Method, apparatus, electronic device and readable storage medium for bridge image detection

By analyzing the current bridge image and historical information, determining the bridge damage status and type, calculating new load-bearing capacity, predicting future damage trends, and formulating maintenance and reinforcement plans, the problem of inefficient maintenance in bridge inspection is solved and efficient bridge maintenance is achieved.

CN115272257BActive Publication Date: 2025-07-11HEBEI DAOQIAO ENG TESTING CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202210925173.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-08-03
Publication Date
2025-07-11
Estimated Expiration
2042-08-03

AI Technical Summary

Technical Problem

Existing bridge detection technology is difficult to efficiently determine the bridge damage status and maintenance plan, resulting in inefficient maintenance.

Method used

By obtaining current bridge images, historical bridge images and historical image information, analyzing historical damage status and types, determining the current bridge damage degree and type, combining historical maintenance plans, calculating new load-bearing capacity, predicting future damage trends, and formulating reinforcement plans.

Benefits of technology

Quickly determine the damage status and maintenance plan of the bridge, improve the efficiency of bridge maintenance, save time, and ensure the safety and service life of the bridge.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115272257B_ABST
    Figure CN115272257B_ABST
Patent Text Reader

Abstract

This application relates to a method, device, electronic device and readable storage medium for bridge image detection, and relates to the technical field of image detection. The method includes: obtaining a current bridge image, a historical bridge image and historical image information, where the historical image information includes: a historical damage status and a historical repair plan, the current bridge image includes: an image of the current bridge damage location, and analyzing the current bridge image based on the historical damage status and the historical bridge image to obtain the current bridge damage status, where the current bridge damage status includes: the current bridge damage degree and the current bridge damage type, and then determining the current bridge repair plan based on the current bridge damage status and the historical image information. The method, device, electronic device and readable storage medium for bridge image detection provided by this application can save the time for the user to determine the current bridge plan, so as to improve the efficiency of bridge maintenance.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of image detection, and in particular, to a method, device, electronic device and readable storage medium for bridge image detection. Background Art

[0002] With the development of science and technology, and the rapid growth of the construction scale and speed of large bridge projects, various bridge engineering accidents have inevitably increased to some extent. The abnormal monitoring work of bridge structures has become even more important. Due to changes in the natural environment and usage environment, the bridge has suffered a certain degree of damage. In order to ensure smooth traffic, the damaged bridge needs to be repaired.

[0003] The inventors found during the research process that: with the development of bridge detection technology, people's requirements for bridge detection are getting higher and higher. Therefore, how to improve the maintenance efficiency of bridges has become increasingly important. Summary of the Invention

[0004] The purpose of the present application is to provide a method, device, electronic device and readable storage medium for bridge image detection, which is used to solve at least one of the above problems.

[0005] The above-mentioned invention purpose of the present application is achieved through the following technical solutions:

[0006] In a first aspect, a method for bridge image detection is provided, and the method includes:

[0007] Obtain the current bridge image, historical bridge images and historical image information, where the historical image information includes: historical damage status and historical maintenance plan, and the current bridge image includes: an image of the current bridge damage location;

[0008] Based on the historical damage status and the historical bridge images, analyze the current bridge image to obtain the current bridge damage status, where the current bridge damage status includes: the current bridge damage degree and the current bridge damage type;

[0009] Based on the current bridge damage status and the historical image information, determine the current bridge maintenance plan.

[0010] In a possible implementation manner, the historical damage status includes: historical damage degree and historical damage type;

[0011] The step of analyzing the current bridge image based on the historical damage status and the historical bridge images to obtain the current bridge damage status includes:

[0012] Match the current bridge image with the historical bridge images, and based on the matching result, determine the current bridge damage type from the historical damage types;

[0013] Match the current bridge image based on the current bridge damage type and the historical damage degree to determine the current bridge damage degree.

[0014] In another possible implementation, after matching the current bridge image based on the current bridge damage type and the historical damage degree to determine the current bridge damage degree, it further includes:

[0015] Obtain the current bridge basic information, where the current bridge basic information includes: the original load-bearing capacity of the current bridge;

[0016] Calculate the new load-bearing capacity of the current bridge based on the current bridge damage type, the current bridge damage degree, and the original load-bearing capacity of the current bridge.

[0017] In another possible implementation, determining the current bridge maintenance plan based on the current bridge damage state and the historical image information includes:

[0018] Establish a first correspondence between the historical damage state and the historical maintenance plan;

[0019] Determine the current bridge maintenance plan from the historical maintenance plans based on the first correspondence and the current bridge damage state.

[0020] In another possible implementation, after analyzing the current bridge image based on the historical damage state and the historical bridge image to obtain the current bridge damage state, it further includes:

[0021] Obtain the current bridge type, and based on the current bridge type and the current bridge damage state, predict the future damage trend of the current bridge image after a first preset time period through a prediction model, where the future damage trend includes: the future damage direction and the future damage range;

[0022] Obtain the historical damage trend and the historical reinforcement plan, and establish a second correspondence between the historical damage trend and the historical reinforcement plan, where the historical damage trend includes: the historical damage trend direction and the historical damage trend range;

[0023] Determine the reinforcement plan of the current bridge from the historical reinforcement plans based on the second correspondence and the future damage trend.

[0024] In another possible implementation, before obtaining the current bridge type and predicting the future damage trend of the current bridge image after a first preset time period based on the current bridge type and the current bridge damage state through a prediction model, it further includes:

[0025] Obtain the historical bridge types, vectorize the historical bridge types and the historical damage trends to obtain historical bridge data features;

[0026] Input the historical bridge data features into the original model for training according to the time sequence to obtain a prediction model.

[0027] In another possible implementation manner, after determining the current bridge maintenance plan based on the current bridge damage state and the historical image information, it further includes:

[0028] Obtain the bridge repair image corresponding to the current bridge image after an interval of a second preset time period;

[0029] Based on the historical damage state, determine whether the bridge repair image is in a damaged state to obtain a judgment result;

[0030] If the judgment result is yes, obtain the location information of the current bridge, and send a warning message based on the location information of the current bridge.

[0031] In a second aspect, a device for bridge image detection is provided. The device includes:

[0032] A first acquisition module, configured to acquire a current bridge image, a historical bridge image, and historical image information, where the historical image information includes: a historical damage state and a historical maintenance plan, and the current bridge image includes: an image of the damaged position of the current bridge;

[0033] An analysis module, configured to analyze the current bridge image based on the historical damage state and the historical bridge image to obtain the current bridge damage state, where the current bridge damage state includes: the current bridge damage degree and the current bridge damage type;

[0034] A first determination module, configured to determine the current bridge maintenance plan based on the current bridge damage state and the historical image information.

[0035] In a possible implementation manner, the historical damage state includes: a historical damage degree and a historical damage type;

[0036] When analyzing the current bridge image based on the historical damage state and the historical bridge image to obtain the current bridge damage state, the analysis module is specifically configured to:

[0037] Match the current bridge image based on the historical bridge image, and determine the current bridge damage type from the historical damage types based on the matching result;

[0038] Match the current bridge image based on the current bridge damage type and the historical damage degree to determine the current bridge damage degree.

[0039] In another possible implementation, the device further includes: a second acquisition module and a calculation module, where,

[0040] The second acquisition module is configured to acquire current bridge basic information, and the current bridge basic information includes: the original load-bearing capacity of the current bridge;

[0041] The calculation module is configured to calculate the new load-bearing capacity of the current bridge based on the current bridge damage type, the current bridge damage degree, and the original load-bearing capacity of the current bridge.

[0042] In another possible implementation, when determining the current bridge maintenance plan based on the current bridge damage state and the historical image information, the first determination module is specifically configured to:

[0043] Establish a first correspondence between the historical damage state and the historical maintenance plan;

[0044] Based on the first correspondence and the current bridge damage state, determine the current bridge maintenance plan from the historical maintenance plans.

[0045] In another possible implementation, the device further includes: a prediction module, an establishment module, a matching module, and a second determination module, where,

[0046] The prediction module is configured to acquire the current bridge type, and based on the current bridge type and the current bridge damage state, predict the future damage trend after a first preset time period of the current bridge image through a prediction model, where the future damage trend includes: the future damage direction and the future damage range;

[0047] The establishment module is configured to acquire the historical damage trend and the historical reinforcement plan, and establish a second correspondence between the historical damage trend and the historical reinforcement plan, where the historical damage trend includes: the historical damage trend direction and the historical damage trend range;

[0048] The second determination module is configured to determine the reinforcement plan of the current bridge from the historical reinforcement plans based on the second correspondence and the future damage trend.

[0049] In another possible implementation, the device further includes: a vectorization module and a training module, where,

[0050] The vectorization module is used to obtain the historical bridge types, and vectorize the historical bridge types and the historical damage trends to obtain historical bridge data features;

[0051] The training module is used to input the historical bridge data features into the original model for training according to the time sequence to obtain a prediction model.

[0052] In another possible implementation manner, the device further includes: a third acquisition module, a judgment module, and a sending module, where,

[0053] The third acquisition module is used to acquire the bridge repair image corresponding to the current bridge after an interval of a second preset time period;

[0054] The judgment module is used to judge whether the bridge repair image is in a damaged state based on the historical damage state to obtain a judgment result;

[0055] The sending module is used to, if the judgment result is yes, acquire the location information of the current bridge, and send a warning message based on the location information of the current bridge.

[0056] In a third aspect, an electronic device is provided, and the electronic device includes:

[0057] One or more processors;

[0058] A memory;

[0059] One or more applications, where the one or more applications are stored in the memory and are configured to be executed by the one or more processors, and the one or more applications are configured to: execute the operations corresponding to the method for bridge image detection shown in any possible implementation manner in the first aspect.

[0060] In a fourth aspect, a computer-readable storage medium is provided, and the storage medium stores at least one instruction, at least one segment of program, a code set or an instruction set, and the at least one instruction, at least one segment of program, the code set or the instruction set is loaded and executed by a processor to implement the method for bridge image detection shown in any possible implementation manner in the first aspect.

[0061] In summary, the present application includes at least one of the following beneficial technical effects:

[0062] The present application provides a method, an apparatus, an electronic device, and a readable storage medium for bridge image detection. Compared with the related art, in the present application, by obtaining a current bridge image, a historical bridge image, and historical image information, where the historical image information includes a historical damage status and a historical repair plan, and the current bridge image includes an image of the current bridge damage location, and quickly analyzing the current bridge image based on the historical damage status to obtain the current bridge damage status, the current bridge damage status includes the current bridge damage degree and the current bridge damage type, so that after obtaining the current bridge damage status, determining the current bridge repair plan based on the current bridge damage status and the historical image information, saving the time for the user to determine the current bridge repair plan, thereby improving the bridge repair efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 is a schematic flowchart of a method for bridge image detection provided by an embodiment of the present application.

[0064] Figure 2 is a schematic structural diagram of an apparatus for bridge image detection provided by an embodiment of the present application.

[0065] Figure 3 is a schematic structural diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0066] The following further describes the present application in detail with reference to the accompanying drawings.

[0067] This specific embodiment is only an explanation of the present application, and it is not a limitation of the present application. Those skilled in the art can make modifications without creative contributions to this embodiment according to needs after reading this specification, but as long as they are within the scope of the claims of the present application, they are protected by the patent law.

[0068] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without making creative efforts belong to the scope of protection of the present application.

[0069] In addition, the term "and / or" in this article is only a description of the associated correspondence relationship of the associated objects, indicating that there can be three corresponding relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this article generally represents an "or" corresponding relationship between the associated objects before and after, unless otherwise specified.

[0070] The embodiments of the present application will be further described in detail below with reference to the accompanying drawings of the specification.

[0071] The embodiments of the present application provide a method for detecting bridge images, which is executed by an electronic device. The electronic device can be a server or a terminal device. Among them, the server can be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc., but is not limited thereto. The terminal device and the server can be directly or indirectly connected through wired or wireless communication methods, which are not limited in the embodiments of the present application. Among them, as Figure 1 shown, the method may include:

[0072] Step S101, obtain the current bridge image, the historical bridge image, and the historical image information.

[0073] Among them, the historical image information includes: the historical damage status and the historical repair plan, and the current bridge image includes: the image of the current bridge damage location.

[0074] For the embodiments of the present application, the current bridge image can be obtained through a remote sensing image, or the current bridge image can be obtained through lidar. In order to analyze the current bridge image, the electronic device can obtain the current bridge image, the historical bridge image, and the historical image information in real time, or obtain the current bridge image, the historical bridge image, and the historical image information at specific intervals, or when detecting the current bridge image analysis instruction triggered by the user, obtain the current bridge image, the historical bridge image, and the historical image information. In the embodiments of the present application, the historical image and the historical image information can be obtained from local storage or from other devices, which are not limited in the embodiments of the present application.

[0075] Among them, the historical image and the historical image information can be the historical image and the historical image information of the previous month or the previous year corresponding to the current time of the current bridge image, and the specific time range is not limited in the embodiments of the present application.

[0076] In the above embodiments of the application, after the electronic device obtains the current bridge image, the historical bridge image, and the historical image information, the current bridge image can be stored locally, or the current bridge image can be sent to other devices for storage, such as a USB flash drive device.

[0077] Step S102, analyze the current bridge image based on the historical damage status and the historical bridge image to obtain the current bridge damage status.

[0078] Among them, the current bridge damage state includes: the current bridge damage degree and the current bridge damage type.

[0079] For the embodiments of the present application, when the bridge is damaged, a maintenance plan is determined based on the current damage state of the bridge. In order to improve the maintenance efficiency of the bridge, the current damage state is obtained based on the historical damage state, so as to quickly determine the maintenance plan.

[0080] Step S103: Determine the current bridge maintenance plan based on the current bridge damage state and the historical image information.

[0081] For the embodiments of the present application, the historical image information includes: the historical damage state and the historical maintenance plan. The specific historical maintenance plan is determined based on the historical damage state. When determining the current bridge maintenance plan, it is necessary to determine the current bridge maintenance plan based on the current bridge damage state. In order to further improve the maintenance efficiency of the bridge, the current bridge maintenance plan is determined based on the historical maintenance plan.

[0082] The embodiments of the present application provide a method for bridge image detection. Compared with the related technologies, in the embodiments of the present application, by obtaining the current bridge image, the historical bridge image, and the historical image information, where the historical image information includes: the historical damage state and the historical maintenance plan, and the current bridge image includes: the image of the current bridge damage location, and quickly analyzing the current bridge image based on the historical damage state to obtain the current bridge damage state, the current bridge damage state includes: the current bridge damage degree and the current bridge damage type, so that after obtaining the current bridge damage state, the current bridge maintenance plan is determined based on the current bridge damage state and the historical image information, saving the user's time to determine the current bridge maintenance plan, thereby improving the maintenance efficiency of the bridge.

[0083] A possible implementation manner of the embodiments of the present application is that the historical damage state includes: the historical damage degree and the historical damage type;

[0084] In step S102, based on the historical damage state and the historical bridge image, the current bridge image is analyzed to obtain the current bridge damage state, which may specifically include: step S1021 (not shown in the figure) and step S1022 (not shown in the figure), where

[0085] Step S1021: Match the current bridge image based on the historical bridge image, and determine the current bridge damage type from the historical damage types based on the matching result.

[0086] For the embodiments of the present application, by extracting the respective corresponding image features of the historical bridge images and the current bridge image, and searching in the database for the historical bridge image that matches the current bridge image, where the matching historical bridge image is the historical bridge image with the highest similarity to the current bridge image among all historical bridge images, and the historical damage type corresponding to the matching historical bridge image is the current bridge damage type, the bridge damage type can be accurately determined.

[0087] Step S1022: Based on the current bridge damage type and the historical damage degree, perform matching on the current bridge image to determine the current bridge damage degree.

[0088] For the embodiments of the present application, the damage degree of the bridge is related to the damage type. When determining the current bridge damage degree, it is necessary to determine the current bridge damage degree based on the current bridge damage type. When determining the current bridge damage type, perform re - matching on the current bridge image. The damage surface area and damage depth of the current bridge image can be used to perform matching on the damage degree of the bridge to determine the current bridge damage degree, and the current bridge damage degree can be determined more accurately.

[0089] Another possible implementation manner of the embodiments of the present application is to perform matching on the current bridge image based on the current bridge damage type and the historical damage degree to determine the current bridge damage degree. After that, it further includes: Step Sa1 (not shown in the figure) and Step Sa2 (not shown in the figure), where

[0090] Step Sa1: Obtain the current bridge basic information.

[0091] Among them, the current bridge basic information includes: the original load - bearing capacity of the current bridge.

[0092] For the embodiments of the present application, the current bridge basic information can be obtained from local storage, can also be obtained from other devices, or the current bridge basic information input by the user can be obtained. After the bridge is damaged, the original load - bearing capacity of the current bridge decreases. By obtaining the current bridge basic information, the new load - bearing capacity of the current bridge can be calculated.

[0093] Step Sa2: Based on the current bridge damage type, the current bridge damage degree, and the original load - bearing capacity of the current bridge, calculate the new load - bearing capacity of the current bridge.

[0094] For the embodiments of the present application, the basic information of the bridge also includes: the span of the bridge. Based on , determine the new load - bearing capacity of the current bridge, where Q is used to represent the loss coefficient of the current bridge, is used to represent the current bridge damage type, is used to represent the current bridge damage degree, For characterizing the span of a bridge, For characterizing the original load-bearing capacity of the current bridge, For characterizing the new load-bearing capacity of the current bridge. By calculating the new load-bearing capacity of the current bridge, it is possible to avoid the bridge from being damaged again due to exceeding its load-bearing capacity.

[0095] Another possible implementation manner of the embodiment of the present application. In step S103, based on the current bridge damage state and historical image information, determine the current bridge maintenance plan, which may specifically include: step S1031 (not shown in the figure) and step S1032 (not shown in the figure), where,

[0096] Step S1031: Establish a first correspondence between the historical damage state and the historical maintenance plan.

[0097] For the embodiment of the present application, the historical maintenance plan is determined based on the historical damage state. Different bridge damage states are different, and the historical maintenance plans are also different. Each historical damage state corresponds to at least one historical maintenance plan. After establishing the first correspondence between the historical damage state and the historical maintenance plan, the first correspondence can be stored in the database. For example, the historical maintenance plan corresponding to the historical damage state 1 is the historical maintenance plan 1, and the historical maintenance plan corresponding to the historical damage state 2 is the historical maintenance plan 2.

[0098] Step S1032: Based on the first correspondence and the current bridge damage state, determine the current bridge maintenance plan from the historical maintenance plans.

[0099] For the embodiment of the present application, the current bridge damage state is obtained by matching from the historical damage states. Based on the first correspondence between the historical damage state and the historical maintenance plan, the corresponding historical maintenance plan is found from the database and used as the current bridge maintenance plan, which improves the efficiency of determining the current bridge maintenance plan.

[0100] Another possible implementation manner of the embodiment of the present application. Analyze the current bridge image based on the historical damage state and the historical bridge image to obtain the current bridge damage state. After that, it further includes: step Sb1 (not shown in the figure), step Sb2 (not shown in the figure), and step Sb3 (not shown in the figure), where step Sb1 can be executed before step Sb2, step Sb1 can also be executed after step Sb2, and step Sb1 can also be executed simultaneously with step Sb2.

[0101] Step Sb1: Obtain the current bridge type, and based on the current bridge type and the current bridge damage state, predict the future damage trend of the current bridge image after a first preset time period through a prediction model.

[0102] Among them, the future damage trend includes: the future damage direction and the future damage scope.

[0103] For the embodiments of the present application, the current bridge type can be obtained from local storage, can also be obtained from other devices, or can also obtain the bridge type input by the user. The current bridge types and current bridge damage states of different bridges are different, and the future damage trends of the bridges are also different. The prediction model is a model obtained through training by inputting historical image features. In the embodiments of the present application, the first preset time can be one month or one day. Vectorize the current bridge type and the current bridge damage state into the current bridge damage state data features, that is, convert non-numerical values into numerical features, and input the current bridge damage state data features into the prediction model to obtain the future damage trend. For example, the current bridge type of the current bridge image 1 is a steel bridge, the current bridge damage type is a longitudinal crack, and the current bridge damage degree is level two. Through the prediction model, it is predicted that the future damage direction of the current bridge image 1 extends upward, and the future damage scope is 10 cm. The current bridge damage type of the current bridge image 2 is a pier cap crack, and the current bridge damage degree is level one. Through the prediction model, it is predicted that the future damage direction of the bridge image 2 extends around, and the future damage scope is 10 square centimeters.

[0104] Step Sb2: Obtain the historical damage trend and the historical reinforcement plan, and establish a second correspondence between the historical damage trend and the historical reinforcement plan.

[0105] Among them, the historical damage trend includes: the historical damage trend direction and the historical damage trend scope.

[0106] For the embodiments of the present application, after establishing the second correspondence between the historical damage trend and the historical reinforcement plan, store the second correspondence in the database. Different historical damage trends correspond to different historical reinforcement plans. The historical damage trend and the historical reinforcement plan can be obtained from local storage or from other devices. In the embodiments of the present application, the historical damage trend and the historical reinforcement plan can be the historical damage trend and the historical reinforcement plan of the previous month or the previous year of the current time.

[0107] Step Sb3: Determine the reinforcement plan for the current bridge from the historical reinforcement plans based on the second correspondence and the future damage trend.

[0108] For the embodiments of the present application, the future damage trend is obtained from the historical damage trend. Through the corresponding relationship between the historical damage trend and the historical reinforcement plan, further, the corresponding relationship between the future damage trend and the historical reinforcement plan can be determined, and the reinforcement plan for the current bridge image can be determined from the historical reinforcement plans.

[0109] Another possible implementation of the embodiment of the present application is to obtain the current bridge type, and based on the current bridge type and the current bridge damage status, predict the future damage trend after the first preset time period for the current bridge image through a prediction model. Before that, it also includes: Step Sc1 (not shown in the figure) and Step Sc2 (not shown in the figure), where

[0110] Step Sc1: Obtain the historical bridge type, and vectorize the historical bridge type and the historical damage trend to obtain the historical bridge data features.

[0111] For the embodiment of the present application, vectorize the historical bridge type and the historical damage trend to obtain the historical bridge data features. The historical bridge data features include: bridge type data features and historical damage trend data features. The historical damage trend data features include: historical damage trend direction data features and historical damage trend range data features, that is, convert non-numerical features into numerical features.

[0112] Step Sc2: Input the historical bridge data features into the original model for training according to the time sequence to obtain the prediction model.

[0113] For the embodiment of the present application, since the historical damage trend is related to the time sequence, input the historical bridge data features into the original model for training according to the time sequence, and convert the historical bridge data features into a feature matrix:

[0114]

[0115] Among them, m is used to represent the bridge type data features, and n is used to represent the historical damage trend data features.

[0116] For the embodiment of the present application, a bidirectional long short-term memory network (Long Short-Term Memory, LSTM) model is used as an example for the preset algorithm model, including but not limited to the bidirectional LSTM model. Specifically, for the construction of the preset algorithm model, the main body of the model uses bidirectional LSTM as the trend prediction model. LSTM is mainly composed of a forget gate, an input gate, and an output gate. After being filtered by the forget gate and the input gate, a feature matrix is output. After the above-described LSTM, a layer of LSTM network layer is connected in reverse. Through this process, a BI-LSTM layer can be obtained. Since it is the combined training of multiple historical bridge data features; add a historical bridge data feature joint learning layer, initialize the size of the associated vector matrix as m*n, take the output vector of the last layer of LSTM, transpose and multiply the associated vector parameter matrix, and finally connect the regression loss function to complete the construction of the prediction model.

[0117] For the embodiments of the present application, by vectorizing the historical bridge types and historical damage trends, historical bridge data features are obtained. The historical bridge data features are converted into a feature matrix, and the feature matrix is input into the original model for training to obtain a prediction model, making the obtained prediction model more accurate.

[0118] Another possible implementation manner of the embodiments of the present application is to determine the current bridge maintenance plan based on the current bridge damage status and historical image information. After that, it further includes: step Sd1 (not shown in the figure), step Sd2 (not shown in the figure), and step Sd3 (not shown in the figure), where

[0119] Step Sd1: Obtain the bridge repair image corresponding to the current bridge image after an interval of a second preset time period.

[0120] For the embodiments of the present application, after determining the maintenance plan for the current bridge, by obtaining the bridge repair image corresponding to the current bridge after an interval of a second preset time period to determine whether the bridge has been repaired. In the embodiments of the present application, the second preset time can be one week or one month.

[0121] Step Sd2: Based on the historical damage status, determine whether the bridge repair image is in a damaged state to obtain a judgment result.

[0122] For the embodiments of the present application, a first threshold is determined based on the historical damage type and a second threshold is determined based on the historical damage degree. The first threshold is the lowest threshold for the bridge to be of the damage type, and the second threshold is the lowest threshold for the bridge to be of the damage degree. By extracting the repair features of the bridge repair image, the repair features include: repair type and repair degree, comparing the repair type with the first threshold and the repair degree with the second threshold to determine whether the bridge repair image is in the historical damaged state.

[0123] Step Sd3: If the judgment result is yes, obtain the location information of the current bridge and send a warning message based on the location information of the current bridge.

[0124] For the embodiments of the present application, an important reason for the bridge to be damaged is that it is not repaired in time. When the bridge repair status matches the historical damage status, that is, when the bridge repair image is in a damaged state, the bridge has not been repaired, then a warning message is sent to the supervision department. The warning message includes: the location information of the current bridge and the maintenance plan of the current bridge. By determining whether the current bridge has been repaired, if it has not been repaired, a warning message is sent to the supervision department to supervise the bridge, so that the current bridge can be repaired as soon as possible, further improving the bridge maintenance efficiency.

[0125] The above embodiments introduced a method for bridge image detection from the perspective of the method process. The following embodiments introduce a device for bridge image detection from the perspective of virtual modules or virtual units. For details, please refer to the following embodiments.

[0126] An embodiment of the present application provides a device for bridge image detection, as Figure 2 shown. The bridge image detection device 20 may specifically include: a first acquisition module 21, an analysis module 22, and a first determination module 23. Among them,

[0127] The first acquisition module 21 is configured to acquire the current bridge image, the historical bridge image, and the historical image information. The historical image information includes: the historical damage status and the historical repair plan. The current bridge image includes: an image of the current bridge damage location;

[0128] The analysis module 22 is configured to analyze the current bridge image based on the historical damage status and the historical bridge image to obtain the current bridge damage status. The current bridge damage status includes: the current bridge damage degree and the current bridge damage type;

[0129] The first determination module 23 is configured to determine the current bridge repair plan based on the current bridge damage status and the historical image information.

[0130] In a possible implementation manner of the embodiment of the present application, the historical damage status includes: the historical damage degree and the historical damage type;

[0131] When the analysis module 22 analyzes the current bridge image based on the historical damage status and the historical bridge image to obtain the current bridge damage status, it is specifically configured to:

[0132] Match the current bridge image based on the historical bridge image, and determine the current bridge damage type from the historical damage types based on the matching result;

[0133] Match the current bridge image based on the current bridge damage type and the historical damage degree to determine the current bridge damage degree.

[0134] In another possible implementation manner of the embodiment of the present application, the device 20 further includes: a second acquisition module and a calculation module. Among them,

[0135] The second acquisition module is configured to acquire the current bridge basic information. The current bridge basic information includes: the original load-bearing capacity of the current bridge;

[0136] The calculation module is configured to calculate the new load-bearing capacity of the current bridge based on the current bridge damage type, the current bridge damage degree, and the original load-bearing capacity of the current bridge.

[0137] In another possible implementation, when determining the current bridge repair plan based on the current bridge damage status and historical image information, the first determination module 23 is specifically configured to:

[0138] Establish a first correspondence between the historical damage status and the historical repair plan;

[0139] Determine the current bridge repair plan from the historical repair plans based on the first correspondence and the current bridge damage status.

[0140] In another possible implementation, the device 20 further includes: a prediction module, an establishment module, a matching module, and a second determination module, where

[0141] The prediction module is configured to obtain the current bridge type, and based on the current bridge type and the current bridge damage status, predict the future damage trend after a first preset time period for the current bridge image through a prediction model. The future damage trend includes: the future damage direction and the future damage range;

[0142] The establishment module is configured to obtain the historical damage trend and the historical reinforcement plan, and establish a second correspondence between the historical damage trend and the historical reinforcement plan. The historical damage trend includes: the historical damage trend direction and the historical damage trend range;

[0143] The second determination module is configured to determine the reinforcement plan for the current bridge from the historical reinforcement plans based on the second correspondence and the future damage trend.

[0144] In another possible implementation, the device 20 further includes: a vectorization module and a training module, where

[0145] The vectorization module is configured to obtain the historical bridge type, and vectorize the historical bridge type and the historical damage trend to obtain the historical bridge data features;

[0146] The training module is configured to input the historical bridge data features into the original model for training according to the time sequence to obtain the prediction model.

[0147] In another possible implementation, the device 20 further includes: a third acquisition module, a judgment module, and a sending module, where

[0148] The third acquisition module is configured to acquire the bridge repair image corresponding to the current bridge image after a second preset time period;

[0149] The judgment module is configured to judge whether the bridge repair image is in a damaged state based on the historical damage status, and obtain a judgment result;

[0150] The sending module is configured to send a warning message when the judgment result is yes.

[0151] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working process of the device for bridge image detection described above can refer to the corresponding process in the foregoing method embodiments and will not be elaborated herein.

[0152] The embodiment of the present application provides a device for bridge image detection. Compared with the related art, in the embodiment of the present application, by acquiring the current bridge image, the historical bridge image, and the historical image information, where the historical image information includes: the historical damage status and the historical maintenance plan, and the current bridge image includes: the image of the current bridge damage position, and quickly analyzing the current bridge image based on the historical damage status to obtain the current bridge damage status, where the current bridge damage status includes: the current bridge damage degree and the current bridge damage type, so that after obtaining the current bridge damage status, determining the current bridge maintenance plan based on the current bridge damage status and the historical image information, saving the time for the user to determine the current bridge maintenance plan, thereby improving the maintenance efficiency of the bridge.

[0153] The embodiment of the present application provides an electronic device, such as Figure 3 shown. Figure 3 The electronic device 30 shown includes: a processor 301 and a memory 303. Among them, the processor 301 and the memory 303 are connected, such as through a bus 302. Optionally, the electronic device 30 may further include a transceiver 304. It should be noted that in practical applications, the transceiver 304 is not limited to one, and the structure of the electronic device 30 does not constitute a limitation to the embodiment of the present application.

[0154] The processor 301 may be a CPU (Central Processing Unit, central processor), a general-purpose processor, a DSP (Digital Signal Processor, data signal processor), an ASIC (Application Specific Integrated Circuit, application-specific integrated circuit), an FPGA (Field Programmable Gate Array, field programmable gate array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute various exemplary logical blocks, modules, and circuits described in combination with the disclosure of the present application. The processor 301 may also be a combination for implementing computing functions, such as a combination including one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0155] The bus 302 may include a path for transmitting information between the above components. The bus 302 can be a PCI (Peripheral Component Interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, or the like. The bus 302 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 only a thick line is used in Figure 3 , but it does not mean that there is only one bus or one type of bus.

[0156] The memory 303 can be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or it can also be an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory), or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disk storage media, or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0157] The memory 303 is used to store the application program code for implementing the solution of this application, and is controlled by the processor 301 for execution. The processor 301 is used to execute the application program code stored in the memory 303 to implement the content shown in the foregoing method embodiments.

[0158] Among them, the electronic device includes but is not limited to: mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Tablet Computers), PMPs (Portable Multimedia Players), in-vehicle terminals (such as in-vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. It can also be a server, etc. Figure 3 The shown electronic device is only an example and should not impose any restrictions on the functions and usage scope of the embodiments of this application.

[0159] An embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program runs on a computer, the computer can execute the corresponding content in the foregoing method embodiment. Compared with the related art, in the embodiment of the present application, by obtaining a current bridge image, a historical bridge image, and historical image information, where the historical image information includes: a historical damage state and a historical maintenance plan, and the current bridge image includes: an image of the current bridge damage location, and quickly analyzing the current bridge image based on the historical damage state to obtain the current bridge damage state, where the current bridge damage state includes: the current bridge damage degree and the current bridge damage type, so that after obtaining the current bridge damage state, determining the current bridge maintenance plan based on the current bridge damage state and the historical image information, saving the time for the user to determine the current bridge maintenance plan, thereby improving the maintenance efficiency of the bridge.

[0160] It should be understood that although the steps in the flowchart of the accompanying drawings are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps is not strictly limited in order, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed alternately or alternately with at least a part of other steps or sub-steps or stages of other steps.

[0161] The above are only some embodiments of the present application. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present application, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present application.

Claims

1. A method for bridge image detection, characterized in that, Including: Obtain the current bridge image, historical bridge images, and historical image information. The historical image information includes: historical damage status and historical repair plans. The current bridge image includes: an image of the current damaged position of the bridge. Based on the historical damage status and the historical bridge images, analyze the current bridge image to obtain the current bridge damage status. The current bridge damage status includes: the current bridge damage degree and the current bridge damage type. Obtain the current bridge type, and based on the current bridge type and the current bridge damage status, predict the future damage trend of the current bridge image after a first preset time period through a prediction model. The future damage trend includes: the future damage direction and the future damage range. Obtain the historical damage trend and historical reinforcement plans, and establish a second correspondence between the historical damage trend and the historical reinforcement plans. The historical damage trend includes: the historical damage trend direction and the historical damage trend range. Based on the second correspondence and the future damage trend, determine the reinforcement plan for the current bridge from the historical reinforcement plans. Based on the current bridge damage status and the historical image information, determine the current bridge repair plan.

2. The method according to claim 1, wherein The historical damage status includes: historical damage degree and historical damage type. The analyzing the current bridge image based on the historical damage status and the historical bridge images to obtain the current bridge damage status includes: Match the current bridge image based on the historical bridge images, and determine the current bridge damage type from the historical damage types based on the matching result. Match the current bridge image based on the current bridge damage type and the historical damage degree to determine the current bridge damage degree.

3. The method according to claim 2, characterized in that, After determining the current bridge damage degree by matching the current bridge image based on the current bridge damage type and the historical damage degree, it further includes: Obtain the current bridge foundation information. The current bridge foundation information includes: the original load-bearing capacity of the current bridge. Based on the current bridge damage type, the current bridge damage degree, and the original load-bearing capacity of the current bridge, calculate the new load-bearing capacity of the current bridge.

4. The method according to claim 1, characterized in that, The determining the current bridge repair plan based on the current bridge damage status and the historical image information includes: Establish a first correspondence between the historical damage status and the historical repair plans. Based on the first correspondence and the current bridge damage status, determine the current bridge repair plan from the historical repair plans.

5. The method according to claim 1, wherein Before obtaining the current bridge type and predicting the future damage trend of the current bridge image after a first preset time period based on the current bridge type and the current bridge damage status through a prediction model, it further includes: Obtain the historical bridge types, and vectorize the historical bridge types and the historical damage trends to obtain historical bridge data features. Input the historical bridge data features into the original model for training according to the time sequence to obtain a prediction model.

6. The method according to claim 1, wherein Based on the current bridge damage status and the historical image information, determining the current bridge maintenance plan, and then further including: Obtaining a bridge repair image corresponding to the current bridge image after an interval of a second preset time period; Judging whether the bridge repair image is in a damaged state based on the historical damage status to obtain a judgment result; If the judgment result is yes, obtaining the location information of the current bridge and sending a warning message based on the location information of the current bridge.

7. A device for detecting bridge images, characterized in that, Including: A first acquisition module, configured to acquire a current bridge image, a historical bridge image, and historical image information, where the historical image information includes: a historical damage status and a historical maintenance plan, and the current bridge image includes: an image of the damaged location of the current bridge; An analysis module, configured to analyze the current bridge image based on the historical damage status and the historical bridge image to obtain the current bridge damage status, where the current bridge damage status includes: the current bridge damage degree and the current bridge damage type; A prediction module, configured to obtain the current bridge type, and based on the current bridge type and the current bridge damage status, predict the future damage trend of the current bridge image after an interval of a first preset time period through a prediction model, where the future damage trend includes: the future damage direction and the future damage range; A building module, configured to obtain a historical damage trend and a historical reinforcement plan, and establish a second corresponding relationship between the historical damage trend and the historical reinforcement plan, where the historical damage trend includes: the historical damage trend direction and the historical damage trend range; A second determination module, configured to determine the reinforcement plan of the current bridge from the historical reinforcement plans based on the second corresponding relationship and the future damage trend; A first determination module, configured to determine the current bridge maintenance plan based on the current bridge damage status and the historical image information.

8. An electronic device, characterized in that, Including: One or more processors; A memory; One or more applications, where the one or more applications are stored in the memory and are configured to be executed by the one or more processors, and the one or more applications are configured to: execute a method for detecting a bridge image according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements a method for detecting a bridge image according to any one of claims 1 to 6.

Citation Information

Patent Citations

  • BIM-based steel structure bridge informatization operation and maintenance system and processing method

    CN110516820A

  • Vehicle information processing method and device, storage medium and electronic device

    CN111178552A