Foreign matter removing method and device based on laser obstacle clearing instrument, storage medium and equipment

Abstract

The present disclosure relates to a foreign matter removing method and device based on a laser obstacle removing instrument, a storage medium and equipment, comprising: determining first position information of the foreign matter to be removed in a real-time monitoring image, adjusting the monitoring pose of the laser obstacle removing instrument according to the first position information and the preset crosshair position of the laser obstacle removing instrument in the real-time monitoring image, measuring the distance between the center position of the foreign matter to be removed and the laser obstacle removing instrument according to the set ranging parameter of the laser obstacle removing instrument to generate the target distance of the foreign matter to be removed, determining the target preset position parameter of the sliding focusing lens matched with the target distance from the preset mapping relationship, adjusting the position of the sliding focusing lens between a plurality of fixed focusing lenses according to the target preset position parameter, and emitting the set obstacle removing laser to the foreign matter to be removed based on the laser obstacle removing instrument. Thus, the detected foreign matter to be removed is processed by long-distance obstacle removing in the form of laser obstacle removing, and the obstacle removing convenience and accuracy are improved.

Description

Technical Field

[0001] This disclosure relates to the field of optoelectronic technology, and in particular to a method, apparatus, storage medium and device for removing foreign objects based on a laser obstacle removal device. Background Technology

[0002] Outdoor power transmission and distribution lines are frequently exposed to hazards such as floating debris and icing. A phase-to-phase short circuit can cause significant economic losses and accidents for the power sector. Traditional solutions require either power outages or live-line work. Power outages result in economic losses and reduce power supply reliability. Live-line work requires personnel to climb towers and make indirect or direct contact with live conductors, posing a high risk. Summary of the Invention

[0003] To overcome the technical problem of high risk in power line obstacle removal operations in related technologies, this disclosure provides a method, apparatus, storage medium, and equipment for removing foreign objects based on a laser obstacle removal device.

[0004] According to a first aspect of the present disclosure, a method for removing foreign objects based on a laser obstacle removal device is provided, applied to a laser obstacle removal device, the laser obstacle removal device including a plurality of fixed focusing lenses and a sliding focusing lens, the sliding focusing lens being located between the plurality of fixed focusing lenses, the method comprising:

[0005] In response to the identification of a foreign object to be removed in a real-time monitoring image, the first location information of the foreign object to be removed in the real-time monitoring image is determined;

[0006] Based on the first location information and the preset crosshair position of the laser obstacle clearing device in the real-time monitoring image, the monitoring posture of the laser obstacle clearing device is adjusted so that the center position of the foreign object to be cleared overlaps with the preset crosshair position of the real-time monitoring image.

[0007] In response to the fact that the center position of the foreign object to be removed is located at the preset crosshair position, the distance between the center position of the foreign object to be removed and the laser obstacle removal device is measured according to the set ranging parameters of the laser obstacle removal device, so as to generate the target distance of the foreign object to be removed;

[0008] The target preset position parameters of the sliding focusing lens that match the target distance are determined from the preset mapping relationship, wherein the preset mapping relationship includes a one-to-one correspondence between multiple distances and multiple preset position parameters;

[0009] The position of the sliding focusing lens is adjusted among the plurality of fixed focusing lenses according to the target preset position parameters, so that the laser light emitted by the laser obstacle clearing device is focused at the preset crosshair position after being refracted by the plurality of fixed focusing lenses and the sliding focusing lens. In response to the sliding focusing lens moving to the target position corresponding to the target preset position parameters, the laser obstacle clearing device emits a set obstacle clearing laser towards the foreign object to be cleared.

[0010] Optionally, the method further includes:

[0011] Acquire the real-time monitoring image;

[0012] The real-time monitoring image is identified by a preset convolutional neural network to generate a foreign object monitoring result for the real-time monitoring image. The preset convolutional neural network is used to identify foreign objects on the wire to be monitored in the monitoring image to generate a foreign object monitoring result for the wire to be monitored.

[0013] If, based on the foreign object monitoring results, it is determined that the coverage area of ​​the foreign object to be removed reaches a set threshold, then it is determined that the foreign object to be removed exists in the real-time monitoring image.

[0014] Optionally, determining the first location information of the foreign object to be removed in the real-time monitoring image includes:

[0015] The real-time monitoring image is preprocessed to generate a target recognition image. The preprocessing includes at least one of image noise reduction, image filtering, and grayscale image contrast enhancement.

[0016] An image registration algorithm based on corner features is used to register the foreign object to be removed in the target recognition image to determine the location range of the foreign object to be removed in the real-time monitoring image.

[0017] Based on a preset planar coordinate system, the coordinate information corresponding to the center position of the position range is determined as the first position information.

[0018] Optionally, the corner-feature-based image registration algorithm registers the foreign object to be removed in the target recognition image to determine the location range of the foreign object in the real-time monitoring image, including:

[0019] Based on the image registration algorithm of the corner features, identify multiple corner information of the foreign object to be removed in the target recognition image;

[0020] Determine the image features of the region surrounding the multiple corner point information in the target recognition image, and generate multiple local feature vectors;

[0021] The multiple local characteristic vectors are matched with the local feature vector group to determine the foreign object category information of the foreign object to be removed;

[0022] Based on the foreign object category information, determine the boundary line type of the foreign object to be removed;

[0023] Based on the boundary line type, the foreign object to be removed in the real-time monitoring image is selected to generate the location range.

[0024] Optionally, matching the plurality of local feature vectors with the local feature vector group to determine the foreign object category information of the foreign object to be removed includes:

[0025] Determine multiple similarity information between the plurality of local feature vectors and the plurality of initial local feature vectors in the local feature vector group;

[0026] Based on the multiple similarity information, obtain the target local feature vector group with the highest similarity;

[0027] The target foreign object category information corresponding to the target local feature vector group is determined as the foreign object category information of the foreign object to be removed.

[0028] Optionally, the laser obstacle removal device includes a stepper motor sliding device, which controls the movement of the sliding focusing lens among the plurality of fixed focusing lenses. Adjusting the position of the sliding focusing lens among the plurality of fixed focusing lenses according to the target preset position parameters includes:

[0029] The number of drive pulses for the stepper motor sliding device is determined based on the preset position parameters.

[0030] The stepper motor sliding device is driven according to the number of driving pulses, which in turn drives the sliding focusing lens to move between the plurality of fixed focusing lenses.

[0031] Optionally, determining the number of drive pulses for the stepper motor sliding device based on the preset position parameters includes:

[0032] Determine the first distance information between the sliding focusing lens and the first fixed focusing lens, wherein the first fixed focusing lens is the lens among the plurality of fixed focusing lenses that is closest to the lens of the laser obstacle clearing device;

[0033] Based on the first distance information and the preset position parameters, the distance difference information of the sliding focusing lens is determined;

[0034] The number of driving pulses is determined based on the distance difference information.

[0035] According to a second aspect of the present disclosure, a foreign object removal device based on a laser obstacle removal device is provided, applied to a laser obstacle removal device, the laser obstacle removal device including a plurality of fixed focusing lenses and a sliding focusing lens, the sliding focusing lens being located between the plurality of fixed focusing lenses, the device comprising:

[0036] The first determining module is used to determine the first location information of the foreign object to be removed in the real-time monitoring image in response to the identification of the foreign object to be removed in the real-time monitoring image;

[0037] The adjustment module is used to adjust the monitoring posture of the laser obstacle clearing device according to the first position information and the preset crosshair position of the laser obstacle clearing device in the real-time monitoring image, so that the center position of the foreign object to be cleared overlaps with the preset crosshair position of the real-time monitoring image.

[0038] The generation module is used to, in response to the fact that the center position of the foreign object to be removed is located at the preset crosshair position, measure the distance between the center position of the foreign object to be removed and the laser obstacle removal device according to the set ranging parameters of the laser obstacle removal device, so as to generate the target distance of the foreign object to be removed;

[0039] The second determining module is used to determine the target preset position parameter of the sliding focusing lens that matches the target distance from the preset mapping relationship, wherein the preset mapping relationship includes a one-to-one correspondence between multiple distances and multiple preset position parameters;

[0040] The execution module is used to adjust the position of the sliding focusing lens among the plurality of fixed focusing lenses according to the target preset position parameters, so that the laser light emitted by the laser obstacle clearing device is focused at the preset crosshair position after being refracted by the plurality of fixed focusing lenses and the sliding focusing lens. In response to the sliding focusing lens moving to the target position corresponding to the target preset position parameters, the laser obstacle clearing device emits a set obstacle clearing laser towards the foreign object to be cleared.

[0041] According to a third aspect of the present disclosure, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps of the method described in any of the first aspects.

[0042] According to a fourth aspect of the present disclosure, an electronic device is provided, comprising:

[0043] processor;

[0044] Memory used to store processor-executable instructions;

[0045] The processor is configured to execute executable instructions in the memory to implement the method described in any one of the first aspects.

[0046] The technical solutions provided by the embodiments of this disclosure may include the following beneficial effects:

[0047] The above scheme determines the first position information of the foreign object to be removed in the real-time monitoring image. Based on the first position information and the preset crosshair position of the laser obstacle removal device in the real-time monitoring image, the monitoring posture of the laser obstacle removal device is adjusted. According to the set ranging parameters of the laser obstacle removal device, the distance between the center position of the foreign object to be removed and the laser obstacle removal device is measured to generate the target distance of the foreign object to be removed. The target preset position parameters of the sliding focusing lens matching the target distance are determined from a preset mapping relationship. The position of the sliding focusing lens among the multiple fixed focusing lenses is adjusted according to the target preset position parameters. The laser obstacle removal device emits a set obstacle removal laser towards the foreign object to be removed. Thus, by using laser obstacle removal, the detected foreign object to be removed can be removed at a long distance, ensuring the accuracy of the foreign object aiming and solving the problem of energy dispersion during laser transmission, thereby improving the convenience and accuracy of obstacle removal.

[0048] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0049] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0050] Figure 1 This is a flowchart illustrating a foreign object removal method based on a laser obstacle clearer, according to an exemplary embodiment.

[0051] Figure 2 This is a schematic diagram of an electrically focused optical path according to an exemplary embodiment.

[0052] Figure 3 This is a schematic diagram illustrating a foreign object removal method based on a laser obstacle removal device according to an exemplary embodiment.

[0053] Figure 4 This is a block diagram illustrating a foreign object removal device based on a laser obstacle clearer, according to an exemplary embodiment. Detailed Implementation

[0054] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0055] It should be noted that all actions involving the acquisition of signals, information, or data in this application are carried out in compliance with the relevant data protection laws and policies of the country where the application is located, and with the authorization granted by the owner of the relevant device.

[0056] In related technologies, transmission and distribution lines and small overhead lines are located in urban and suburban areas with complex and variable surrounding environments. Short circuits are frequently caused by objects such as kites and ribbons, threatening power grid safety. Currently, the most common method for clearing these obstacles is to cut off power and climb the lines, which is time-consuming, labor-intensive, and inefficient. During inspections of transmission and distribution overhead lines, it is common to encounter kites, sky lanterns, plastic bags, and other hanging objects. This hazard is especially difficult to address promptly during holidays.

[0057] Existing laser obstacle removal devices suffer from efficiency transmission and aiming problems. For example, most laser obstacle removal devices use collimation or fixed-focus methods in their optical paths, which cannot simultaneously maximize the efficiency of the laser at both close and long distances. Many electronically controlled pan-tilt units in laser obstacle removal devices lack sufficient precision, making it difficult to aim at foreign objects at long distances, resulting in either inability to remove the object or a prolonged removal time. Furthermore, the coaxial imaging and beam emission scheme of laser obstacle removal devices leads to blurred imaging at long distances, making it difficult to aim at foreign objects and again resulting in either inability to remove the object or a prolonged removal time.

[0058] In view of this, this application proposes a portable laser-based live-line obstacle removal device. Maintenance personnel can record potential hazards during inspections and address them promptly. With the development of laser technology, the application fields of lasers are expanding, making high-power, long-distance laser cutting a reality. This device can clear suspended objects quickly and efficiently without power interruption, rapidly eliminating potential safety hazards to the power grid, greatly improving work efficiency, and possessing strong practical significance and value.

[0059] Statistics show that short circuits caused by hanging objects on power lines account for 25% of all external damage, and the length of 10 kV transmission and distribution lines accounts for 60% of the total overhead power lines in the entire power grid. Therefore, hanging objects on overhead transmission and distribution lines urgently need to be addressed with more scientific and effective methods. The laser-based live-line obstacle removal device proposed in this application greatly helps reduce power outage time for customers. In the entire power grid, transmission lines directly supply power to customers. When encountering hanging objects requiring power outages, the number of unplanned line outages increases, directly impacting power outage time for customers and affecting residents' daily lives and production. Related data shows that fault outages account for nearly 50% of average outage time, and line obstacle removal accounts for 40% of fault outage time. Using the laser-based live-line obstacle removal device in this application allows obstacle removal to be completed while the line is energized, significantly reducing power outage time for customers.

[0060] Figure 1 This is a flowchart illustrating a foreign object removal method based on a laser obstacle removal device according to an exemplary embodiment. The method is applied to a laser obstacle removal device, which includes multiple fixed focusing lenses and a sliding focusing lens, the sliding focusing lens being located between the multiple fixed focusing lenses. See also... Figure 1 As shown, the method includes:

[0061] In step S11, in response to the identification of a foreign object to be removed in the real-time monitoring image, the first location information of the foreign object to be removed in the real-time monitoring image is determined.

[0062] For example, this embodiment is applied to a laser obstacle clearance device, which includes multiple fixed focusing lenses and one sliding focusing lens. The sliding focusing lens focuses the laser beam emitted from the center of the laser obstacle clearance device's lens. By controlling the position of the sliding focusing lens among the multiple fixed focusing lenses, the laser beam emitted from the lens of the laser obstacle clearance device is refracted by the multiple focusing lenses and focused onto a single point. The center of the sliding focusing lens, the centers of the multiple fixed focusing lenses, and the center of the laser beam emitted by the laser obstacle clearance device are all on the same straight line. The position of the focal point of the laser beam is adjusted by using the sliding focusing lens.

[0063] Figure 2 This is a schematic diagram illustrating an electrically focused optical path according to an exemplary embodiment, such as... Figure 2The diagram illustrates the optical path of a laser beam emitted by a laser obstacle clearing device, showing its propagation between multiple fixed focusing lenses and one sliding focusing lens. This embodiment includes three fixed focusing lenses and one sliding focusing lens. For example, a stepper motor sliding mechanism can be used to control the extension and retraction of the second lens to achieve dynamic focusing. The sliding and fixed focusing lenses are mounted on a fixed structural component. The distances A and B of the sliding focusing lens are changed by controlling the sliding mechanism's movement via a stepper motor, while the other fixed focusing lenses remain stationary on the structural component. The stepper motor has a step angle of 1.8°, and the sliding mechanism has a lead of 0.05 mm. Higher control precision is achieved through stepper motor microstepping.

[0064] For example, in this embodiment, a higher-precision electronically controlled gimbal can also be used, with an accuracy of up to 0.0072°. The electronically controlled gimbal uses a worm gear mechanism, employing a multi-stage reduction gear system to improve the accuracy of the gimbal. It uses a two-stage reduction gear system, with each stage having a gear ratio of 50, resulting in an overall reduction ratio of 50*50=2500. If a stepper motor with a step angle of 1.8° is used, the calculated accuracy is 1.8 / 2500=0.0072°. If higher accuracy is required, a stepper motor with a step angle of 0.9° can be used, theoretically achieving an accuracy of 0.9 / 2500=0.00036°.

[0065] Relevant personnel can visually determine the approximate location of the foreign object to be removed and manually adjust the lens of the laser obstacle removal device to ensure the object is within the real-time monitoring image. When the laser obstacle removal device identifies the foreign object in the real-time monitoring image using a relevant recognition algorithm, it determines the object's initial position information within the image. For example, this embodiment can be applied to high-voltage power line obstacle removal scenarios, clearing foreign objects from high-voltage power lines. These objects may include ice crystals, hanging wires, kite debris, tape debris, etc. After visually identifying the object, personnel control the laser obstacle removal device's lens to ensure the object is within the device's real-time monitoring image.

[0066] Optionally, prior to step S12 above, the method further includes:

[0067] Acquire real-time monitoring images;

[0068] The pre-set convolutional neural network is used to identify foreign objects on the wire to be monitored in the monitoring image, so as to generate foreign object monitoring results for the wire to be monitored.

[0069] If, based on the foreign object monitoring results, it is determined that the coverage area of ​​the foreign object to be removed reaches a set threshold, then it is determined that there is a foreign object to be removed in the real-time monitoring image.

[0070] For example, in this embodiment, a convolutional neural network is used to identify foreign objects to be removed in a real-time monitoring image. This convolutional neural network is trained in the following manner:

[0071] (1) Data Acquisition: First, it is necessary to collect image and video data around the high-voltage power lines, including normal conditions and conditions with foreign objects. This data can be acquired through professional drones, cameras or other equipment.

[0072] (2) Data annotation: The collected image and video data are annotated to indicate which parts are high-voltage power lines and which parts are potential foreign objects. This step requires a lot of annotation work.

[0073] (3) Training based on convolutional neural networks (CNN): Deep learning models such as convolutional neural networks (CNN) are used for training to identify foreign objects on power lines. A large amount of labeled image data can be used to train deep learning models to identify various foreign objects on high-voltage power lines.

[0074] (4) Model validation: The trained deep learning model is validated using validation and test data to check the model’s accuracy in recognizing foreign objects.

[0075] (5) Deployment: Deploy the validated deep learning model to a real-world application environment and use image detection and recognition of foreign objects.

[0076] The initial convolutional neural network is trained using the above method to generate a preset convolutional neural network. Based on this preset convolutional neural network, the real-time monitoring image is identified, generating the foreign object detection result for the real-time monitoring image. It should be noted that in this embodiment, the area covered by the foreign object needs to be evaluated to determine whether the foreign object requires removal. When the area covered by the foreign object reaches a set threshold, it is determined that a foreign object exists in the real-time monitoring image, and the laser obstacle removal device in this embodiment needs to remove the foreign object.

[0077] In step S12, the monitoring posture of the laser obstacle clearer is adjusted according to the first position information and the preset crosshair position of the laser obstacle clearer in the real-time monitoring image, so that the center position of the foreign object to be cleared overlaps with the preset crosshair position of the real-time monitoring image.

[0078] For example, in this embodiment, the laser obstacle removal device includes an image acquisition device for capturing real-time monitoring images. To calibrate the position of the foreign object to be removed, a crosshair is positioned at the center of the image acquisition device to calibrate the crosshair's position relative to the center of the foreign object. The crosshair, the laser beam focusing position, and the center of the focusing lens are all on the same straight line. By determining the relative positional relationship between the first position of the foreign object in the real-time monitoring image and the corresponding position of the crosshair, the monitoring posture of the laser obstacle removal device is fine-tuned so that the center of the foreign object is positioned at the crosshair's position.

[0079] Optionally, in some embodiments, step S12 above includes:

[0080] The real-time monitoring image is preprocessed to generate a target recognition image. The preprocessing includes at least one of image noise reduction, image filtering, and grayscale image contrast enhancement.

[0081] The corner feature-based image registration algorithm registers the foreign object to be removed in the target recognition image to determine the location range of the foreign object in the real-time monitoring image.

[0082] Based on a preset planar coordinate system, the coordinate information corresponding to the center position of the location range is determined as the first location information.

[0083] For example, in this embodiment, the real-time monitoring image is preprocessed to avoid the influence of noise in the image on the recognition result. This preprocessing includes at least one of image noise reduction, image filtering, and grayscale image contrast enhancement. This removes noise from the image and generates a target recognition image. Then, an image registration algorithm based on corner features is used to register the foreign object to be removed in the target recognition image. The foreign object category is identified through a database, and the location range of the foreign object to be removed in the real-time monitoring image is selected based on this category. It should be noted that in this embodiment, a center cut-out method is used to remove the foreign object. The center position of the location range is determined, and the foreign object is removed from this center position. Based on a preset planar coordinate system, the coordinate information corresponding to the center position of the location range is determined as the first position information. In this embodiment, a preset planar rectangular coordinate system can be established using the center of the real-time monitoring image as the origin, determining the positional relationship between this center and the center of the foreign object to be removed, and determining the coordinates of this center position as the first position information of the foreign object to be removed.

[0084] Optionally, in some embodiments, the above step "the image registration algorithm based on corner features registers the foreign object to be removed in the target recognition image to determine the location range of the foreign object to be removed in the real-time monitoring image" includes:

[0085] Based on the image registration algorithm of the corner features, identify multiple corner information of the foreign object to be removed in the target recognition image;

[0086] Determine the image features of the region surrounding the multiple corner point information in the target recognition image, and generate multiple local feature vectors;

[0087] The multiple local characteristic vectors are matched with the local feature vector group to determine the foreign object category information of the foreign object to be removed;

[0088] Based on the foreign object category information, determine the boundary line type of the foreign object to be removed;

[0089] Based on the boundary line type, the foreign object to be removed in the real-time monitoring image is selected to generate the location range.

[0090] For example, in this embodiment, the type of foreign object to be removed is identified based on the corner features of the boundary contour corresponding to the foreign object to be removed. According to the image registration algorithm of corner features, multiple corner points of the foreign object to be removed in the target recognition image are determined. These corner points indicate the contour of the foreign object to be removed in the target recognition image. The image features of the surrounding area corresponding to the multiple corner points in the target recognition image are determined, and multiple local feature vectors are generated based on each corner point. These multiple local feature vectors are matched with local feature vector groups to determine the foreign object category information. It should be noted that these local feature vector groups are generated by relevant personnel through corner point marking to identify different types of foreign objects. Different types of foreign objects correspond to different feature vector groups. The multiple local feature vectors of the foreign object to be removed are compared with the local feature vectors in each feature vector group to determine the foreign object category information. Based on the foreign object category, the boundary line type of the foreign object to be removed is determined. Based on the boundary line type, the foreign object to be removed in the real-time monitoring image is selected by box selection, thereby generating the location range of the foreign object to be removed.

[0091] Optionally, in some embodiments, the above step "matching the plurality of local feature vectors with the local feature vector group to determine the foreign object category information of the foreign object to be removed" includes:

[0092] Determine multiple similarity information between the plurality of local feature vectors and the plurality of initial local feature vectors in the local feature vector group;

[0093] Based on the multiple similarity information, obtain the target local feature vector group with the highest similarity;

[0094] The target foreign object category information corresponding to the target local feature vector group is determined as the foreign object category information of the foreign object to be removed.

[0095] For example, in this embodiment, the laser obstacle removal device stores multiple local feature vector groups, with each local feature vector group corresponding to multiple initial local feature vectors of a certain type of foreign object. The multiple local feature vectors of the foreign object to be removed are matched with the multiple initial local feature vectors in each group to determine multiple similarity information between the multiple local feature vectors corresponding to the foreign object to be removed and the local feature vectors in each group. The target local feature vector group with the highest similarity is determined, and the target foreign object category information corresponding to this target local feature vector group is determined, thereby determining the foreign object category information of the foreign object to be removed.

[0096] In step S13, in response to the center position of the foreign object to be removed being located at the preset crosshair position, the distance between the center position of the foreign object to be removed and the laser obstacle remover is measured according to the set ranging parameters of the laser obstacle remover, so as to generate the target distance of the foreign object to be removed.

[0097] For example, the detection pose of the laser obstacle removal device is adjusted in the above manner to overlap the center position of the object to be removed with the preset crosshair position. Based on the laser obstacle removal device's set ranging parameters, the distance between the center position of the object to be removed and the laser obstacle removal device after pose calibration is measured, generating the target distance for the object to be removed.

[0098] In step S14, the target preset position parameters of the sliding focusing lens that match the target distance are determined from the preset mapping relationship. The preset mapping relationship includes a one-to-one correspondence between multiple distances and multiple preset position parameters.

[0099] For example, in this embodiment, relevant personnel determine the correspondence between the laser beam focusing position and the target preset position parameters corresponding to the sliding focusing lens through limited experiments, generating a preset mapping relationship. For instance, data parameters ranging from 5 to 500 meters are measured and calculated at 1-meter intervals to generate a one-to-one correspondence between multiple distances and multiple preset position parameters. After determining the target distance, based on this preset mapping relationship, target pre-configuration parameters matching the target distance are determined.

[0100] In step S15, the position of the sliding focusing lens among multiple fixed focusing lenses is adjusted according to the target preset position parameters so that the laser light emitted by the laser obstacle clearer is focused on the preset crosshair position after being refracted by multiple fixed focusing lenses and the sliding focusing lens. In response to the sliding focusing lens moving to the target position corresponding to the target preset position parameters, the laser obstacle clearer emits a set obstacle clearing laser towards the foreign object to be cleared.

[0101] For example, after determining the target preset position parameters of the sliding focusing lens using the above method, the position of the sliding focusing lens among multiple fixed focusing lenses is adjusted. It should be noted that during the position adjustment process, the center of the sliding focusing lens remains on the straight line formed by the centers of the multiple fixed focusing lenses. Based on the adjusted sliding focusing lens and the multiple fixed focusing lenses, the laser beam emitted by the laser obstacle removal device is focused, converging the laser beam at the center of the object to be removed, and thus removing the object.

[0102] Optionally, in some embodiments, the laser obstacle removal device includes a stepper motor sliding device, wherein the aforementioned "the stepper motor sliding device is used to control the sliding focusing lens to move between the plurality of fixed focusing lenses, and the adjustment of the position of the sliding focusing lens between the plurality of fixed focusing lenses according to the target preset position parameter" includes:

[0103] The number of drive pulses for the stepper motor sliding device is determined based on the preset position parameters.

[0104] The stepper motor sliding device is driven according to the number of driving pulses, which in turn drives the sliding focusing lens to move between the plurality of fixed focusing lenses.

[0105] For example, in this embodiment, a stepper motor sliding device is provided in the laser obstacle removal device. The sliding focusing lens is mounted on the stepper motor sliding device. By controlling the stepper motor to drive the sliding device, the sliding focusing lens is driven to reciprocate in a preset direction. After determining the preset position parameters of the sliding focusing lens, the number of drive pulses for the stepper motor sliding device is determined according to a preset pulse algorithm. Based on the number of drive pulses, the stepper motor sliding device is driven to move the sliding focusing lens between multiple fixed focusing lenses.

[0106] Optionally, in some embodiments, the step "determining the number of drive pulses for the stepper motor sliding device based on the preset position parameters" includes:

[0107] Determine the first distance information between the sliding focusing lens and the first fixed focusing lens, wherein the first fixed focusing lens is the lens among the plurality of fixed focusing lenses that is closest to the lens of the laser obstacle clearing device;

[0108] Based on the first distance information and the preset position parameters, the distance difference information of the sliding focusing lens is determined;

[0109] The number of driving pulses is determined based on the distance difference information.

[0110] For example, in this embodiment, the first distance information between the sliding focusing lens and the first fixed focusing lens in the current state is first determined. An infrared ranging device can be configured in the laser obstacle clearing device to monitor the distance between the sliding focusing lens and the first fixed focusing lens in real time. The first fixed focusing lens is the lens closest to the lens of the laser obstacle clearing device among multiple fixed focusing lenses. Based on the first distance information and preset position parameters, the distance difference information of the sliding focusing lens is determined, and based on this distance difference, the number of driving pulses for the sliding focusing lens is determined.

[0111] The above scheme determines the first position information of the foreign object to be removed in the real-time monitoring image. Based on the first position information and the preset crosshair position of the laser obstacle removal device in the real-time monitoring image, the monitoring posture of the laser obstacle removal device is adjusted. According to the set ranging parameters of the laser obstacle removal device, the distance between the center position of the foreign object to be removed and the laser obstacle removal device is measured to generate the target distance of the foreign object to be removed. The target preset position parameters of the sliding focusing lens matching the target distance are determined from a preset mapping relationship. The position of the sliding focusing lens among the multiple fixed focusing lenses is adjusted according to the target preset position parameters. The laser obstacle removal device emits a set obstacle removal laser towards the foreign object to be removed. Thus, by using laser obstacle removal, the detected foreign object to be removed can be removed at a long distance, ensuring the accuracy of the foreign object aiming and solving the problem of energy dispersion during laser transmission, thereby improving the convenience and accuracy of obstacle removal.

[0112] Figure 3 This is a schematic diagram illustrating a foreign object removal method based on a laser obstacle removal device according to an exemplary embodiment, such as... Figure 3 As shown.

[0113] In this embodiment, the foreign object aiming method based on the laser obstacle clearing device is as follows: A rangefinder with imaging aiming is used to directly view the video of the targeted foreign object and obtain the precise target distance. The focal length of the optical path is automatically adjusted according to the target distance to optimize its energy. A pre-set position is directly invoked based on the target distance to ensure that the crosshair on the screen coincides perfectly with the targeted foreign object. A camera with an ultra-long focal length is used to observe the foreign object, and the camera video is superimposed on the crosshair to ensure complete alignment and overlap with the foreign object.

[0114] For example, the optical focusing principle of this method is as follows: the laser light emitted from the laser is divergent, and the light path is focused onto a point at a certain distance through multiple stages of lenses to maximize its energy. Because the focusing point varies with distance, we store the optimal motor data (controlling the number of motor steps) for different distances in the circuit control board before shipment, for example, data for 5 to 500 meters (at 1-meter intervals). In field use, a rangefinder measures the actual distance and transmits the distance to the control circuit board. The control board automatically retrieves the motor parameters based on the distance and controls the lenses to be at the designated position (the distance corresponding to the highest energy).

[0115] It should be noted that, due to errors in the installation process, there is a certain deviation between the laser transmission optical path and the camera imaging in this embodiment. In this embodiment, preset position parameters for the crosshair position on the display screen at different distances are stored in the circuit board control, such as data from 5 to 500 meters (intervals of 1 meter). During on-site use, a rangefinder is used to measure the actual distance, which is then transmitted to the control circuit board. The circuit control board automatically retrieves the saved preset position parameters based on the distance, ensuring that they are completely superimposed on the crosshair.

[0116] The above methods solve the technical problem of energy dispersion during laser beam transmission over long and short distances, address the issue of long-distance aiming at foreign objects, and resolve the challenges of aiming at foreign objects at different distances while ensuring optimal laser energy. This results in long-distance, concentrated energy transmission while maintaining even higher energy density at closer distances. The electronically controlled pan-tilt unit requires high precision, is compact, and can be precisely controlled at long distances. The imaging video is clear, allowing for clearer observation of foreign object details. This enables long-distance, non-contact foreign object removal.

[0117] Figure 4 This is a block diagram illustrating a foreign object removal device based on a laser obstacle clearing instrument according to an exemplary embodiment. The device is applied to a laser obstacle clearing instrument, which includes multiple fixed focusing lenses and a sliding focusing lens, wherein the sliding focusing lens is located between the multiple fixed focusing lenses. Figure 4 As shown, the device 100 includes:

[0118] The first determining module 110 is configured to determine the first location information of the foreign object to be removed in the real-time monitoring image in response to the identification of the foreign object to be removed in the real-time monitoring image;

[0119] The adjustment module 120 is used to adjust the monitoring posture of the laser obstacle clearing device according to the first position information and the preset crosshair position of the laser obstacle clearing device in the real-time monitoring image, so that the center position of the foreign object to be cleared overlaps with the preset crosshair position of the real-time monitoring image.

[0120] The generation module 130 is used to, in response to the fact that the center position of the foreign object to be removed is located at the preset crosshair position, measure the distance between the center position of the foreign object to be removed and the laser obstacle removal device according to the set ranging parameters of the laser obstacle removal device, so as to generate the target distance of the foreign object to be removed;

[0121] The second determining module 140 is used to determine the target preset position parameter of the sliding focusing lens that matches the target distance from the preset mapping relationship, wherein the preset mapping relationship includes a one-to-one correspondence between multiple distances and multiple preset position parameters;

[0122] The execution module 150 is used to adjust the position of the sliding focusing lens among the plurality of fixed focusing lenses according to the target preset position parameters, so that the laser light emitted by the laser obstacle clearing device is focused at the preset crosshair position after being refracted by the plurality of fixed focusing lenses and the sliding focusing lens. In response to the sliding focusing lens moving to the target position corresponding to the target preset position parameters, the laser obstacle clearing device emits a set obstacle clearing laser towards the foreign object to be cleared.

[0123] Optionally, the device 100 further includes a determination module, which is used for:

[0124] Acquire the real-time monitoring image;

[0125] The real-time monitoring image is identified by a preset convolutional neural network to generate a foreign object monitoring result for the real-time monitoring image. The preset convolutional neural network is used to identify foreign objects on the wire to be monitored in the monitoring image to generate a foreign object monitoring result for the wire to be monitored.

[0126] If, based on the foreign object monitoring results, it is determined that the coverage area of ​​the foreign object to be removed reaches a set threshold, then it is determined that the foreign object to be removed exists in the real-time monitoring image.

[0127] Optionally, the first determining module 110 includes:

[0128] A generation submodule is used to preprocess the real-time monitoring image to generate a target recognition image. The preprocessing includes at least one of image noise reduction, image filtering, and grayscale image contrast enhancement.

[0129] The first determining submodule is used to register the foreign object to be removed in the target recognition image using an image registration algorithm based on corner features, so as to determine the location range of the foreign object to be removed in the real-time monitoring image;

[0130] The second determining submodule is used to determine the coordinate information corresponding to the center position of the position range as the first position information based on a preset planar coordinate system.

[0131] Optionally, the first determining submodule includes:

[0132] The identification unit is used to identify multiple corner information of the foreign object to be removed in the target identification image according to the image registration algorithm of the corner features;

[0133] The first determining unit is used to determine the image features of the area surrounding the multiple corner point information in the target recognition image and generate multiple local feature vectors.

[0134] The second determining unit is used to match the plurality of local characteristic vectors with the local feature vector group to determine the foreign object category information of the foreign object to be removed;

[0135] The third determining unit is used to determine the boundary line type of the foreign object to be removed based on the foreign object category information;

[0136] The generation unit is used to select the foreign object to be removed in the real-time monitoring image based on the boundary line type, so as to generate the location range.

[0137] Optionally, the second determining unit is used for:

[0138] Determine multiple similarity information between the plurality of local feature vectors and the plurality of initial local feature vectors in the local feature vector group;

[0139] Based on the multiple similarity information, obtain the target local feature vector group with the highest similarity;

[0140] The target foreign object category information corresponding to the target local feature vector group is determined as the foreign object category information of the foreign object to be removed.

[0141] Optionally, the laser obstacle removal device includes a stepper motor sliding device, which controls the movement of the sliding focusing lens among the plurality of fixed focusing lenses. The adjustment module 120 includes:

[0142] The third determining subunit is used to determine the number of drive pulses of the stepper motor sliding device according to the preset position parameters;

[0143] An execution subunit is used to drive the stepper motor sliding device to move the sliding focusing lens among the plurality of fixed focusing lenses according to the number of driving pulses.

[0144] Optionally, the third determining subunit is used for:

[0145] Determine the first distance information between the sliding focusing lens and the first fixed focusing lens, wherein the first fixed focusing lens is the lens among the plurality of fixed focusing lenses that is closest to the lens of the laser obstacle clearing device;

[0146] Based on the first distance information and the preset position parameters, the distance difference information of the sliding focusing lens is determined;

[0147] The number of driving pulses is determined based on the distance difference information.

[0148] The above scheme determines the first position information of the foreign object to be removed in the real-time monitoring image. Based on the first position information and the preset crosshair position of the laser obstacle removal device in the real-time monitoring image, the monitoring posture of the laser obstacle removal device is adjusted. According to the set ranging parameters of the laser obstacle removal device, the distance between the center position of the foreign object to be removed and the laser obstacle removal device is measured to generate the target distance of the foreign object to be removed. The target preset position parameters of the sliding focusing lens matching the target distance are determined from a preset mapping relationship. The position of the sliding focusing lens among the multiple fixed focusing lenses is adjusted according to the target preset position parameters. The laser obstacle removal device emits a set obstacle removal laser towards the foreign object to be removed. Thus, by using laser obstacle removal, the detected foreign object to be removed can be removed at a long distance, ensuring the accuracy of the foreign object aiming and solving the problem of energy dispersion during laser transmission, thereby improving the convenience and accuracy of obstacle removal.

[0149] This disclosure also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the methods described in the foregoing embodiments.

[0150] This disclosure also provides an electronic device, including:

[0151] processor;

[0152] Memory used to store processor-executable instructions;

[0153] The processor is configured to execute executable instructions in the memory to implement the method described in any of the foregoing embodiments.

[0154] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of this disclosure. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the following claims.

[0155] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A method for removing foreign objects based on a laser obstacle removal device, characterized in that, An application is made to a laser obstacle clearance device, the laser obstacle clearance device comprising multiple fixed focusing lenses and a sliding focusing lens, the sliding focusing lens being located between the multiple fixed focusing lenses, the method comprising: In response to the identification of a foreign object to be removed in a real-time monitoring image, the first location information of the foreign object to be removed in the real-time monitoring image is determined; Based on the first location information and the preset crosshair position of the laser obstacle clearing device in the real-time monitoring image, the monitoring posture of the laser obstacle clearing device is adjusted so that the center position of the foreign object to be cleared overlaps with the preset crosshair position of the real-time monitoring image. In response to the fact that the center position of the foreign object to be removed is located at the preset crosshair position, the distance between the center position of the foreign object to be removed and the laser obstacle removal device is measured according to the set ranging parameters of the laser obstacle removal device, so as to generate the target distance of the foreign object to be removed; The target preset position parameters of the sliding focusing lens that match the target distance are determined from the preset mapping relationship, wherein the preset mapping relationship includes a one-to-one correspondence between multiple distances and multiple preset position parameters; The position of the sliding focusing lens is adjusted among the plurality of fixed focusing lenses according to the target preset position parameters, so that the laser light emitted by the laser obstacle clearing device is focused at the preset crosshair position after being refracted by the plurality of fixed focusing lenses and the sliding focusing lens. In response to the sliding focusing lens moving to the target position corresponding to the target preset position parameters, the laser obstacle clearing device emits a set obstacle clearing laser towards the foreign object to be cleared. Determining the first location information of the foreign object to be removed in the real-time monitoring image includes: The real-time monitoring image is preprocessed to generate a target recognition image. The preprocessing includes at least one of image noise reduction, image filtering, and grayscale image contrast enhancement. An image registration algorithm based on corner features is used to register the foreign object to be removed in the target recognition image to determine the location range of the foreign object to be removed in the real-time monitoring image. Based on a preset planar coordinate system, the coordinate information corresponding to the center position of the position range is determined as the first position information; The corner feature-based image registration algorithm registers the foreign object to be removed in the target recognition image to determine the location range of the foreign object in the real-time monitoring image, including: Based on the image registration algorithm of the corner features, identify multiple corner information of the foreign object to be removed in the target recognition image; Determine the image features of the region surrounding the multiple corner point information in the target recognition image, and generate multiple local feature vectors; The multiple local characteristic vectors are matched with the local feature vector group to determine the foreign object category information of the foreign object to be removed; Based on the foreign object category information, determine the boundary line type of the foreign object to be removed; Based on the boundary line type, the foreign object to be removed in the real-time monitoring image is selected to generate the location range; The step of matching the plurality of local characteristic vectors with the local feature vector group to determine the foreign object category information of the foreign object to be removed includes: Determine multiple similarity information between the plurality of local feature vectors and the plurality of initial local feature vectors in the local feature vector group; Based on the multiple similarity information, obtain the target local feature vector group with the highest similarity; The target foreign object category information corresponding to the target local feature vector group is determined as the foreign object category information of the foreign object to be removed.

2. The foreign object removal method based on a laser obstacle removal device according to claim 1, characterized in that, The method further includes: Acquire the real-time monitoring image; The real-time monitoring image is identified by a preset convolutional neural network to generate a foreign object monitoring result for the real-time monitoring image. The preset convolutional neural network is used to identify foreign objects on the wire to be monitored in the monitoring image to generate a foreign object monitoring result for the wire to be monitored. If, based on the foreign object monitoring results, it is determined that the coverage area of ​​the foreign object to be removed reaches a set threshold, then it is determined that the foreign object to be removed exists in the real-time monitoring image.

3. The foreign object removal method based on a laser obstacle removal device according to claim 1 or 2, characterized in that, The laser obstacle removal device includes a stepper motor sliding device, which controls the movement of the sliding focusing lens among a plurality of fixed focusing lenses. Adjusting the position of the sliding focusing lens among the plurality of fixed focusing lenses according to the target preset position parameters includes: The number of drive pulses for the stepper motor sliding device is determined based on the preset position parameters. The stepper motor sliding device is driven according to the number of driving pulses, which in turn drives the sliding focusing lens to move between the plurality of fixed focusing lenses.

4. The foreign object removal method based on a laser obstacle removal device according to claim 3, characterized in that, Determining the number of drive pulses for the stepper motor sliding device based on the preset position parameters includes: Determine the first distance information between the sliding focusing lens and the first fixed focusing lens, wherein the first fixed focusing lens is the lens among the plurality of fixed focusing lenses that is closest to the lens of the laser obstacle clearing device; Based on the first distance information and the preset position parameters, the distance difference information of the sliding focusing lens is determined; The number of driving pulses is determined based on the distance difference information.

5. A foreign object removal device based on a laser obstacle removal instrument, characterized in that, An application in a laser obstacle clearance device, the laser obstacle clearance device comprising multiple fixed focusing lenses and a sliding focusing lens, the sliding focusing lens being located between the multiple fixed focusing lenses, the device comprising: The first determining module is used to determine the first location information of the foreign object to be removed in the real-time monitoring image in response to the identification of the foreign object to be removed in the real-time monitoring image; Determining the first location information of the foreign object to be removed in the real-time monitoring image includes: preprocessing the real-time monitoring image to generate a target recognition image, wherein the preprocessing includes at least one of image noise reduction processing, image filtering processing, and grayscale image contrast enhancement processing; registering the foreign object to be removed in the target recognition image using an image registration algorithm based on corner features to determine the location range of the foreign object to be removed in the real-time monitoring image; and determining the coordinate information corresponding to the center position of the location range as the first location information based on a preset planar coordinate system. The corner feature-based image registration algorithm registers the foreign object to be removed in the target recognition image to determine the location range of the foreign object in the real-time monitoring image. This includes: identifying multiple corner points of the foreign object to be removed in the target recognition image based on the corner feature-based image registration algorithm; determining image features of the surrounding area of ​​the multiple corner points in the target recognition image to generate multiple local feature vectors; matching the multiple local feature vectors with the local feature vector group to determine the foreign object category information; determining the boundary line type of the foreign object to be removed based on the foreign object category information; and selecting the foreign object to be removed in the real-time monitoring image based on the boundary line type to generate the location range. The step of matching the plurality of local feature vectors with the local feature vector group to determine the foreign object category information of the foreign object to be removed includes: determining multiple similarity information between the plurality of local feature vectors and multiple initial local feature vectors in the local feature vector group; obtaining the target local feature vector group with the highest similarity based on the multiple similarity information; and determining the target foreign object category information corresponding to the target local feature vector group as the foreign object category information of the foreign object to be removed. The adjustment module is used to adjust the monitoring posture of the laser obstacle clearing device according to the first position information and the preset crosshair position of the laser obstacle clearing device in the real-time monitoring image, so that the center position of the foreign object to be cleared overlaps with the preset crosshair position of the real-time monitoring image. The generation module is used to, in response to the fact that the center position of the foreign object to be removed is located at the preset crosshair position, measure the distance between the center position of the foreign object to be removed and the laser obstacle removal device according to the set ranging parameters of the laser obstacle removal device, so as to generate the target distance of the foreign object to be removed; The second determining module is used to determine the target preset position parameter of the sliding focusing lens that matches the target distance from the preset mapping relationship, wherein the preset mapping relationship includes a one-to-one correspondence between multiple distances and multiple preset position parameters; The execution module is used to adjust the position of the sliding focusing lens among the plurality of fixed focusing lenses according to the target preset position parameters, so that the laser light emitted by the laser obstacle clearing device is focused at the preset crosshair position after being refracted by the plurality of fixed focusing lenses and the sliding focusing lens. In response to the sliding focusing lens moving to the target position corresponding to the target preset position parameters, the laser obstacle clearing device emits a set obstacle clearing laser towards the foreign object to be cleared.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the program implements the steps of the method described in any one of claims 1-4.

7. An electronic device, characterized in that, include: processor; Memory used to store processor-executable instructions; The processor is configured to execute executable instructions in the memory to implement the method according to any one of claims 1-4.

Images