Tower footing ponding hidden danger identification method and device, computer equipment and storage medium
Through the automated identification technology of real-time tower foundation inspection images, the location and contour of the tower foundation and the water body are identified and the intersection is analyzed, and the problem of insufficient identification of tower foundation hidden dangers in the existing technology is solved, achieving efficient and accurate tower foundation water Hidden danger detection to ensure the safety of the power system.
Patent Information
- Application Number
- CN202411150074.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-21
- Publication Date
- 2024-12-03
AI Technical Summary
The existing transmission tower foundation detection algorithm has limited capabilities in identifying tower foundation hidden dangers and cannot meet the needs of efficient and accurate inspections, especially the identification and judgment of potential hidden dangers such as tower foundation water.
Through real-time tower foundation inspection image identification and positioning, the position, profile and minimum external rectangle of the tower foundation and the water body are obtained, the intersection of the water body and the tower foundation is analyzed, and whether there is water accumulation abnormality is used in the tower foundation. Example segmentation model and image processing technology are used. Carry out automated identification.
It realizes accurate identification of hidden dangers for water accumulation in tower foundations, reduces dependence on manual inspections, improves inspection speed and coverage, promptly detects and deals with hidden dangers of water accumulation, and ensures the safe and stable operation of the power system.
Smart Images

Figure CN119068250A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of tower foundation image recognition, and in particular to a tower foundation water accumulation hazard recognition method, device, computer equipment, computer-readable storage medium and computer program product. Background Art
[0002] As an important part of the power system, the stability and safety of the transmission tower foundation are directly related to the reliable operation of the power system. At present, the detection of transmission tower foundation mainly relies on manual inspection and some traditional detection technologies. Although the existing transmission tower foundation detection algorithms have made some progress in tower foundation identification, these algorithms usually only focus on the identification of tower foundations, but ignore the identification and judgment of potential hidden dangers of tower foundations.
[0003] In the actual power transmission inspection production environment, simply identifying the location of the tower base is far from enough. Potential hidden dangers in the transmission tower base, such as water accumulation, may lead to serious safety accidents if not discovered and handled in time. Existing detection algorithms have limited ability to identify tower base hidden dangers and cannot meet the needs of efficient and accurate inspections. Summary of the invention
[0004] Based on this, it is necessary to provide a tower base water accumulation hazard identification method, device, computer equipment, computer-readable storage medium and computer program product that can identify tower base hidden dangers and meet efficient and accurate inspection requirements in response to the above-mentioned technical problems.
[0005] In a first aspect, the present application provides a method for identifying hidden dangers of water accumulation in a tower foundation, comprising:
[0006] Identify and locate the real-time tower base inspection image to obtain the tower base position and water body position;
[0007] According to the tower base position and the water body position, obtaining a tower base contour and a water body contour;
[0008] Based on the tower base outline, obtaining the minimum circumscribed rectangle of the tower base;
[0009] According to the water body outline and the minimum circumscribed rectangle of the tower base, obtaining the intersection of the water body and the tower base;
[0010] According to the intersection of the water body and the tower base, the tower base water accumulation result is obtained.
[0011] In one embodiment, an instance segmentation model is used in the process of identifying and locating the real-time tower base inspection image; wherein the training process of the instance segmentation model includes:
[0012] Obtain historical datasets of tower base inspection images;
[0013] Annotating the historical data set in image format to obtain an annotation format file;
[0014] An instance segmentation algorithm is adopted to train the instance segmentation model for the annotation format file and the historical data set.
[0015] In one embodiment, obtaining the tower base water accumulation result according to the intersection of the water body and the tower base includes:
[0016] According to the intersection of the water body and the tower base, obtaining a first ratio between the area of the intersection and the area of the tower base contour;
[0017] When the first ratio is greater than a first preset ratio threshold, the tower foundation water accumulation result is that an abnormal defect of water accumulation occurs in the tower foundation.
[0018] In one embodiment, obtaining the tower base water accumulation result according to the intersection of the water body and the tower base includes:
[0019] According to the intersection of the water body and the tower base, obtaining a second ratio between the area of the intersection and the area of the minimum circumscribed rectangle of the tower base;
[0020] When the second ratio is greater than a second preset ratio threshold, the tower foundation water accumulation result is that an abnormal defect of water accumulation occurs in the tower foundation.
[0021] In one embodiment, obtaining the minimum circumscribed rectangle of the tower base based on the tower base contour includes:
[0022] According to the tower base outline, a black and white binary drawing of the tower base is obtained;
[0023] According to the black and white binary drawing of the tower base, a minimum area rectangle calculation function is used to calculate and obtain a black and white binary drawing having a minimum circumscribed rectangle of the tower base.
[0024] In one embodiment, obtaining the intersection of the water body and the tower base according to the water body contour and the minimum circumscribed rectangle of the tower base includes:
[0025] Obtaining a black and white binary map of the water body according to the water body contour;
[0026] The intersection of the water body and the tower base is obtained according to the black-and-white binary mapping of the water body and the black-and-white binary mapping of the minimum circumscribed rectangle of the tower base.
[0027] In a second aspect, the present application also provides a tower base water accumulation hidden danger identification device, comprising:
[0028] Position recognition module, used to identify and locate the real-time tower base inspection image to obtain the tower base position and water body position;
[0029] A contour recognition module, used for obtaining a tower foundation contour and a water body contour according to the tower foundation position and the water body position;
[0030] A calculation module, used for obtaining a minimum circumscribed rectangle of the tower base based on the tower base outline;
[0031] The calculation module is further used to obtain the intersection of the water body and the tower base according to the water body outline and the minimum circumscribed rectangle of the tower base;
[0032] The discrimination module is used to obtain the tower base water accumulation result according to the intersection of the water body and the tower base.
[0033] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:
[0034] Identify and locate the real-time tower base inspection image to obtain the tower base position and water body position;
[0035] According to the tower base position and the water body position, obtaining a tower base contour and a water body contour;
[0036] Based on the tower base outline, obtaining the minimum circumscribed rectangle of the tower base;
[0037] According to the water body outline and the minimum circumscribed rectangle of the tower base, obtaining the intersection of the water body and the tower base;
[0038] According to the intersection of the water body and the tower base, the tower base water accumulation result is obtained.
[0039] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:
[0040] Identify and locate the real-time tower base inspection image to obtain the tower base position and water body position;
[0041] According to the tower base position and the water body position, obtaining a tower base contour and a water body contour;
[0042] Based on the tower base outline, obtaining the minimum circumscribed rectangle of the tower base;
[0043] According to the water body outline and the minimum circumscribed rectangle of the tower base, obtaining the intersection of the water body and the tower base;
[0044] According to the intersection of the water body and the tower base, the tower base water accumulation result is obtained.
[0045] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:
[0046] Identify and locate the real-time tower base inspection image to obtain the tower base position and water body position;
[0047] According to the tower base position and the water body position, obtaining a tower base contour and a water body contour;
[0048] Based on the tower base outline, obtaining the minimum circumscribed rectangle of the tower base;
[0049] According to the water body outline and the minimum circumscribed rectangle of the tower base, obtaining the intersection of the water body and the tower base;
[0050] According to the intersection of the water body and the tower base, the tower base water accumulation result is obtained.
[0051] The above-mentioned tower base water accumulation hidden danger identification method, device, computer equipment, computer readable storage medium and computer program product reduce the dependence on manual inspections and improve the speed and coverage of inspections through automated image recognition technology. It includes accurate identification and positioning of the tower base and water body positions, providing accurate basic data for subsequent hidden danger analysis. By obtaining the contours of the tower base and the water body, the distribution and scope of the accumulated water can be understood more accurately. The minimum circumscribed rectangle is used to define the boundary of the tower base, providing a clear reference framework for determining whether the accumulated water constitutes a hidden danger. By analyzing the intersection of the minimum circumscribed rectangle of the water body and the tower base, the specific location and impact range of the accumulated water can be determined. Timely discovery and treatment of water accumulation hidden dangers can avoid power system failures or accidents that may be caused by them, and ensure the safe and stable operation of the power system. BRIEF DESCRIPTION OF THE DRAWINGS
[0052] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.
[0053] FIG1 is an application environment diagram of a tower foundation water accumulation hidden danger identification method according to an embodiment;
[0054] FIG2 is a schematic flow diagram of a method for identifying hidden dangers of water accumulation in a tower base according to an embodiment;
[0055] FIG3 is a black and white drawing of the tower base outline in one embodiment;
[0056] FIG4 is a black and white mapping of the contour of a water body in one embodiment;
[0057] FIG5 is a black and white drawing of the minimum circumscribed rectangle in one embodiment;
[0058] FIG6 is a black and white drawing of the intersection area of the water body and the tower base in one embodiment;
[0059] FIG7 is a schematic flow chart of a method for identifying a hidden danger of water accumulation in a tower base according to another embodiment;
[0060] FIG8 is a structural block diagram of a tower base water accumulation hidden danger identification device in one embodiment;
[0061] FIG. 9 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION
[0062] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0063] The tower foundation water accumulation hidden danger identification method provided in the embodiment of the present application can be applied to the application environment shown in FIG1. The terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers.
[0064] Server 104 is used to identify and locate the real-time tower base inspection image to obtain the tower base position and the water body position; obtain the tower base contour and the water body contour based on the tower base position and the water body position; obtain the minimum circumscribed rectangle of the tower base based on the tower base contour; obtain the intersection of the water body and the tower base based on the water body contour and the minimum circumscribed rectangle of the tower base; obtain the tower base water accumulation result based on the intersection of the water body and the tower base.
[0065] The terminal 102 may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, IoT devices, and portable wearable devices. The IoT devices may be smart speakers, smart TVs, smart air conditioners, smart car devices, projection devices, etc. Portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc. Head-mounted devices may be virtual reality (VR) devices, augmented reality (AR) devices, smart glasses, etc. The server 104 may be an independent physical server, a server cluster or distributed system consisting of multiple physical servers, or a cloud server that provides cloud computing services.
[0066] In an exemplary embodiment, as shown in FIG2 , a tower foundation water accumulation hazard identification method is provided, and the method is applied to the server in FIG1 as an example for description, including the following steps S202 to S210. Among them:
[0067] Step S202: identify and locate the real-time tower base inspection image to obtain the tower base position and the water body position.
[0068] Specifically, real-time tower base inspection images refer to images of transmission tower bases acquired in real time by drones, cameras or other image acquisition devices. Then, computer vision technology is used to automatically identify specific objects in the image, namely the transmission tower base and possible water bodies. The recognition algorithm needs to be able to accurately find the location of the tower base in the image, which usually involves technologies such as image segmentation and feature detection. In addition to the tower base, the algorithm also needs to identify water bodies in the image, which may include stagnant water, rivers and other water sources that may affect the safety of the tower base. Next, image preprocessing (such as denoising, contrast enhancement), feature extraction, instance segmentation and other steps are performed to improve the accuracy of recognition.
[0069] Step S204, acquiring the tower foundation contour and the water body contour according to the tower foundation position and the water body position.
[0070] Specifically, the locations of the tower base and water bodies are identified in the image, usually in the form of pixel coordinates or bounding boxes. The contour refers to the outer boundary of an object and is the part of the image where the object and background change most significantly. Using image processing techniques, such as edge detection algorithms (e.g., the Canny algorithm), the tower base contour is extracted from the image (as shown in Figure 3). Similarly, edge detection or other image segmentation techniques are used to extract the contour of the water body (as shown in Figure 4), which may include stagnant water, rivers, etc. Contour acquisition usually involves image segmentation, which is the process of dividing the image into an object and background. During the contour acquisition process, other features may also need to be extracted, such as shape, size, texture, etc., for subsequent analysis.
[0071] Step S206, based on the tower base outline, obtaining the minimum circumscribed rectangle of the tower base.
[0072] Specifically, based on the tower base outline, the minimum enclosing rectangle of the tower base is obtained, as shown in Figure 5. The minimum enclosing rectangle refers to a rectangle that can completely contain the tower base outline and has the smallest area. The sides of this rectangle are parallel to the coordinate axes or rotated at a certain angle to adapt to the shape of the outline. This process involves calculating the geometric properties of the tower base outline, such as the bounding box, center point, area, etc. The algorithm to achieve the minimum enclosing rectangle may include finding the boundary points of the outline and then calculating the minimum rectangle formed by these points. Finding the minimum enclosing rectangle can be viewed as an optimization problem, where the goal is to minimize the area of the rectangle while ensuring that the tower base outline is completely contained.
[0073] Step S208: Obtain the intersection of the water body and the tower base according to the water body outline and the minimum circumscribed rectangle of the tower base.
[0074] Specifically, the intersection refers to the area where the water body outline and the minimum circumscribed rectangle of the tower base overlap. The process involves analyzing the relative positions of the water body and the tower base in space to determine whether they intersect. As shown in Figure 6, this is the intersection area of the two, that is, the part of the tower base covered by the water body.
[0075] Step S210, obtaining the tower base water accumulation result according to the intersection of the water body and the tower base.
[0076] Specifically, the water accumulation results refer to the information obtained through the intersection analysis on the presence and distribution of water accumulation around or on the tower foundation. If the intersection area shows that the water body is in contact with the tower foundation, this may indicate the existence of water accumulation hazards, which requires further attention and treatment. The size, location and characteristics of the intersection can be used to evaluate the potential risk of water accumulation to the stability and safety of the tower foundation.
[0077] In the above tower base water accumulation hazard identification method, the automated image recognition technology is used to reduce the reliance on manual inspections and improve the speed and coverage of inspections. It includes accurate identification and positioning of the tower base and water body locations, providing accurate basic data for subsequent hazard analysis. By obtaining the contours of the tower base and water body, the distribution and scope of water accumulation can be understood more accurately. The minimum enclosing rectangle is used to define the boundaries of the tower base, providing a clear reference framework for determining whether water accumulation constitutes a hazard. By analyzing the intersection of the minimum enclosing rectangle of the water body and the tower base, the specific location and impact range of the water accumulation can be determined. Timely discovery and treatment of water accumulation hazards can avoid power system failures or accidents that may be caused by them, and ensure the safe and stable operation of the power system.
[0078] In an exemplary embodiment, as shown in FIG7 , an instance segmentation model is used in the process of identifying and locating the real-time tower base inspection image; wherein the training process of the instance segmentation model includes:
[0079] Step S702, obtaining a historical data set of tower foundation inspection images;
[0080] Step S704, annotating the historical data set in an image format (for example, VOC format) to obtain an annotation format file;
[0081] Step S707: Use an instance segmentation algorithm (such as YOLOv8) to train an instance segmentation model based on the annotated format file and the historical data set.
[0082] Specifically, first, a large number of tower base inspection images need to be collected as historical data sets. These images can be taken by drones, captured by cameras, or obtained by other means. The historical data set should contain images under various conditions to ensure the generalization ability of the model.
[0083] For training instance segmentation models, objects in the image (such as tower bases, water bodies, etc.) need to be annotated to clearly indicate their location and category. Annotation format files (such as VOC format) define how to store annotation information of objects in the image. VOC format annotation refers to using the VOC (PASCAL Visual Object Classes) annotation format to describe objects in the image. The VOC format usually includes information such as the object's category, bounding box coordinates, and difficulty level.
[0084] Use an instance segmentation algorithm (such as YOLOv8) to train an instance segmentation model using annotated format files and historical datasets. Instance segmentation not only identifies objects in an image, but also distinguishes different instances of the same object.
[0085] Instance segmentation is an advanced image segmentation technique that can distinguish different instances of the same type of objects in an image. This is very useful for accurate recognition in complex scenes. The training process includes multiple stages, such as data preprocessing, model initialization, loss function calculation, parameter optimization, etc. Through iterative training on a large amount of labeled data, the model gradually learns how to recognize and segment objects in the image. During and after the training process, the performance of the model needs to be evaluated to ensure its effectiveness and accuracy in practical applications. The trained instance segmentation model can be applied to the recognition and positioning of real-time tower base inspection images to quickly and accurately identify the tower base and possible water accumulation hazards. For example, the trained instance segmentation model is used to identify the input visible light image, accurately locate the position of the tower base and the water body in the image, and obtain the outline of the tower base and the water body in the image. ,in, .
[0086] In this embodiment, a large number of tower base inspection images are collected and labeled, a model capable of instance segmentation is trained, and then this model is applied to real-time image recognition and positioning to improve the automation and intelligence level of transmission tower base inspection.
[0087] In an exemplary embodiment, obtaining a tower base water accumulation result according to the intersection of the water body and the tower base includes:
[0088] According to the intersection of the water body and the tower foundation, a first ratio between the area area of the intersection and the area area of the tower foundation contour is obtained; when the first ratio is greater than a first preset ratio threshold, the tower foundation water accumulation result is that the tower foundation has an abnormal water accumulation defect.
[0089] Specifically, the area of the intersection refers to the area of the area where the water body outline intersects with the minimum circumscribed rectangle of the tower base. This intersection area represents the part of the tower base covered by the water body. The area of the tower base outline refers to the area of the entire area enclosed by the tower base outline, excluding the part intersecting with the water body.
[0090] The first ratio refers to the ratio between the area of the intersection and the area of the tower base outline. This ratio is used to quantify the degree to which the tower base is covered by water. The first preset ratio threshold is a pre-set threshold, such as 50%, which is used to determine whether there is abnormal water accumulation in the tower base. If the first ratio exceeds the first preset ratio threshold, it is considered that there is abnormal water accumulation in the tower base. When the first ratio is greater than the first preset ratio threshold, it means that the degree of water accumulation in the tower base exceeds the safety standard, and corresponding maintenance or repair measures may need to be taken.
[0091] This method can automatically assess the water accumulation in the tower base, identify potential safety hazards in a timely manner, and take appropriate measures. This method can be integrated into the intelligent inspection system to improve the efficiency and accuracy of the inspection.
[0092] In an exemplary embodiment, obtaining a tower base water accumulation result according to the intersection of the water body and the tower base includes:
[0093] According to the intersection of the water body and the tower base, a second ratio between the area of the intersection and the area of the minimum circumscribed rectangle of the tower base is obtained;
[0094] When the second ratio is greater than the second preset ratio threshold, the tower foundation water accumulation result is that the tower foundation has an abnormal water accumulation defect.
[0095] Specifically, the second ratio refers to the ratio between the area of the intersection and the area of the minimum circumscribed rectangle of the tower base. This ratio is used to measure the degree to which the water covers the tower base. The second preset ratio threshold is a pre-set threshold, such as 5%, which is used to determine whether the degree of water accumulation in the tower base exceeds the normal range. If the second ratio is greater than the second preset ratio threshold, this indicates that the degree of water accumulation in the tower base is high and may pose a safety hazard. This method provides a means of quantitatively evaluating the water accumulation in the tower base by calculating the ratio and comparing it with the threshold to determine whether the water accumulation is abnormal.
[0096] In this embodiment, the water accumulation in the tower base can be automatically evaluated, possible safety hazards can be identified in time, and corresponding measures can be taken. This method can be integrated into the intelligent inspection system to improve the efficiency and accuracy of the inspection.
[0097] In an exemplary embodiment, based on the tower base contour, obtaining the minimum circumscribed rectangle of the tower base includes:
[0098] According to the outline of the tower base, obtain the black and white second drawing of the tower base;
[0099] According to the black and white binary drawing of the tower base, the minimum area rectangle calculation function is used to calculate the black and white binary drawing of the minimum circumscribed rectangle of the tower base.
[0100] Specifically, first, as shown in Figure 3, the image containing the tower base outline needs to be converted into a black and white binary image (also called a binarized image). In this image, the tower base outline will be displayed in white on a black background, usually achieved through a threshold operation. This image processing method can remove grayscale information and only retain the outline boundary, simplifying the subsequent outline detection and analysis process.
[0101] Since the IoU value between the tower base and the water body is small (IoU (Intersection over Union) is a common metric in the field of computer vision to evaluate the performance of object detection and image segmentation algorithms. IoU calculates the overlap between the predicted object boundary (for example, the bounding box obtained by the instance segmentation model) and the real object boundary (usually from the labeled data)), it is impossible to directly use the contours of the two for logical judgment. This solution uses a specific minimum area rectangle calculation function (for example, the minAreaRect function in Opencv) to determine the minimum enclosing rectangle containing the tower base contour. This function is based on geometric algorithms, such as the minimum coverage area algorithm. According to the tower base contour in the binary image, a minimum enclosing rectangle is calculated and determined, which completely contains the tower base contour and has the smallest area. As shown in Figure 5, the calculated minimum enclosing rectangle can also be represented on a black and white binary map, usually with a white rectangle covering the tower base contour. Compared with a vertical rectangle, the minimum enclosing rectangle covers less background factors, occupies a smaller proportion in the image, and fits the target contour more closely, which can effectively filter out some of the background factors caused by the water body near the tower base.
[0102] In this embodiment, the image of the tower base outline is converted into a black and white binary image, and then a specific calculation function is used to determine a minimum circumscribed rectangle that completely contains the tower base outline. This helps to more accurately analyze the position and shape of the tower base in the image, providing important information for the inspection of the power system transmission tower base.
[0103] In an exemplary embodiment, obtaining the intersection of the water body and the tower base according to the water body contour and the minimum circumscribed rectangle of the tower base includes:
[0104] Obtain black and white mapping of water bodies based on their contours;
[0105] According to the black-and-white binary mapping of the water body and the black-and-white binary mapping of the minimum circumscribed rectangle of the tower base, the intersection of the water body and the tower base is obtained.
[0106] Specifically, first, the image containing the water body contour needs to be converted into a black and white binary map. In this image, as shown in FIG4, the water body contour will be displayed in white on a black background, usually achieved through a threshold operation. This image processing method can remove grayscale information and retain only the water body contour boundary, simplifying the subsequent contour detection and analysis process. Using image processing techniques, such as bit operations (such as AND or OR operations), the black and white binary map of the water body and the black and white binary map of the minimum circumscribed rectangle of the tower base are logically operated to determine the intersection area of the two. Among them, after obtaining the minimum circumscribed rectangle of the tower base, the mask of the minimum circumscribed rectangle of the tower base is obtained, and the masks formed by the contours of each water body identified in the image are used to calculate the intersection and union.
[0107] The intersection area refers to the part where the water body outline overlaps with the minimum circumscribed rectangle of the tower base, as shown in Figure 6. This area represents where the tower base is covered or touched by the water body. In the image analysis software, the two black and white images can be superimposed to visually observe the intersection area.
[0108] In this embodiment, the image of the minimum circumscribed rectangle of the water body outline and the tower base is converted into a black and white binary map, and then the image processing technology is used to determine the intersection area of the two. This helps to assess whether the tower base is affected by the water body and provides important information for the inspection of the power system transmission tower base.
[0109] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.
[0110] Based on the same inventive concept, the embodiment of the present application also provides a tower foundation water accumulation hidden danger identification device for implementing the tower foundation water accumulation hidden danger identification method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more tower foundation water accumulation hidden danger identification device embodiments provided below can refer to the limitations of the tower foundation water accumulation hidden danger identification method above, and will not be repeated here.
[0111] In an exemplary embodiment, as shown in FIG8 , a tower foundation water accumulation hazard identification device is provided, comprising: a position identification module 802 for identifying and locating a real-time tower foundation inspection image to obtain a tower foundation position and a water body position;
[0112] The contour recognition module 804 is used to obtain the tower foundation contour and the water body contour according to the tower foundation position and the water body position;
[0113] A calculation module 806 is used to obtain a minimum circumscribed rectangle of the tower base based on the tower base outline;
[0114] The calculation module 806 is further used to obtain the intersection of the water body and the tower base according to the water body outline and the minimum circumscribed rectangle of the tower base;
[0115] The determination module 808 is used to obtain the tower base water accumulation result according to the intersection of the water body and the tower base.
[0116] In an exemplary embodiment, an instance segmentation model is used in the process of identifying and locating the real-time tower base inspection image;
[0117] An acquisition module is used to obtain historical data sets of tower base inspection images;
[0118] A processing module is used to annotate the historical data set with image formats and obtain an annotation format file;
[0119] The model training module is used to adopt the instance segmentation algorithm to train the instance segmentation model for the annotated format files and historical data sets.
[0120] In an exemplary embodiment, the discrimination module 808 is also used to obtain a first ratio between the area area of the intersection and the area area of the tower base contour based on the intersection of the water body and the tower base; when the first ratio is greater than a first preset ratio threshold, the tower base water accumulation result is an abnormal water accumulation defect in the tower base.
[0121] In an exemplary embodiment, the determination module 808 is further configured to obtain, based on the intersection of the water body and the tower base, a second ratio between the area of the intersection and the area of the minimum circumscribed rectangle of the tower base;
[0122] When the second ratio is greater than the second preset ratio threshold, the tower foundation water accumulation result is that the tower foundation has an abnormal water accumulation defect.
[0123] In an exemplary embodiment, the calculation module 806 is also used to obtain a black and white binary drawing of the tower base according to the tower base contour; based on the black and white binary drawing of the tower base, a minimum area rectangle calculation function is used to calculate and obtain a black and white binary drawing of the minimum circumscribed rectangle of the tower base.
[0124] In an exemplary embodiment, the calculation module 806 is also used to obtain a black-and-white binary map of the water body according to the contour of the water body; and obtain the intersection of the water body and the tower base according to the black-and-white binary map of the water body and the black-and-white binary map of the minimum circumscribed rectangle of the tower base.
[0125] Each module in the tower foundation water accumulation hazard identification device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.
[0126] In an exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be shown in FIG9. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface is connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store real-time tower base inspection image data and historical data sets of tower base inspection images. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a tower base water accumulation hazard identification method is implemented.
[0127] Those skilled in the art will understand that the structure shown in FIG. 9 is merely a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.
[0128] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:
[0129] Identify and locate the real-time tower base inspection image to obtain the tower base position and water body position;
[0130] According to the tower base position and the water body position, obtain the tower base contour and the water body contour;
[0131] Based on the tower base outline, obtain the minimum circumscribed rectangle of the tower base;
[0132] According to the minimum circumscribed rectangle of the water body outline and the tower base, the intersection of the water body and the tower base is obtained;
[0133] According to the intersection of the water body and the tower base, the water accumulation result of the tower base is obtained.
[0134] In one embodiment, when the processor executes the computer program, the following steps are also implemented:
[0135] The instance segmentation model is used in the process of identifying and locating the real-time tower base inspection image; the training process of the instance segmentation model includes:
[0136] Obtain historical datasets of tower base inspection images;
[0137] Annotate the historical data set in image format and obtain the annotation format file;
[0138] The instance segmentation algorithm is used to train the instance segmentation model based on the annotated format files and historical data sets.
[0139] In one embodiment, when the processor executes the computer program, the following steps are also implemented:
[0140] According to the intersection of the water body and the tower base, a first ratio between the area of the intersection and the area of the tower base contour is obtained;
[0141] When the first ratio is greater than the first preset ratio threshold, the tower foundation water accumulation result is that the tower foundation has an abnormal water accumulation defect.
[0142] In one embodiment, when the processor executes the computer program, the following steps are also implemented:
[0143] According to the intersection of the water body and the tower base, a second ratio between the area of the intersection and the area of the minimum circumscribed rectangle of the tower base is obtained;
[0144] When the second ratio is greater than the second preset ratio threshold, the tower foundation water accumulation result is that the tower foundation has an abnormal water accumulation defect.
[0145] In one embodiment, when the processor executes the computer program, the following steps are also implemented:
[0146] According to the outline of the tower base, obtain the black and white second drawing of the tower base;
[0147] According to the black and white binary drawing of the tower base, the minimum area rectangle calculation function is used to calculate the black and white binary drawing of the minimum circumscribed rectangle of the tower base.
[0148] In one embodiment, when the processor executes the computer program, the following steps are also implemented:
[0149] Obtain black and white mapping of water bodies based on their contours;
[0150] According to the black-and-white binary mapping of the water body and the black-and-white binary mapping of the minimum circumscribed rectangle of the tower base, the intersection of the water body and the tower base is obtained.
[0151] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:
[0152] Identify and locate the real-time tower base inspection image to obtain the tower base position and water body position;
[0153] According to the tower base position and the water body position, obtain the tower base contour and the water body contour;
[0154] Based on the tower base outline, obtain the minimum circumscribed rectangle of the tower base;
[0155] According to the minimum circumscribed rectangle of the water body outline and the tower base, the intersection of the water body and the tower base is obtained;
[0156] According to the intersection of the water body and the tower base, the water accumulation result of the tower base is obtained.
[0157] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0158] The instance segmentation model is used in the process of identifying and locating the real-time tower base inspection image; the training process of the instance segmentation model includes:
[0159] Obtain historical datasets of tower base inspection images;
[0160] Annotate the historical data set in image format and obtain the annotation format file;
[0161] The instance segmentation algorithm is used to train the instance segmentation model based on the annotated format files and historical data sets.
[0162] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0163] According to the intersection of the water body and the tower base, a first ratio between the area of the intersection and the area of the tower base contour is obtained;
[0164] When the first ratio is greater than the first preset ratio threshold, the tower foundation water accumulation result is that the tower foundation has an abnormal water accumulation defect.
[0165] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0166] According to the intersection of the water body and the tower base, a second ratio between the area of the intersection and the area of the minimum circumscribed rectangle of the tower base is obtained;
[0167] When the second ratio is greater than the second preset ratio threshold, the tower foundation water accumulation result is that the tower foundation has an abnormal water accumulation defect.
[0168] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0169] According to the outline of the tower base, obtain the black and white second drawing of the tower base;
[0170] According to the black and white binary drawing of the tower base, the minimum area rectangle calculation function is used to calculate the black and white binary drawing of the minimum circumscribed rectangle of the tower base.
[0171] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0172] Obtain black and white mapping of water bodies based on their contours;
[0173] According to the black-and-white binary mapping of the water body and the black-and-white binary mapping of the minimum circumscribed rectangle of the tower base, the intersection of the water body and the tower base is obtained.
[0174] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:
[0175] Identify and locate the real-time tower base inspection image to obtain the tower base position and water body position;
[0176] According to the tower base position and the water body position, obtain the tower base contour and the water body contour;
[0177] Based on the tower base outline, obtain the minimum circumscribed rectangle of the tower base;
[0178] According to the minimum circumscribed rectangle of the water body outline and the tower base, the intersection of the water body and the tower base is obtained;
[0179] According to the intersection of the water body and the tower base, the water accumulation result of the tower base is obtained.
[0180] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0181] The instance segmentation model is used in the process of identifying and locating the real-time tower base inspection image; the training process of the instance segmentation model includes:
[0182] Obtain historical datasets of tower base inspection images;
[0183] Annotate the historical data set in image format and obtain the annotation format file;
[0184] The instance segmentation algorithm is used to train the instance segmentation model based on the annotated format files and historical data sets.
[0185] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0186] According to the intersection of the water body and the tower base, a first ratio between the area of the intersection and the area of the tower base contour is obtained;
[0187] When the first ratio is greater than the first preset ratio threshold, the tower foundation water accumulation result is that the tower foundation has an abnormal water accumulation defect.
[0188] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0189] According to the intersection of the water body and the tower base, a second ratio between the area of the intersection and the area of the minimum circumscribed rectangle of the tower base is obtained;
[0190] When the second ratio is greater than the second preset ratio threshold, the tower foundation water accumulation result is that the tower foundation has an abnormal water accumulation defect.
[0191] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0192] According to the outline of the tower base, obtain the black and white second drawing of the tower base;
[0193] According to the black and white binary drawing of the tower base, the minimum area rectangle calculation function is used to calculate the black and white binary drawing of the minimum circumscribed rectangle of the tower base.
[0194] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0195] Obtain black and white mapping of water bodies based on their contours;
[0196] According to the black-and-white binary mapping of the water body and the black-and-white binary mapping of the minimum circumscribed rectangle of the tower base, the intersection of the water body and the tower base is obtained.
[0197] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.
[0198] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.
[0199] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.
[0200] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.
Claims
1. A method for identifying hidden dangers of water accumulation at the tower foundation. It is characterized in that The method comprises: Identify and locate the real-time tower base inspection image to obtain the tower base position and water body position; According to the tower base position and the water body position, obtaining a tower base contour and a water body contour; Based on the tower base outline, obtaining the minimum circumscribed rectangle of the tower base; According to the water body outline and the minimum circumscribed rectangle of the tower base, obtaining the intersection of the water body and the tower base; According to the intersection of the water body and the tower base, the tower base water accumulation result is obtained.
2. The method according to claim 1, It is characterized in that The method further includes: using an instance segmentation model in the process of identifying and locating the real-time tower base inspection image; wherein the training process of the instance segmentation model includes: Obtain historical datasets of tower base inspection images; Annotating the historical data set in image format to obtain an annotation format file; An instance segmentation algorithm is adopted to train the instance segmentation model for the annotation format file and the historical data set.
3. The method according to claim 1, It is characterized in that The step of obtaining the tower base water accumulation result according to the intersection of the water body and the tower base includes: According to the intersection of the water body and the tower base, obtaining a first ratio between the area of the intersection and the area of the tower base contour; When the first ratio is greater than a first preset ratio threshold, the tower foundation water accumulation result is an abnormal defect of water accumulation in the tower foundation.
4. The method according to claim 1, It is characterized in that The step of obtaining the tower base water accumulation result according to the intersection of the water body and the tower base includes: According to the intersection of the water body and the tower base, obtaining a second ratio between the area of the intersection and the area of the minimum circumscribed rectangle of the tower base; When the second ratio is greater than a second preset ratio threshold, the tower foundation water accumulation result is that an abnormal defect of water accumulation occurs in the tower foundation.
5. The method according to claim 1, It is characterized in that The step of obtaining a minimum circumscribed rectangle of the tower base based on the tower base contour includes: According to the tower base outline, a black and white drawing of the tower base is obtained; According to the black and white binary drawing of the tower base, a minimum area rectangle calculation function is used to calculate and obtain a black and white binary drawing having a minimum circumscribed rectangle of the tower base.
6. The method according to claim 5, It is characterized in that The step of obtaining the intersection of the water body and the tower base according to the water body contour and the minimum circumscribed rectangle of the tower base comprises: Obtaining a black and white binary map of the water body according to the water body contour; The intersection of the water body and the tower base is obtained according to the black-and-white binary mapping of the water body and the black-and-white binary mapping of the minimum circumscribed rectangle of the tower base.
7. A tower base water accumulation hidden danger identification device, It is characterized in that The device comprises: Position recognition module, used to identify and locate the real-time tower base inspection image to obtain the tower base position and water body position; A contour recognition module, used for obtaining a tower foundation contour and a water body contour according to the tower foundation position and the water body position; A calculation module, used for obtaining a minimum circumscribed rectangle of the tower base based on the tower base outline; The calculation module is further used to obtain the intersection of the water body and the tower base according to the water body outline and the minimum circumscribed rectangle of the tower base; The discrimination module is used to obtain the tower base water accumulation result according to the intersection of the water body and the tower base.
8. A computer device comprising a memory and a processor, wherein the memory stores a computer program. It is characterized in that When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.
9. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.
10. A computer program product comprising a computer program, It is characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.
Citation Information
Patent Citations
Vision-based road waterlogging detection method, electronic equipment and vehicle alarm system
CN114219791A
Method and device for detecting water level of accumulated water at tower footing of wind generating set
CN115059583A
Accumulated water depth identification method and device, electronic equipment and readable storage medium
CN117095178A
Road waterlogging trend prediction method and equipment based on machine vision, and medium
CN118505732A
Concrete dam defect time sequence image intelligent identification method
WO2023216721A1
