Ground penetrating radar image enhancement method and device, electronic equipment and storage medium
By adopting a transformation strategy-based image enhancement method in ground penetrating radar, the problem of weak target signals and high background noise in ground penetrating radar is solved, and more accurate underground target detection is achieved.
Patent Information
- Application Number
- CN202410972277.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-19
- Publication Date
- 2024-11-26
AI Technical Summary
When ground penetrating radar scans the underground, the target signal is weak and the background noise is high, making it difficult to accurately detect underground targets.
Image enhancement methods based on preset transformation strategies and inverse transformation strategies, including normalization processing, nonlinear transformation, discrete cosine transformation, logarithmic transformation, histogram matching and inverse transformation processing, are adopted to enhance the return signal and attenuate the background noise.
Effectively enhance the return signal, reduce background noise, and more accurately detect underground targets.
Smart Images

Figure CN119027320A_ABST
Abstract
Description
Technical Field
[0001] The present application belongs to the field of image enhancement technology, and in particular, relates to a ground penetrating radar image enhancement method, device, electronic equipment and storage medium. Background Art
[0002] Ground Penetrating Radar (GPR) is a commonly used instrument for non-invasive underground detection. In urban areas, ground penetrating radar can not only detect and characterize hazards, but also monitor underground resources, including underground infrastructure, historical sites, and agricultural detection. GPR provides characteristics of shallow underground layers and is particularly suitable for detecting non-metallic objects.
[0003] The basic principle is that when an ultra-wideband (UWB) pulse signal propagates underground, if the dielectric constant of the underground medium is uniform and there are no other objects, then there will be no return signal except the component returned from the surface. However, due to the existence of various types of dielectric objects underground, which are the targets we want to detect, there is discontinuity in the underground dielectric constant, and the pulse signal is reflected or refracted, and a corresponding return signal is obtained. By calculating based on the return signal, the corresponding characteristics of the underground object can be obtained.
[0004] However, since actual ground penetrating radar signals are contaminated by various types of noise, or when the target is a small object, the return signal is often weak and contains more noise, making it difficult to accurately detect underground targets. Summary of the invention
[0005] In view of this, the present application aims to propose a ground penetrating radar image enhancement method, device, electronic device and storage medium to solve the problem that the target signal scanned by the ground penetrating radar is weak and the background noise is large, making it difficult to accurately detect underground targets.
[0006] To achieve the above purpose, the technical solution of this application is implemented as follows:
[0007] In a first aspect, the present application provides a ground penetrating radar image enhancement method, comprising:
[0008] Normalizing an input image, wherein the input image is a scanned image collected by a ground penetrating radar;
[0009] Performing a transformation process on the normalized image based on a preset first transformation strategy to obtain a target image, and performing a transformation process on the normalized image based on a preset second transformation strategy to obtain a reference image;
[0010] Performing histogram matching on the target image and the reference image to obtain a matching result;
[0011] The matching result is subjected to inverse transformation processing based on a preset inverse transformation strategy to obtain an output image.
[0012] Furthermore, the transforming process is performed on the normalized image based on a preset first transformation strategy to obtain a target image, including:
[0013] Performing a nonlinear transformation on the normalized image according to a nonlinear transformation algorithm to obtain a transformed first intermediate image, and performing a two-dimensional discrete cosine transform on the first intermediate image to obtain a transformed second intermediate image;
[0014] Performing logarithmic transformation on the second intermediate image according to a logarithmic transformation algorithm to obtain a transformed third intermediate image, and using the third intermediate image as a target image.
[0015] Furthermore, the transforming process is performed on the normalized image based on a preset second transformation strategy to obtain a reference image, including:
[0016] Perform a two-dimensional discrete cosine transform on the normalized image to obtain a transformed fourth intermediate image, perform a logarithmic transform on the fourth intermediate image according to a logarithmic transform algorithm to obtain a transformed fourth intermediate image, and use the fourth intermediate image as a reference image.
[0017] Furthermore, performing histogram matching on the target image and the reference image to obtain a matching result includes:
[0018] Calculating histograms of the target image and the reference image;
[0019] Performing cumulative probability density function calculation on the histogram of the target image and the histogram of the reference image respectively;
[0020] Each pixel value of the target image is mapped to the corresponding pixel value on the reference image through a lookup table to obtain a corresponding matching result.
[0021] Furthermore, the inverse transformation process is performed on the matching result based on a preset inverse transformation strategy to obtain an output image, including:
[0022] Performing an inverse logarithmic transformation on the matching result according to an inverse logarithmic transformation algorithm, performing phase recovery on the inversely transformed fifth intermediate image, and performing a two-dimensional inverse discrete cosine transform on the image result after phase recovery to obtain an inverse transformation result;
[0023] The inverse transformation result is normalized to obtain a final output image.
[0024] In the second aspect, based on the same inventive concept, the present application also provides a ground penetrating radar image enhancement device, comprising:
[0025] A preprocessing module is configured to perform normalization processing on an input image, wherein the input image is a scanned image collected by a ground penetrating radar;
[0026] A transformation processing module is configured to perform transformation processing on the normalized image based on a preset first transformation strategy to obtain a target image, and to perform transformation processing on the normalized image based on a preset second transformation strategy to obtain a reference image;
[0027] A matching module is configured to perform histogram matching on the target image and the reference image to obtain a matching result;
[0028] The output module is configured to perform inverse transformation processing on the matching result based on a preset inverse transformation strategy to obtain an output image.
[0029] In a third aspect, based on the same inventive concept, the present application also provides an electronic device, comprising 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 described in the first aspect is implemented.
[0030] In a fourth aspect, based on the same inventive concept, the present application also provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the method described in the first aspect.
[0031] Compared with the prior art, the ground penetrating radar image enhancement method, device, electronic device and storage medium described in this application have the following beneficial effects:
[0032] The ground penetrating radar image enhancement method, device, electronic device and storage medium described in the present application are based on an image enhancement method that combines a preset transformation strategy and an inverse transformation strategy. It can enhance the return signal and attenuate the background area signal to solve the problems of weak target signal and large background noise in the ground penetrating radar scanning image, and can detect underground targets more accurately. BRIEF DESCRIPTION OF THE DRAWINGS
[0033] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:
[0034] Figure 1 This is a flow chart of the ground penetrating radar image enhancement method described in an embodiment of the present application;
[0035] Figure 2 This is a specific method flow chart of the ground penetrating radar image enhancement method described in the embodiment of the present application;
[0036] Figure 3 This is a schematic diagram of an output image with λ=0.4 described in the first embodiment of the present application;
[0037] Figure 4 This is a schematic diagram of an output image with λ=0.6 described in Embodiment 1 of the present application;
[0038] Figure 5 This is a schematic diagram of an output image with λ=0.8 described in the first embodiment of the present application;
[0039] Figure 6 This is a schematic diagram of an output image when λ=1 according to the first embodiment of the present application;
[0040] Figure 7 This is a schematic diagram of an output image with λ=1.2 described in the first embodiment of the present application;
[0041] Figure 8 This is a schematic diagram of direct wave interference described in an embodiment of the present application;
[0042] Fig. 9 This is a schematic diagram of an output image when δ=1 according to an embodiment of the present application;
[0043] Fig.10 This is a schematic diagram of an output image when δ=1.4 described in an embodiment of the present application;
[0044] Fig.11 This is a schematic diagram of an output image when δ=2 according to an embodiment of the present application;
[0045] Fig.12 This is a schematic diagram of an output image when δ=2.4 described in an embodiment of the present application;
[0046] Fig.13 This is a schematic diagram of an output image when δ=2.5 described in an embodiment of the present application;
[0047] Fig.14 This is a schematic diagram of an output image when δ=2.6 described in an embodiment of the present application;
[0048] Fig.15 This is a schematic diagram of an output image when δ=2.8 described in an embodiment of the present application;
[0049] Fig.16 This is a graph showing image quality assessment using the BRISQUE algorithm described in an embodiment of the present application;
[0050] Fig.17 This is a graph showing image quality assessment using the PIQE algorithm described in an embodiment of the present application;
[0051] Fig.18 This is a graph showing image quality assessment using the NIQE algorithm described in an embodiment of the present application;
[0052] Fig.19 This is a schematic diagram of the structure of the ground penetrating radar image enhancement device described in an embodiment of the present application;
[0053] Fig. 20 This is a schematic diagram of the hardware structure of the electronic device described in the embodiment of the present application. DETAILED DESCRIPTION
[0054] In order to make the objectives, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below in combination with specific embodiments and with reference to the accompanying drawings.
[0055] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present application should be the usual meanings understood by people with ordinary skills in the field to which the present application belongs. The "first", "second" and similar words used in the embodiments of the present application do not represent any order, quantity or importance, but are only used to distinguish different components. "Including" or "comprising" and similar words mean that the elements or objects appearing in front of the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.
[0056] The embodiments of the present application are described in detail below with reference to the accompanying drawings.
[0057] See also Figure 1 and Figure 2 As shown, this embodiment provides a ground penetrating radar image enhancement method, including:
[0058] Step S101: normalize an input image, wherein the input image is a scanned image collected by a ground penetrating radar.
[0059] Specifically, in this embodiment, the data normalization process is to scale the data so that it falls into a specific small interval, such as the [0, 1] interval in this embodiment, that is, the image I M After normalization, it is transformed into image I, and the data value range of image I is [0, 1].
[0060] The purpose of the above processing operation is to effectively ensure that the larger parts of the image are of uniform size in numerical terms, while reducing the impact of image noise and distortion on the algorithm.
[0061] Step S102: transform the normalized image based on a preset first transformation strategy to obtain a target image, and transform the normalized image based on a preset second transformation strategy to obtain a reference image.
[0062] Specifically, in this embodiment, a nonlinear transformation operation is first performed on the normalized image I to obtain the image I NL_F , and then perform a two-dimensional discrete cosine transform operation to obtain image I DC_F , and finally perform logarithmic transformation to obtain image I LT_F , retain the transformed result, i.e. as the target image;
[0063] At the same time, the normalized image I is directly subjected to discrete cosine transform operation to obtain image I DC_S , and then perform logarithmic transformation to obtain image I LT_S , retain the transformed result, which is used as the reference image.
[0064] Furthermore,
[0065] 1) Using nonlinear transformation algorithm, transform image I into image I NL_F
[0066] The first step is as formula (1), where image I is the input image I M The normalized result of .
[0067] I1=log(I+1) (1)
[0068] The second step is as shown in formula (2), where I is the normalized input image.
[0069] I2=1-exp(-I) (2)
[0070] The third step is to apply the LIP model as shown in formula (3).
[0071]
[0072] The fourth step is to apply the modified cumulative distribution function of the hyperbolic secant distribution (CDF-HSD) as shown in formula (4).
[0073] I NL_F =erf(λ*arctan(exp(I3))-0.5*I3) (4)
[0074] Finally, the nonlinear transformation algorithm result I is obtained NL_FIn formula (4), erf() is the error function, λ is the set parameter to be obtained, and there are two methods for obtaining the parameter λ, one is to obtain it by visual subjective judgment, and the other is to obtain it by objective judgment using an image quality assessment method. In this embodiment, the full reference image quality assessment method that can be used here is any one of the Spearman rank correlation coefficient (SRCC), Kendall rank correlation coefficient (KRCC), Pearson correlation coefficient (PLCC), mean square root error (RMSE), peak signal-to-noise ratio (PSNR), and structural similarity (SSIM).
[0075] 2) Discrete cosine transform, image I NL_F Transformed into image I DC_F
[0076] The orthogonal transform makes the transformed coefficients more independent or unrelated, and at the same time the redundant data becomes less. Therefore, due to these characteristics, it has been widely used in image enhancement technology. The commonly used orthogonal transform functions for image enhancement are discrete cosine transform and discrete Fourier transform. This embodiment adopts discrete cosine transform.
[0077] The two-dimensional discrete cosine transform (DCT) is defined as:
[0078]
[0079] Where f(i,j) is the image I NL_F The function representation is: f(i,j) is the pixel value at position (i,j) in the image; i,u=0,1,2,...,M-1; j,v=0,1,2,...,N-1, image I NL_F The size is M*N;
[0080] When u=0, In other cases, C(u) = 1;
[0081] When v = 0, In other cases, C(v) = 1;
[0082] After calculation of formula (5), we get the two-dimensional discrete cosine transform result F(u,v), which is the image I DC_F .
[0083] 3) Logarithmic transformation, image I DC_F Transformed into image I LT_F
[0084] The logarithmic transformation algorithm is defined as:
[0085] S(i,j)=log(|f(i,j)|+δ) (6)
[0086] Where f(i,j) is the image IDC_F The function representation is: f(i,j) is the pixel value at position (i,j) in the image; i,u=0,1,2,...,M-1; j,v=0,1,2,...,N-1, image I DC_F The size of is M*N; δ is an offset parameter, which can be set according to the actual situation and is not specifically limited here;
[0087] After calculation of formula (6), we get the logarithmic transformation result S(i,j), which is the image I LT_F .
[0088] 4) Discrete cosine transform, image I is transformed into image I DC_S
[0089] The two-dimensional discrete cosine transform (DCT) is defined as:
[0090]
[0091] Where, f(i,j) is the function representation of image I, that is, f(i,j) is the pixel value at (i,j) in the image; i,u=0,1,2,...,M-1; j,v=0,1,2,...,N-1, and the size of image I is M*N;
[0092] When u=0, In other cases, C(u) = 1;
[0093] When v = 0, In other cases, C(v) = 1;
[0094] After calculation of formula (7), we get the two-dimensional discrete cosine transform result F(u,v), which is the image I DC_S .
[0095] 5) Logarithmic transformation, image I DC_S Transformed into image I LT_S
[0096] The logarithmic transformation algorithm is defined as:
[0097] S(i,j)=log(f(i,j)+δ) (8)
[0098] Where f(i,j) is the image I DC_S The function representation is: f(i,j) is the pixel value at image (i,j); i = 0, 1, 2, ..., M-1; j = 0, 1, 2, ..., N-1, image I DC_S The size of is M*N; δ is an offset parameter, which can be set according to the actual situation and is not specifically limited here;
[0099] After calculation of formula (8), we get the logarithmic transformation result S(i,j), which is the image I LT_S .
[0100] Step S103: Perform histogram matching on the target image and the reference image to obtain a matching result.
[0101] Specifically, in this embodiment,
[0102] 6) Histogram matching
[0103] Image I LT_S Image I LT_F As the reference image, perform histogram matching to obtain the matching result I HM .
[0104] Histogram matching is to map the grayscale distribution of the target image to the grayscale distribution of the reference image through histogram equalization. The specific steps are as follows:
[0105] a. Calculate the histogram of the target image and the reference image;
[0106] b. Calculate the cumulative probability density function (CDF) of the histogram of the target image;
[0107] c. Calculate the cumulative probability density function (CDF) of the histogram of the reference image;
[0108] d. Map each pixel value of the target image to the corresponding pixel value on the reference image through a lookup table.
[0109] Step S104: perform inverse transformation processing on the matching result based on a preset inverse transformation strategy to obtain an output image.
[0110] 7) Inverse logarithmic transformation, image I HM Transformed into image I LIT
[0111] The inverse logarithmic transform algorithm is defined as:
[0112] f(i,j)=e |S(i,j)| -δ (9)
[0113] Where S(i,j) is the image I HM The function representation is: S(i,j) is the pixel value at image (i,j); i = 0, 1, 2, ..., M-1; j = 0, 1, 2, ..., N-1, image I HM The size is M*N;
[0114] After calculation of formula (9), we get the logarithmic transformation result f(i, j), which is image I LITThere are two methods for obtaining the offset parameter δ, one is to obtain it by visual subjective judgment, and the other is to adopt an image quality assessment method. The image quality assessment method adopted in this embodiment is a reference-free image quality assessment method, which are the BRISQUE algorithm, the PIQE algorithm and the NIQE algorithm. The above algorithms are conventional algorithms well known to those skilled in the art. For the three algorithms, the smaller the value, the better the image quality. The specific methods will not be further described here.
[0115] 8) Phase recovery, image I LIT Transformed into image I PR
[0116] I PR =|I LIT |exp(angle(I DC_S )*i) (10)
[0117] Where i is an imaginary number and angle() is the phase angle function.
[0118] 9) Inverse discrete cosine transform, image I PR Transformed into image I DCT
[0119] The two-dimensional inverse discrete cosine (DCT) transform is defined as:
[0120]
[0121] Where F(u,v) is the image I PR The function representation is: F(u,v) is the pixel value at (u,v) in the image; i,u=0,1,2,...,M-1; j,v=0,1,2,...,N-1, image I PR The size is M*N;
[0122] When u=0, In other cases, C(u) = 1;
[0123] When v = 0, In other cases, C(v) = 1;
[0124] After calculation of formula (11), we get the two-dimensional discrete cosine inverse transform result f(i, j), which is the image I DCT .
[0125] 10) Normalization processing, image I DCT Transformed into image I IE
[0126] Data normalization refers to scaling the data so that it falls into a specific small interval, such as the [0, 1] interval in this patent, that is, image IDCT After normalization, it is transformed into the final output image I IE , the data value range is [0, 1].
[0127] The ground penetrating radar image enhancement method described in this embodiment is an image enhancement method based on a preset transformation strategy and an inverse transformation strategy. It can enhance the return signal and attenuate the background area signal to solve the problems of weak target signal and large background noise in the ground penetrating radar scanning image, and can detect underground targets more accurately.
[0128] Embodiments of the present application:
[0129] Embodiment 1:
[0130] 1) Only nonlinear transformation operation is performed, and when the λ value is different, the following is obtained: Figures 3 to 7 The output image is shown.
[0131] Table 1 Full reference image quality assessment method under different λ conditions:
[0132] Evaluation Methodology λ=0.4 λ=0.6 λ=0.8 λ=1.0 λ=1.2 SRCC 1 1 1 1 -0.9277 KRCC 1 1 1 1 -0.9156 PLCC 1 1 1 0.9998 0.7866 RMSE 1.6241e-04 1.1719e-04 6.1683e-05 0.0025 0.0753 PSNR 17.5160 19.3739 24.3540 15.1202 6.3313 SSIM 0.9647 0.9763 0.9919 0.8663 -0.0809
[0133] For the Spearman rank correlation coefficient (SRCC), Kendall rank correlation coefficient (KRCC), Pearson correlation coefficient (PLCC), and structural similarity (SSIM), the closer the value is to 1, the better the image quality is. For the mean square error (RMSE) evaluation method, the smaller the value, the better. For the peak signal-to-noise ratio (PSNR) evaluation method, the larger the value, the better.
[0134] 2) Image enhancement algorithm described in this embodiment
[0135] Only performing nonlinear transformation operations can improve image quality, but the adaptability is not strong. Therefore, we hope to improve the adaptability of the algorithm while maintaining its performance, so that it can adapt to more occasions and more shooting conditions; at the same time, automatically remove Figure 8 The direct wave interference in the top grey area.
[0136] In the whole algorithm process, the offset coefficient δ in the logarithmic transformation needs to be clear. In most cases where image enhancement is required, δ = 1 can be taken. However, in the case of ground penetrating radar image enhancement, in order to better remove the direct wave and reduce other noise, the δ value may not be 1, such as Figures 9 to 15 As shown, where λ = 0.8. When the value of δ ranges from 1 to 2.8, Figures 9 to 15 From the intuitive perception of the image, from 1 to 2.6, the contrast is enhanced, and the direct wave is gradually eliminated. However, when the value of δ exceeds 2.5, the image enhancement effect begins to drop sharply.
[0137] The non-reference image quality assessment methods are BRISQUE algorithm, PIQE algorithm and NIQE algorithm. Figures 9 to 15 Conduct an objective assessment to obtain Figures 16 to 18 .
[0138] from Figures 16 to 18 It can be clearly seen that when the value of δ is about 2.5, the values of the BRISQUE algorithm and the PIQE algorithm are at the lowest level, and the value of the NIQE algorithm is at a lower level. From a comprehensive analysis, when the value of δ is 2.5, the overall image quality is better, which is also consistent with Figures 9 to 15 is consistent with the subjective judgment.
[0139] It should be noted that the above describes some embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the above embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
[0140] Based on the same inventive concept, corresponding to any of the above-mentioned embodiments and methods, an embodiment of the present application further provides a ground penetrating radar image enhancement device.
[0141] like Fig.19 As shown, the ground penetrating radar image enhancement device comprises:
[0142] The preprocessing module 11 is configured to perform normalization processing on the input image, wherein the input image is a scanned image collected by a ground penetrating radar;
[0143] The transformation processing module 12 is configured to perform transformation processing on the normalized image based on a preset first transformation strategy to obtain a target image, and perform transformation processing on the normalized image based on a preset second transformation strategy to obtain a reference image;
[0144] The matching module 13 is configured to perform histogram matching between the target image and the reference image to obtain a matching result;
[0145] The output module 14 is configured to perform inverse transformation processing on the matching result based on a preset inverse transformation strategy to obtain an output image.
[0146] For the convenience of description, the above devices are described in terms of functions and are divided into various modules. Of course, when implementing the embodiments of the present application, the functions of each module can be implemented in the same or multiple software and / or hardware.
[0147] The device of the above embodiment is used to implement the corresponding method in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be described in detail here.
[0148] Based on the same inventive concept, corresponding to any of the above-mentioned embodiments and methods, an embodiment of the present application also provides an electronic device, including 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 described in any of the above embodiments is implemented.
[0149] Fig. 20 A more specific schematic diagram of the hardware structure of an electronic device provided in this embodiment is shown, and the device may include: a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040 are connected to each other through the bus 1050 in the device.
[0150] The processor 1010 can be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.
[0151] The memory 1020 may be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 may store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program codes are stored in the memory 1020 and are called and executed by the processor 1010.
[0152] The input / output interface 1030 is used to connect the input / output module to realize information input and output. The input / output module can be configured in the device as a component (not shown in the figure), or it can be externally connected to the device to provide corresponding functions. The input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device may include a display, a speaker, a vibrator, an indicator light, etc.
[0153] The communication interface 1040 is used to connect a communication module (not shown) to realize communication interaction between the device and other devices. The communication module can realize communication through a wired mode (such as USB, network cable, etc.) or a wireless mode (such as mobile network, WIFI, Bluetooth, etc.).
[0154] The bus 1050 includes a path that transmits information between the various components of the device (eg, the processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040).
[0155] It should be noted that, although the above device only shows the processor 1010, the memory 1020, the input / output interface 1030, the communication interface 1040 and the bus 1050, in the specific implementation process, the device may also include other components necessary for normal operation. In addition, it can be understood by those skilled in the art that the above device may also only include the components necessary for implementing the embodiments of the present specification, and does not necessarily include all the components shown in the figure.
[0156] The electronic device of the above embodiment is used to implement the corresponding method in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be described in detail here.
[0157] Based on the same inventive concept, corresponding to any of the above-mentioned embodiments, the present application also provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the method described in any of the above embodiments.
[0158] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, 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, read-only compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, tape 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.
[0159] The computer instructions stored in the storage medium of the above embodiments are used to enable the computer to execute the method described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.
[0160] Those skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present application (including the claims) is limited to these examples. In line with the concept of the present application, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of the different aspects of the embodiments of the present application as described above, which are not provided in detail for the sake of simplicity.
[0161] In addition, to simplify the description and discussion, and in order not to make the embodiments of the present application difficult to understand, the known power supply / ground connection with the integrated circuit (IC) chip and other components may or may not be shown in the provided drawings. In addition, the device can be shown in the form of a block diagram to avoid making the embodiments of the present application difficult to understand, and this also takes into account the fact that the details of the implementation of these block diagram devices are highly dependent on the platform to be implemented in the embodiments of the present application (that is, these details should be fully within the scope of understanding of those skilled in the art). In the case of elaborating specific details (e.g., circuits) to describe exemplary embodiments of the present application, it is obvious to those skilled in the art that the embodiments of the present application can be implemented without these specific details or when these specific details are changed. Therefore, these descriptions should be considered to be illustrative rather than restrictive.
[0162] Although the present application has been described in conjunction with specific embodiments of the present application, many replacements, modifications and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may use the embodiments discussed.
[0163] The embodiments of the present application are intended to cover all such substitutions, modifications and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present application should be included in the scope of protection of the present application.
Claims
1. A ground penetrating radar image enhancement method, characterized in that: include: Normalizing an input image, wherein the input image is a scanned image collected by a ground penetrating radar; Performing a transformation process on the normalized image based on a preset first transformation strategy to obtain a target image, and performing a transformation process on the normalized image based on a preset second transformation strategy to obtain a reference image; Performing histogram matching on the target image and the reference image to obtain a matching result; The matching result is subjected to inverse transformation processing based on a preset inverse transformation strategy to obtain an output image.
2. The method according to claim 1, characterized in that: The step of transforming the normalized image based on a preset first transformation strategy to obtain a target image includes: Performing a nonlinear transformation on the normalized image according to a nonlinear transformation algorithm to obtain a transformed first intermediate image, and performing a two-dimensional discrete cosine transform on the first intermediate image to obtain a transformed second intermediate image; Performing logarithmic transformation on the second intermediate image according to a logarithmic transformation algorithm to obtain a transformed third intermediate image, and using the third intermediate image as a target image.
3. The method according to claim 1, characterized in that The step of transforming the normalized image based on a preset second transformation strategy to obtain a reference image includes: Perform a two-dimensional discrete cosine transform on the normalized image to obtain a transformed fourth intermediate image, perform a logarithmic transform on the fourth intermediate image according to a logarithmic transform algorithm to obtain a transformed fourth intermediate image, and use the fourth intermediate image as a reference image.
4. The method according to claim 1, characterized in that: The performing histogram matching on the target image and the reference image to obtain a matching result includes: Calculating histograms of the target image and the reference image; Performing cumulative probability density function calculation on the histogram of the target image and the histogram of the reference image respectively; Each pixel value of the target image is mapped to the corresponding pixel value on the reference image through a lookup table to obtain a corresponding matching result.
5. The method according to claim 1, characterized in that The performing inverse transformation processing on the matching result based on a preset inverse transformation strategy to obtain an output image includes: Performing an inverse logarithmic transformation on the matching result according to an inverse logarithmic transformation algorithm, performing phase recovery on the inversely transformed fifth intermediate image, and performing a two-dimensional inverse discrete cosine transform on the image result after phase recovery to obtain an inverse transformation result; The inverse transformation result is normalized to obtain a final output image.
6. A ground penetrating radar image enhancement device, characterized in that: include: A preprocessing module is configured to perform normalization processing on an input image, wherein the input image is a scanned image collected by a ground penetrating radar; A transformation processing module is configured to perform transformation processing on the normalized image based on a preset first transformation strategy to obtain a target image, and to perform transformation processing on the normalized image based on a preset second transformation strategy to obtain a reference image; A matching module is configured to perform histogram matching on the target image and the reference image to obtain a matching result; The output module is configured to perform inverse transformation processing on the matching result based on a preset inverse transformation strategy to obtain an output image.
7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method according to any one of claims 1 to 5 is implemented.
8. A non-transitory computer-readable storage medium, characterized in that: in, The non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to cause a computer to execute the method according to any one of claims 1 to 5.
Citation Information
Cited By
Ground penetrating radar image quality evaluation method and system for asphalt pavement cavity disease identification
CN119596305A
Ground penetrating radar image quality evaluation method and system for asphalt pavement cavity disease identification
CN119596305B
