A drilling TV detection and recognition system based on machine vision in adverse environment

Abstract

The present invention discloses a borehole television detection and identification system based on machine vision in adverse environments, which specifically includes: a brightness data acquisition module: based on machine vision technology, a borehole image is acquired, and the borehole image is divided into regions, and then analyzed and processed, and the brightness value of the borehole image region is output; the image inside the borehole is collected using machine vision technology to acquire the borehole image; the acquired borehole image is divided into a plurality of image sub-regions, and the brightness value of each image sub-region is calculated and output. The present invention enables operators to quickly understand the brightness status of the borehole image. In the case of poor balance, operators can take timely measures to adjust, thereby reducing the waste of time and resources due to image quality problems, optimizing the efficiency of the detection task, making the work more efficient and orderly, and improving the reliability of the detection results. At the same time, it can ensure that the image information quality based on which the subsequent image processing or detection tasks are based is reliable.

Description

Technical Field

[0001] The invention relates to the technical field of borehole television detection, and in particular to a borehole television detection and recognition system based on machine vision in adverse environments. Background Art

[0002] In the fields of geological exploration and engineering investigation, borehole television detection technology, as an important non-destructive detection method, is widely used in the detection of underground structure, rock distribution, soil properties, etc.

[0003] However, in practical applications, the acquisition of borehole images is often affected by adverse environments, such as insufficient light and uneven lighting, which leads to a decline in image quality and brings difficulties to subsequent image processing or detection tasks. Traditional borehole television detection systems are often unable to effectively deal with the problem of uneven image brightness when facing adverse environments. Uneven image brightness will directly affect the clarity of detailed information in the image, making it difficult for operators to accurately judge key information such as underground structure, rock distribution or soil properties. This lack of information or misjudgment may lead to large errors in detection results, which in turn affects subsequent geological analysis, engineering design or construction decisions, thereby increasing safety risks during the construction process. Summary of the invention

[0004] The object of the present invention is to provide a borehole television detection and identification system based on machine vision in adverse environments to solve at least one of the above-mentioned prior art problems.

[0005] A borehole television detection and recognition system based on machine vision in adverse environments, specifically comprising:

[0006] Brightness data acquisition module: based on machine vision technology, it acquires drilling images, divides the drilling images into regions, performs analysis and processing, and outputs the brightness values ​​of the drilling image regions;

[0007] Use machine vision technology to collect images inside the borehole and obtain the borehole image;

[0008] Divide the acquired drilling image into a number of image sub-regions, and calculate and output the brightness value of each image sub-region;

[0009] Brightness balance judgment module: Based on the output drilling image area brightness value, the output drilling image brightness balance degree signal is identified through the quadratic stability algorithm;

[0010] The balance degree signal includes a poor balance signal and a good balance signal;

[0011] Coincidence identification module: Based on the output balance difference signal, the predicted position of the detection target is marked in combination with the position of the balance difference area, the coincidence judgment value is output, and the signal of the degree of coincidence between the output predicted position and the balance difference area is identified;

[0012] Image processing module: based on the overlap degree signal, determine the drilling image processing method and optimize the drilling image;

[0013] Influencing factor judgment module: After the optimization process is completed, the drilling image is judged for balance again. If the output result is still poor balance, the influence of the light source emission angle on the balance of the drilling image brightness is analyzed, and the output influence degree signal is identified;

[0014] The impact degree signal includes a low impact degree signal and a high impact degree signal.

[0015] Beneficial effects of the present invention:

[0016] 1. The present invention enables operators to quickly understand the brightness status of the borehole image. In the case of poor balance, operators can take timely measures to adjust, thereby reducing the waste of time and resources due to image quality problems, optimizing the efficiency of detection tasks, making work more efficient and orderly, and improving the reliability of detection results. At the same time, it can ensure the quality of image information based on subsequent image processing or detection tasks.

[0017] 2. The present invention can determine the degree of overlap between the poorly balanced area in the drilling image and the predicted position of the detection target, so as to select a more appropriate processing method, reduce the detection error caused by uneven image brightness, and improve the accuracy of detection. According to the overlap degree signal, it can intelligently select histogram equalization processing or adaptive histogram equalization processing, avoiding unnecessary complex adjustments, which not only improves the efficiency of image processing, but also reduces the labor intensity of operators. By flexibly adjusting the processing method, it improves adaptability and flexibility. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0019] Figure 1 It is a flow chart of a borehole television detection and identification method based on machine vision in adverse environments of the present invention;

[0020] Figure 2It is a structural schematic diagram of a borehole television detection and identification system based on machine vision in adverse environments of the present invention;

[0021] Figure 3 It is a structural schematic diagram of a borehole television detection and identification method and equipment based on machine vision in adverse environments according to the present invention.

[0022] In the figure: 3, computer device; 301, processor; 302, memory; 303, computer program. DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0024] Embodiment 1

[0025] Figure 1 A flowchart of a borehole television detection and identification method based on machine vision in an adverse environment is provided for the first embodiment of the present invention. The embodiment of the present invention is applicable to the situation of performing borehole detection in an adverse environment. The borehole television detection and identification method based on machine vision in an adverse environment can be executed by a borehole television detection and identification system based on machine vision in an adverse environment. The borehole television detection and identification system based on machine vision in an adverse environment can be implemented by software and / or hardware. The borehole television detection and identification system based on machine vision in an adverse environment can be configured in a borehole television detection and identification device based on machine vision in an adverse environment. Optionally, a borehole television detection and identification device based on machine vision in an adverse environment can be an electronic device, which can be a notebook, a desktop computer, a smart tablet, etc., and the embodiment of the present invention does not limit this.

[0026] Adverse environment includes poor lighting conditions. The present invention introduces the situation of drilling TV detection and identification in an environment with poor lighting conditions. Insufficient light or uneven light distribution makes it difficult for the machine vision system to obtain clear and high-quality images. Such changes in lighting conditions will directly affect the quality of image acquisition and the accuracy of subsequent processing;

[0027] like Figure 2 As shown, an embodiment of the present invention provides a borehole television detection and identification system based on machine vision in adverse environments, specifically comprising:

[0028] Brightness data acquisition module: based on machine vision technology, it acquires drilling images, divides the drilling images into regions, performs analysis and processing, and outputs the brightness values ​​of the drilling image regions;

[0029] In some embodiments, a camera or image sensor in machine vision technology is used to capture images of the inside of the borehole to obtain borehole images. During the acquisition process, it is necessary to ensure that the position and angle of the camera can clearly capture the details of the inside of the borehole;

[0030] Divide the acquired borehole image into a plurality of image sub-areas, wherein the image division is performed by a person skilled in the art according to image content, features, detection requirements, and analysis requirements;

[0031] Calculate and output the brightness value of each image sub-region, where the brightness value can be obtained through Python analysis;

[0032] For example, the cv2.mean() function in the OpenCV library is used to calculate the average brightness. The average grayscale value of all pixels in each image sub-region is calculated to obtain the overall brightness level of the image sub-region, that is, the brightness value of each image sub-region is obtained;

[0033] Brightness balance judgment module: Based on the output drilling image area brightness value, the output drilling image brightness balance degree signal is identified through the quadratic stability algorithm;

[0034] The balance degree signal includes a poor balance signal and a good balance signal;

[0035] In some embodiments, the brightness value of each image sub-region is obtained, each image sub-region is numbered in sequence, and the brightness values ​​are integrated into a brightness value data group in the order of the numbers;

[0036] For the brightness value data group, a first amplitude FY and a second amplitude FE are set, and corresponding first stability standards and second stability standards are set, wherein the first amplitude change FY, the second amplitude FE, the first stability index and the second stability index are summarized and set by those skilled in the art based on experience and image equalization requirements;

[0037] The brightness value data in the brightness value data group are summed and averaged to obtain the brightness mean value LJ;

[0038] The interval [LJ-FY, J+FY] is taken as a primary stable region, the number of values ​​in the brightness value data group that are in the primary stable region is counted, and the ratio of the number of values ​​in the primary stable region to the total number of values ​​in the brightness value data group is calculated to obtain a primary stable ratio value;

[0039] The interval [LJ-FE, J+FE] is taken as the secondary stable region, the number of values ​​in the brightness value data group that are in the secondary stable region is counted, and the ratio of the number of values ​​in the secondary stable region to the total number of values ​​in the brightness value data group is calculated to obtain the secondary stable ratio;

[0040] The primary stability ratio value is compared with the first stability index, and the secondary stability ratio value is compared with the second stability index;

[0041] If the primary stability ratio is greater than the first stability index and the secondary stability ratio is greater than the second stability index, a brightness array stable signal is generated; otherwise, a brightness array unstable signal is generated;

[0042] It should be noted that the situations corresponding to generating the unstable signal of the brightness array include: the primary stability ratio is less than or equal to the first stability index and the secondary stability ratio is less than or equal to the second stability index, the primary stability ratio is greater than the first stability index and the secondary stability ratio is less than or equal to the second stability index, the primary stability ratio is less than or equal to the first stability index and the secondary stability ratio is greater than the second stability index;

[0043] Based on the generated brightness array stable signal, the primary stable proportion value is calculated to be different from the first stable index, the absolute value of the difference is taken to obtain the primary stable proportion value difference, the secondary stable proportion value is calculated to be different from the second stable index, the absolute value of the difference is taken to obtain the secondary stable proportion value difference;

[0044] Extract the maximum brightness and the minimum brightness in the brightness value array, perform difference calculation to obtain the brightness extreme value difference, perform ratio calculation on the brightness extreme value difference and the brightness mean to obtain the brightness extreme value ratio;

[0045] Substitute into the formula , the equalization value JH is calculated, where JZ represents the brightness extreme value ratio, YC represents the primary stable proportion value difference, EC represents the secondary stable proportion value difference, a and b are preset proportional coefficients, the value of a is 6.285, and the value of b is 7.715;

[0046] It needs to be explained that the smaller the difference between the primary stable proportion value and the secondary stable proportion value, the worse the balance, and the larger the brightness extreme value ratio, the worse the balance;

[0047] Compare the equilibrium value with the equilibrium threshold, wherein the equilibrium threshold is set by a person skilled in the art based on a summary of multiple historical experimental data;

[0048] If the balance value is greater than the balance threshold, a poor balance signal is generated; if the balance value is less than or equal to the balance threshold, a good balance signal is generated;

[0049] The technical solution of this embodiment is: the brightness value of the borehole image is obtained through the brightness data acquisition module, and the brightness value is analyzed by a secondary stability algorithm using the brightness balance judgment module, so as to identify the degree of balance of the borehole image brightness. The system can output a poor balance signal or a good balance signal, which provides an important reference for subsequent image processing or detection tasks, can reduce processing errors caused by uneven image brightness, and improve the accuracy and reliability of image processing.

[0050] Embodiment 2

[0051] Based on the above embodiments, Figure 2 As shown, an embodiment of the present invention provides a borehole television detection and identification system based on machine vision in adverse environments, specifically comprising:

[0052] Coincidence identification module: Based on the output balance difference signal, the predicted position of the detection target is marked, and combined with the position of the balance difference area, the coincidence judgment value is output, and the signal of the degree of coincidence between the output predicted position and the balance difference area is identified;

[0053] The coincidence degree signal includes a low coincidence signal and a high coincidence signal;

[0054] In some embodiments, based on the balance difference signal, an unbalanced image sub-region is extracted, wherein the unbalanced image sub-region corresponds to an image sub-region corresponding to a brightness value outside the primary stable region and the secondary stable region, and is marked in the drilling image;

[0055] Obtain the predicted position of the detection target according to the detection requirements and mark it in the drilling image;

[0056] Calculate the intersection area of ​​the unbalanced image sub-region and the predicted position, calculate the ratio of the intersection area to the total area of ​​the unbalanced sub-region to obtain a first overlap ratio value, calculate the ratio of the intersection area to the total area of ​​the predicted position to obtain a second overlap ratio value;

[0057] The first overlap ratio value and the second overlap ratio value are weighted and calculated to obtain an overlap judgment value, wherein the weight of the first overlap ratio value is less than the weight of the second overlap ratio value, the weight of the first overlap ratio value is 0.428, and the weight of the second overlap ratio value is 0.572;

[0058] Exemplarily, the intersection area is calculated according to the marked unbalanced image sub-region and the predicted position, and the specific process is as follows:

[0059] Establishing a two-dimensional coordinate system for the borehole image, wherein the establishment of the two-dimensional coordinate system includes but is not limited to: establishing based on pixel coordinates of the image and based on the actual size and shape of the borehole;

[0060] It should be noted that the imbalanced image sub-regions and the detection prediction positions are expressed in the same two-dimensional coordinate system;

[0061] Obtaining boundary coordinates of the unbalanced image sub-region and the detection prediction position, and calculating the intersection area of ​​the unbalanced image sub-region and the detection prediction position according to the boundary coordinates of the unbalanced image sub-region and the detection prediction position;

[0062] Compare the overlap judgment value with the overlap judgment threshold, wherein the overlap judgment threshold is set by a person skilled in the art based on a summary of multiple historical experimental data;

[0063] If the coincidence judgment value is greater than the coincidence judgment threshold, it means that the coincidence between the unbalanced image sub-region and the detection prediction position is high, and a high coincidence signal is generated;

[0064] If the coincidence judgment value is less than or equal to the coincidence judgment threshold, it means that the coincidence between the unbalanced image sub-region and the detection prediction position is low, and a low coincidence signal is generated;

[0065] Image processing module: based on the overlap degree signal, determine the drilling image processing method and optimize the drilling image;

[0066] Among them, the image processing methods include histogram equalization processing and adaptive histogram equalization processing;

[0067] Based on the generation of coincident low signals, the image is optimized using histogram equalization processing;

[0068] The reason for choosing the histogram equalization processing method is that when the overlap is low, it means that the predicted position of the detection target does not overlap with the imbalanced area (i.e. the area where there may be problems). At this time, it may be more efficient to use general histogram equalization processing because it does not require complex adjustments for specific areas. Equalization processing can improve the brightness and contrast of the image as a whole, which helps to show the details in the image more clearly.

[0069] Based on the generation of high coincidence signals, the image is optimized using adaptive histogram equalization processing;

[0070] The reason for selecting the histogram adaptive equalization processing method is that when the overlap is high, it means that the predicted position of the detection target is highly overlapped with the imbalanced area, which means that there may be anomalies or defects in the area. It is more appropriate to use the adaptive histogram equalization processing because it can make local adjustments according to the brightness distribution of different areas in the image, so as to more accurately highlight or enhance the details of specific areas. This processing method can more effectively identify and analyze potential problems in drilling images;

[0071] By performing histogram equalization optimization processing or adaptive equalization optimization processing on the image, the image quality and brightness balance can be improved, thereby enhancing the efficiency of drilling image analysis;

[0072] The technical solution of this embodiment is: by judging the overlap between the poorly balanced area of ​​the drilling image and the predicted position of the detection target, an overlap degree signal is output. Based on the overlap degree signal, the image processing module selects an appropriate drilling image processing method, such as histogram equalization processing or adaptive histogram equalization processing, to optimize the image quality. It combines machine vision and intelligent analysis to improve the detection and recognition capabilities of drilling images in adverse environments.

[0073] Embodiment 3

[0074] Based on the above embodiments, Figure 2 As shown, the light source emission angle directly affects the brightness distribution of the borehole image (for example, the light source emission will produce shadows in a bad environment, affecting the brightness of the borehole image). Under bad ambient lighting conditions, if the light source angle is inappropriate, some areas of the image may be too bright or too dark, thereby affecting the overall brightness balance. Compared with other factors, it is better to optimize. An embodiment of the present invention provides a borehole TV detection and recognition system based on machine vision in a bad environment, which specifically includes:

[0075] Influencing factor judgment module: After the optimization process is completed, the drilling image is judged for balance again. If the output result is still poor balance, the influence of the light source emission angle on the balance of the drilling image brightness is analyzed, and the output influence degree signal is identified;

[0076] The impact degree signal includes a low impact degree signal and a high impact degree signal;

[0077] In some embodiments, the processed drilling image is subjected to a balance judgment again, wherein the balance judgment process utilizes the brightness data acquisition module and the brightness balance judgment module in the first embodiment to judge, which will not be described in detail here;

[0078] If the signal output by the brightness balance judgment module is a poor balance signal, the influence of the light source emission angle is analyzed. The specific process is as follows:

[0079] Extracting light source emission angle data corresponding to the drilling image in the historical data, and obtaining a balance value corresponding to the drilling image, wherein the light source emission angle data includes a horizontal angle and a vertical angle;

[0080] Use correlation analysis algorithm to determine the correlation between the balance value and the light source emission angle data;

[0081] Among them, correlation analysis algorithms include but are not limited to: Pearson correlation coefficient, Spearman correlation coefficient, distance correlation coefficient;

[0082] In this embodiment, the specific process of using the distance correlation coefficient to determine the correlation between the balance value and the light source emission angle data is as follows: The calculation steps are as follows:

[0083] Calculate the distance covariance and variance: where the distance covariance The calculation formula is: , distance variance and The calculation formulas are:

[0084] , ,in, and It is the matrix element obtained after a specific transformation based on the distance matrix of X and Y. n is the number of samples, M is the balance value, N is the emission angle of the light source, i and j are the i-th sample and j-th sample respectively;

[0085] Distance correlation coefficient ;

[0086] The reason for choosing to use the distance correlation coefficient is that the distance correlation coefficient can capture not only linear relationships, but also nonlinear relationships. The value range of the distance correlation coefficient is between 0 and 1. When the two variables are completely independent, the distance correlation coefficient is 0. When there is a strong dependence between the two variables, the distance correlation coefficient is close to 1.

[0087] The distance correlation coefficient and P value were calculated using SPSS software. When the P value was less than 0.05, a correlation threshold was set, and the absolute value of the distance correlation coefficient was taken to obtain the absolute value of the distance correlation coefficient, which was compared with the correlation threshold. If the absolute value of the distance correlation coefficient was greater than the correlation threshold, a high-impact signal was generated, otherwise, a low-impact signal was generated.

[0088] Based on the low impact signal generated, other factors are checked, including but not limited to: light source intensity, camera parameters;

[0089] Based on the generated high-impact signal, the light source emission angle is adjusted. The adjustment methods include but are not limited to: intelligently recommending the best light source emission angle combination based on historical data and current environmental conditions. If the light source emission angle has reached the limit or the adjustment effect is not good, the system will issue an early warning to prompt the operator to check other factors, such as light source intensity, camera parameters, etc.; the operator manually fine-tunes the light source emission angle according to the system's recommendations or actual needs, and adds a real-time preview function so that the operator can intuitively see the adjustment effect, thereby making more precise adjustments;

[0090] During the adjustment process, the brightness balance of the drilling image is monitored and calculated;

[0091] The technical solution of this embodiment is: by re-judging the brightness balance of the drilling image, and analyzing the influence of the light source emission angle when the balance is poor, the correlation analysis algorithm (such as the distance correlation coefficient) is used to judge the correlation between the balance value and the light source emission angle data, and an influence degree signal is generated according to the judgment result. Based on the generated influence degree signal, the system intelligently recommends methods for adjusting the light source emission angle, or checks other factors that may affect the image brightness. During the adjustment process, the system monitors and calculates the brightness balance of the drilling image in real time to ensure the adjustment effect.

[0092] Embodiment 4

[0093] Based on the above embodiments, Figure 1 As shown, an embodiment of the present invention provides a borehole television detection and identification method based on machine vision in an adverse environment, which specifically includes the following steps:

[0094] Step 1: Based on machine vision technology, the drilling image is obtained, and the drilling image is divided into regions, and then analyzed and processed to output the brightness value of the drilling image region;

[0095] Step 2: Based on the outputted borehole image area brightness value, a signal of the degree of balance of the outputted borehole image brightness is identified by a quadratic stability algorithm;

[0096] The balance degree signal includes a poor balance signal and a good balance signal;

[0097] Step 3: Based on the output balance difference signal, mark the predicted position of the detection target combined with the position of the balance difference area, output the overlap judgment value, and identify the overlap degree signal of the output predicted position and the balance difference area;

[0098] The coincidence degree signal includes a low coincidence signal and a high coincidence signal;

[0099] Step 4: Based on the overlap degree signal, determine the drilling image processing methods respectively, and optimize the drilling image;

[0100] Among them, the image processing methods include histogram equalization processing and adaptive histogram equalization processing;

[0101] Step 5: Perform a balance judgment on the processed drilling image again. If the output result is still poor balance, analyze the influence of the light source emission angle on the balance of the drilling image brightness, and identify the output influence degree signal;

[0102] The impact degree signal includes a low impact degree signal and a high impact degree signal.

[0103] Embodiment 5

[0104] like Figure 3 As shown, an embodiment of the present invention further provides a computer device 3, comprising: a memory 302 and a processor 301 and a computer program 303 stored in the memory 302. When the computer program 303 is executed on the processor 301, a drilling television detection and identification method based on machine vision in an adverse environment as described in any of the above methods is implemented.

[0105] The computer device 3 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The computer device 3 may include, but is not limited to, a processor 301 and a memory 302. Those skilled in the art will appreciate that

[0106] Figure 3 It is only an example of computer device 3 and does not constitute a limitation on computer device 3. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components, for example, it may also include input and output devices, network access devices, etc.

[0107] The processor 301 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0108] In some embodiments, the memory 302 may be an internal storage unit of the computer device 3, such as a hard disk or memory of the computer device 3. In other embodiments, the memory 302 may also be an external storage device of the computer device 3, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the computer device 3. Further, the memory 302 may also include both an internal storage unit and an external storage device of the computer device 3. The memory 302 is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program. The memory 302 may also be used to temporarily store data that has been output or is to be output.

[0109] Embodiment 6

[0110] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for borehole television detection and identification based on machine vision in adverse environments as described in any one of the above methods is implemented.

[0111] In this embodiment, if the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the camera / terminal device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, USB flash drive, mobile hard disk, disk or optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0112] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0113] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0114] In the embodiments disclosed in the present application, it should be understood that the disclosed apparatus / terminal equipment and method can be implemented in other ways. For example, the apparatus / terminal equipment embodiments described above are merely illustrative. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0115] One point, the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, which may be electrical, mechanical or other forms.

[0116] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0117] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0118] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A borehole TV detection and identification system based on machine vision in adverse environments, characterized in that: Specifically include: Brightness data acquisition module: based on machine vision technology, it acquires drilling images, divides drilling images into regions, performs analysis and processing, and outputs the brightness values ​​of drilling image regions; Use machine vision technology to collect images inside the borehole and obtain the borehole image; Divide the acquired drilling image into a number of image sub-regions, and calculate and output the brightness value of each image sub-region; Brightness balance judgment module: Based on the output drilling image area brightness value, the output drilling image brightness balance degree signal is identified through the quadratic stability algorithm; The balance degree signal includes a poor balance signal and a good balance signal; Obtain the brightness value of each image sub-region, number each image sub-region in sequence, and integrate the brightness values ​​into a brightness value data group in the order of the numbers; For the brightness value data group, a first amplitude FY and a second amplitude FE are set, and a corresponding first stability standard and a second stability standard are set; The brightness value data in the brightness value data group are summed and averaged to obtain the brightness mean value LJ; The interval [LJ-FY, LJ+FY] is taken as a primary stable region, the number of values ​​in the brightness value data group that are in the primary stable region is counted, and the ratio of the number of values ​​in the primary stable region to the total number of values ​​in the brightness value data group is calculated to obtain a primary stable ratio value; The interval [LJ-FE, LJ+FE] is taken as the secondary stable region, the number of values ​​in the brightness value data group that are in the secondary stable region is counted, and the ratio of the number of values ​​in the secondary stable region to the total number of values ​​in the brightness value data group is calculated to obtain the secondary stable ratio; The primary stability ratio value is compared with the first stability index, and the secondary stability ratio value is compared with the second stability index; If the primary stability ratio is greater than the first stability index and the secondary stability ratio is greater than the second stability index, a brightness array stable signal is generated; otherwise, a brightness array unstable signal is generated; Based on the generated brightness array stable signal, the primary stable proportion value is calculated to be different from the first stable index, the absolute value of the difference is taken to obtain the primary stable proportion value difference, the secondary stable proportion value is calculated to be different from the second stable index, the absolute value of the difference is taken to obtain the secondary stable proportion value difference; Extract the maximum brightness and the minimum brightness in the brightness value array, perform difference calculation to obtain the brightness extreme value difference, perform ratio calculation on the brightness extreme value difference and the brightness mean to obtain the brightness extreme value ratio; The data is processed according to the primary stable proportion value difference, the secondary stable proportion value difference and the brightness extreme value ratio to obtain the equilibrium value; Compare the equalization value with the equalization threshold, if the equalization value is greater than the equalization threshold, generate a poor equalization signal, if the equalization value is less than or equal to the equalization threshold, generate a good equalization signal; Coincidence identification module: Based on the output balance difference signal, the predicted position of the detection target is marked, and combined with the position of the balance difference area, the coincidence judgment value is output, and the signal of the degree of coincidence between the output predicted position and the balance difference area is identified; Image processing module: based on the overlap degree signal, determine the drilling image processing method and optimize the drilling image; Based on generating coincident low signals, a histogram equalization processing method is used; Based on generating high coincidence signals, adaptive histogram equalization is used Influencing factor judgment module: After the optimization process is completed, the drilling image is judged for balance again. If the output result is still poor balance, the influence of the light source emission angle on the balance of the drilling image brightness is analyzed, and the output influence degree signal is identified; The impact degree signal includes a low impact degree signal and a high impact degree signal.

2. According to the machine vision-based borehole television detection and identification system in adverse environments according to claim 1, it is characterized in that: The process of obtaining the equilibrium value is as follows: Obtain the primary stable ratio value difference, the secondary stable ratio value difference, and the brightness extreme value ratio; Substitute into the formula , the equalization value JH is calculated, where JZ represents the brightness extreme value ratio, YC represents the primary stable proportion value difference, EC represents the secondary stable proportion value difference, and a and b are preset proportional coefficients.

3. According to the machine vision-based borehole television detection and identification system in adverse environments as described in claim 1, it is characterized in that: The process of generating the coincidence degree signal is: Obtaining a coincidence judgment value, and comparing the coincidence judgment value with a coincidence judgment threshold; If the overlap judgment value is greater than the overlap judgment threshold, a high overlap signal is generated; if the overlap judgment value is less than or equal to the overlap judgment threshold, a low overlap signal is generated.

4. According to the machine vision-based borehole television detection and identification system in adverse environments as described in claim 1, it is characterized in that: The process of obtaining the overlap judgment value is as follows: Based on the balance difference signal, an unbalanced image sub-region is extracted, wherein the unbalanced image sub-region corresponds to an image sub-region corresponding to a brightness value outside the primary stable region and the secondary stable region, and is marked in the drilling image; Obtain the predicted position of the detection target according to the detection requirements and mark it in the drilling image; Calculate the intersection area of ​​the unbalanced image sub-region and the predicted position, calculate the ratio of the intersection area to the total area of ​​the unbalanced sub-region to obtain a first overlap ratio value, calculate the ratio of the intersection area to the total area of ​​the predicted position to obtain a second overlap ratio value; The first overlap ratio value and the second overlap ratio value are weightedly summed to obtain an overlap judgment value, wherein the weight of the first overlap ratio value is less than the weight of the second overlap ratio value.

5. The borehole television detection and identification system based on machine vision in adverse environments according to claim 1 is characterized in that: The process of analyzing the influence of the light source emission angle on the brightness balance of the drilling image is as follows: The distance correlation coefficient and P value were calculated using SPSS statistical software. When the P value was less than 0.05, a correlation threshold was set, and the absolute value of the distance correlation coefficient was taken to obtain the absolute value of the distance correlation coefficient, which was compared with the correlation threshold. If the absolute value of the distance correlation coefficient was greater than the correlation threshold, a high-impact signal was generated; otherwise, a low-impact signal was generated.

6. The borehole television detection and identification system based on machine vision in adverse environments according to claim 5 is characterized in that: The process of obtaining the distance correlation coefficient is as follows: The processed drilling image is judged for balance again. If the signal output by the brightness balance judgment module is a poor balance signal, the influence of the light source emission angle is analyzed. The specific process is as follows: Extracting light source emission angle data corresponding to the drilling image in the historical data, and obtaining a balance value corresponding to the drilling image, wherein the light source emission angle data includes a horizontal angle and a vertical angle; The specific process of using the distance correlation coefficient to determine the correlation between the balance value and the light source emission angle data is as follows: The calculation steps are as follows: Calculate the distance covariance and variance: where the distance covariance The calculation formula is: , distance variance and The calculation formulas are: , ,in, and It is the matrix element obtained by transforming the distance matrix based on X and Y, n is the number of samples, M is the balance value, N is the emission angle of the light source, i and j are the i-th sample and j-th sample respectively; Distance correlation coefficient .

Images