained classification model to obtain the image type of the coal mine degraded image through the classification model.

[0014] In one embodiment of the present application, the enhancement module includes: a first acquisition unit, used to acquire an image enhancement algorithm corresponding to the image type; an enhancement unit, used to perform image enhancement on the coal mine degraded image according to the image enhancement algorithm to obtain an enhanced target coal mine enhanced image.

[0015] In one embodiment of the present application, when the image enhancement algorithm is a dark channel enhancement algorithm, the enhancement unit is specifically used to: obtain image parameters of the coal mine degraded image; input the image parameters into the dark channel enhancement algorithm for calculation to obtain a dark channel image and a transmittance map of the coal mine degraded image; estimate the atmospheric light intensity corresponding to the coal mine degraded image based on the dark channel image of the coal mine degraded image; optimize the edge values ​​in the transmittance map to obtain a target transmittance map with a preset lower limit value; determine a fog-free image of the coal mine degraded image based on the atmospheric light intensity corresponding to the coal mine degraded image, the dark channel image and the target transmittance; and use the fog-free image as the enhanced target coal mine enhanced image.

[0016] In one embodiment of the present application, the hologram generation algorithm is an angular spectrum diffraction algorithm or an adaptive weighted GS algorithm.

[0017] In one embodiment of the present application, when the hologram generation algorithm is an adaptive weighted GS algorithm, the generation module includes: a second acquisition unit, used to acquire the plane wave constant amplitude and the initialization random phase of the target coal mine enhanced image; a determination unit, used to determine the current hologram of the target coal mine enhanced image according to the plane wave constant amplitude and the initialization random phase; a processing unit, used to iteratively process the current hologram according to the adaptive weighted GS algorithm to obtain the initial hologram of the target coal mine enhanced image; an input unit, used to use the initial hologram as input for the next iterative processing until the number of iterations of the current hologram is equal to a preset iteration number threshold; a generation unit, used to use the target hologram obtained when the number of iterations is equal to the iteration number threshold as the hologram of the target coal mine enhanced image in the application scenario.

[0018] In one embodiment of the present application, the processing unit is specifically used to: forward diffract the current hologram onto an image plane to obtain a complex amplitude of the image plane; determine the spatially constrained amplitude of the image plane based on the amplitude in the complex amplitude of the image plane; determine the target complex amplitude of the image plane based on the spatially constrained amplitude and a random phase corresponding to the current hologram; and reversely diffract the target complex amplitude to obtain an initial hologram of the target coal mine enhanced image.

[0019] The present application proposes a hologram generation device for coal mine degraded images, which classifies coal mine degraded images to obtain image types of coal mine degraded images, performs image enhancement on the coal mine degraded images according to the image types to obtain enhanced target coal mine enhanced images, determines a hologram generation algorithm corresponding to the application scenario according to the application scenario corresponding to the target coal mine enhanced image, processes the target coal mine enhanced image according to the hologram generation algorithm, and generates a hologram of the target coal mine enhanced image in the application scenario. Thus, based on image enhancement of different types of degraded images and generating holograms according to the hologram generation algorithms corresponding to the degraded images in different application scenarios, the image quality of the coal mine degraded images is enhanced and a high-quality hologram of the coal mine degraded images is obtained.

[0020] The third aspect embodiment of the present application proposes an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the hologram generation method of the coal mine degradation image in the embodiment of the present application is implemented.

[0021] The fourth aspect of the present application provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the hologram generation method of the coal mine degradation image in the embodiment of the present application is implemented.

[0022] Other effects of the above optional manner will be described below in conjunction with specific embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0024] Figure 1 It is a schematic flow chart of a method for generating a hologram of a coal mine degradation image provided in an embodiment of the present application;

[0025] Figure 2 It is a flow chart of another method for generating a hologram of a coal mine degradation image provided in an embodiment of the present application;

[0026] Figure 3 It is a schematic diagram of a processing flow of enhancing a degraded coal mine image using a dark channel algorithm provided in an embodiment of the present application;

[0027] Figure 4 It is a flow chart of another method for generating a hologram of a coal mine degradation image provided in an embodiment of the present application;

[0028] Figure 5 It is a schematic diagram of a process of calculating a hologram based on an adaptive weighted GS algorithm provided in an embodiment of the present application;

[0029] Figure 6 It is a schematic diagram of a process for calculating a hologram based on an angular spectrum diffraction algorithm provided in an embodiment of the present application;

[0030] Figure 7 It is a structural schematic diagram of a hologram generating device for coal mine degradation images provided in an embodiment of the present application;

[0031] Figure 8 It is a structural schematic diagram of another hologram generating device for coal mine degradation images provided in an embodiment of the present application;

[0032] Fig. 9 It is a block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0033] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0034] The following describes the method, device and electronic device for generating a hologram of a coal mine degradation image according to an embodiment of the present application with reference to the accompanying drawings.

[0035] Figure 1 It is a flow chart of a method for generating a hologram of a degraded coal mine image provided in an embodiment of the present application. It should be noted that the executor of the method for generating a hologram of a degraded coal mine image provided in this embodiment is a hologram generating device for a degraded coal mine image, which can be implemented by software and / or hardware. The hologram generating device for a degraded coal mine image in this embodiment can be configured in an electronic device, and the electronic device in this embodiment can include a server. This embodiment does not specifically limit the electronic device.

[0036] Figure 1 It is a flow chart of a method for generating a hologram of a coal mine degradation image provided in an embodiment of the present application.

[0037] like Figure 1 As shown, the method for generating a hologram of a coal mine degradation image may include:

[0038] Step 101: classify the degraded coal mine image to obtain the image type of the degraded coal mine image.

[0039] In some embodiments, one implementation method for classifying coal mine degraded images to obtain image types of coal mine degraded images may be to input the coal mine degraded images into a pre-trained classification model to obtain the image types of the coal mine degraded images through the classification model, thereby improving the classification efficiency of coal mine degraded images.

[0040] Among them, the historical coal mine degradation images can be manually classified and labeled to obtain historical coal mine degradation images with labels, and the classification model corresponding to the coal mine degradation images can be obtained by training the classifier.

[0041] In some embodiments, the image types of coal mine degradation images may include dust and fog images, water mist images, low illumination images, strong noise images, jitter and blurred images, and out-of-focus images, but are not limited to these. This embodiment does not specifically limit this.

[0042] Step 102: performing image enhancement on the degraded coal mine image according to the image type to obtain an enhanced target coal mine enhanced image.

[0043] In some embodiments, for different image types, multiple different image enhancement algorithms may be selected to process the degraded coal mine images, so as to improve the enhancement effect of the degraded coal mine images corresponding to each image type.

[0044] Step 103, according to the application scenario corresponding to the target coal mine enhanced image, determine the hologram generation algorithm corresponding to the application scenario.

[0045] In some embodiments, the application scenarios corresponding to the target coal mine enhanced image may include scenarios corresponding to real-time or rapid generation of holograms, and scenarios corresponding to generation of high-quality holograms, but are not limited thereto.

[0046] In some embodiments, in the case of real-time or rapid generation of a hologram corresponding to a scene, in order to achieve real-time and rapid generation of a corresponding hologram for a target coal mine enhanced image, an angular spectrum diffraction algorithm may be used as a hologram generation method for the target coal mine enhanced image.

[0047] In other embodiments, in order to improve the quality of the corresponding hologram generated for the target coal mine enhanced image in the case of generating a high-quality hologram, an adaptive weighted Gerchberg-Saxton (GS) algorithm may be used as a hologram generation method for the target coal mine enhanced image.

[0048] Step 104, processing the target coal mine enhanced image according to a hologram generation algorithm to generate a hologram of the target coal mine enhanced image in an application scenario.

[0049] In some embodiments, when the hologram generation algorithm is an angular spectrum diffraction algorithm, the angular spectrum diffraction algorithm can be used to process the target coal mine enhanced image to quickly generate a hologram corresponding to the target coal mine enhanced image.

[0050] In other embodiments, when the hologram generation algorithm is an adaptive weighted GS algorithm, the adaptive weighted GS algorithm can be used to process the target coal mine enhanced image to generate a high-quality hologram corresponding to the target coal mine enhanced image.

[0051] The present application proposes a hologram generation method for coal mine degraded images, classifies the coal mine degraded images to obtain the image type of the coal mine degraded images, performs image enhancement on the coal mine degraded images according to the image type to obtain the enhanced target coal mine enhanced images, determines the hologram generation algorithm corresponding to the application scenario according to the application scenario corresponding to the target coal mine enhanced image, processes the target coal mine enhanced image according to the hologram generation algorithm, and generates a hologram of the target coal mine enhanced image in the application scenario. Thus, based on image enhancement of different types of degraded images and generating holograms according to the hologram generation algorithms corresponding to the degraded images in different application scenarios, the image quality of the coal mine degraded images is enhanced and a high-quality hologram of the coal mine degraded images is obtained.

[0052] For a clear understanding of this application, the following Figure 2 An exemplary description is given of the processing procedure of a method for generating a hologram of a coal mine degradation image, wherein this embodiment is a further refinement or expansion of the above-mentioned embodiment.

[0053] like Figure 2 As shown, the method for generating a hologram of a coal mine degradation image may include:

[0054] Step 201 , classifying the degraded coal mine image to obtain the image type of the degraded coal mine image.

[0055] It should be noted that, for the specific implementation of step 201, reference may be made to the relevant description in the above embodiment.

[0056] Step 202: Obtain an image enhancement algorithm corresponding to the image type.

[0057] In some embodiments, the image type may include multiple types. This embodiment takes a low-light image, a strong noise image, a blurred image, and a dust or water mist image as examples for description, and the details are as follows:

[0058] First, when processing low-light images, since the color of low-light images is not affected by light intensity and has consistency, a color constancy perception (Retinex, retina-cortex) algorithm can be used to enhance the low-light images.

[0059] Secondly, when processing images with strong noise, classical image filtering algorithms can be used to enhance the images with strong noise.

[0060] Among them, the classic image filtering algorithm may include but is not limited to Gaussian filtering, median filtering, mean filtering, local mean square error filtering and bilateral filtering, and this embodiment does not make specific limitations on this.

[0061] In an embodiment of the present application, a bilateral filtering algorithm can be used to enhance a strong noise image, thereby taking into account the spatial information and grayscale similarity of the strong noise image, effectively removing noise while retaining the details of the strong noise image, and reducing information loss at the edge of the strong noise image.

[0062] Thirdly, when processing blurred images, Wiener filtering can be used to deblur the model image.

[0063] Fourthly, when processing dust or water mist images, since the processed dust or water mist images are degraded images of coal mines, which do not include the sky area, the dark channel enhancement algorithm can be used to enhance the dust or water mist images, thereby improving the enhancement effect of the dust or water mist images.

[0064] In some embodiments, histogram equalization, Retinex algorithm, wavelet transform, homomorphic filtering, single image defogging algorithm, single image defogging algorithm, fast image restoration algorithm, Bayesian defogging algorithm can also be used to process dust fog or water fog images, but are not limited to these.

[0065] Step 203: perform image enhancement on the degraded coal mine image according to an image enhancement algorithm to obtain an enhanced target coal mine enhanced image.

[0066] In some embodiments, when the image enhancement algorithm is a dark channel enhancement algorithm, an implementation method of performing image enhancement on a degraded coal mine image according to the image enhancement algorithm to obtain an enhanced target coal mine enhanced image may be to obtain image parameters of the degraded coal mine image, input the image parameters into the dark channel enhancement algorithm for calculation to obtain a dark channel image and a transmittance map of the degraded coal mine image, estimate the atmospheric light intensity corresponding to the degraded coal mine image based on the dark channel image of the degraded coal mine image, optimize the edge values ​​in the transmittance map to obtain a target transmittance map with a preset lower limit value, determine a fog-free image of the degraded coal mine image based on the atmospheric light intensity, dark channel image and target transmittance map corresponding to the degraded coal mine image, and use the fog-free image as the enhanced target coal mine enhanced image.

[0067] Specifically, Figure 3 As shown, Figure 31 is a schematic diagram of a processing flow of enhancing a degraded coal mine image using a dark channel algorithm provided in an embodiment of the present application. A degraded coal mine image with dust or mist is input, and a dark channel image is calculated based on image parameters of the degraded coal mine image. The dark channel image J dark The calculation method can be:

[0068]

[0069] J dark →0

[0070] Among them, x represents the coordinate of the pixel point, Liang shows the dark primary color of each channel of the fog-free color image, Ω(x) represents the local area centered on pixel x, excluding the sky area, c represents the red R, green G, and blue B channels, J dark The intensity is very low and close to 0, and the transmittance map is calculated based on the image parameters of the coal mine degradation image. The calculation method can be:

[0071]

[0072] Among them, ω is the correction factor, I(x) represents the dust fog image, A represents the atmospheric light intensity corresponding to the coal mine degradation image, and then the guided filtering algorithm is used to correct the transmittance image. To optimize edge values, you can set a transmittance map The lower limit value t o , so that when hour, Among them, t o It can be 0.1, so as to obtain a target transmittance map with a preset lower limit value, and then according to the dark channel image J dark The atmospheric light intensity A corresponding to the coal mine degradation image is estimated, so as to calculate the enhanced image of the target coal mine without fog. The calculation method of the enhanced image of the target coal mine without fog J(x) can be:

[0073]

[0074] Step 204, according to the application scenario corresponding to the target coal mine enhanced image, determine the hologram generation algorithm corresponding to the application scenario.

[0075] Step 205, processing the target coal mine enhanced image according to the hologram generation algorithm to generate a hologram of the target coal mine enhanced image in the application scenario.

[0076] The present application proposes a hologram generation method for coal mine degraded images, classifies the coal mine degraded images to obtain image types of the coal mine degraded images, obtains an image enhancement algorithm corresponding to the image type, performs image enhancement on the coal mine degraded images according to the image enhancement algorithm to obtain an enhanced target coal mine enhanced image, determines a hologram generation algorithm corresponding to the application scenario according to the application scenario corresponding to the target coal mine enhanced image, processes the target coal mine enhanced image according to the hologram generation algorithm, and generates a hologram of the target coal mine enhanced image in the application scenario. Thus, based on image enhancement of different types of degraded images and according to the hologram generation algorithm corresponding to the degraded images in different application scenarios, a high-quality and fast-converging hologram is obtained to ensure safe production in coal mines.

[0077] It can be understood that, when the hologram generation algorithm is an adaptive weighted GS algorithm, the embodiment of the present application provides a flow chart of a method for generating a hologram of a coal mine degradation image, such as Figure 4 shown.

[0078] Step 401 , classifying the degraded coal mine image to obtain the image type of the degraded coal mine image.

[0079] Step 402: performing image enhancement on the degraded coal mine image according to the image type to obtain an enhanced target coal mine enhanced image.

[0080] It should be noted that, for the specific implementation of step 401 to step 402, reference may be made to the relevant description in the above embodiment.

[0081] Step 403, according to the application scenario corresponding to the target coal mine enhanced image, determine the hologram generation algorithm corresponding to the application scenario.

[0082] In some embodiments, after obtaining the enhanced image of the target coal mine and before using the angular spectrum diffraction algorithm or the adaptive weighted GS algorithm to calculate the hologram, it is necessary to decompose the full-color target coal mine enhanced image into a red channel R, a blue channel B, and a green channel G according to the principle of three primary colors, and then calculate the hologram of each color channel, that is, a single-channel hologram, and then calculate the single-channel hologram according to the hologram algorithm of the target coal mine enhanced image.

[0083] Step 404, obtaining the plane wave constant amplitude and initializing the random phase of the target coal mine enhanced image. In some embodiments, the plane wave constant amplitude A of the target coal mine enhanced image can be obtained. o , and initialize the random phase φ o (x o ,y o ), where the plane wave constant amplitude A oIt can be a matrix of all 1s, but is not limited to this.

[0084] Step 405, determining the current hologram of the target coal mine enhanced image according to the plane wave constant amplitude and the initialization random phase.

[0085] In some embodiments, according to the plane wave constant amplitude A o and initialize the random phase φ o (x o ,y o ), determine the current hologram U of the target coal mine enhanced image o (x o ,y o ), where the current hologram U o (x o ,y o ) can be calculated as:

[0086] U0(x0,y0)=A0exp[jφ0(x0,y0)]

[0087] Step 406, iteratively process the current hologram according to the adaptive weighted GS algorithm to obtain an initial hologram of the target coal mine enhanced image.

[0088] In some embodiments, an implementation method of iteratively processing the current hologram according to the adaptive weighted GS algorithm to obtain an initial hologram of the target coal mine enhanced image is: forward diffracting the current hologram onto the image plane to obtain the complex amplitude of the image plane, determining the spatial constraint amplitude of the image plane based on the amplitude in the complex amplitude of the image plane, determining the target complex amplitude of the image plane based on the spatial constraint amplitude and the random phase corresponding to the current hologram, and reversely diffracting the target complex amplitude to obtain the initial hologram of the target coal mine enhanced image.

[0089] Step 407, using the initial hologram as input for the next iterative process until the number of iterations of the current hologram is equal to a preset iteration number threshold.

[0090] Step 408, taking the target hologram obtained when the number of iterations is equal to the iteration number threshold as the hologram of the target coal mine enhanced image in the application scenario.

[0091] In summary, the embodiment of the present application also provides a schematic diagram of a process for calculating a hologram based on an adaptive weighted GS algorithm, such as Figure 5 As shown, specifically, the plane wave constant amplitude A can be o and initialize the random phase φ o (x o ,y o ), determine the current iteration number n corresponding to the coal mine degradation image, and the hologram U' when n = 0o (x o ,y o ),in:

[0092] U′0(x0,y0)=A0exp[jφ0(x0,y0)]

[0093] For the holographic surface U in the nth cycle n (x o ,y o ), and take its phase as φ o (x o ,y o ). Use A o Replace its amplitude. Complex amplitude U' n (x o ,y o ) can be calculated as:

[0094] U′ n (x0, y0) = A0exp[jφ n (x0, y0)]

[0095] In the current iteration of the hologram U' n (x o ,y o ) is diffracted forward onto the image plane by Fraunhofer to obtain the complex amplitude U of the image plane. n (x, y), complex amplitude U n (x, y) can be calculated as:

[0096]

[0097] The image plane is the observation plane (image plane) with a distance z from the hologram in the adaptive weighted GS algorithm, and then according to the complex amplitude U n The amplitude A1 in (x, y) determines the spatial constraint amplitude A2 of the image plane. The calculation method of the spatial constraint amplitude A2 can be:

[0098]

[0099] Among them, T is the amplitude of the target coal mine enhanced image, so according to the spatial domain constraint amplitude A2 and the random phase φ corresponding to the current holographic surface n (x, y), determine the target complex amplitude U' of the image plane n (x, y), target complex amplitude U' n (x, y) can be calculated as:

[0100] U′ n (x, y) = A2exp[jφ n (x, y)]

[0101] Finally, for the target complex amplitude U' n (x, y) is subjected to Fraunhofer inverse diffraction to obtain the initial hologram U of the target coal mine enhanced image n+1 (x o ,y o ), initial hologram U n+1 (x o ,y o ) can be calculated as:

[0102]

[0103] After obtaining the initial hologram, the iteration can be continued, and the Fraunhofer forward diffraction and Fraunhofer reverse diffraction can be repeatedly performed until the number of iterations n is equal to the iteration number threshold N, so as to obtain the target hologram U N (x o ,y o ), and as the holographic U in the application scenario of the target coal mine enhanced image N (x o ,y o ), and output the hologram U N (x o ,y o ) corresponds to the pure phase hologram.

[0104] The present application proposes a hologram generation method for coal mine degraded images, classifies coal mine degraded images to obtain image types of coal mine degraded images, enhances coal mine degraded images according to image types to obtain enhanced target coal mine enhanced images, determines a hologram generation algorithm corresponding to an application scenario according to an application scenario corresponding to the target coal mine enhanced image, obtains a plane wave constant amplitude and an initialization random phase of the target coal mine enhanced image, determines a current hologram of the target coal mine enhanced image according to the plane wave constant amplitude and the initialization random phase, iterates the current hologram according to an adaptive weighted GS algorithm to obtain an initial hologram of the target coal mine enhanced image, uses the initial hologram as input for the next iterative processing until the number of iterations of the current hologram is equal to a preset iteration number threshold, and uses the target hologram obtained when the number of iterations is equal to the iteration number threshold as the hologram of the target coal mine enhanced image in the application scenario. Thus, based on image enhancement of different types of degraded images and according to the hologram generation algorithm corresponding to the degraded image in different application scenarios, a high-quality hologram is obtained to ensure safe production in coal mines.

[0105] In some embodiments, when the hologram generation algorithm is an angular spectrum diffraction algorithm, the embodiment of the present application provides a flow chart of calculating a hologram based on the angular spectrum diffraction algorithm, such as Figure 6As shown, specifically, a single-channel dehazed image, wavelength, reconstruction distance and pixel size of the target coal mine enhanced image, as well as an initialized random phase corresponding to the target coal mine enhanced image are obtained, and then the hologram of the target coal mine enhanced image is calculated through an angular spectrum diffraction algorithm, and a pure phase hologram corresponding to the hologram is output.

[0106] Figure 7 It is a structural schematic diagram of a hologram generation device for coal mine degradation images provided in an embodiment of the present application.

[0107] like Figure 7 As shown, the hologram generation device 700 of the coal mine degradation image includes: a classification module 701, an enhancement module 702, a determination module 703 and a generation module 704, wherein:

[0108] The classification module 701 is used to classify the degraded coal mine image to obtain the image type of the degraded coal mine image.

[0109] The enhancement module 702 is used to perform image enhancement on the degraded coal mine image according to the image type to obtain an enhanced target coal mine enhanced image.

[0110] The determination module 703 is used to determine the hologram generation algorithm corresponding to the application scenario according to the application scenario corresponding to the target coal mine enhanced image.

[0111] The generation module 704 is used to process the target coal mine enhanced image according to the hologram generation algorithm to generate a hologram of the target coal mine enhanced image in an application scenario.

[0112] The present application proposes a hologram generation device for coal mine degraded images, which classifies coal mine degraded images to obtain image types of coal mine degraded images, performs image enhancement on the coal mine degraded images according to the image types to obtain enhanced target coal mine enhanced images, determines a hologram generation algorithm corresponding to the application scenario according to the application scenario corresponding to the target coal mine enhanced image, processes the target coal mine enhanced image according to the hologram generation algorithm, and generates a hologram of the target coal mine enhanced image in the application scenario. Thus, based on image enhancement of different types of degraded images and generating holograms according to the hologram generation algorithms corresponding to the degraded images in different application scenarios, the image quality of the coal mine degraded images is enhanced and a high-quality hologram of the coal mine degraded images is obtained.

[0113] In one embodiment of the present application, Figure 8 is a schematic diagram of the structure of another hologram generating device for coal mine degradation images provided in an embodiment of the present application, such as Figure 8As shown, the hologram generation device 800 of the coal mine degradation image can also include: a classification module 801, an enhancement module 802, a determination module 803 and a generation module 804, wherein the enhancement module 802 includes a first acquisition unit 8021 and an enhancement unit 8022, and the generation module 804 includes a second acquisition unit 8041, a determination unit 8042, a processing unit 8043, an input unit 8044 and a generation unit 8045.

[0114] For detailed description of the classification module 801, the enhancement module 802, the determination module 803 and the generation module 804, please refer to Figure 7 The description of the classification module 701, the enhancement module 702, the determination module 703 and the generation module 704 in the illustrated embodiment will not be described here.

[0115] In one embodiment of the present application, Figure 8 As shown, the classification module 801 is specifically used for:

[0116] The coal mine degraded images are input into a pre-trained classification model to obtain the image type of the coal mine degraded images through the classification model.

[0117] In one embodiment of the present application, Figure 8 As shown, the enhancement module 802 includes:

[0118] The first acquisition unit 8021 is used to acquire an image enhancement algorithm corresponding to the image type.

[0119] The enhancement unit 8022 is used to perform image enhancement on the degraded coal mine image according to the image enhancement algorithm to obtain an enhanced target coal mine enhanced image.

[0120] In one embodiment of the present application, Figure 8 As shown, when the image enhancement algorithm is a dark channel enhancement algorithm, the enhancement unit 8022 is specifically used to:

[0121] Get the image parameters of coal mine degradation images.

[0122] The image parameters are input into the dark channel enhancement algorithm for calculation to obtain the dark channel image and transmittance map of the coal mine degradation image.

[0123] According to the dark channel image of the coal mine degradation image, the atmospheric light intensity corresponding to the coal mine degradation image is estimated.

[0124] The edge values ​​in the transmittance map are optimized to obtain a target transmittance map with a preset lower limit value.

[0125] Based on the atmospheric light intensity, dark channel image and target transmittance corresponding to the coal mine degraded image, the fog-free image of the coal mine degraded image is determined.

[0126] The fog-free image is used as the enhanced target coal mine enhanced image.

[0127] In one embodiment of the present application, the hologram generation algorithm is an angular spectrum diffraction algorithm or an adaptive weighted GS algorithm.

[0128] In one embodiment of the present application, Figure 8 As shown, when the hologram generation algorithm is an adaptive weighted GS algorithm, the generation module 804 includes:

[0129] The second acquisition unit 8041 is used to acquire the plane wave constant amplitude and initialize the random phase of the target coal mine enhanced image.

[0130] The determination unit 8042 is used to determine the current hologram of the target coal mine enhanced image according to the plane wave constant amplitude and the initialization random phase.

[0131] The processing unit 8043 is used to iteratively process the current hologram according to the adaptive weighted GS algorithm to obtain an initial hologram of the target coal mine enhanced image.

[0132] The input unit 8044 is used to use the initial hologram as the input for the next iterative processing until the number of iterations of the current hologram is equal to a preset iteration number threshold.

[0133] The generating unit 8045 is used to use the target hologram obtained when the number of iterations is equal to the iteration number threshold as the hologram of the target coal mine enhanced image in the application scenario.

[0134] In one embodiment of the present application, Figure 8 As shown, the processing unit 8043 is specifically used for:

[0135] The current hologram is forward diffracted onto the image plane to obtain the complex amplitude of the image plane.

[0136] The spatial domain constraint amplitude of the image plane is determined according to the amplitude in the complex amplitude of the image plane.

[0137] The target complex amplitude of the image plane is determined according to the spatial constraint amplitude and the random phase corresponding to the current holographic surface.

[0138] The target complex amplitude is inversely diffracted to obtain the initial hologram of the target coal mine enhanced image.

[0139] The present application proposes a hologram generation device for coal mine degraded images, which classifies coal mine degraded images to obtain image types of coal mine degraded images, performs image enhancement on the coal mine degraded images according to the image types to obtain enhanced target coal mine enhanced images, determines a hologram generation algorithm corresponding to the application scenario according to the application scenario corresponding to the target coal mine enhanced image, processes the target coal mine enhanced image according to the hologram generation algorithm, and generates a hologram of the target coal mine enhanced image in the application scenario. Thus, based on image enhancement of different types of degraded images and generating holograms according to the hologram generation algorithms corresponding to the degraded images in different application scenarios, the image quality of the coal mine degraded images is enhanced and a high-quality hologram of the coal mine degraded images is obtained.

[0140] like Fig. 9 , which is a block diagram of an electronic device according to an embodiment of the present application.

[0141] like Fig. 9 As shown, the electronic device includes:

[0142] A memory 901 , a processor 902 , and computer instructions stored in the memory 901 and executable on the processor 902 .

[0143] When the processor 902 executes the instructions, the hologram generation method of the coal mine degradation image provided in the above embodiment is implemented.

[0144] Furthermore, the electronic device further comprises:

[0145] The communication interface 903 is used for communication between the memory 901 and the processor 902 .

[0146] The memory 901 is used to store computer instructions that can be executed on the processor 902 .

[0147] The memory 901 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0148] The processor 902 is used to implement the hologram generation method of the coal mine degradation image of the above embodiment when executing the program.

[0149] If the memory 901, the processor 902 and the communication interface 903 are implemented independently, the communication interface 903, the memory 901 and the processor 902 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Fig. 9 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0150] Optionally, in a specific implementation, if the memory 901, the processor 902 and the communication interface 903 are integrated on a chip, the memory 901, the processor 902 and the communication interface 903 can communicate with each other through an internal interface.

[0151] The processor 902 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0152] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0153] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0154] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A method for generating a hologram of a coal mine degradation image, characterized in that: The method comprises: Classifying the coal mine degraded image to obtain an image type of the coal mine degraded image; According to the image type, the degraded coal mine image is enhanced to obtain an enhanced target coal mine enhanced image; According to the application scenario corresponding to the target coal mine enhanced image, determining a hologram generation algorithm corresponding to the application scenario; Processing the target coal mine enhanced image according to the hologram generation algorithm to generate a hologram of the target coal mine enhanced image in the application scenario; Wherein, in the case of a scene corresponding to a hologram being generated in real time or quickly, an angular spectrum diffraction algorithm is used as a hologram generation method for a target coal mine enhanced image; In the case of generating high-quality holograms, the adaptive weighted Geisberg-Saxon algorithm is used as the hologram generation method for the target coal mine enhanced image.

2. The method according to claim 1, characterized in that: The classifying the coal mine degraded image to obtain the image type of the coal mine degraded image includes: The coal mine degraded image is input into a pre-trained classification model to obtain the image type of the coal mine degraded image through the classification model.

3. The method according to claim 1, characterized in that According to the image type, the degraded coal mine image is enhanced to obtain an enhanced target coal mine enhanced image, including: Acquire an image enhancement algorithm corresponding to the image type; According to the image enhancement algorithm, the degraded coal mine image is enhanced to obtain an enhanced target coal mine enhanced image.

4. The method according to claim 3, characterized in that: In the case where the image enhancement algorithm is a dark channel enhancement algorithm, performing image enhancement on the degraded coal mine image according to the image enhancement algorithm to obtain an enhanced target coal mine enhanced image includes: Acquire image parameters of the coal mine degradation image; Inputting the image parameters into the dark channel enhancement algorithm for calculation to obtain a dark channel image and a transmittance map of the coal mine degradation image; estimating the atmospheric light intensity corresponding to the coal mine degradation image according to the dark channel image of the coal mine degradation image; Optimizing edge values ​​in the transmittance map to obtain a target transmittance map with a preset lower limit value; Determining a fog-free image of the coal mine degraded image based on the atmospheric light intensity corresponding to the coal mine degraded image, the dark channel image, and the target transmittance; The fog-free image is used as the enhanced target coal mine enhanced image.

5. The method according to claim 1, characterized in that In the case where the hologram generation algorithm is an adaptive weighted GS algorithm, the target coal mine enhanced image is processed according to the hologram generation algorithm to generate a hologram of the target coal mine enhanced image in the application scenario, including: Acquiring the plane wave constant amplitude and initialization random phase of the target coal mine enhanced image; Determining a current hologram of the target coal mine enhanced image according to the plane wave constant amplitude and the initialization random phase; Iteratively processing the current hologram according to the adaptive weighted GS algorithm to obtain an initial hologram of the target coal mine enhanced image; Using the initial hologram as input for the next iterative process until the number of iterations of the current hologram is equal to a preset iteration number threshold; The target hologram obtained when the number of iterations is equal to the iteration number threshold is used as the hologram of the target coal mine enhanced image in the application scenario.

6. The method according to claim 5, characterized in that The iterative processing of the target coal mine enhanced image according to the adaptive weighted GS algorithm to obtain an initial hologram of the target coal mine enhanced image includes: Forward diffracting the current hologram onto an image plane to obtain a complex amplitude of the image plane; Determining a spatial domain constraint amplitude of the image plane according to an amplitude in the complex amplitude of the image plane; Determining a target complex amplitude of the image plane according to the spatial domain constraint amplitude and a random phase corresponding to the current hologram; The target complex amplitude is inversely diffracted to obtain an initial hologram of the target coal mine enhanced image.

7. A hologram generation device for coal mine degradation images, characterized in that: The device comprises: A classification module, used for classifying the coal mine degraded image to obtain the image type of the coal mine degraded image; An enhancement module, used for performing image enhancement on the degraded coal mine image according to the image type to obtain an enhanced target coal mine enhanced image; A determination module, used to determine a hologram generation algorithm corresponding to the application scenario according to the application scenario corresponding to the target coal mine enhanced image; A generating module, used for processing the target coal mine enhanced image according to the hologram generating algorithm, and generating a hologram of the target coal mine enhanced image in the application scenario; Wherein, in the case of a scene corresponding to a hologram being generated in real time or quickly, an angular spectrum diffraction algorithm is used as a hologram generation method for a target coal mine enhanced image; In the case of generating high-quality holograms, the adaptive weighted Geisberg-Saxon algorithm is used as the hologram generation method for the target coal mine enhanced image.

8. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for generating a hologram of a coal mine degradation image as described in any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method for generating a hologram of a coal mine degradation image as described in any one of claims 1 to 6 is implemented.

Images