Foreign matter inspection method and device for power transmission tower and storage medium

Abstract

The invention discloses a foreign matter inspection method and device for a power transmission tower and a storage medium, and the method comprises the steps: calling a camera in a first automatic aircraft to collect original image data of the power transmission tower when the first automatic aircraft is controlled to fly according to a preset inspection path, carrying out the preprocessing of the original image data, and obtaining target image data, calculating an index value in shape for multiple pieces of contour data in the target image data, if the index value is greater than or equal to a preset index threshold value, determining that the contour data is a foreign matter on the power transmission tower, and generating the position and the category of the foreign matter according to the contour data, the second automatic aircraft is controlled to fly to the position, and the cleaning device matched with the category is used for cleaning the foreign matter. Intelligent inspection and foreign matter cleaning are carried out on the power transmission tower through the automatic aircraft, the foreign matter is accurately recognized and positioned through the image processing technology, a proper cleaning device is selected according to the foreign matter category, and the power transmission tower foreign matter inspection efficiency is remarkably improved.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of power transmission equipment maintenance, and in particular to a foreign object inspection method, equipment and storage medium for a power transmission tower. Background Art

[0002] Transmission towers are one of the basic infrastructures in the power transmission network. They bear the weight of overhead transmission lines and ensure that electric energy can be efficiently and safely transmitted to different regions. Since transmission towers are exposed to the natural environment all year round, they are easily affected by various foreign objects, which may cause failures of power equipment, power outages or safety accidents.

[0003] Traditional transmission tower inspection methods mainly rely on manual inspection and ground monitoring equipment, which usually requires workers to climb and inspect and clean, which is not only labor-intensive but also poses a high safety risk. Manual inspections are difficult to promptly detect and deal with foreign objects that may exist on transmission towers, affecting the efficiency of foreign object inspections on transmission towers. Summary of the invention

[0004] The invention provides a foreign body inspection method, equipment and storage medium for a transmission tower, which are used to improve the efficiency of the foreign body inspection for the transmission tower.

[0005] In a first aspect, an embodiment of the present invention provides a method for inspecting foreign objects on a transmission tower, comprising:

[0006] When controlling the first automatic aerial vehicle to fly according to a preset inspection path, calling a camera in the first automatic aerial vehicle to collect raw image data of the transmission tower;

[0007] Preprocessing the original image data to obtain target image data;

[0008] Calculating shape index values ​​for a plurality of contour data in the target image data;

[0009] If the index value is greater than or equal to a preset index threshold, determining that the profile data is a foreign object on the transmission tower;

[0010] generating the position of the foreign object and the category of the foreign object according to the contour data;

[0011] The second automatic flying vehicle is controlled to fly to the location, and a cleaning device matching the category is used to clean the foreign matter.

[0012] In a second aspect, an embodiment of the present invention provides a foreign body inspection device for a transmission tower, comprising:

[0013] A raw image data acquisition module, used to call a camera in the first automatic aircraft to collect raw image data of the transmission tower when controlling the first automatic aircraft to fly according to a preset inspection path;

[0014] A target image data acquisition module, used for preprocessing the original image data to obtain target image data;

[0015] An index value calculation module, used for calculating the index value on the shape of the multiple contour data in the target image data;

[0016] A foreign object determination module, configured to determine that the profile data is a foreign object on the transmission tower if the index value is greater than or equal to a preset index threshold;

[0017] A foreign body information acquisition module, used for generating the position of the foreign body and the category of the foreign body according to the contour data;

[0018] The foreign matter cleaning module is used to control the second automatic flying vehicle to fly to the position and use a cleaning device matching the category to clean the foreign matter.

[0019] In a third aspect, an embodiment of the present invention further provides a computer device, the computer device comprising:

[0020] one or more processors;

[0021] A storage device for storing one or more programs;

[0022] When the one or more programs are executed by the one or more processors, the one or more processors implement the foreign object inspection method for a transmission tower as provided in the first aspect of the present invention.

[0023] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the foreign object inspection method for a transmission tower as provided in the first aspect of the present invention.

[0024] In a fifth aspect, an embodiment of the present invention further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the foreign object inspection method for a transmission tower provided in the first aspect of the present invention.

[0025] In the embodiment of the present invention, when the first automatic aircraft is controlled to fly according to the preset inspection path, the camera in the first automatic aircraft is called to collect raw image data of the transmission tower, the raw image data is preprocessed to obtain target image data, and the shape index value is calculated for multiple contour data in the target image data. If the index value is greater than or equal to the preset index threshold, the contour data is determined to be a foreign object on the transmission tower, the position of the foreign object and the category of the foreign object are generated according to the contour data, and the second automatic aircraft is controlled to fly to the position and use a cleaning device matching the category to clean the foreign object. The automatic aircraft performs intelligent inspection on the transmission tower, calculates the shape index value of the contour data, quickly screens out potential foreign objects, accurately calculates the position and category of the foreign object based on the potential foreign object according to the contour data, and selects a suitable cleaning device according to the category of the foreign object. The combination of the two calculations not only improves the overall calculation efficiency, but also ensures the high precision of foreign object identification and cleaning, thereby optimizing the automatic inspection and cleaning process of the aircraft, significantly improving the efficiency of foreign object inspection of the transmission tower, reducing labor costs and risks, and ensuring the stable operation of the transmission tower. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 A flow chart of a method for inspecting foreign objects on a transmission tower provided in Embodiment 1 of the present invention;

[0027] Figure 2 A schematic diagram of the structure of a cleaning device provided in Embodiment 1 of the present invention;

[0028] Figure 3 A schematic diagram of the structure of a clamping mechanism provided in Embodiment 1 of the present invention;

[0029] Figure 4 A schematic diagram of the structure of an adsorption component provided in Embodiment 1 of the present invention;

[0030] Figure 5 A structural block diagram of a foreign body inspection device for a transmission tower provided in Embodiment 2 of the present invention;

[0031] Figure 6 A schematic diagram of the structure of a computer device provided in Embodiment 3 of the present invention. DETAILED DESCRIPTION

[0032] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0033] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present invention described herein can cover sequential implementations other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0034] Embodiment 1

[0035] See also Figure 1 , shows a flow chart of a method for inspecting foreign objects on a transmission tower provided by the first embodiment of the present invention. The method can be executed by a foreign object inspection device for a transmission tower. The foreign object inspection device for a transmission tower can be implemented in the form of hardware and / or software. The foreign object inspection device for a transmission tower can be configured in a computer device. Figure 1 As shown, the method includes:

[0036] Step 101: When controlling a first automatic aerial vehicle to fly along a preset inspection path, a camera in the first automatic aerial vehicle is called to collect raw image data of a transmission tower.

[0037] An autonomous aircraft is a flying device that can complete flight missions without human piloting, through preset programs or remote control. An autonomous aircraft is usually equipped with advanced sensors, cameras and navigation systems, and can perform a variety of operations such as cruising, filming, and monitoring according to specific mission requirements.

[0038] Transmission towers are tall structures used to support power transmission lines, usually made of strong materials such as steel. The main purpose of transmission towers is to carry high-voltage power lines overhead, allowing electricity to be transmitted from power plants to different regions or cities. Transmission towers are usually distributed over a wide geographical area and undertake the critical task of power supply. Since transmission towers are located outdoors and are often in remote or difficult-to-reach places, they need to be inspected and maintained regularly.

[0039] In this embodiment, by controlling the first automatic aircraft to fly according to a predetermined inspection route, the camera on the first automatic aircraft is used to collect the original image data of the transmission tower, so as to realize comprehensive and real-time monitoring of the transmission tower, so as to timely discover the foreign objects that may exist on the transmission tower. By shooting high-quality original image data during the inspection process, accurate data support can be provided for subsequent image processing and foreign object detection, ensuring that the detection coverage of the transmission tower is wide and accurate. At the same time, compared with traditional manual inspections, the use of the first automatic aircraft for inspections has higher efficiency, can reduce human errors and dangers, and improve the safety and reliability of inspection work.

[0040] Step 102: pre-process the original image data to obtain target image data.

[0041] In this embodiment, the original image data is preprocessed to optimize the quality of the original image data, remove noise and interference, and ensure the accuracy of subsequent analysis. The original image data usually contains some noise due to environmental factors or equipment limitations, which may affect the accuracy of foreign body recognition. The clarity of the original image data is improved by preprocessing technology to obtain target image data, thereby improving the accuracy of subsequent foreign body detection.

[0042] Exemplarily, the preprocessing includes performing noise reduction, contrast enhancement and color correction on the original image data, and converting the original image data into a gray image (ie, target image data).

[0043] Noise reduction: Noise reduction is one of the important steps in the preprocessing of raw image data. Its purpose is to remove image noise caused by environmental factors, sensor limitations or other external interference. These image noises will affect subsequent image analysis and lead to inaccurate detection of foreign objects. Noise reduction methods include filtering methods such as median filtering, mean filtering, Gaussian filtering and bilateral filtering, which are not limited in the present invention.

[0044] Contrast enhancement: Contrast enhancement is to improve the contrast between light and dark in the original image data, making the details of the original image data clearer. Many important features in the original image data may not be easy to identify under low contrast conditions. Enhancing the contrast helps to highlight the contour data of foreign objects on the transmission tower, thereby improving the distinction between the target object and the background. Contrast enhancement methods include histogram equalization, adaptive contrast enhancement, and gamma correction, etc., and the present invention is not limited here.

[0045] Color correction: Color correction is to correct the color cast in the original image data caused by lighting, camera settings or shooting angles. During the processing, color correction can make the color of the original image data more accurate and natural, avoiding misidentification of contours or classification errors caused by color cast. Color correction methods include white balance adjustment, color mapping, color space conversion and color correction algorithms, etc., and the present invention is not limited here.

[0046] Converting raw image data to grayscale images: Converting raw image data to grayscale images is one of the steps in preprocessing. Grayscale images only have brightness information, but remove the interference of color, which makes the subsequent target image data analysis simpler and more efficient. Grayscale images can usually better preserve the shape and structural features of objects in the original image data, which is convenient for image processing tasks such as edge detection and contour extraction.

[0047] Step 103: Calculate the shape index value for the multiple contour data in the target image data.

[0048] In this embodiment, the index value on the shape is calculated in order to objectively analyze and classify the contour data, avoid human interference or misjudgment, and distinguish different categories of objects in the contour data, such as whether it is part of a normal structure or a foreign object that needs to be cleaned; when inspecting transmission towers, the resources of the dispatched automatic aerial vehicles are limited, so calculating the index value is the initial step in screening out foreign objects. A simple algorithm is used to filter out possible foreign objects, eliminate unnecessary interference, and reduce the subsequent amount of calculations, because the subsequent search for the real foreign objects from these possible foreign objects requires higher-precision calculations. After the initial screening step, the objects that need to be calculated are greatly reduced, ensuring that the resources of the automatic aerial vehicle are within an acceptable range.

[0049] In one embodiment of the present invention, step 103 may include the following steps:

[0050] Step 1031: Perform edge detection on the target image data to obtain edge image data.

[0051] In this embodiment, edge detection is performed on the target image data to extract the boundary information of the object in the target image data, which can clearly identify the contour data of the object in the target image data and remove background clutter, making subsequent contour extraction and analysis more accurate.

[0052] Exemplarily, the Canny edge detection algorithm is used to perform edge detection on the target image data to obtain a binary edge image. The Canny edge detection algorithm is a classic edge detection method that removes noise through smoothing, calculates the gradient of the image, and applies non-maximum suppression to accurately locate the edge. It also connects and refines the edge through a dual threshold algorithm, thereby effectively extracting the edge information in the target image data.

[0053] Step 1032: extract multiple contour data from the edge image data.

[0054] In this embodiment, extracting contour data is a further processing of edge image data. By identifying edge-connected regions in edge image data, contour data of multiple objects in edge image data can be obtained, and these contour data reflect the geometric shapes of objects in edge image data. Extracting contour data is a step of object recognition in edge image data, ensuring that the object of subsequent analysis is the actual object in edge image data, rather than noise or background information.

[0055] Exemplarily, findContours in the computer vision library (OpenCV) is used to perform contour detection on the edge image data, and the contour data of all potential foreign objects in the edge image data are extracted. If there is no contour data determined to be a foreign object in the edge image, the transmission tower area captured by the edge image is marked as having no foreign object risk.

[0056] Step 1033: Calculate the original area of ​​each contour data.

[0057] In this embodiment, the original area of ​​each contour data is counted to quantify the size of the object. The contour data represents the geometric appearance of the object. The original area, as an important geometric feature of the object, can help distinguish different objects, such as bird nests, garbage or other foreign objects. In the recognition and classification process, the size of the original area can be used as a preliminary screening standard to help filter out contour data that does not meet the foreign object standard, thereby improving the efficiency and accuracy of inspection.

[0058] Step 1034: Calculate the original complexity of the shape of the contour data according to the original area.

[0059] In this embodiment, calculating the original complexity of the contour data can help analyze whether the shape of the object meets the characteristics of a foreign object. The original complexity usually involves the boundary characteristics of the contour data, such as perimeter, area, etc. Measuring the complexity by the original area can more accurately evaluate the shape characteristics of the object. If the shape of a contour data lake is irregular and the boundaries are complex, it may be a foreign object. This step helps to improve the recognition accuracy of foreign objects and avoid misjudgment.

[0060] Exemplarily, the original complexity calculation formula is as follows:

[0061]

[0062] In the formula, F i Indicates the original complexity of the i-th contour data, C i Represents the perimeter value of the i-th contour data, P i Represents the original area of ​​the i-th contour data, C i and P i Available through the computer vision library (OpenCV).

[0063] Step 1035: normalize each original complexity to obtain a target complexity.

[0064] In this embodiment, the normalization of the original complexity is to eliminate the dimensional differences in the complexity between different contour data, so that the complexity of different contour data can be compared under a unified standard. The normalized target complexity can make a fairer comparison of the shapes of each contour data, which helps to accurately distinguish whether it is a foreign body in the subsequent judgment, improve the stability of judging foreign bodies, and reduce errors.

[0065] Exemplarily, the calculation formula of target complexity is as follows:

[0066]

[0067] In the formula, Re i Indicates the target complexity of the i-th profile data, F min Indicates the minimum value of the original complexity among multiple contour data, F max Indicates the maximum value of the original complexity of multiple contour data, F i Indicates the original complexity of the i-th contour data.

[0068] Step 1036: normalize each original area to obtain a target area.

[0069] In this embodiment, similar to the target complexity, the normalization of the original area is to eliminate the difference in size between different contour data, so that the target area comparison is more standardized. This allows contour data of different sizes to be analyzed by a unified standard, which helps to further determine whether the contour data is a foreign object. For example, a small, irregular object may be considered a foreign object, while a large area and regular structure is unlikely to be a foreign object.

[0070] Exemplarily, the target area calculation formula is as follows:

[0071]

[0072] In the formula, Res i represents the target area of ​​the i-th contour data, P min Represents the minimum value of the original area among multiple contour data, P max Indicates the maximum value of the original area among multiple contour data, P i Represents the original area of ​​the i-th contour data.

[0073] Step 1037: For the same contour data, the target complexity and target area are fused into the index value on the shape.

[0074] In this embodiment, the target complexity and target area are integrated into the shape index value in order to comprehensively evaluate the shape characteristics of the contour data and more comprehensively judge whether the shape characteristics of a contour data meet the standards of foreign matter. The target complexity reflects the boundary characteristics of the contour data, while the target area reflects the scale of the contour data.

[0075] Exemplarily, the indicator value calculation formula is as follows:

[0076] QM i =α×Re i +β×Res i ;

[0077] In the formula, QM i Represents the index value of the i-th contour data, Re i Represents the target complexity of the i-th contour data, Res i represents the target area of ​​the i-th contour data, α represents the first weight of the target complexity, β represents the second weight of the target area, the value range of α is between 0.2 and 0.4, and the value range of β is between 0.6 and 0.8. α and β can be set according to actual conditions, and the present invention is not limited here.

[0078] Step 104: If the index value is greater than or equal to a preset index threshold, it is determined that the profile data is a foreign object on the transmission tower.

[0079] In this embodiment, the index value calculated for each profile data is compared with a preset index threshold. If the index value is greater than or equal to the preset index threshold, the profile data corresponding to the index value is determined to be a foreign object on the transmission tower. If the index value is less than the preset index threshold, the profile data corresponding to the index value is not a foreign object and the profile data is discarded.

[0080] Step 105: Generate the location and type of the foreign object based on the contour data.

[0081] In this embodiment, when the contour data is confirmed as a foreign object, the locator placed in the first automatic flight will collect the position of the contour data and transmit it back to the control system. The shape, area, color and texture features of the contour data will be extracted through the computer vision library (OpenCV), and the shape, area, color and texture features will be input into the preset foreign object classification model to identify the category of the foreign object.

[0082] Exemplarily, the foreign body classification model can be trained by classification algorithms such as support vector machines, random forests and / or convolutional neural networks, and the present invention is not limited here.

[0083] Step 106: Control the second automatic aerial vehicle to fly to the location and use a cleaning device that matches the category to clean the foreign matter.

[0084] In this embodiment, the second automatic aircraft is controlled to fly to a position where the control system receives the data collected by the first automatic aircraft, and a cleaning device matching the type of the foreign object is used to clean the foreign object, ensuring that the foreign object is cleaned in a timely and effective manner, thereby ensuring the safety and normal operation of the transmission tower.

[0085] For example, Figure 2 The figure shows a schematic diagram of the structure of the cleaning device, which includes a box body 1 fixed to the bottom of the body of the second automatic aircraft, a side groove 3 on the side wall of the box body, a receiving port on the bottom wall 4 of the side groove 3, an audio player on the box body 1, and a clamping mechanism in the side groove 3, wherein the clamping mechanism includes a third telescopic drive rod 5, a second telescopic drive rod 6, and a first telescopic drive rod 7; wherein a cavity 2 is arranged inside the box body 1, the side groove 3 is arranged at a concave part of the box side wall relative to the box body 1, the corresponding concave area of ​​the side groove 3 is a groove cavity, and the cavity 2 is used to store foreign matter collected and cleaned by the clamping mechanism.

[0086] For example, Figure 3 The figure shows a schematic diagram of the structure of the clamping mechanism, which includes a first telescopic drive rod 7 arranged on the side groove, a second telescopic drive rod 6 arranged on the side groove and correspondingly located below the first telescopic drive rod, a third telescopic drive rod 5 arranged on the side groove and correspondingly located below the second telescopic drive rod, a negative pressure motor fixed in the cavity 2 for generating negative pressure in the cavity 2, an electric-driven scissors 8 fixed to the other end of the first telescopic drive rod 7, a clamper 9 fixed to the other end of the second telescopic drive rod 6, and an adsorbent fixed to the third telescopic drive rod 5; an upper rod wall 10, a lower rod wall 11, a connecting rod 13 and a side rod 14 are arranged on the third telescopic drive rod 5; wherein the first telescopic drive rod 7, the second telescopic drive rod 6 and the third telescopic drive rod 5 are arranged parallel to each other.

[0087] For example, Figure 4The figure shows a schematic diagram of the structure of the adsorption component, which includes a U-shaped rod which is horizontally arranged and has a hollow structure inside, a plurality of adsorption holes 15 which are sequentially arranged on the upper rod wall 10 and the side rod wall 12 of the U-shaped rod, a through hole arranged on the lower rod wall of the U-shaped rod, a plurality of ducts for connecting the adsorption holes with the through holes respectively, an air suction pump fixed on the box body, a transmission duct for connecting the air suction end of the air suction pump with the through holes respectively, and a control unit for controlling the air suction operation intensity of the air suction pump; the air suction pump operation enables each adsorption hole 15 to generate an adsorption force; the plurality of ducts are located in the hollow structure of the U-shaped rod, the U-shaped rod is composed of two parallel side rods and a connecting rod connecting the two side rods, the side rods and the connecting rod are located on the same horizontal plane, the bottom surfaces of the side rods and the connecting rod constitute the bottom wall of the U-shaped rod, the top surfaces of the side rods and the connecting rod constitute the top wall of the U-shaped rod, and the inner surfaces opposite to each other of the two side rods are the side walls of the U-shaped rod.

[0088] In one embodiment of the present invention, step 106 may include the following steps:

[0089] Step 1061: If the category is a dynamic object, use an audio player to play a specified audio signal to drive away the dynamic object.

[0090] In this embodiment, dynamic objects, especially birds, may stay on or around the transmission tower, affecting the normal operation of the transmission tower and even causing damage to the power facilities. Traditionally, these animals may be driven away by physical means, but this method may increase risks and labor costs. By using an audio player to play audio signals of specific frequencies, animals can be effectively driven away through sound stimulation without contacting or interfering with their normal activities, thereby reducing potential threats to transmission towers. In addition, audio signals driving dynamic objects away are safer and more efficient than direct physical intervention, avoiding potential dangers caused by manual driving, especially in high-altitude working environments, ensuring the safety of equipment and operators.

[0091] Step 1062: If the category is a static object, a clamping mechanism is used to clamp the static object, and an adsorbent is used to adsorb the static object according to the category information of the static object to cooperate with the clamping operation of the clamping mechanism to complete the cleaning of the static object.

[0092] In this embodiment, when a static object (such as a branch, a plastic bag, a cloth and / or paper, etc.) is detected, the clamping mechanism arranged in the second automatic aerial vehicle will clamp the static object and clean it in combination with the adsorption piece. Static objects are usually not as agile as dynamic objects, so they can be cleaned by physical means. The main function of the clamping mechanism is to accurately grasp the static object and take it down or remove it. At the same time, according to the different categories of static objects (such as materials or sizes), the cleaning device will adjust the suction value of the adsorption piece to ensure that the static object can be safely and effectively adsorbed and cleaned. For example, for lighter debris or small objects, a smaller suction force may be required, while for heavier or firmer objects, a larger suction force is required to ensure that it is firmly adsorbed and successfully removed. This process ensures that static objects can be cleaned efficiently and accurately, avoiding potential damage to transmission towers or power facilities caused by static objects, while improving the automation and accuracy of the entire cleaning operation, reducing manual intervention, and improving safety and operational efficiency.

[0093] Specifically, the second automatic flying vehicle hovers near the foreign object on the transmission tower, the second telescopic driving rod is started and extended to the target position, so that the clamp is close to the foreign object. At the same time, the third telescopic driving rod is also started, so that the adsorbent and the clamp reach the foreign object position synchronously, and the clamp clamps the foreign object to ensure its stability. At the same time, the adsorbent generates suction through the negative pressure motor and the suction pump to firmly adsorb the foreign object to improve the stability of the grasping; the first telescopic driving rod is started, and the electric-driven scissors on the first telescopic driving rod are started after the clamping and adsorption are completed, and the foreign objects such as branches, plastic bags, cloth and / or paper are cut to separate the foreign objects from the transmission tower. After the foreign objects are cut and separated by the electric-driven scissors, the clamp and the adsorbent move the foreign objects to the groove cavity position of the box body, and pass the foreign objects into the cavity inside the box body through the receiving port to collect the foreign objects into the cavity to complete the cleaning of the foreign objects.

[0094] Exemplarily, a suction value is configured for the adsorbent according to the category information of the static object, and the adsorbent is controlled to adsorb the static object according to the suction value to cooperate with the clamping operation of the clamping mechanism to complete the cleaning of the static object.

[0095] Among them, the suction value is expressed as:

[0096]

[0097] Where P m Indicates the suction value, P baserepresents the suction reference value, γ represents the weight for adjusting the adsorption area, Ksc represents the scaling parameter, P represents the area of ​​the contour data characterizing the foreign matter, Pref represents the reference area, Kt represents the coefficient of the category information, when the category information is plastic bag and / or paper, the value of Kt may be between 0.8 and 1; when the category information is cloth, the value of Kt may be between 1 and 1.3; when the category information is tree branch, the value of Kt may be between 1.3 and 1.6; the value range of Kt may be set according to actual needs, and the present invention does not limit it here; γ is set to initial values ​​by technicians in this field based on rich practical experience, and is gradually adjusted and optimized through multiple experiments and feedback from actual applications to ensure the weight for adjusting the adsorption area.

[0098] In the embodiment of the present invention, when the first automatic aircraft is controlled to fly according to the preset inspection path, the camera in the first automatic aircraft is called to collect raw image data of the transmission tower, the raw image data is preprocessed to obtain target image data, and the shape index value is calculated for multiple contour data in the target image data. If the index value is greater than or equal to the preset index threshold, the contour data is determined to be a foreign object on the transmission tower, the position of the foreign object and the category of the foreign object are generated according to the contour data, and the second automatic aircraft is controlled to fly to the position and use a cleaning device matching the category to clean the foreign object. The automatic aircraft performs intelligent inspection on the transmission tower, calculates the shape index value of the contour data, quickly screens out potential foreign objects, accurately calculates the position and category of the foreign object based on the potential foreign object according to the contour data, and selects a suitable cleaning device according to the category of the foreign object. The combination of the two calculations not only improves the overall calculation efficiency, but also ensures the high precision of foreign object identification and cleaning, thereby optimizing the automatic inspection and cleaning process of the aircraft, significantly improving the efficiency of foreign object inspection of the transmission tower, reducing labor costs and risks, and ensuring the stable operation of the transmission tower.

[0099] Embodiment 2

[0100] Figure 5 A schematic diagram of the structure of a foreign body inspection device for a transmission tower provided in the second embodiment of the present invention is shown in FIG. Figure 5 As shown, the device comprises:

[0101] The original image data acquisition module 501 is used to call the camera in the first automatic aircraft to collect original image data of the transmission tower when controlling the first automatic aircraft to fly according to the preset inspection path;

[0102] The target image data acquisition module 502 is used to pre-process the original image data to obtain the target image data;

[0103] An index value calculation module 503, used for calculating the index value of the shape of the multiple contour data in the target image data;

[0104] A foreign object determination module 504, configured to determine that the profile data is a foreign object on the transmission tower if the index value is greater than or equal to a preset index threshold;

[0105] A foreign body information acquisition module 505, used to generate the location of the foreign body and the category of the foreign body according to the contour data;

[0106] The foreign object cleaning module 506 is used to control the second automatic flying vehicle to fly to the location and use a cleaning device matching the category to clean the foreign objects.

[0107] In one embodiment of the present invention, the indicator value calculation module 503 includes:

[0108] An edge image data acquisition module is used to perform edge detection on the target image data to obtain edge image data;

[0109] A contour data extraction module, used for extracting a plurality of contour data from the edge image data;

[0110] An original area statistics module, used for counting the original area of ​​each of the contour data;

[0111] An original complexity calculation module, used for calculating the original complexity of the shape of the contour data according to the original area;

[0112] A target complexity acquisition module is used to normalize each of the original complexities to obtain a target complexity;

[0113] A target area acquisition module is used to normalize each of the original areas to obtain a target area;

[0114] The index value fusion module is used to fuse the target complexity and the target area into the index value on the shape for the same contour data.

[0115] In one embodiment of the present invention, the indicator value is expressed as:

[0116]

[0117]

[0118]

[0119] QM i =α×Re i +β×Res i ;

[0120] In the formula, F irepresents the original complexity of the i-th contour data, C i represents the perimeter value of the i-th contour data, P i Re represents the original area of ​​the i-th contour data, i represents the target complexity of the i-th contour data, F min represents the minimum value of the original complexity among the plurality of contour data, F max Res represents the maximum value of the original complexity among the multiple contour data. i represents the target area of ​​the i-th contour data, P min represents the minimum value of the original area among the plurality of contour data, P max Indicates the maximum value of the original area among the plurality of contour data, QM i represents the index value of the i-th contour data, α represents the first weight of the target complexity, and β represents the second weight of the target area.

[0121] In one embodiment of the present invention, the cleaning device comprises a box body fixed to the bottom of the body of the second automatic flying vehicle, a side groove on the side wall of the box body, a receiving port on the bottom wall of the groove of the side groove, an audio player on the box body, and a clamping mechanism in the side groove;

[0122] Wherein, a cavity is provided inside the box body, the side groove is provided at a concave position of the box side wall relative to the box body, the corresponding concave area of ​​the side groove is the groove cavity, and the cavity is used to store the foreign matter collected and cleaned by the clamping mechanism.

[0123] In one embodiment of the present invention, the clamping mechanism includes a first telescopic driving rod provided on the side groove, a second telescopic driving rod provided on the side groove and correspondingly located below the first telescopic driving rod, a third telescopic driving rod provided on the side groove and correspondingly located below the second telescopic driving rod, a negative pressure motor fixed in the cavity for generating negative pressure in the cavity, an electric driven scissors fixed to the other end of the first telescopic driving rod, a clamp fixed to the other end of the second telescopic driving rod, and an adsorbent fixed to the third telescopic driving rod;

[0124] Wherein, the first telescopic driving rod, the second telescopic driving rod and the third telescopic driving rod are arranged parallel to each other.

[0125] In one embodiment of the present invention, the adsorption member includes a U-shaped rod which is horizontally arranged and has a hollow structure inside, a plurality of adsorption holes which are sequentially arranged on the upper rod wall and the side rod wall of the U-shaped rod, a through hole which is arranged on the lower rod wall of the U-shaped rod, a plurality of ducts which are used to connect the adsorption holes with the through holes respectively, an air suction pump fixed on the box body, a transmission duct which is used to connect the air suction end of the air suction pump with the through holes respectively, and a control unit which is used to control the air suction operation intensity of the air suction pump; the air suction pump operates to realize the adsorption force generated by each of the adsorption holes;

[0126] The multi-branch catheter is located in the hollow structure of the U-shaped rod, and the U-shaped rod is composed of two parallel side rods and a connecting rod connecting the two side rods. The side rods and the connecting rod are both located on the same horizontal plane, and the bottom surfaces of the side rods and the connecting rod constitute the bottom wall of the U-shaped rod, and the top surfaces of the side rods and the connecting rod constitute the top wall of the U-shaped rod, and the inner surfaces opposite to each other of the two side rods are the side walls of the U-shaped rod.

[0127] In one embodiment of the present invention, the foreign matter cleaning module 506 includes:

[0128] A dynamic object cleaning module, for, if the category is a dynamic object, using the audio player to play a specified audio signal to drive away the dynamic object;

[0129] The static object cleaning module is used to clamp the static object with the clamping mechanism if the category is a static object, and to absorb the static object with the adsorbent according to the category information of the static object to cooperate with the clamping operation of the clamping mechanism to complete the cleaning of the static object.

[0130] In one embodiment of the present invention, the static object cleaning module includes:

[0131] A suction value configuration module, used for configuring the suction value of the adsorbent according to the category information of the static object;

[0132] A static object adsorption module, used for controlling the adsorption member to adsorb the static object according to the suction value, so as to cooperate with the clamping operation of the clamping mechanism to complete the cleaning of the static object;

[0133] Wherein, the suction value is expressed as:

[0134]

[0135] Where P m represents the suction value, P baserepresents a suction reference value, Kt represents a coefficient of the category information, γ represents a weight for adjusting the adsorption area, Ksc represents a scale parameter, P represents an area of ​​the contour data characterizing the foreign matter, and Pref represents a reference area.

[0136] The foreign object inspection device for a transmission tower provided in an embodiment of the present invention can execute the foreign object inspection method for a transmission tower provided in any embodiment of the present invention, and has corresponding functional modules and beneficial effects for executing the foreign object inspection method for a transmission tower.

[0137] Embodiment 3

[0138] See also Figure 6 , showing a schematic diagram of the structure of a computer device provided by an embodiment of the present invention. The computer device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, blade servers, mainframe computers, and other suitable computers. The computer device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0139] like Figure 6 As shown, the computer device 20 includes at least one processor 21, and a memory connected to the at least one processor 21, such as a read-only memory (ROM) 22, a random access memory (RAM) 23, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 21 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 22 or the computer program loaded from the storage unit 28 to the random access memory (RAM) 23. In the RAM 13, various programs and data required for the operation of the computer device 20 can also be stored. The processor 21, ROM 12 and RAM 13 are connected to each other through a bus 24. An input / output (I / O) interface 25 is also connected to the bus 24.

[0140] A number of components in the computer device 20 are connected to the I / O interface 25, including: an input unit 26, such as a keyboard, a mouse, etc.; an output unit 27, such as various types of displays, speakers, etc.; a storage unit 28, such as a disk, an optical disk, etc.; and a communication unit 29, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 29 allows the computer device 20 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0141] The processor 21 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 21 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 21 executes the various methods and processes described above, such as the foreign object inspection method for the transmission tower.

[0142] In some embodiments, the foreign object inspection method for a transmission tower may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 28. In some embodiments, part or all of the computer program may be loaded and / or installed on the computer device 20 via the ROM 12 and / or the communication unit 29. When the computer program is loaded into the RAM 13 and executed by the processor 21, one or more steps of the foreign object inspection method for a transmission tower described above may be performed. Alternatively, in other embodiments, the processor 21 may be configured to execute the foreign object inspection method for a transmission tower in any other appropriate manner (e.g., by means of firmware).

[0143] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0144] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0145] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0146] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0147] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0148] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0149] Embodiment 4

[0150] An embodiment of the present invention further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the foreign object inspection method for a transmission tower provided in any embodiment of the present invention is implemented.

[0151] In the process of implementation, the computer program product can be written in one or more programming languages ​​or a combination thereof to perform the computer program code of the present invention, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0152] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0153] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for inspecting foreign objects on a transmission tower, characterized in that: include: When controlling the first automatic aerial vehicle to fly according to a preset inspection path, calling a camera in the first automatic aerial vehicle to collect raw image data of the transmission tower; Preprocessing the original image data to obtain target image data; Calculating shape index values ​​for a plurality of contour data in the target image data; If the index value is greater than or equal to a preset index threshold, determining that the profile data is a foreign object on the transmission tower; generating the position of the foreign object and the category of the foreign object according to the contour data; The second automatic flying vehicle is controlled to fly to the location, and a cleaning device matching the category is used to clean the foreign matter.

2. The method according to claim 1, characterized in that The step of calculating the shape index value of the plurality of contour data in the target image data comprises: Performing edge detection on the target image data to obtain edge image data; extracting a plurality of contour data from the edge image data; Counting the original area of ​​each of the contour data; Calculating the original complexity of the shape of the contour data according to the original area; Normalizing each of the original complexity levels to obtain a target complexity level; Normalizing each of the original areas to obtain a target area; For the same contour data, the target complexity and the target area are fused into an index value on the shape.

3. The method according to claim 2, characterized in that The index value is expressed as: QM i =α×Re i +β×Res i ; In the formula, F i represents the original complexity of the i-th contour data, C i represents the perimeter value of the i-th contour data, P i Re represents the original area of ​​the i-th contour data, i represents the target complexity of the i-th contour data, F min represents the minimum value of the original complexity among the plurality of contour data, F max Res represents the maximum value of the original complexity among the multiple contour data. i represents the target area of ​​the i-th contour data, P min represents the minimum value of the original area among the plurality of contour data, P max Indicates the maximum value of the original area among the plurality of contour data, QM i represents the index value of the i-th contour data, α represents the first weight of the target complexity, and β represents the second weight of the target area.

4. The method according to claim 1, characterized in that The cleaning device comprises a box body fixed to the bottom of the body of the second automatic flying vehicle, a side groove on the side wall of the box body, a receiving port on the bottom wall of the groove of the side groove, an audio player on the box body, and a clamping mechanism in the side groove; Wherein, a cavity is provided inside the box body, the side groove is provided at a concave position of the box side wall relative to the box body, the corresponding concave area of ​​the side groove is the groove cavity, and the cavity is used to store the foreign matter collected and cleaned by the clamping mechanism.

5. The method according to claim 4, characterized in that The clamping mechanism includes a first telescopic driving rod provided on the side groove, a second telescopic driving rod provided on the side groove and correspondingly located below the first telescopic driving rod, a third telescopic driving rod provided on the side groove and correspondingly located below the second telescopic driving rod, a negative pressure motor fixed in the cavity for generating negative pressure in the cavity, an electric driven scissors fixed to the other end of the first telescopic driving rod, a clamper fixed to the other end of the second telescopic driving rod, and an adsorbent fixed to the third telescopic driving rod; Wherein, the first telescopic driving rod, the second telescopic driving rod and the third telescopic driving rod are arranged parallel to each other.

6. The method according to claim 5, characterized in that The adsorption member includes a U-shaped rod which is horizontally arranged and has a hollow structure inside, a plurality of adsorption holes which are sequentially arranged on the upper rod wall and the side rod wall of the U-shaped rod, a through hole which is arranged on the lower rod wall of the U-shaped rod, a plurality of ducts which are used to connect the adsorption holes with the through holes respectively, an air suction pump which is fixed on the box body, a transmission duct which is used to connect the air suction end of the air suction pump with the through holes respectively, and a control unit which is used to control the air suction operation intensity of the air suction pump; the air suction pump operates to realize the adsorption force generated by each of the adsorption holes; The multi-branch catheter is located in the hollow structure of the U-shaped rod, and the U-shaped rod is composed of two parallel side rods and a connecting rod connecting the two side rods. The side rods and the connecting rod are both located on the same horizontal plane, and the bottom surfaces of the side rods and the connecting rod constitute the bottom wall of the U-shaped rod, and the top surfaces of the side rods and the connecting rod constitute the top wall of the U-shaped rod, and the inner surfaces opposite to each other of the two side rods are the side walls of the U-shaped rod.

7. The method according to any one of claims 4 to 6, characterized in that: The method of using a cleaning device matching the category to clean the foreign matter comprises: If the category is a dynamic object, the audio player is used to play a specified audio signal to drive away the dynamic object; If the category is a static object, the clamping mechanism is used to clamp the static object, and the adsorbent is used to adsorb the static object according to the category information of the static object, so as to cooperate with the clamping operation of the clamping mechanism to complete the cleaning of the static object.

8. The method according to claim 7, characterized in that Adsorbing the static object using the adsorbent according to the category information of the static object includes: Configuring a suction value for the adsorbent according to the category information of the static object; Controlling the adsorbent to adsorb the static object according to the suction value to cooperate with the clamping operation of the clamping mechanism to complete the cleaning of the static object; Wherein, the suction value is expressed as: Where P m represents the suction value, P base represents a suction reference value, Kt represents a coefficient of the category information, γ represents a weight for adjusting the adsorption area, Ksc represents a scale parameter, P represents an area of ​​the contour data characterizing the foreign matter, and Pref represents a reference area.

9. A computer device, characterized in that: The computer device comprises: one or more processors; A storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the foreign object inspection method for the transmission tower as described in any one of claims 1-8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the foreign object inspection method for a transmission tower as described in any one of claims 1-8 is implemented.

Images