Underwater cable tracking methods, electronic devices, and storage media

Abstract

This invention discloses an underwater cable tracking method, electronic device, and storage medium. The method, belonging to the field of power systems, includes: acquiring underwater video captured by an underwater navigation device, wherein the underwater video represents video footage taken of an initial area where underwater cables are deployed; identifying the underwater video based on a cable identification model to obtain cable identification results, wherein the cable identification model is deployed in the underwater navigation device, and the cable identification results represent the position of the underwater cable in the initial area; constructing a navigation path for the device based on the cable identification results; and controlling the underwater navigation device to track the underwater cable based on the navigation path. This invention solves the technical problem of low accuracy in underwater cable identification in related technologies.

Description

Technical Field

[0001] This invention relates to the field of power systems, and more specifically, to an underwater cable tracking method, electronic device, and storage medium. Background Technology

[0002] Underwater cable and pipeline systems, as critical infrastructure connecting land and sea, and different islands, are essential for modern power, communication, and marine development. They not only undertake the tasks of power transmission and data transmission, but also play a vital role in marine scientific research and oil and gas extraction. However, these underwater facilities are exposed to the harsh marine environment for extended periods, making them susceptible to corrosion, abrasion, biofouling, and natural disasters. Therefore, regular inspection and maintenance are crucial for ensuring their safety and reliability.

[0003] In recent years, with the rapid development of artificial intelligence technology, Autonomous Underwater Vehicles (AUVs) have attracted widespread attention due to their autonomy, flexibility, and cost-effectiveness in underwater operations. AUVs are equipped with vision systems and sensors that can continuously monitor the underwater environment and collect real-time data on cable status; however, image processing technology has become a key limiting factor for their performance. Underwater image acquisition faces challenges such as insufficient lighting, turbid water, and turbulent interference, leading to decreased image quality and consequently, lower accuracy when using image processing technology to identify underwater cables.

[0004] There is currently no effective solution to the above problems. Summary of the Invention

[0005] This invention provides an underwater cable tracking method, electronic device, and storage medium to at least solve the technical problem of low accuracy in identifying underwater cables in related technologies.

[0006] According to one aspect of the present invention, an underwater cable tracking method is provided, comprising: acquiring underwater video captured by an underwater navigation device, wherein the underwater video is used to characterize a video obtained by shooting an initial area where underwater cables are deployed; identifying the underwater video based on a cable identification model to obtain a cable identification result, wherein the cable identification model is deployed in the underwater navigation device, and the cable identification result is used to characterize the position of the underwater cable in the initial area; constructing a navigation path of the device based on the cable identification result; and controlling the underwater navigation device to track the underwater cable based on the device navigation path.

[0007] Furthermore, the underwater video is identified based on the cable recognition model to obtain cable recognition results, including: performing complexity identification on the underwater video to obtain a complexity index of the initial region, wherein the complexity index is used to characterize the difficulty of identifying underwater cables from the initial region; extracting multiple initial image frames from the underwater video based on the complexity index and the video parameters of the underwater video; performing standardization processing on the multiple initial image frames to obtain multiple target image frames; and inputting the multiple target image frames into the cable recognition model to obtain cable recognition results.

[0008] Furthermore, complexity identification is performed on the underwater video to obtain a complexity index for the initial region, including: obtaining the region type of the initial region; performing obstacle identification on the underwater video to obtain obstacle identification results, wherein the obstacle identification results include the type and number of obstacles present in the initial region; and determining the complexity index based on the region type, the type and number of obstacles.

[0009] Furthermore, constructing a navigation path for the device based on the cable identification results includes: determining the integrity of the underwater cable based on its position in the initial area, where integrity is used to characterize whether all underwater cables are in the initial area; in response to the integrity of the underwater cable indicating that not all underwater cables are in the initial area, determining the cable direction based on the cable identification results; determining a target area based on the cable direction, where the target area is used to characterize the area outside the initial area that contains the underwater cable; and constructing a navigation path for the device based on the target area, the initial area, and the cable direction.

[0010] Furthermore, the method also includes: acquiring a target video set, wherein the target video set represents a set of videos captured from underwater areas with different complexity indices, and underwater cables are installed in the underwater areas; dividing the videos contained in the target video set to obtain training videos, validation videos, and test videos, wherein the number of training videos is greater than the number of validation videos, and the number of validation videos is greater than the number of test videos; training an initial recognition model based on the training videos to obtain a trained recognition model; validating the trained recognition model based on the validation videos to obtain a validated recognition model; and testing the validated recognition model based on the test videos to obtain a cable recognition model.

[0011] Furthermore, the verification recognition model is tested based on the test video to obtain a cable recognition model, including: inputting the test video into the verification recognition model to obtain the video recognition result; matching the video recognition result with the cable labeling result corresponding to the test video to obtain the video matching result; determining the model evaluation index of the verification recognition model based on the video matching result, wherein the model evaluation index is used to reflect the accuracy of the recognition result of the verification recognition model; and determining the verification recognition model as a cable recognition model in response to the model evaluation index being greater than a preset index threshold.

[0012] Furthermore, the evaluation metrics for the verification and recognition model are determined based on the video matching results, including: identifying positive and negative samples from the video matching results, wherein positive samples are used to characterize test videos where the matching degree between the video recognition results and the cable labeling results is greater than a first matching degree threshold, and negative samples are used to characterize test videos where, excluding positive samples, the matching degree between the video recognition results and the cable labeling results is greater than a second matching degree threshold, wherein the first matching degree threshold is greater than the second matching degree threshold; determining the precision and recall of the verification and recognition model based on the positive and negative samples; and determining the evaluation metrics for the verification and recognition model based on the precision and recall.

[0013] According to another aspect of the present invention, an underwater cable tracking device is also provided, comprising: a video acquisition module for acquiring underwater video captured by an underwater navigation device, wherein the underwater video is used to characterize a video obtained by shooting an initial area where an underwater cable is deployed; a video recognition module for recognizing the underwater video based on a cable recognition model to obtain a cable recognition result, wherein the cable recognition model is deployed in the underwater navigation device, and the cable recognition result is used to characterize the position of the underwater cable in the initial area; a path construction module for constructing a navigation path for the device based on the cable recognition result; and a device control module for controlling the underwater navigation device to track the underwater cable based on the device navigation path.

[0014] According to another aspect of the present invention, an electronic device is also provided, comprising: a memory storing an executable program; and a processor for running the program, wherein the program executes the methods of various embodiments of the present invention during runtime.

[0015] According to another aspect of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored executable program, wherein, when the executable program is executed, it controls the device where the computer-readable storage medium is located to perform the methods of various embodiments of the present invention.

[0016] According to another aspect of the present invention, a computer program product is also provided, including a computer program that, when executed by a processor, implements the methods of various embodiments of the present invention.

[0017] According to another aspect of the present invention, a computer program product is also provided, including a non-volatile computer-readable storage medium storing a computer program that, when executed by a processor, implements the methods of various embodiments of the present invention.

[0018] According to another aspect of the present invention, a computer program is also provided, which, when executed by a processor, implements the methods of the various embodiments of the present invention.

[0019] In this embodiment of the invention, the underwater navigation equipment captures underwater video; the underwater video is identified based on a cable identification model to obtain cable identification results; a navigation path for the equipment is constructed based on the cable identification results; and the underwater navigation equipment is controlled to track underwater cables based on the navigation path. By identifying the underwater video through the cable identification model to accurately locate the specific position of the underwater cable, and setting the tracking path of the underwater navigation equipment based on the position, the complex underwater environment can be avoided from affecting the tracking of underwater cables. This allows the underwater navigation equipment to quickly and accurately classify and track underwater cables, thereby improving the accuracy and robustness of underwater cable image classification and achieving the technical effect of improving the accuracy of underwater cable identification. This solves the technical problem of low accuracy in underwater cable identification in related technologies. Attached Figure Description

[0020] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0021] Figure 1 This is a flowchart of an underwater cable tracing method according to an embodiment of the present invention;

[0022] Figure 2 This is a flowchart of the training process for an optional underwater cable identification model according to an embodiment of the present invention;

[0023] Figure 3 This is a flowchart of an optional data acquisition and data preprocessing method according to an embodiment of the present invention;

[0024] Figure 4 This is a schematic diagram of an optional confusion matrix according to an embodiment of the present invention;

[0025] Figure 5 This is a schematic diagram of an underwater cable tracking device according to an embodiment of the present invention. Detailed Implementation

[0026] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0027] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0028] According to an embodiment of the present invention, an embodiment of an underwater cable tracing method is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0029] Figure 1 This is a flowchart of an underwater cable tracing method according to an embodiment of the present invention, such as... Figure 1 As shown, the method includes the following steps:

[0030] Step S102: Acquire underwater video captured by the underwater navigation equipment, wherein the underwater video is used to characterize the video obtained by shooting the initial area where underwater cables are deployed.

[0031] The aforementioned underwater navigation equipment can be any type of equipment and tool capable of operating underwater, such as underwater drones, underwater vehicles, etc., but is not limited to these. The aforementioned initial area can be an area where underwater cables are deployed.

[0032] In one alternative embodiment, considering that the underwater environment may be complex, and that underwater video can help operators visually see the location and status of the cable, which is crucial for determining the exact location of the cable and identifying its type, the underwater cable tracking system (hereinafter referred to as the tracking system) can use underwater navigation equipment to take pictures of the initial area where the underwater cable is deployed and return the captured video to the tracking system, so that the tracking system can identify and locate the underwater cable based on the video.

[0033] For example, to accurately acquire video information of an initial area where underwater cables are deployed, the aforementioned underwater navigation equipment can be an autonomous underwater vehicle (AUV). This AUV can be equipped with cameras and lighting equipment, and has sufficient power and video storage space. The tracking system can pre-define the AUV's underwater activity area based on the initial area where underwater cables are deployed, allowing the AUV to capture video within this area. The tracking system can acquire the underwater video captured in real time by the AUV via wireless communication or a physical connection.

[0034] Step S104: The underwater video is identified based on the cable identification model to obtain the cable identification result. The cable identification model is deployed in the underwater navigation equipment, and the cable identification result is used to characterize the position of the underwater cable in the initial area.

[0035] The cable identification model described above can be a machine learning or deep learning model used to identify and classify different types of cables. For example, it can be a deep convolutional neural network model, a support vector machine, etc., but it is not limited to these. The cable identification results described above can be used to indicate the specific location of underwater cables.

[0036] In an optional embodiment, considering that the underwater environment shown in the underwater video may be complex, manually identifying underwater cables is not only time-consuming and labor-intensive but also prone to errors. To improve the efficiency and accuracy of underwater cable identification, the tracking system can use the aforementioned cable identification model to identify the underwater video, thereby obtaining cable identification results and reducing errors caused by human factors. The cable identification results can indicate the specific location of the underwater cable in the initial area, providing a basis for subsequent tracking work.

[0037] For example, the cable recognition model mentioned above could be a deep convolutional neural network (DCNN) model. Assuming the tracking system has already pre-trained this DCNN model, to accurately locate the underwater cable, after acquiring the underwater video captured by the underwater navigation equipment, the tracking system can first perform preprocessing operations on the underwater video, including noise reduction, contrast enhancement, and brightness and contrast adjustment, to improve cable visibility. Then, the tracking system can input the preprocessed underwater video into the trained DCNN model, which can perform cable recognition on each frame of the underwater video, thereby obtaining a cable recognition result representing the position of the underwater cable in the initial region.

[0038] Step S106: Construct the device navigation path based on the cable identification results.

[0039] The navigation path of the aforementioned equipment can be the movement path of the aforementioned underwater navigation equipment when tracking underwater cables.

[0040] In one optional embodiment, considering that the underwater environment may interfere with underwater cable tracking—for example, there may be obstacles such as rocks and vegetation—if the underwater navigation equipment does not have a clear navigation path, it may collide with these obstacles, causing damage to the underwater navigation equipment or failure of the underwater cable tracking task, thereby reducing the efficiency of underwater cable tracking. Therefore, the tracking system can accurately plan the navigation path of the underwater navigation equipment based on the cable identification results, to help the underwater navigation equipment collect cable data more quickly and accurately, thereby improving the efficiency of underwater cable tracking and reducing underwater operation costs.

[0041] For example, in order to rationally plan the navigation path of the underwater navigation equipment and thus improve the efficiency and accuracy of underwater cable tracking, the tracking system can analyze the underwater environment based on the underwater video to determine the navigation path influencing factors, including underwater obstacles. Then, based on the cable identification results and navigation path influencing factors, the system can use a path planning algorithm to set the navigation path of the underwater navigation equipment.

[0042] Step S108: Control the underwater navigation equipment to track the underwater cable based on the equipment navigation path.

[0043] In an optional embodiment, considering that the above-mentioned device navigation path is based on the specific location of the underwater cable, by precisely controlling the navigation path of the underwater navigation device, the interference of the underwater environment on the underwater cable tracking can be avoided, thereby improving the efficiency and accuracy of tracking the underwater cable. Therefore, the tracking system can control the underwater navigation device to track the underwater cable based on the device navigation path.

[0044] For example, staff can equip the underwater navigation equipment with precise positioning and control devices in advance, so that the tracking system can monitor the position of the underwater navigation equipment in real time during underwater operations. If the course of the underwater navigation equipment is found to deviate, the tracking system can detect it in time and correct the course of the underwater navigation equipment, thereby improving the efficiency and accuracy of underwater cable tracking.

[0045] In this embodiment of the invention, the underwater navigation equipment captures underwater video; the underwater video is identified based on a cable identification model to obtain cable identification results; a navigation path for the equipment is constructed based on the cable identification results; and the underwater navigation equipment is controlled to track underwater cables based on the navigation path. By identifying the underwater video through the cable identification model to accurately locate the specific position of the underwater cable, and setting the tracking path of the underwater navigation equipment based on the position, the complex underwater environment can be avoided from affecting the tracking of underwater cables. This allows the underwater navigation equipment to quickly and accurately classify and track underwater cables, thereby improving the accuracy and robustness of underwater cable image classification and achieving the technical effect of improving the accuracy of underwater cable identification. This solves the technical problem of low accuracy in underwater cable identification in related technologies.

[0046] Furthermore, the underwater video is identified based on the cable recognition model to obtain cable recognition results, including: performing complexity identification on the underwater video to obtain a complexity index of the initial region, wherein the complexity index is used to characterize the difficulty of identifying underwater cables from the initial region; extracting multiple initial image frames from the underwater video based on the complexity index and the video parameters of the underwater video; performing standardization processing on the multiple initial image frames to obtain multiple target image frames; and inputting the multiple target image frames into the cable recognition model to obtain cable recognition results.

[0047] The aforementioned complexity index can be an indicator of the ease with which underwater cables can be identified from the initial area. For example, the complexity index may include at least one or more of the following: lighting conditions, water turbidity, target occlusion level, etc., but is not limited to these. The aforementioned video parameters can be parameters used to describe the characteristics of underwater video. For example, the aforementioned video parameters may include at least one or more of the following: video duration, video encoding format, color space, etc., but are not limited to these. The aforementioned initial image frames may be a batch of image frames extracted from underwater video. The aforementioned standardization processing may be to convert the aforementioned initial image frames to a uniform scale to improve the efficiency and accuracy of subsequent processing; for example, it may be adjusted to a size of 75×75 pixels. The aforementioned target image frame may refer to the image frame after standardization processing, which has been converted into a format suitable for input into the cable recognition model.

[0048] In one optional embodiment, considering that the complexity of the underwater environment can severely affect cable identification—for example, underwater lighting conditions, water current disturbances, suspended objects, and obstacles can all increase the difficulty of cable identification—the tracking system can obtain a complexity index for the initial region by performing complexity identification on the underwater video. This index quantifies the difficulty of underwater cable identification, and the tracking system can perform subsequent processing based on this complexity index. Furthermore, considering that only some image frames in the underwater video may capture underwater cables, or that only some image frames may have environmental conditions more suitable for underwater cable identification, the tracking system can extract multiple initial image frames based on the aforementioned complexity index and video parameters. This ensures that the initial image frames used for identification have good cable identification conditions, while avoiding processing a large amount of useless or repetitive information, thereby effectively reducing computational load and improving processing speed. To further improve the accuracy of underwater cable identification, the tracking system can also standardize the multiple initial image frames to obtain multiple target image frames, ensuring that the image data input into the cable identification model has consistent parameters, thereby reducing the uncertainty of the model when processing images. At this point, the tracking system can input the aforementioned multiple target image frames into the cable recognition model. Since the aforementioned multiple target image frames are preprocessed and standardized images, removing factors that may interfere with underwater cable recognition, the cable recognition model can more accurately obtain the aforementioned cable recognition results.

[0049] For example, the cable recognition model mentioned above could be a deep convolutional neural network model. Assuming the underwater environment is complex and variable, to determine the difficulty of underwater cable recognition in such an environment, the tracking system can perform complexity assessment on underwater video based on a pre-built deep learning algorithm. This algorithm can consider factors such as lighting conditions, water turbidity, environmental complexity (e.g., distribution of underwater vegetation, sediment, and rocks), and potential obstructions (e.g., underwater organisms, underwater structures) to calculate a complexity index for the initial region. This index can be a value between 0 and 1; a higher value indicates greater complexity and greater difficulty in recognizing underwater cables. Since the underwater environment contains many obstacles, this index value is relatively high, making underwater cable recognition more difficult. After obtaining the complexity index, the system can divide the underwater video duration equally according to a fixed number of image frames, based on the complexity index and parameters such as the video length, to extract multiple initial image frames from the underwater video, thereby ensuring the accuracy of underwater cable recognition in complex underwater environments. Then, the tracking system can adjust the initial image frames to a size of 75×75 pixels and set the image frames to RGB color mode to obtain the target image frames, thereby enhancing the visibility of underwater cables in the image. After completing the above standardization process, the tracking system can input the target image frames into the deep convolutional neural network model, which will identify the cables in each frame and output the cable identification results.

[0050] For example, suppose the underwater environment described above is a swimming pool without obstacles. In this environment, the underwater navigation equipment can clearly capture underwater cables. The tracking system can use a pre-built deep learning algorithm to identify the complexity of the underwater video, thereby calculating the aforementioned complexity index. Since the underwater environment of the swimming pool is relatively simple and the visibility of the cables is high, after obtaining the complexity index, the system can extract fewer initial image frames from the underwater video image frames at pre-set time intervals based on the complexity index and parameters such as the video duration, to improve the efficiency of underwater cable identification in the swimming pool environment. Then, the tracking system can adjust the size of the initial image frames to 75×75 pixels and set the image frames to RGB color mode to obtain the target image frames. After completing the above standardization process, the tracking system can input the target image frames into the deep convolutional neural network model, which will identify the cables in each frame and output the cable identification results.

[0051] It should be noted that the specific values ​​such as the pixel size after the initial image frame is adjusted are only shown as examples. Staff can set them according to their actual needs, and there are no restrictions here.

[0052] Furthermore, complexity identification is performed on the underwater video to obtain a complexity index for the initial region, including: obtaining the region type of the initial region; performing obstacle identification on the underwater video to obtain obstacle identification results, wherein the obstacle identification results include the type and number of obstacles present in the initial region; and determining the complexity index based on the region type, the type and number of obstacles.

[0053] The aforementioned region type can be the underwater environment type corresponding to the aforementioned initial region. The aforementioned obstacle identification result can be the type and number of obstacles present in the initial region obtained by identifying the aforementioned underwater video.

[0054] In one optional embodiment, considering that different underwater environments can affect the underwater cable identification process, the tracking system can first obtain the region type of the initial area and adjust the processing strategy according to the region type to improve the accuracy of underwater cable identification under different region types. Furthermore, considering that underwater obstacles may obstruct underwater cables and cause visual interference, the tracking system can further perform obstacle identification on the underwater video to assess the impact of different types and numbers of underwater obstacles on the underwater cable identification task. The tracking system can comprehensively consider the aforementioned region type, obstacle type, and obstacle number to obtain a complexity index reflecting the overall difficulty of underwater cable identification, thereby providing a reference for subsequent underwater cable identification.

[0055] For example, the underwater region types included in the aforementioned underwater videos can include open water, underwater vegetation areas, underwater sediment areas, and underwater structure areas. Specifically, for open water, the color distribution in the underwater video images may be relatively uniform. For underwater vegetation areas, the underwater video images may contain a large number of green or brown areas. For underwater sediment areas, the underwater video images may show large areas of gray or brown. For underwater structure areas, the underwater video images may contain more edges and textures. The tracking system can identify the region type of the initial region based on feature extraction and clustering algorithms. By analyzing and comparing the features of the different region types, the type of the initial region can be determined to be an underwater sediment area. To accurately obtain the type and number of underwater obstacles, the tracking system can use a deep learning-based obstacle recognition model, such as the Mask R-CNN model (Mask Region-based Convolutional Neural Network), to analyze each frame in the video, thereby outputting the type and number of obstacles present in the initial region. Finally, the tracking system can analyze the aforementioned complexity indicators based on the area type, obstacle type, and number of obstacles.

[0056] Furthermore, constructing a navigation path for the device based on the cable identification results includes: determining the integrity of the underwater cable based on its position in the initial area, where integrity is used to characterize whether all underwater cables are in the initial area; in response to the integrity of the underwater cable indicating that not all underwater cables are in the initial area, determining the cable direction based on the cable identification results; determining a target area based on the cable direction, where the target area is used to characterize the area outside the initial area that contains the underwater cable; and constructing a navigation path for the device based on the target area, the initial area, and the cable direction.

[0057] The aforementioned integrity level can be an indicator used to assess whether an underwater cable is within the current "initial area." The aforementioned cable orientation can refer to the direction in which the cable extends within the underwater environment. The aforementioned target area can refer to the area that the underwater navigation equipment needs to explore to detect the integrity of the cable.

[0058] In one optional embodiment, considering that the underwater navigation equipment's camera or sensor has a limited field of view, if one end or part of the cable exceeds this range, complete cable information cannot be obtained. Therefore, the tracking system can first determine the integrity of the underwater cable based on its position in the initial area. This helps identify whether the position or orientation of the underwater navigation equipment needs to be adjusted to capture the complete portion of the cable. When the integrity indicates that the underwater cable is not fully present in the initial area, the tracking system can determine the extension direction of the underwater cable based on the cable identification result. This guides the next action of the underwater navigation equipment, i.e., in which direction the equipment should move to track the remaining parts of the cable. After determining the extension direction of the underwater cable, the tracking system can calculate the possible extension area of ​​the cable, i.e., the target area, to ensure complete tracking. Finally, the tracking system can comprehensively consider the target area, the initial area, and the direction of the underwater cable to construct a navigation path for the underwater navigation equipment to continue tracking the cable. This avoids unnecessary detours, saves time and energy, and improves the tracking efficiency of the underwater cable.

[0059] For example, assuming the tracking system has acquired a set of underwater videos captured in real-time by the underwater navigation equipment, to track the underwater cable more completely, the tracking system can use the underwater video to determine the cable's integrity based on its position in the initial area. This integrity indicates that the underwater cable is interrupted at the right boundary of the underwater video image and does not appear completely within the initial area. At this point, the tracking system can determine, based on the cable's current position and total length, that the underwater cable will extend to the upper right of the current initial area, and designate the area located to the upper right of the current initial area as the target area. Then, the tracking system can combine the target area, the initial area, and the cable direction to plan the underwater navigation equipment's navigation path. This path can guide the underwater navigation equipment to track along the cable's direction until the entire length of the cable is detected.

[0060] Furthermore, the method also includes: acquiring a target video set, wherein the target video set represents a set of videos captured from underwater areas with different complexity indices, and underwater cables are installed in the underwater areas; dividing the videos contained in the target video set to obtain training videos, validation videos, and test videos, wherein the number of training videos is greater than the number of validation videos, and the number of validation videos is greater than the number of test videos; training an initial recognition model based on the training videos to obtain a trained recognition model; validating the trained recognition model based on the validation videos to obtain a validated recognition model; and testing the validated recognition model based on the test videos to obtain a cable recognition model.

[0061] The aforementioned target video set can refer to a series of videos taken in underwater areas with varying complexity levels. The aforementioned training videos can be a majority segment of the target video set, used to train the cable recognition model. The aforementioned validation videos can be a smaller subset of the target video set, fewer in number than the training videos, used to validate the model's performance during training. The aforementioned test videos can be an even smaller subset of the target video set, fewer in number than the validation videos, used to ultimately evaluate the cable recognition model's performance. The aforementioned initial recognition model can be an initially constructed underwater cable recognition model with low accuracy, requiring further model training. The aforementioned training recognition model can be a model obtained by training the initial recognition model based on the training videos. The aforementioned validation recognition model can be a model obtained by validating the training recognition model based on the validation videos.

[0062] In an optional embodiment, considering the low accuracy of the initial recognition model built by the tracking system, and to avoid overfitting the initial recognition model to a specific environment or condition, and to ensure better generalization ability in actual underwater environments, the tracking system can first acquire the target video set. This set includes videos taken of underwater areas with different complexity indices. This means that the initial recognition model will have the opportunity to learn the characteristics of underwater cables under various underwater conditions. To improve the training effect of the initial recognition model, the tracking system can further divide the target video set into three categories: training videos, validation videos, and test videos. Among these, the training videos are more numerous and are mainly used to train the model, enabling it to learn the characteristics and patterns of cables. A large amount of training data can help the model extract richer information and improve recognition accuracy. The tracking system trains the initial recognition model based on the training videos to obtain a trained recognition model. The number of validation videos is less than the number of training videos. These validation videos are used to fine-tune model parameters during training, monitor overfitting, and ensure the model performs well on unseen data. Feedback from the validation set allows for adjustments to model complexity and optimization of hyperparameters. The tracking system validates the trained recognition model based on these validation videos, resulting in a validated recognition model. The number of test videos is also less than the number of validation videos. These test videos are used to evaluate the final performance of the validated recognition model after the initial training and validation processes are complete. The tracking system tests the validated recognition model based on these test videos, resulting in a cable recognition model.

[0063] For example, we can assume that the tracking system has already built an initial recognition model for underwater cable identification based on a deep convolutional neural network. The tracking system can collect 1000 underwater video clips from various underwater cable detection projects. Each video clip is filmed in an underwater area with varying complexity and contains images of underwater cables. The tracking system can then randomly select 700 clips from these 1000 clips as a training set, 200 as a validation set, and the remaining 100 as a test set. This ensures the model is trained on a large dataset, validated on a smaller but sufficient dataset, and finally tested on entirely new, unseen data to evaluate its generalization ability. Subsequently, the tracking system can use the videos from the training set as input to train the initial recognition model, resulting in a trained recognition model that learns how to identify cables from video frames, including details such as cable location, shape, and texture. To enhance the model's robustness and accuracy, the tracking system can also apply data augmentation techniques, such as rotation, flipping, and scaling, to increase the diversity of the training data. Then, the tracking system can use the videos in the validation set to validate the trained recognition model, thus obtaining the validated recognition model. The cable positions and attributes in the validation videos have been pre-labeled, and this labeled data will serve as the benchmark for evaluating the trained recognition model. The performance of the trained recognition model on the validation set is used to adjust the model's parameters, such as reducing overfitting and optimizing the model's structure, ensuring that the model performs well not only on training data but also maintains high performance on new data. Finally, the tracking system can use the videos in the test set to perform a final performance test on the validated recognition model, thus obtaining the cable recognition model. The test set data was not used in either the training or validation phases to ensure the fairness and validity of the test results.

[0064] It should be noted that the specific values ​​mentioned above, such as the number of underwater videos, the number of videos in the training set, the number of videos in the validation set, and the number of videos in the test set, are only for illustrative purposes. Staff can set them according to their actual needs, and there are no restrictions here.

[0065] Furthermore, the verification recognition model is tested based on the test video to obtain a cable recognition model, including: inputting the test video into the verification recognition model to obtain the video recognition result; matching the video recognition result with the cable labeling result corresponding to the test video to obtain the video matching result; determining the model evaluation index of the verification recognition model based on the video matching result, wherein the model evaluation index is used to reflect the accuracy of the recognition result of the verification recognition model; and determining the verification recognition model as a cable recognition model in response to the model evaluation index being greater than a preset index threshold.

[0066] The cable labeling results mentioned above can refer to the ground truth information obtained by manually or automatically labeling the cable positions in each frame of the test video. The video matching results mentioned above can be the comparison results of the model's recognition results on the test video with the cable labeling results. The model evaluation metrics mentioned above can be a set of standards used to quantitatively evaluate the performance of the cable recognition model. For example, the model evaluation metrics mentioned above can include at least one or more of the following: accuracy, recall, etc., but are not limited to these. The preset threshold values ​​mentioned above can be pre-set values ​​used to determine whether the performance of the above-mentioned verification recognition model can meet the needs of practical applications.

[0067] In an optional embodiment, considering that the test video is not the data encountered during the training of the verification and recognition model, it can be used to evaluate the generalization ability of the verification and recognition model, i.e., whether the verification and recognition model can accurately identify unseen underwater cable images. Therefore, the tracking system can input the test video into the verification and recognition model to obtain video recognition results. Simultaneously, the tracking system can match the video recognition results with the cable labeling results corresponding to the test video to obtain video matching results. Then, the tracking system can match the video recognition results of the verification and recognition model with the cable labeling results corresponding to the test video to obtain video matching results. By comparing the cable position, direction, and state identified by the model with the manually labeled "ground truth" information, the tracking system can further calculate the model evaluation index of the verification and recognition model. Finally, the tracking system can determine whether the verification and recognition model has reached the predetermined performance standard based on the model evaluation index determined by the video matching results. If the model evaluation index of the verification and recognition model is greater than the preset index threshold, it indicates that the verification and recognition model is mature and accurate enough to handle actual underwater cable identification tasks. At this point, the tracking system can determine the verification and recognition model as the cable identification model, i.e., the identification model ultimately deployed in practical applications.

[0068] For example, we can assume that after the training and verification steps described above, the tracking system has obtained the verification and recognition model, and the preset threshold value can be 0.8. To obtain a cable recognition model with high accuracy, the tracking system can input pre-divided test videos into the verification and recognition model to obtain video recognition results. Simultaneously, professionals in the power system field can perform detailed underwater cable annotation on the test videos to obtain cable annotation results. Then, the tracking system can use a matching algorithm to compare the recognition output of the verification and recognition model with the cable annotation results to determine the correctness and accuracy of the verification and recognition model, i.e., the model evaluation index. We can assume that the determined model evaluation index value is 0.85. Finally, the tracking system can compare the model evaluation index with the preset threshold value. Since the model evaluation index value is greater than the preset threshold value, it indicates that the verification and recognition model exhibits high accuracy and comprehensiveness in identifying underwater cables. Therefore, the tracking system can identify the verification and recognition model as the cable recognition model.

[0069] It should be noted that the specific values ​​of the preset indicator thresholds and model evaluation indicators mentioned above are only for illustrative purposes. Staff can set them according to their actual needs, and there are no restrictions here.

[0070] Furthermore, the evaluation metrics for the verification and recognition model are determined based on the video matching results, including: identifying positive and negative samples from the video matching results, wherein positive samples are used to characterize test videos where the matching degree between the video recognition results and the cable labeling results is greater than a first matching degree threshold, and negative samples are used to characterize test videos where, excluding positive samples, the matching degree between the video recognition results and the cable labeling results is greater than a second matching degree threshold, wherein the first matching degree threshold is greater than the second matching degree threshold; determining the precision and recall of the verification and recognition model based on the positive and negative samples; and determining the evaluation metrics for the verification and recognition model based on the precision and recall.

[0071] The aforementioned positive samples can refer to test videos where the matching degree between the video recognition result and the cable labeling result is greater than the aforementioned first matching degree threshold. The aforementioned negative samples can refer to test videos, excluding positive samples, where the matching degree between the video recognition result and the cable labeling result is greater than the aforementioned second matching degree threshold. The aforementioned first matching degree threshold can be a threshold used to determine whether the matching degree between the model recognition result and the cable labeling result is sufficiently high. The aforementioned second matching degree threshold can be a threshold used to distinguish samples with a low matching degree between the model recognition result and the cable labeling result. The aforementioned precision can be the proportion of samples predicted as cables by the aforementioned verification recognition model that are actually cables. The aforementioned recall can be the proportion of all actual cables correctly identified by the aforementioned verification recognition model.

[0072] In an optional embodiment, considering that differentiating the video matching results helps to more comprehensively understand the performance of the verification and identification model, the tracking system can first determine positive and negative samples from the video matching results. This division is based on the matching degree between the model's identification results and the actual annotation results. Specifically, the tracking system can classify test videos where the matching degree between the video identification results and the cable annotation results is greater than the first matching degree threshold as positive samples, and test videos where the matching degree is less than or equal to the first matching degree threshold but greater than the second matching degree threshold as negative samples. Then, based on the positive and negative samples, the tracking system can further determine the precision and recall of the verification and identification model, and can determine the model evaluation metrics based on precision and recall. Precision and recall quantify the accuracy and comprehensiveness of the verification and identification model in identifying underwater cables, thus more specifically describing the performance of the verification and identification model under different conditions, and whether the model can effectively detect all existing cables while avoiding unnecessary false alarms.

[0073] For example, assuming the tracking system has obtained the aforementioned verification and recognition model after the training and verification steps, to accurately obtain the model evaluation metrics and thus more precisely understand its recognition performance, the tracking system can set the first matching threshold to 0.85 and the second matching threshold to 0.4. Then, for each frame in the test video, the tracking system can calculate the intersection-over-union (IoU) between the cable bounding box identified by the verification and recognition model and the cable bounding box annotated by the expert. If the IoU is greater than 0.85, the tracking system can mark this frame as a positive sample, meaning that the verification and recognition model accurately identified the underwater cable in this frame. Subsequently, the tracking system can mark video frames with an IoU greater than 0.4 but less than or equal to 0.85 as negative samples. These samples indicate that although the verification and recognition model has not reached the "high matching" standard, it can still find the approximate location of the underwater cable. Based on the positive and negative samples, the tracking system can calculate the precision and recall of the verification and recognition model. The precision calculation formula is as follows:

[0074]

[0075] In the formula, P represents precision. true P represents the number of samples in which the verification model correctly identified the cable, i.e., the number of positive samples. falseThis represents the number of samples where the validation model incorrectly identified non-cable areas as cables. The recall rate can be calculated using the following formula:

[0076]

[0077] In the formula, γ represents the recall rate, and N false This represents the number of samples where the underwater cable actually exists but the verification and identification model failed to identify it. The interpretations of other symbols in the formula are consistent with those in the previous formula and will not be repeated here. Finally, the tracking system can further determine the model evaluation metrics for the verification and identification model based on the aforementioned precision and recall.

[0078] It should be noted that the specific values ​​of the first matching degree threshold, the second matching degree threshold, etc. mentioned above are only shown as examples. Staff can set them according to their actual needs, and there are no restrictions here.

[0079] For ease of understanding, Figure 2 This is a flowchart illustrating the training process of an optional underwater cable recognition model according to an embodiment of the present invention, such as... Figure 2 As shown, the tracking system can perform data acquisition and preprocessing, and construct a deep neural network model. Specifically, the tracking system can obtain multiple videos of underwater cable tracking and inspection from underwater cable service companies. These videos cover different types of underwater cables and their status under various environmental conditions. The tracking system can convert the collected videos into a series of still images (video frames) for subsequent image analysis and processing. Then, the tracking system can normalize these video frames to 75×75 pixels and arrange them accordingly. Next, the tracking system can input these video frames into a deep convolutional neural network model for training. Transfer learning and data augmentation are used to optimize the deep convolutional neural network model, achieving a cable image classification accuracy of over 90%. Finally, based on the classification results, the tracking system can further optimize the deep convolutional neural network model for underwater cable image classification.

[0080] It should be noted that the specific values ​​such as the pixel size after standardization of the video frames mentioned above are only for illustrative purposes. Staff can set them according to their actual needs, and there are no restrictions here.

[0081] Figure 3 This is a flowchart of an optional data acquisition and data preprocessing method according to an embodiment of the present invention, such as... Figure 3As shown, data acquisition includes acquiring video sets and extracting video frames. Acquiring video sets refers to obtaining a set of video clips related to underwater cables from multiple underwater cable service companies. These videos contain actual images of underwater cables under different environments, such as varying lighting conditions, water clarity, and cable condition. Extracting video frames involves segmenting the collected videos into a series of static images, i.e., video frames, for image analysis and training of the deep convolutional neural network (DNN) model. After data acquisition, dataset preprocessing can be performed, including constructing positive and negative samples, adjusting the video frame size to 3×75×75 pixels, and building training, validation, and test datasets. Constructing positive and negative samples helps to more comprehensively understand the performance of the DNN model. Adjusting the video frame size ensures consistency of images when inputting them into the DNN model for training. Building training, validation, and test datasets improves the training effect of the DNN model, thereby increasing its recognition accuracy. After dataset preprocessing, the DNN model can be constructed, and then trained based on the dataset.

[0082] It should be noted that the specific values ​​such as the video frame size mentioned above are only for illustrative purposes. Staff can set them according to their actual needs, and there are no restrictions here.

[0083] Figure 4 This is a schematic diagram of an optional confusion matrix according to an embodiment of the present invention, such as... Figure 4 As shown in the diagram, TP represents a true positive, meaning the model correctly predicts an image containing underwater cables as a positive class. This indicates that the model not only detected the cable but also correctly classified it as "with cable." FP represents a false positive, meaning the model incorrectly predicts an image without underwater cables as a positive class, i.e., the model mistakenly identifies an image without cables as "with cable." FN represents a false negative, meaning the model fails to correctly predict an image containing underwater cables as a positive class, i.e., the model misses an image with cables. TN represents a true negative, meaning the model correctly predicts an image without underwater cables as a negative class, i.e., the model accurately identifies an image without cables. The confusion matrix provides an intuitive view of the underwater cable recognition model's performance, helping to understand the model's classification ability, especially its performance when dealing with positive classes (images with cables) and negative classes (images without cables). By analyzing the confusion matrix, we can identify the model's shortcomings and further optimize its parameters or improve data processing strategies to enhance the model's overall performance and reliability.

[0084] According to an embodiment of the present invention, an underwater cable tracking device is provided. It should be noted that this device can be used to execute the aforementioned underwater cable tracking method. The specific implementation and application scenarios are the same as in the above embodiment, and will not be repeated here. Figure 5 This is a schematic diagram of an underwater cable tracking device according to an embodiment of the present invention, as shown below. Figure 5 As shown, the device includes:

[0085] The video acquisition module 502 is used to acquire underwater videos captured by the underwater navigation equipment. The underwater videos are used to represent the videos obtained by shooting the initial area where underwater cables are deployed.

[0086] The video recognition module 504 is used to recognize underwater video based on the cable recognition model to obtain cable recognition results. The cable recognition model is deployed in the underwater navigation equipment, and the cable recognition results are used to characterize the position of the underwater cable in the initial area.

[0087] The path construction module 506 is used to construct the device navigation path based on the cable identification results.

[0088] The equipment control module 508 controls the underwater navigation equipment to track underwater cables based on the equipment's navigation path.

[0089] Furthermore, the video recognition module is also used to: perform complexity identification on the underwater video to obtain a complexity index of the initial region, wherein the complexity index is used to characterize the difficulty of identifying the underwater cable from the initial region; based on the complexity index and the video parameters of the underwater video, extract multiple initial image frames from the underwater video; perform standardization processing on the multiple initial image frames to obtain multiple target image frames; input the multiple target image frames into the cable recognition model to obtain the cable recognition result.

[0090] Furthermore, the video recognition module is also used to: obtain the region type of the initial region; perform obstacle recognition on the underwater video to obtain obstacle recognition results, wherein the obstacle recognition results include the type and number of obstacles existing in the initial region; and determine the complexity index based on the region type, the type and number of obstacles.

[0091] Furthermore, the path construction module is also used to: determine the integrity of the underwater cable based on its position in the initial area, wherein the integrity is used to characterize whether the underwater cable is entirely within the initial area; in response to the integrity of the underwater cable indicating that the underwater cable is not entirely within the initial area, determine the cable direction based on the cable identification result; determine the target area based on the cable direction, wherein the target area is used to characterize the area outside the initial area that contains the underwater cable; and construct the equipment navigation path based on the target area, the initial area, and the cable direction.

[0092] Furthermore, the device also includes: a first acquisition module for acquiring a target video set, wherein the target video set represents a set of videos captured from underwater areas with different complexity indices, and underwater cables are installed in the underwater areas; a first partitioning module for partitioning the videos contained in the target video set to obtain training videos, verification videos, and test videos, wherein the number of training videos is greater than the number of verification videos, and the number of verification videos is greater than the number of test videos; a model training module for training an initial recognition model based on the training videos to obtain a trained recognition model; a model verification module for verifying the trained recognition model based on the verification videos to obtain a verified recognition model; and a model testing module for testing the verified recognition model based on the test videos to obtain a cable recognition model.

[0093] Furthermore, the model testing module is also used for: inputting a test video into the verification recognition model to obtain a video recognition result; matching the video recognition result with the cable labeling result corresponding to the test video to obtain a video matching result; determining the model evaluation index of the verification recognition model based on the video matching result, wherein the model evaluation index is used to reflect the accuracy of the recognition result of the verification recognition model; and determining the verification recognition model as a cable recognition model in response to the model evaluation index being greater than a preset index threshold.

[0094] Furthermore, the model testing module is also used to: determine positive and negative samples from the video matching results, wherein positive samples are used to characterize test videos in which the matching degree between the video recognition result and the cable labeling result is greater than a first matching degree threshold, and negative samples are used to characterize test videos in which, excluding positive samples, the matching degree between the video recognition result and the cable labeling result is greater than a second matching degree threshold, wherein the first matching degree threshold is greater than the second matching degree threshold; determine the precision and recall of the verification recognition model based on the positive and negative samples; and determine the model evaluation index of the verification recognition model based on the precision and recall.

[0095] Embodiments of this application also provide an electronic device, including: a memory storing an executable program; and a processor for running the program, wherein the program executes the methods in various embodiments of the present invention during runtime.

[0096] Embodiments of this application also provide a computer-readable storage medium including a stored executable program, wherein, when the executable program is running, it controls the device where the computer-readable storage medium is located to perform the methods of various embodiments of the present invention.

[0097] Embodiments of this application also provide a computer program product, including a computer program that, when executed by a processor, implements the methods of various embodiments of the present invention.

[0098] Embodiments of this application also provide a computer program product, including a non-volatile computer-readable storage medium for storing a computer program that, when executed by a processor, implements the methods in various embodiments of the present invention.

[0099] Embodiments of this application also provide a computer program that, when executed by a processor, implements the methods described in the various embodiments of the present invention.

[0100] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0101] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0102] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0103] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0104] If the integrated unit is implemented as 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 technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0105] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for underwater cable tracking, characterized in that, include: Acquire underwater video captured by underwater navigation equipment, wherein the underwater video is used to characterize the video obtained by shooting an initial area where underwater cables are deployed; The underwater video is identified based on a cable identification model to obtain cable identification results. The cable identification model is deployed in the underwater navigation equipment, and the cable identification results are used to characterize the position of the underwater cable in the initial area. The device navigation path is constructed based on the cable identification results; The underwater navigation equipment is controlled to track the underwater cable based on the navigation path of the equipment. The process of identifying underwater cables based on a cable identification model to obtain cable identification results includes: performing complexity identification on the underwater video to obtain a complexity index for the initial region, wherein the complexity index is used to characterize the difficulty of identifying the underwater cables from the initial region; extracting multiple initial image frames from the underwater video based on the complexity index and the video parameters of the underwater video; performing standardization processing on the multiple initial image frames to obtain multiple target image frames; and inputting the multiple target image frames into the cable identification model to obtain the cable identification results. Constructing a device navigation path based on the cable identification result includes: determining the integrity of the underwater cable based on its position in the initial area, wherein the integrity is used to characterize whether the underwater cable is entirely within the initial area; in response to the integrity of the underwater cable indicating that it is not entirely within the initial area, determining the cable direction based on the cable identification result; determining a target area based on the cable direction, wherein the target area characterizes an area outside the initial area that contains the underwater cable; and constructing the device navigation path based on the target area, the initial area, and the cable direction.

2. The method according to claim 1, characterized in that, Complexity identification is performed on the underwater video to obtain a complexity index for the initial region, including: Obtain the region type of the initial region; Obstacle identification is performed on the underwater video to obtain obstacle identification results, wherein the obstacle identification results include the type and number of obstacles present in the initial area; The complexity index is determined based on the region type, the obstacle type, and the number of obstacles.

3. The method according to claim 1, characterized in that, The method further includes: Obtain a target video set, wherein the target video set is used to represent a video set obtained by shooting underwater areas with different complexity indices, and the underwater area is equipped with the underwater cable; The target video set is divided into training videos, verification videos, and test videos, wherein the number of training videos is greater than the number of verification videos, and the number of verification videos is greater than the number of test videos; an initial recognition model is trained based on the training videos to obtain a trained recognition model; The trained recognition model is validated based on the validation video to obtain the validated recognition model; The verification and recognition model is tested based on the test video to obtain the cable recognition model.

4. The method according to claim 3, characterized in that, The verification and recognition model is tested based on the test video to obtain the cable recognition model, including: Input the test video into the verification and recognition model to obtain the video recognition result; The video recognition result is matched with the cable labeling result corresponding to the test video to obtain the video matching result; The model evaluation index of the verification and recognition model is determined based on the video matching results, wherein the model evaluation index is used to reflect the accuracy of the recognition results of the verification and recognition model; If the model evaluation index is greater than a preset index threshold, the verification and identification model is determined to be the cable identification model.

5. The method according to claim 4, characterized in that, Based on the video matching results, the model evaluation metrics for the verification and recognition model are determined, including: Positive and negative samples are determined from the video matching results. The positive samples are used to characterize test videos where the matching degree between the video recognition result and the cable labeling result is greater than a first matching degree threshold. The negative samples are used to characterize test videos where, excluding the positive samples, the matching degree between the video recognition result and the cable labeling result is greater than a second matching degree threshold. The first matching degree threshold is greater than the second matching degree threshold. Based on the positive and negative samples, determine the precision and recall of the verification and identification model; Based on the precision and the recall, the model evaluation index of the verification and identification model is determined.

6. An electronic device, characterized in that, include: Memory, which stores executable programs; A processor for running the program, wherein the program, when running, performs the method according to any one of claims 1 to 5.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored executable program, wherein, when the executable program is executed, it controls the device on which the storage medium is located to perform the method according to any one of claims 1 to 5.

8. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method according to any one of claims 1 to 5.

Images