Method and apparatus for determining intersection over union threshold value of magnetic flux leakage internal inspection of pipeline

Abstract

Provided in the present disclosure are a method and apparatus for determining an intersection over union threshold value of magnetic flux leakage internal inspection of a pipeline. The method comprises: acquiring magnetic flux leakage internal inspection data, the magnetic flux leakage internal inspection data being magnetic flux leakage amplitudes of a plurality of sampling points of a target pipeline acquired by means of a plurality of sensors; performing defect annotation on the magnetic flux leakage internal inspection data so as to obtain defect data corresponding to each of a plurality of defect regions of the target pipeline, the defect data being the magnetic flux leakage amplitudes acquired by a plurality of sensors respectively with respect to a plurality of sampling points comprised in the defect region; on the basis of the defect data corresponding to each of the plurality of defect regions, determining an average magnetization level value corresponding to the magnetic flux leakage internal inspection data; and, on the basis of the average magnetization level value corresponding to the magnetic flux leakage internal inspection data, determining an intersection over union threshold value of pipeline magnetic flux leakage internal inspection.

Description

Method and device for determining intersection over union threshold of pipeline magnetic flux leakage internal detection

[0001] The present disclosure claims priority to Chinese Patent Application No. 202411323783.7, filed on September 23, 2024, the entire contents of which are incorporated herein by reference. TECHNICAL FIELD

[0002] The present disclosure relates to the field of image detection, and in particular to a method and device for determining an intersection over union threshold of pipeline magnetic flux leakage internal detection. BACKGROUND

[0003] In recent years, with the rapid development of economy, the use of oil and natural gas has been increasing. However, when transporting oil and natural gas through pipelines, the pipelines may be threatened by material corrosion and external factors, leading to a continuous rise in safety risks. Once the pipeline is damaged and oil and gas leakage occurs, not only will it cause serious energy waste, but also will cause serious environmental pollution. Therefore, it is crucial to regularly inspect the pipeline to ensure its safe operation. In pipeline detection, defect recognition is a crucial step that can effectively find potential damage sites. Designing an accurate defect recognition algorithm is of great significance to the detection of actual engineering. SUMMARY

[0004] In a first aspect, a method for determining an intersection over union threshold of pipeline magnetic flux leakage internal detection is provided. The method includes: obtaining magnetic flux leakage internal detection data, the magnetic flux leakage internal detection data being leakage magnetic amplitude values of a plurality of sampling points of a target pipeline obtained by a plurality of sensors; defect labeling the magnetic flux leakage internal detection data to obtain defect data corresponding to each defect region of a plurality of defect regions of the target pipeline, the defect data being leakage magnetic amplitude values obtained by the plurality of sensors for a plurality of sampling points included in the defect region; determining an average magnetization level value corresponding to the magnetic flux leakage internal detection data according to the defect data corresponding to each defect region of the plurality of defect regions; and determining an intersection over union threshold of pipeline magnetic flux leakage internal detection according to the average magnetization level value corresponding to the magnetic flux leakage internal detection data.

[0005] In an implementation form of the first aspect, the average magnetization level value corresponding to the magnetic flux leakage internal detection data is determined according to the defect data corresponding to each defect region of the plurality of defect regions, including: determining a magnetization level value corresponding to each defect region according to the defect data corresponding to each defect region of the plurality of defect regions; and determining the average magnetization level value corresponding to the magnetic flux leakage internal detection data according to the magnetization level value corresponding to each defect region.

[0006] The formula for determining the magnetization level value GS corresponding to each defect region is:

[0007] m is the number of sampling points included in each defect region, n is the number of sensors corresponding to each defect data, mid(x i ) is the median of the magnetic flux leakage amplitude of the m sampling points obtained by the ith sensor, i is less than or equal to n

[0008] The average magnetization level value GS average corresponding to the magnetic flux leakage internal detection data is determined by the following formula:

[0009] B N is a preset batch number, GS i is the magnetization level value corresponding to the ith defect region.

[0010] In an implementation form of the first aspect, the IoU threshold of the magnetic flux leakage internal detection of the pipeline is determined according to the average magnetization level value corresponding to the magnetic flux leakage internal detection data, comprising: in a case that the average magnetization level value corresponding to the magnetic flux leakage internal detection data is greater than or equal to a first preset threshold, determining the IoU threshold of the magnetic flux leakage internal detection of the pipeline as 0.75; in a case that the average magnetization level value corresponding to the magnetic flux leakage internal detection data is less than a second preset threshold, determining the IoU threshold of the magnetic flux leakage internal detection of the pipeline as 0.5; in a case that the average magnetization level value corresponding to the magnetic flux leakage internal detection data is less than the first preset threshold and greater than or equal to the second preset threshold, the IoU threshold of the magnetic flux leakage internal detection of the pipeline is determined by the following formula: IoU=0.1×ln(B N / 3×GS average -B N ×(F max -F min ))+P r ;

[0011] F max is the first preset threshold, F min is the second preset threshold, P r is the proportion of unqualified data in the defect data, N f is the number of unqualified data in the defect data, and N all is the total number of defect data, and the unqualified data is defect data with a peak signal-to-noise ratio less than a preset peak signal-to-noise ratio.

[0012] In an implementation form of the first aspect, before determining the IoU threshold of the magnetic flux leakage internal detection of the pipeline according to the average magnetization level value corresponding to the magnetic flux leakage internal detection data, the method further comprises: determining the peak signal-to-noise ratio corresponding to each defect data; and determining the number of unqualified data in the defect data according to the peak signal-to-noise ratio corresponding to each defect data.

[0013] The peak signal-to-noise ratio PSNR i of the ith defect data is determined by the following formula:

[0014] x i the magnetic flux leakage amplitude corresponding to the ith sampling point acquired by the target sensor for acquiring the ith defect data, max the maximum value among the magnetic flux leakage amplitudes corresponding to the n sampling points acquired by the target sensor for acquiring the ith defect data, the average value among the magnetic flux leakage amplitudes corresponding to the n sampling points acquired by the target sensor for acquiring the ith defect data, the peak-valley difference of the target sensor for acquiring the ith defect data is the maximum value among the peak-valley differences of the sensors for acquiring the ith defect data, and the peak-valley difference is the difference between the maximum value and the minimum value among the magnetic flux leakage amplitudes of the n sampling points.

[0015] In an implementation form of the first aspect, the method further includes: determining a feature parameter corresponding to the magnetic flux leakage internal detection data, the feature parameter including an average peak-valley difference, an average surface energy, and an average volume energy; determining an image compression coefficient corresponding to the magnetic flux leakage internal detection data according to the feature parameter corresponding to the magnetic flux leakage internal detection data; and processing the magnetic flux leakage internal detection data according to the image compression coefficient corresponding to the magnetic flux leakage internal detection data to obtain a color magnetic flux leakage internal detection image.

[0016] In an implementation form of the first aspect, the determination of the feature parameter corresponding to the magnetic flux leakage internal detection data includes: determining a peak-valley difference, a surface energy, and a volume energy corresponding to each defect data included in the magnetic flux leakage internal detection data; determining an average peak-valley difference as a ratio of an average value of the peak-valley difference corresponding to each defect data to a maximum value among the peak-valley differences corresponding to each defect data, an average surface energy as a ratio of an average value of the surface energy corresponding to each defect data to a maximum value among the surface energies corresponding to each defect data, and an average volume energy as a ratio of an average value of the volume energy corresponding to each defect data to a maximum value among the volume energies corresponding to each defect data.

[0017] In an implementation form of the first aspect, a determination formula of the image compression coefficient CR corresponding to the magnetic flux leakage internal detection data is: CR=A′ fg ×K fg +A′ s ×K s +A′ v ×K v ;

[0018] wherein A′ fg is the average peak-valley difference, K fg is a peak-valley difference weight coefficient, A′ s is the average surface energy, K s is a surface energy weight coefficient, A′ v is the average volume energy, and K v is a volume energy weight coefficient.

[0019] In an implementation form of the first aspect, the processing the magnetic flux leakage internal detection data according to the image compression coefficient corresponding to the magnetic flux leakage internal detection data to obtain a color magnetic flux leakage internal detection image comprises: converting the magnetic flux leakage internal detection data into a gray image based on a gray mapping method; and processing the gray image according to the image compression coefficient corresponding to the magnetic flux leakage internal detection data to obtain the color magnetic flux leakage internal detection image.

[0020] In a second aspect, the disclosure provides a pipeline magnetic flux leakage internal detection intersection-over-union threshold determination device, the device comprising: a data acquisition unit configured to acquire magnetic flux leakage internal detection data, the magnetic flux leakage internal detection data being magnetic flux leakage amplitudes of a plurality of sampling points of a target pipeline acquired by a plurality of sensors; a defect labeling unit configured to label defects in the magnetic flux leakage internal detection data to obtain defect data corresponding to each of a plurality of defect regions of the target pipeline, the defect data being magnetic flux leakage amplitudes of a plurality of sampling points included in the defect region acquired by the plurality of sensors respectively; a magnetization determination unit configured to determine an average magnetization level value corresponding to the magnetic flux leakage internal detection data according to the defect data corresponding to each of the plurality of defect regions; and a threshold determination unit configured to determine a pipeline magnetic flux leakage internal detection intersection-over-union threshold according to the average magnetization level value corresponding to the magnetic flux leakage internal detection data.

[0021] In a third aspect, an electronic device is provided, comprising a memory and one or more processors; the memory is coupled to the processor; wherein the memory stores computer program code, the computer program code comprises computer instructions, when the computer instructions are executed by the processor, the electronic device executes the method in any implementation form of the first aspect.

[0022] In a fourth aspect, a computer readable storage medium is provided, comprising computer instructions, when the computer instructions are run on an electronic device, the electronic device executes the method in any implementation form of the first aspect.

[0023] In a fifth aspect, a computer program product is provided, when the computer program product is run on a computer, the computer executes the method in any implementation form of the first aspect.

[0024] In a sixth aspect, a computer program is provided, when the computer program is run on a computer, the computer executes the method in any implementation form of the first aspect. BRIEF DESCRIPTION OF DRAWINGS

[0025] FIG. 1 is a schematic diagram of a hardware structure of an electronic device according to an embodiment of the disclosure.

[0026] FIG. 2 is a flowchart of a pipeline magnetic flux leakage internal detection intersection-over-union threshold determination method according to an embodiment of the disclosure.

[0027] FIG. 3 is a flow chart of another method for determining an intersection over union threshold value for pipeline magnetic internal inspection according to an embodiment of the present disclosure.

[0028] FIG. 4 is a flow chart of yet another method for determining an intersection over union threshold value for pipeline magnetic internal inspection according to an embodiment of the present disclosure.

[0029] FIG. 5 is a schematic diagram of a hardware structure of a determination device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0030] The technical solutions in the embodiments of the present disclosure will be described below with reference to the accompanying drawings. In the description of the present disclosure, unless otherwise specified, " / " represents an "or" relationship between the objects before and after the " / " symbol, for example, A / B can represent A or B; "and / or" in the present disclosure is only a description of the relationship between the associated objects, which means that there can be three relationships, for example, A and / or B can represent: only A, A and B, only B, where A and B can be singular or plural. In addition, in the description of the present disclosure, unless otherwise specified, "multiple" means two or more than two. "At least one of the following" or the like means any combination of the items, including any combination of single item or multiple items.

[0031] In addition, in order to clearly describe the technical solutions of the embodiments of the present disclosure, in the embodiments of the present disclosure, "first", "second", and the like are used to distinguish the same items or similar items with basically the same function and effect. Those skilled in the art can understand that "first", "second", and the like do not limit the quantity and execution order, and "first", "second", and the like do not necessarily mean different.

[0032] At the same time, in the embodiments of the present disclosure, "exemplary" or "for example" and the like are used to represent as an example, illustration or description. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of the present disclosure should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. Rather, the use of "exemplary" or "for example" and the like is intended to present the relevant concept in some way, for ease of understanding. Without conflict, the functions, steps, etc. shown in the present disclosure can occur in an order different from that shown in the present disclosure, and there can be other functions, steps, etc. between the two adjacent functions, steps, etc. shown in the present disclosure.

[0033] In recent years, with the rapid development of economy, the use of oil and natural gas has been increasing. However, when transporting oil and natural gas through pipelines, the pipelines may be threatened by material corrosion and external factors, leading to a rising safety risk. Once the pipeline is damaged and oil and gas leakage occurs, not only will it cause serious energy waste, but also will cause serious environmental pollution. Therefore, it is crucial to regularly inspect the pipeline to ensure its safe operation. In pipeline detection, defect identification is a crucial step that can effectively find potential damage sites. Designing an accurate defect identification algorithm is of great significance to the detection of actual engineering.

[0034] Pipeline magnetic flux leakage internal detection is a widely used pipeline non-destructive testing technology. Compared with other technologies, it has higher stability, detection efficiency and accuracy, and can perform well in complex environments. In recent years, magnetic flux leakage internal detection is usually combined with machine learning algorithms to identify and locate pipeline defects. Intersection over union loss plays an important role in the training of defect detection models, and the setting of intersection over union threshold will have an important impact on the detection accuracy and generalization ability of the final detection model. Using a global threshold to set the intersection over union threshold, due to the existence of noise and uncertainty in the magnetic flux leakage internal detection image, this will affect the setting of the intersection over union threshold, and further affect the detection accuracy and positioning ability of the detection model.

[0035] Therefore, there is an urgent need for a pipeline magnetic flux leakage internal detection intersection over union threshold determination method and device to quickly and accurately determine the intersection over union threshold corresponding to different pipeline magnetic flux leakage internal detection data, thereby improving the detection accuracy and positioning ability of the detection model.

[0036] In view of this, the embodiments of the present disclosure provide a pipeline magnetic flux leakage internal detection intersection over union threshold determination method, the method comprises: obtaining magnetic flux leakage internal detection data, the magnetic flux leakage internal detection data being the magnetic flux leakage amplitude of a plurality of sampling points of a target pipeline obtained by a plurality of sensors; defect labeling is performed on the magnetic flux leakage internal detection data to obtain defect data corresponding to each defect region of a plurality of defect regions of the target pipeline, the defect data being the magnetic flux leakage amplitude obtained by a plurality of sensors respectively obtaining a plurality of sampling points included in the defect region; determining an average magnetization level value corresponding to the magnetic flux leakage internal detection data according to the defect data corresponding to each defect region of the plurality of defect regions; and determining the intersection over union threshold of the pipeline magnetic flux leakage internal detection according to the average magnetization level value corresponding to the magnetic flux leakage internal detection data.

[0037] The method provided by the embodiments of the present disclosure can obtain the magnetic flux leakage internal detection data, and then perform defect labeling on the magnetic flux leakage internal detection data to obtain defect data corresponding to each defect region of the plurality of defect regions of the target pipeline; determine an average magnetization level value corresponding to the magnetic flux leakage internal detection data according to the defect data corresponding to each defect region of the plurality of defect regions; and determine the intersection over union threshold value of the pipeline magnetic flux leakage internal detection according to the average magnetization level value corresponding to the magnetic flux leakage internal detection data. In this way, the embodiments of the present disclosure can quickly and accurately determine the intersection over union threshold value corresponding to different pipeline magnetic flux leakage internal detection data, and thus can effectively improve the detection accuracy and positioning ability of the detection model when training the detection model by using different pipeline magnetic flux leakage internal detection data.

[0038] On the other hand, the method provided by the embodiments of the present disclosure can determine the image compression coefficient corresponding to the magnetic flux leakage internal detection data, and perform compression processing on the magnetic flux leakage internal detection data according to the image compression coefficient corresponding to the magnetic flux leakage internal detection data, so as to effectively remove the redundancy of the image and improve the quality of the image data.

[0039] In some embodiments, the intersection over union threshold value determination method of the pipeline magnetic flux leakage internal detection provided by the embodiments of the present disclosure can be executed by an intersection over union threshold value determination apparatus 100 (hereinafter referred to as the determination apparatus 100) of the pipeline magnetic flux leakage internal detection. As an example, the determination apparatus 100 can be any electronic device 200 having a data processing capability, such as a general-purpose computer, a personal computer, a notebook computer, a switch or a tablet computer, and the like, and the implementation of the determination apparatus 100 is not limited herein.

[0040] FIG. 1 shows a hardware structure schematic diagram of an electronic device provided by the embodiments of the present disclosure. The electronic device 200 includes a processor 210, a memory 220 and a communication interface 230.

[0041] The processor 210 can include one or more processing cores. The processor 210 connects various parts in the electronic device 200 by various interfaces and lines, and performs various functions and processes data of the electronic device 200 by running or executing instructions, programs, code sets or instruction sets stored in the memory 220, and calling data stored in the memory 220. In some embodiments, the processor 210 can be implemented in at least one of the following hardware forms: a central processing unit (CPU), a graphics processing unit (GPU), a digital signal processing (DSP), a field-programmable gate array (FPGA), and a programmable logic array (PLA).

[0042] The memory 220 can include a random access memory (RAM) and can also include a read-only memory (ROM). In some embodiments, the memory 220 includes a non-transitory computer-readable storage medium. The memory 220 can be used to store instructions, programs, codes, code sets, or instruction sets. The memory 220 can include a storage program area. The storage program area can store instructions for implementing an operating system, instructions for implementing at least one function (such as a data acquisition function, a data processing function, etc.), instructions for implementing each of the above-mentioned method embodiments, and the like.

[0043] The communication interface 230 is configured to communicate with other devices, equipment, or communication networks, such as data storage devices, image processing equipment, or Ethernet, a radio access network (RAN), a wireless local area network (WLAN), and the like.

[0044] In terms of physical implementation, each of the above-mentioned devices (such as the processor 210, the memory 220, and the communication interface 230) can be a device in the same device (such as a notebook computer). Alternatively, at least two of the devices can be arranged in the same device as different devices in the device, similar to the deployment of devices or components in a distributed system.

[0045] It can be understood that the structure illustrated in the embodiment does not constitute a specific limitation on the electronic device 200. In other embodiments of the present disclosure, the electronic device 200 can include more or fewer components than those illustrated, or combine certain components, or split certain components, or different component arrangements. The illustrated components can be implemented in hardware, software, or a combination of software and hardware.

[0046] The pipeline magnetic internal detection intersection-over-union threshold determination method provided by the embodiments of the present disclosure is described below in conjunction with the accompanying drawings.

[0047] FIG. 2 is a flowchart of a pipeline magnetic internal detection intersection-over-union threshold determination method according to an embodiment of the present disclosure. In some embodiments, the method can be performed by the electronic device 200 shown in FIG. 1, that is, by the determination apparatus 100. The method can include the following S1 to S4:

[0048] S1, obtain magnetic internal detection data, the magnetic internal detection data being magnetic flux leakage amplitudes of a plurality of sampling points of a target pipeline obtained by a plurality of sensors.

[0049] In some embodiments, the internal magnetic flux leakage detection device is provided with a plurality of sensors, the internal magnetic flux leakage detection device moves along the radial direction of the target pipeline during operation, the target pipeline includes a plurality of sampling points, and the internal magnetic flux leakage detection data is the magnetic flux leakage amplitudes of the plurality of sampling points obtained by each of the plurality of sensors.

[0050] For example, referring to Table 1, which is a data table of internal magnetic flux leakage detection data according to an embodiment of the present disclosure, the internal magnetic flux leakage detection device is provided with five sensors, namely sensors 1-5, and the target pipeline includes five sampling points, and the internal magnetic flux leakage detection data is the magnetic flux leakage amplitudes of the sampling points 1-5 obtained by each of the five sensors. Each column of the table corresponds to a sensor, and each row of the table corresponds to a sampling point. X11 is the magnetic flux leakage amplitude of sampling point 1 obtained by sensor 1.

[0051] Table 1

[0052] It should be understood that in different use scenarios, the number of sensors and the number of sampling points provided by the internal magnetic flux leakage detection device can be more than the above examples, for example, the number of sampling points is usually tens of thousands or hundreds of thousands, and the number of sampling points according to the embodiment of the present disclosure can be of any order of magnitude. The above examples are only for ease of explanation and description, and therefore the number of sensors is exemplified as five and the number of sampling points is exemplified as five.

[0053] S2, labeling the internal magnetic flux leakage detection data for defects to obtain defect data corresponding to each of a plurality of defect regions of the target pipeline, the defect data being the magnetic flux leakage amplitudes obtained by the plurality of sensors from a plurality of sampling points included in the defect region.

[0054] In some embodiments, in the case where the target pipeline has a plurality of defect regions, when the internal magnetic flux leakage detection device passes through the defect region, the magnetic flux leakage amplitudes corresponding to the plurality of sampling points included in the defect region obtained by the plurality of sensors are the defect data.

[0055] In combination with Table 1, referring to Table 2, which is a data table of a defect data included in the internal magnetic flux leakage detection data, Table 2 includes the magnetic flux leakage amplitudes corresponding to the sampling points 2-4 obtained by the sensors 1-3 in the internal magnetic flux leakage detection data.

[0056] Table 2

[0057] It should be understood that the above examples of defect data are only for explanation and description, and the number of magnetic flux leakage amplitudes included in the defect data is not particularly limited according to the embodiment of the present disclosure, for example, the defect data can be the magnetic flux leakage amplitudes corresponding to 500 sampling points included in the defect region obtained by 50 sensors.

[0058] S3, determine the average magnetization level value corresponding to the internal magnetic flux leakage detection data according to the defect data corresponding to each of the plurality of defect regions.

[0059] In an implementation, referring to FIG. 3, S3 described above can include the following S31-S32:

[0060] S31, determine the magnetization level value corresponding to each of the plurality of defect regions according to the defect data corresponding to each of the plurality of defect regions.

[0061] In some embodiments, the formula for determining the magnetization level value GS corresponding to each of the plurality of defect regions is:

[0062] m is the number of sampling points included in each of the plurality of defect regions, n is the number of sensors corresponding to each of the plurality of defect data, mid(x i ) is the median of the magnetic flux leakage amplitude of the m sampling points obtained by the i-th sensor, i is less than or equal to n.

[0063] Exemplarily, in combination with Table 2, first determine that the number of sampling points m included in the defect data is 3, the number of sensors n corresponding to each of the plurality of defect data is 3, then determine the median of X21, X31 and X41, the median of X22, X32 and X42, and the median of X23, X33 and X43, respectively. Then, the magnetization level value GS corresponding to each of the plurality of defect regions is obtained according to the above formula.

[0064] It should be understood that the internal magnetic flux leakage detection data includes a plurality of defect data, and the determination manner of the magnetization level value GS corresponding to each of the plurality of defect data is the same as the above example, which will not be described herein.

[0065] In some embodiments, a weight can be assigned according to the reliability of the sensor. The formula for determining the magnetization level value GS corresponding to each of the plurality of defect regions is:

[0066] ω i may be dynamically adjusted based on the historical error rate of the sensor. The greater the error, the smaller the weight. For example, when the error rate is less than 5%, ω i is 1.2.

[0067] S32, determine the average magnetization level value corresponding to the internal magnetic flux leakage detection data according to the magnetization level value corresponding to each of the plurality of defect regions.

[0068] In some embodiments, the formula for determining the average magnetization level value GS average corresponding to the internal magnetic flux leakage detection data is:

[0069] B N is a preset batch number, and GS iThe magnetization level value corresponding to the i-th defect region.

[0070] It should be noted that the preset batch quantity B N According to the actual use scene, the user can preset the batch quantity B N The implementation manner is not particularly limited.

[0071] In some embodiments, before determining the intersection over union threshold value of the pipeline magnetic flux leakage internal detection according to the average magnetization level value corresponding to the magnetic flux leakage internal detection data, the method provided by the embodiments of the present disclosure further includes: determining the peak signal-to-noise ratio corresponding to each defect data; and determining the number of unqualified data in the defect data according to the peak signal-to-noise ratio corresponding to each defect data.

[0072] The peak signal-to-noise ratio PSNR of the i-th defect data is determined according to the following formula:

[0073] x i The magnetic flux leakage amplitude corresponding to the i-th sampling point obtained by the target sensor for obtaining the i-th defect data is x max The maximum value of the magnetic flux leakage amplitude corresponding to the n sampling points obtained by the target sensor for obtaining the i-th defect data is x The average value of the magnetic flux leakage amplitude corresponding to the n sampling points obtained by the target sensor for obtaining the i-th defect data is x The peak-to-valley difference of the target sensor for obtaining the i-th defect data is the maximum value of the peak-to-valley differences of the sensors for obtaining the i-th defect data, and the peak-to-valley difference is the difference between the maximum value and the minimum value of the magnetic flux leakage amplitude corresponding to the n sampling points.

[0074] For example, in combination with Table 2, since the peak-to-valley difference corresponding to sensor 1 is 20, the peak-to-valley difference corresponding to sensor 2 is 10, and the peak-to-valley difference corresponding to sensor 3 is 30, sensor 3 is the target sensor. Therefore, x max is 60, and x N is 70.

[0075] S4, determining the intersection over union threshold value of the pipeline magnetic flux leakage internal detection according to the average magnetization level value corresponding to the magnetic flux leakage internal detection data.

[0076] In one implementation manner, the above S4 can include the following contents.

[0077] In the case that the average magnetization level value corresponding to the magnetic flux leakage internal detection data is greater than or equal to a first preset threshold value, the intersection over union threshold value of the pipeline magnetic flux leakage internal detection is determined to be 0.75.

[0078] In the case that the average magnetization level value corresponding to the magnetic flux leakage internal detection data is less than a second preset threshold value, the intersection over union threshold value of the pipeline magnetic flux leakage internal detection is determined to be 0.5.

[0079] In a case where the average magnetization level value corresponding to the magnetic internal leakage detection data is less than the first preset threshold value and greater than or equal to the second preset threshold value, a determination formula of the intersection over union threshold IoU of the pipeline magnetic internal leakage detection is: IoU = 0.1 x ln(B N / 3 x GS average -B N x (F max -F min ) + P r ;

[0080] F max is the first preset threshold value, F min is the second preset threshold value, P r is a proportion of unqualified data in the defect data, N f is a number of unqualified data in the defect data, N all is a total number of defect data, and the unqualified data is defect data with a peak signal-to-noise ratio less than a preset peak signal-to-noise ratio.

[0081] In an example, the first preset threshold value is 190, the second preset threshold value is 140, and the preset peak signal-to-noise ratio is 10 dB.

[0082] In some embodiments, the intersection over union threshold can be determined based on a neural network model. For example, a lightweight one-dimensional convolutional neural network and a long short-term memory network fusion architecture are adopted to consider spatial features and time sequence dependencies. The input is the average magnetization level value, and the output is the intersection over union threshold of the pipeline magnetic internal leakage detection. Adaptive weighted loss is used for model strategy optimization.

[0083] As can be seen from the above S1-S4, the method provided by the embodiments of the present disclosure obtains magnetic internal leakage detection data, then performs defect labeling on the magnetic internal leakage detection data to obtain defect data corresponding to each defect region in a plurality of defect regions of a target pipeline; determines an average magnetization level value corresponding to the magnetic internal leakage detection data according to the defect data corresponding to each defect region in the plurality of defect regions; and determines an intersection over union threshold of the pipeline magnetic internal leakage detection according to the average magnetization level value corresponding to the magnetic internal leakage detection data. In this way, the embodiments of the present disclosure can quickly and accurately determine the intersection over union threshold corresponding to different pipeline magnetic internal leakage detection data, and thus can effectively improve the detection accuracy and positioning ability of a detection model when training the detection model by using different pipeline magnetic internal leakage detection data.

[0084] In the training process of the detection model, the preprocessing and data enhancement of the image are also crucial to the detection algorithm. Image compression, as a common preprocessing method, can effectively remove image redundancy and improve the quality of the pipeline magnetic flux leakage internal detection data, with the advantages of controllable parameters and simple implementation. However, by setting the image compression coefficient based on experience, it is impossible to guarantee the quality of the image after data compression; at the same time, uniform normalization processing may lead to the loss of important features, thereby affecting the accuracy of the detection algorithm. Therefore, in order to improve the image quality, it is necessary to accurately and quickly determine the image compression coefficient of different pipeline magnetic flux leakage internal detection data to meet the user's use requirements in different use scenarios.

[0085] In some embodiments, referring to FIG. 4, the method provided by the embodiment of the present disclosure further includes the following S51 to S53:

[0086] S51, determine the feature parameters corresponding to the magnetic flux leakage internal detection data, the feature parameters including the average peak-valley difference, the average surface energy and the average volume energy.

[0087] In an implementation manner, the S51 can include the following contents:

[0088] Determine the peak-valley difference, the surface energy and the volume energy corresponding to each defect data included in the magnetic flux leakage internal detection data; determine the average peak-valley difference as the ratio of the average value of the peak-valley difference corresponding to each defect data to the maximum value in the peak-valley difference corresponding to each defect data, determine the average surface energy as the ratio of the average value of the surface energy corresponding to each defect data to the maximum value in the surface energy corresponding to each defect data, and determine the average volume energy as the ratio of the average value of the volume energy corresponding to each defect data to the maximum value in the volume energy corresponding to each defect data.

[0089] In some embodiments, the peak-valley difference corresponding to each defect data is the difference between the maximum value and the minimum value of the magnetic flux amplitude of a plurality of sampling points corresponding to a target sensor of each defect region.

[0090] The determination formula of the peak-valley difference FG corresponding to each defect data is: FG = max(f max -f min );

[0091] The determination formula of the surface energy corresponding to each defect data is:

[0092] X l represents the left valley point of the pipeline defect, X r represents the right valley point of the pipeline defect, F D represents the magnetic field intensity curve of the sensor, F rl represents the straight line formed by the left valley point and the right valley point.

[0093] S52, determining the image compression coefficient corresponding to the magnetic flux leakage internal detection data according to the feature parameter corresponding to the magnetic flux leakage internal detection data;

[0094] In some embodiments, the formula for determining the image compression coefficient CR corresponding to the magnetic flux leakage internal detection data is: CR=A' fg ×K fg +A' s ×K s +A' v ×K v ;

[0095] A' fg is the average peak-valley difference, K fg is the peak-valley difference weight coefficient, A' s is the average surface energy, K s is the surface energy weight coefficient, A' v is the average volume energy, K v is the volume energy weight coefficient.

[0096] In one example, the reference value of K fg is 0.7, the reference value of K s is 0.2, and the reference value of K v is 0.1.

[0097] S53, processing the magnetic flux leakage internal detection data according to the image compression coefficient corresponding to the magnetic flux leakage internal detection data to obtain a color magnetic flux leakage internal detection image.

[0098] In one implementation, the above S53 can include the following content:

[0099] Based on the gray scale mapping method, the magnetic flux leakage internal detection data is converted into a gray scale image; and the gray scale image is processed according to the image compression coefficient corresponding to the magnetic flux leakage internal detection data to obtain a color magnetic flux leakage internal detection image.

[0100] In some embodiments, the data matrix D corresponding to the magnetic flux leakage internal detection data is mapped into a gray scale image by using the gray scale mapping method, and the gray scale image pixels are converted into RGB pseudo-color pixels according to the CLUT table. In this way, all pixels in the gray scale image are traversed to convert the gray scale image into a color magnetic flux leakage internal detection image. An example of the color magnetic flux leakage internal detection image conversion method is as follows:

[0101] f R , f G , f B are respectively the conversion coefficients of the red, green and blue domains in the CLUT table; C R , C G , C Brespectively are red domain coefficient matrix, green domain coefficient matrix and blue domain coefficient matrix of the converted color magnetic flux leakage internal detection image; G gray is a gray image.

[0102] From the above, the method provided by the embodiments of the present disclosure can effectively remove the redundancy of the image and improve the quality of the image data by determining the image compression coefficient corresponding to the magnetic flux leakage internal detection data and compressing the magnetic flux leakage internal detection data according to the image compression coefficient corresponding to the magnetic flux leakage internal detection data.

[0103] The above mainly introduces the scheme of the embodiments of the present disclosure from the perspective of the method. It can be understood that the determination device contains at least one of the corresponding hardware structure and the software module for executing each function in order to realize the above functions. Those skilled in the art should easily realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in the present disclosure can be realized in the form of hardware or the combination of hardware and computer software. Whether a certain function is executed in the form of hardware or computer software driven hardware depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the embodiments of the present disclosure.

[0104] The embodiments of the present disclosure can divide the determination device into functional units according to the above method examples. For example, the determination device can be divided into functional units corresponding to each function, or two or more functions can be integrated into one processing unit. The integrated unit can be realized in the form of hardware or software functional unit. It should be noted that the division of units in the embodiments of the present disclosure is illustrative, and is only a logical functional division. There can be another division method when actually implemented.

[0105] Exemplarily, FIG. 5 shows a structure schematic diagram of a determination device provided by the embodiments of the present disclosure. The determination device 100 comprises: a data acquisition unit 510, configured to acquire magnetic flux leakage internal detection data, the magnetic flux leakage internal detection data being a leakage magnetic amplitude of a plurality of sampling points of a target pipeline acquired by a plurality of sensors; a defect labeling unit 520, configured to perform defect labeling on the magnetic flux leakage internal detection data to obtain defect data corresponding to each defect region of a plurality of defect regions of the target pipeline, the defect data being a leakage magnetic amplitude obtained by the plurality of sensors acquiring a plurality of sampling points included in the defect region; a magnetization determination unit 530, configured to determine an average magnetization level value corresponding to the magnetic flux leakage internal detection data according to the defect data corresponding to each defect region of the plurality of defect regions; and a threshold determination unit 540, configured to determine an intersection-over-union ratio threshold of pipeline magnetic flux leakage internal detection according to the average magnetization level value corresponding to the magnetic flux leakage internal detection data.

[0106] In some embodiments, the magnetization determination unit 530 can be configured to determine a magnetization level value corresponding to each defect region according to the defect data corresponding to each defect region, and determine an average magnetization level value corresponding to the internal magnetic flux leakage detection data according to the magnetization level value corresponding to each defect region.

[0107] The formula for determining the magnetization level value GS corresponding to each defect region is:

[0108] m is the number of sampling points included in each defect region, n is the number of sensors used to obtain each defect data, mid(x i ) is the median of the magnetic flux leakage amplitudes of the m sampling points obtained by the i-th sensor, i is less than or equal to n;

[0109] The formula for determining the average magnetization level value GS average corresponding to the internal magnetic flux leakage detection data is:

[0110] B N is the preset batch number, GS i is the magnetization level value corresponding to the i-th defect region.

[0111] In some embodiments, the threshold determination unit 540 can be configured to determine that the intersection over union threshold for the internal magnetic flux leakage detection of the pipeline is 0.75 when the average magnetization level value corresponding to the internal magnetic flux leakage detection data is greater than or equal to a first preset threshold, determine that the intersection over union threshold for the internal magnetic flux leakage detection of the pipeline is 0.5 when the average magnetization level value corresponding to the internal magnetic flux leakage detection data is less than a second preset threshold, and determine the formula for the intersection over union threshold IoU for the internal magnetic flux leakage detection of the pipeline when the average magnetization level value corresponding to the internal magnetic flux leakage detection data is less than the first preset threshold and greater than or equal to the second preset threshold: IoU = 0.1 x ln(B N / 3 x GS average -B N x (F max -F min ) + P r .

[0112] F max is the first preset threshold, F min is the second preset threshold, P r is the proportion of unqualified data in the defect data, N f is the number of unqualified data in the defect data, and N all is the total number of defect data. The unqualified data is defect data with a peak signal-to-noise ratio less than a preset peak signal-to-noise ratio.

[0113] In some embodiments, the magnetization determination unit 530 is further configured to: determine a peak signal-to-noise ratio corresponding to each defect data; and determine the number of unqualified defect data in the defect data according to the peak signal-to-noise ratio corresponding to each defect data.

[0114] The peak signal-to-noise ratio of the i-th defect data is PSNRi. i The determination formula is:

[0115] x i The magnetic flux leakage amplitude corresponding to the i-th sampling point acquired by the target sensor for acquiring the i-th defect data is x max The maximum value of the magnetic flux leakage amplitudes corresponding to the n sampling points acquired by the target sensor for acquiring the i-th defect data is x The average value of the magnetic flux leakage amplitudes corresponding to the n sampling points acquired by the target sensor for acquiring the i-th defect data is x The peak-to-valley difference of the target sensor for acquiring the i-th defect data is the maximum value of the peak-to-valley differences of the sensors for acquiring the i-th defect data, and the peak-to-valley difference is the difference between the maximum value and the minimum value of the magnetic flux leakage amplitudes corresponding to the n sampling points.

[0116] In some embodiments, the determination apparatus provided by the embodiments of the present disclosure further includes an image compression unit 550 configured to: determine a feature parameter corresponding to the magnetic flux leakage internal detection data, the feature parameter including an average peak-to-valley difference, an average surface energy, and an average volume energy; determine an image compression coefficient corresponding to the magnetic flux leakage internal detection data according to the feature parameter corresponding to the magnetic flux leakage internal detection data; and process the magnetic flux leakage internal detection data according to the image compression coefficient corresponding to the magnetic flux leakage internal detection data to obtain a color magnetic flux leakage internal detection image.

[0117] In some embodiments, the image compression unit 550 can be configured to: determine a peak-to-valley difference, a surface energy, and a volume energy corresponding to each defect data included in the magnetic flux leakage internal detection data; determine an average peak-to-valley difference as a ratio of an average value of the peak-to-valley difference corresponding to each defect data to a maximum value of the peak-to-valley difference corresponding to each defect data, an average surface energy as a ratio of an average value of the surface energy corresponding to each defect data to a maximum value of the surface energy corresponding to each defect data, and an average volume energy as a ratio of an average value of the volume energy corresponding to each defect data to a maximum value of the volume energy corresponding to each defect data.

[0118] In some embodiments, the determination formula of the image compression coefficient CR corresponding to the magnetic flux leakage internal detection data is: CR=A′ fg ×K fg +A′ s ×K s +A′ v ×K v ;

[0119] A′fg is an average peak-valley difference, K fg is a peak-valley difference weight coefficient, A' s is an average surface energy, K s is a surface energy weight coefficient, A' v is an average volume energy, K v is a volume energy weight coefficient.

[0120] In some embodiments, the image compression unit 550 can be configured to: convert the internal magnetic flux leakage detection data into a gray-scale image based on a gray-scale mapping method; and process the gray-scale image according to an image compression coefficient corresponding to the internal magnetic flux leakage detection data to obtain a color internal magnetic flux leakage detection image.

[0121] It should be understood that the description of the above embodiments can refer to the foregoing method embodiments, which will not be described herein again. In addition, the description of the explanation and beneficial effects of any one of the determination apparatuses 100 provided above can refer to the corresponding method embodiments described above, which will not be described herein again.

[0122] The embodiments of the present disclosure further provide a computer-readable storage medium having at least one computer instruction stored therein, which is loaded and executed by a processor to implement the method of any one of the above embodiments. The description of the explanation and beneficial effects of any one of the computer-readable storage media provided above can refer to the corresponding embodiments described above, which will not be described herein again.

[0123] The embodiments of the present disclosure further provide a chip. The chip integrates a control circuit and one or more ports for implementing the functions of the determination apparatus 100 described above. In some embodiments, the functions supported by the chip can refer to the above, which will not be described herein again.

[0124] Those of ordinary skill in the art can understand that all or part of the steps of the above embodiments can be instructed by a program to complete the related hardware, and the program can be stored in a computer-readable storage medium. The storage medium mentioned above can be a read-only memory, a random access memory, etc. The processing unit or processor mentioned above can be a central processing unit, a general-purpose processor, a specific circuit structure (application specific integrated circuit, ASIC), a microprocessor (digital signal processor, DSP), a field programmable gate array (FPGA) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof.

[0125] The embodiments of the present disclosure further provide a computer program product containing instructions, which, when executed on a computer, cause the computer to perform any of the methods described above. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on the computer, the processes or functions according to the embodiments of the present disclosure are wholly or partially generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable apparatus. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center through a wired (for example, coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (for example, infrared, wireless, microwave, etc.) manner. The computer-readable storage medium can be any available medium accessible by a computer or a data storage device such as a server, data center, etc. containing one or more available media sets. The available media can be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium (for example, an SSD), etc.

[0126] It should be noted that the above-mentioned devices for storing computer instructions or computer programs provided by the embodiments of the present disclosure, such as but not limited to the above-mentioned memory, computer-readable storage medium, and communication chip, etc., are all non-volatile (non-transitory). Those skilled in the art should be aware that in one or more of the above examples, the functions described by the embodiments of the present disclosure can be implemented by hardware, software, firmware, or any combination thereof. When implemented by software, these functions can be stored in a computer-readable storage medium or transmitted as one or more instructions or codes on a computer-readable storage medium. The computer-readable storage medium includes computer storage medium and communication medium, wherein the communication medium includes any medium that facilitates the transfer of a computer program from one place to another. The storage medium can be any available medium accessible by a general-purpose or special-purpose computer.

[0127] Although the embodiments of the present disclosure have been shown and described above, it should be understood that the above-mentioned embodiments are exemplary and cannot be understood as limiting the present disclosure, and those skilled in the art can make changes, modifications, replacements, and variations to the above-mentioned embodiments within the scope of the present disclosure.

Claims

1. A method for determining a fusion criterion threshold of pipeline magnetic flux leakage internal detection, comprising: obtaining magnetic flux leakage internal detection data, the magnetic flux leakage internal detection data being magnetic flux leakage amplitudes of a plurality of sampling points of a target pipeline obtained by a plurality of sensors; annotating defects of the magnetic flux leakage internal detection data to obtain defect data corresponding to each of a plurality of defect regions of the target pipeline, the defect data being magnetic flux leakage amplitudes of a plurality of sampling points included in a defect region obtained by a plurality of sensors respectively; determining an average magnetization level value corresponding to the magnetic flux leakage internal detection data according to the defect data corresponding to each of the plurality of defect regions; determining a fusion criterion threshold of pipeline magnetic flux leakage internal detection according to the average magnetization level value corresponding to the magnetic flux leakage internal detection data.

2. The method of claim 1, wherein, The determining of the average magnetization level value corresponding to the magnetic flux leakage internal detection data according to the defect data corresponding to each of the plurality of defect regions comprises: determining a magnetization level value corresponding to each of the plurality of defect regions according to the defect data corresponding to each of the plurality of defect regions; determining the average magnetization level value corresponding to the magnetic flux leakage internal detection data according to the magnetization level value corresponding to each of the plurality of defect regions. The formula for determining the magnetization level value GS corresponding to each defect region is: wherein m is the number of sampling points included in each defect region, n is the number of sensors corresponding to each defect data obtained, mid(x i ) is the median of the magnetic flux leakage amplitudes of the m sampling points obtained by the i-th sensor, i is less than or equal to n; The average magnetization level value GS corresponding to the magnetic flux leakage internal detection data average The determination formula is: wherein B N is a preset batch quantity, GS i is a magnetization level value corresponding to the i-th defect region.

3. The method of claim 1 or 2, wherein, The determining of the fusion criterion threshold of pipeline magnetic flux leakage internal detection according to the average magnetization level value corresponding to the magnetic flux leakage internal detection data comprises: determining the fusion criterion threshold of pipeline magnetic flux leakage internal detection as 0.75 when the average magnetization level value corresponding to the magnetic flux leakage internal detection data is greater than or equal to a first preset threshold; determining the fusion criterion threshold of pipeline magnetic flux leakage internal detection as 0.5 when the average magnetization level value corresponding to the magnetic flux leakage internal detection data is less than a second preset threshold. In a case where the average magnetization level value corresponding to the magnetic flux leakage internal detection data is less than a first preset threshold value and greater than or equal to a second preset threshold value, a determination formula of the intersection over union IoU threshold value of the pipeline magnetic flux leakage internal detection is: wherein F max is a first preset threshold, F min is a second preset threshold, P r is a proportion of unqualified data in the defect data, N f is a number of unqualified data in the defect data, N all is a total number of defect data, and the unqualified data is defect data with a peak signal-to-noise ratio less than a preset peak signal-to-noise ratio.

4. The method of any one of claims 1 to 3, wherein, Before the determining of the fusion criterion threshold of pipeline magnetic flux leakage internal detection according to the average magnetization level value corresponding to the magnetic flux leakage internal detection data, the method further comprises: determining a peak signal-to-noise ratio corresponding to each of the defect data; determining a number of unqualified defect data according to the peak signal-to-noise ratio corresponding to each of the defect data; Peak signal-to-noise ratio, PSNR, of the ith defect data i The determination formula is: x i the maximum value of the magnetic flux leakage amplitudes corresponding to the n sampling points acquired by the target sensor for the i-th defect data, max the maximum value of the magnetic flux leakage amplitudes corresponding to the n sampling points acquired by the target sensor for the i-th defect data, determining an average value of n sampling points corresponding to the magnetic flux leakage amplitudes of the target sensor of the i-th defect data, determining a peak-valley difference of the target sensor of the i-th defect data as a maximum value of peak-valley differences of a plurality of sensors obtaining the i-th defect data, and the peak-valley difference being a difference between a maximum value and a minimum value of the n sampling points corresponding to the magnetic flux leakage amplitudes.

5. The method of any one of claims 1 to 4, wherein, The method further comprises: determining a characteristic parameter corresponding to the magnetic flux leakage internal detection data, the characteristic parameter including an average peak-valley difference, an average surface energy, and an average volume energy; determining an image compression coefficient corresponding to the magnetic flux leakage internal detection data according to the characteristic parameter corresponding to the magnetic flux leakage internal detection data; processing the magnetic flux leakage internal detection data according to the image compression coefficient corresponding to the magnetic flux leakage internal detection data to obtain a color magnetic flux leakage internal detection image.

6. The method of claim 5, wherein, The determining of the characteristic parameter corresponding to the magnetic flux leakage internal detection data comprises: determining a peak-valley difference, a surface energy, and a volume energy corresponding to each of the defect data included in the magnetic flux leakage internal detection data. Determine the ratio of the average of the peak-valley value difference corresponding to each defect data and the maximum of the peak-valley value difference corresponding to each defect data as the average peak-valley value difference, determine the ratio of the average of the surface energy corresponding to each defect data and the maximum of the surface energy corresponding to each defect data as the average surface energy, and determine the ratio of the average of the bulk energy corresponding to each defect data and the maximum of the bulk energy corresponding to each defect data as the average bulk energy.

7. The method of claim 5 or 6, wherein, The determination formula of the image compression coefficient CR corresponding to the magnetic flux leakage internal detection data is: CR=A' fg ×K fg +A′ s ×K s +A′ v ×K v ; Among them, A′ fg K represents the average peak-to-valley difference. fg A′ is the weighting coefficient for the peak-valley difference. s For the average surface energy, K s A′ is the surface energy weighting coefficient. v For average body energy, K v This is the body energy weighting coefficient.

8. The method of any one of claims 5-7, wherein, The processing of the internal magnetic flux leakage detection data according to the image compression coefficient corresponding to the internal magnetic flux leakage detection data to obtain a color internal magnetic flux leakage detection image comprises: Converting the internal magnetic flux leakage detection data into a gray-scale image based on a gray-scale mapping method; Processing the gray-scale image according to the image compression coefficient corresponding to the internal magnetic flux leakage detection data to obtain a color internal magnetic flux leakage detection image.

9. An intersection-over-union threshold value determination device for internal magnetic flux leakage detection of a pipeline, comprising: a data acquisition unit configured to acquire internal magnetic flux leakage detection data, the internal magnetic flux leakage detection data being leakage magnetic flux amplitudes of a plurality of sampling points of a target pipeline acquired by a plurality of sensors; a defect labeling unit configured to label defects in the internal magnetic flux leakage detection data to obtain defect data corresponding to each of a plurality of defect regions of the target pipeline, the defect data being leakage magnetic flux amplitudes of a plurality of sampling points included in a defect region acquired by a plurality of sensors respectively; a magnetization determination unit configured to determine an average magnetization level value corresponding to the internal magnetic flux leakage detection data according to the defect data corresponding to each of the plurality of defect regions; a threshold value determination unit configured to determine an intersection-over-union threshold value for internal magnetic flux leakage detection of a pipeline according to the average magnetization level value corresponding to the internal magnetic flux leakage detection data.

10. An electronic device, comprising: a processor; a memory for storing instructions executable by the processor; wherein the processor is configured to execute the instructions to implement the intersection-over-union threshold value determination method for internal magnetic flux leakage detection of a pipeline according to any one of claims 1 to 8.

11. A computer readable storage medium comprising a computer program or instructions, wherein, When the computer program or instructions are run on a computer, the computer is caused to perform the method according to any one of claims 1 to 8.

12. A computer program product comprising computer instructions which, when executed by a processor, implement the method according to any one of claims 1 to 8.

13. A computer program comprising computer instructions which, when executed by a processor, implement the method according to any one of claims 1 to 8.

Images