Air-ground integrated multi-source data fusion monitoring method and system

Abstract

The application discloses an air-ground integrated multi-source data fusion monitoring method and system, and relates to the field of bridge defect monitoring. The method is applied to a bridge monitoring platform, and the method comprises the following steps: acquiring various monitoring data of a target bridge; constructing a three-dimensional model of the target bridge according to the various monitoring data, wherein the three-dimensional model is composed of multiple model sub-areas, and one model sub-area stores the various monitoring data; calculating the comprehensive signal quality scores of the multiple model sub-areas and updating the three-dimensional model of the target bridge; according to a preset signal quality score threshold, the proportion of abnormal model sub-areas in the three-dimensional model of the target bridge is calculated; when the proportion of the abnormal model sub-areas is less than or equal to a preset first proportion threshold, the three-dimensional model of the target bridge is subjected to defect identification, and defect information of the target bridge is obtained. By implementing the technical scheme, the problem that various monitoring devices are affected by the environment and cause missed judgment or misjudgment of bridge defects is solved.

Description

Technical Field

[0001] The present application relates to the technical field of bridge defect detection, and in particular to an air-ground integrated multi-source data fusion monitoring method and system. Background Art

[0002] With the rise of the low-altitude economy, drones, with their strong operability, freedom from terrain restrictions, and flexible viewing angles, have solved the problems of insufficient coverage, low accuracy, high safety risks in on-site operations, and low efficiency in the existing infrastructure inspection technology system.

[0003] At present, for bridge inspections, drones can be equipped with various types of monitoring equipment. For example, high-definition cameras can capture optical images of the bridge deck, infrared sensors can capture the temperature field characteristics of the bridge body, and lidar can capture the three-dimensional geometric characteristics of the bridge body. Defects can then be identified and verified in various types of monitoring data, and surface and internal structural problems can be discovered, thereby solving the problem of incomplete defect monitoring of single data.

[0004] However, the above bridge defect detection method does not take into account that the actual bridge monitoring environment is in a changing state. At this time, various monitoring devices are affected by the environment and the quality of the detected data is inconsistent, which may cause bridge defects to be missed or misjudged. Summary of the Invention

[0005] To address the problem that various monitoring devices are affected by the environment, resulting in missed or misjudged bridge defects, the present application provides an air-ground integrated multi-source data fusion monitoring method and system.

[0006] In a first aspect, the present application provides an air-ground integrated multi-source data fusion monitoring method, which is applied to a bridge monitoring platform. The method comprises:

[0007] Obtain various monitoring data of the target bridge;

[0008] constructing a three-dimensional model of the target bridge based on the plurality of monitoring data, wherein the three-dimensional model is composed of a plurality of model sub-regions, wherein a plurality of monitoring data are stored in one model sub-region;

[0009] Calculating comprehensive signal quality scores of a plurality of the model sub-areas and updating the scores to the three-dimensional model of the target bridge;

[0010] According to a preset signal quality score threshold, counting the proportion of abnormal model sub-areas in the three-dimensional model of the target bridge;

[0011] When the proportion of the abnormal model sub-area is less than or equal to a preset first proportion threshold, defect identification is performed on the three-dimensional model of the target bridge to obtain defect information of the target bridge.

[0012] Optionally, constructing the three-dimensional model of the target bridge based on the plurality of monitoring data further includes:

[0013] Calculating signal quality scores corresponding to multiple monitoring data in a first model subregion, and using the monitoring data with the highest signal quality score as the benchmark monitoring data, wherein the first model subregion is any one of the multiple model subregions;

[0014] converting the plurality of monitoring data of the first model sub-area into gradient values ​​to obtain a plurality of gradient maps;

[0015] Taking a gradient map of first monitoring data as a reference gradient map, and calculating a gradient similarity between the gradient map of the first monitoring data and the gradient map of second monitoring data, wherein the first monitoring data is the reference monitoring data, and the second monitoring data is any one of the multiple monitoring data in the first model subregion except the first monitoring data;

[0016] The second monitoring data is adjusted according to the gradient similarity to obtain adjusted monitoring data, and the adjusted monitoring data is updated to the first model sub-region.

[0017] Optionally, adjusting the second monitoring data according to the gradient similarity to obtain adjusted monitoring data is specifically:

[0018]

[0019] Wherein, T is the adjusted monitoring data, T0 is the second monitoring data, S1 is the signal quality score of the baseline monitoring data, S2 is the signal quality score of the second monitoring data, and sim is the gradient similarity between the baseline monitoring data and the second monitoring data.

[0020] Optionally, the calculating of the comprehensive signal quality scores of the plurality of model sub-regions is specifically as follows:

[0021] identifying a bridge structure partition of a second model sub-region, the second model sub-region being any one of the plurality of model sub-regions;

[0022] determining, according to the bridge structure partition of the second model sub-area, functional weights of a plurality of monitoring data in the second model sub-area;

[0023] According to the functional weights and signal quality scores of the plurality of monitoring data in the second model sub-region, a comprehensive signal quality score of the second model sub-region is obtained by weighted averaging.

[0024] Optionally, before obtaining the comprehensive signal quality score of the second model sub-area by weighted averaging the functional weights and signal quality scores of the plurality of monitoring data in the second model sub-area, the method further includes:

[0025] calculating a collaborative correlation degree between third monitoring data and fourth monitoring data, where the third monitoring data and the fourth monitoring data are any two of the plurality of monitoring data in the second model sub-region;

[0026] If the cooperative correlation is greater than or equal to a preset correlation threshold, the signal quality score of the fourth monitoring data is compensated according to the signal quality score of the third monitoring data and the cooperative correlation.

[0027] Optionally, when the proportion of the abnormal model sub-areas is less than or equal to a preset first proportion threshold, defect identification is performed on the three-dimensional model of the target bridge to obtain defect information of the target bridge, which specifically further includes:

[0028] Dividing the three-dimensional model of the target bridge into a key monitoring area and a non-key monitoring area according to the functional attributes of the target bridge;

[0029] Identify the proportion of normal model sub-areas within the key monitoring area;

[0030] When the proportion of the normal model sub-area is greater than a preset second proportion threshold, defect identification is performed on the three-dimensional model of the target bridge to obtain defect information of the target bridge.

[0031] In a second aspect, the present application provides an air-ground integrated multi-source data fusion monitoring system, wherein the system is a bridge monitoring platform, and the bridge monitoring platform includes an acquisition module, a processing module, and an output module, wherein:

[0032] The acquisition module is used to acquire various monitoring data of the target bridge;

[0033] The processing module is configured to construct a three-dimensional model of the target bridge based on the plurality of monitoring data, the three-dimensional model being composed of a plurality of model sub-regions, wherein a plurality of monitoring data are stored in one model sub-region; calculate a comprehensive signal quality score of the plurality of model sub-regions and update the score to the three-dimensional model of the target bridge; and calculate a proportion of abnormal model sub-regions in the three-dimensional model of the target bridge based on a preset signal quality score threshold;

[0034] The output module is configured to perform defect identification on the three-dimensional model of the target bridge to obtain defect information of the target bridge when the proportion of the abnormal model sub-area is less than or equal to a preset first proportion threshold.

[0035] In a third aspect, the present application provides an electronic device comprising a processor, a memory, a user interface, and a network interface, wherein the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes a method as described in any one of the first aspects.

[0036] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores instructions, and when the instructions are executed, the method as described in any one of the first aspects is executed.

[0037] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0038] This application obtains multi-source monitoring data such as images, temperature, and space of the target bridge and fuses them into a three-dimensional model to ensure the consistency of various monitoring data with the spatial position of the bridge structure. The three-dimensional model is composed of multiple model sub-areas. At this time, by calculating the comprehensive signal quality score of the model sub-area and updating it to the three-dimensional model, a quantitative assessment of the data quality of the data detected by various monitoring equipment is achieved, thereby quickly locating the low-quality data area caused by environmental interference. Then, by counting the proportion of abnormal model sub-areas and comparing it with the preset threshold, if the proportion of abnormal model sub-areas is less than or equal to the preset first proportion threshold, it means that the overall data quality is high and defects can be identified to avoid missed judgments or misjudgments caused by uneven data quality. If the proportion of abnormal model sub-areas is greater than the preset first proportion threshold, the predetermined low-quality data area can be directly re-detected without the need to detect the entire area, thereby improving monitoring efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 It is a flow chart of an air-ground integrated multi-source data fusion monitoring method provided in an embodiment of the present application.

[0040] Figure 2 It is a structural diagram of an air-ground integrated multi-source data fusion monitoring system provided in an embodiment of the present application.

[0041] Figure 3 This is a structural diagram of an electronic device provided in an embodiment of the present application.

[0042] Explanation of the accompanying drawings: 1. Acquisition module; 2. Processing module; 3. Output module; 300. Electronic device; 301. Processor; 302. Communication bus; 303. User interface; 304. Network interface; 305. Memory. DETAILED DESCRIPTION

[0043] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0044] This application provides an air-ground integrated multi-source data fusion monitoring method, which is applied to bridge monitoring platforms, such as Figure 1 As shown, the method includes steps S101 to S105, which are as follows:

[0045] S101. Acquire various monitoring data of a target bridge.

[0046] In the above steps, since the defects of the target bridge include external defects and internal defects, in order to fully mine the defect information of the target bridge, it is necessary to detect multiple types of monitoring data, which can specifically include: image data, temperature data and spatial data. Among them, image data is used to identify the surface defects of the bridge, and temperature data and spatial data are used to identify the internal defects of the bridge; the structure of the bridge is complex, and data collection of some dangerous parts is difficult to rely on manual work. Therefore, part of the data needs to be collected by drones equipped with various types of monitoring equipment to collect relevant information of the bridge. At this time, the drone group plans the inspection route according to the information to be collected, and then collects relevant information of the target bridge according to the inspection route, and finally uploads the bridge-related information to the bridge monitoring platform. In addition, the ground monitoring equipment also uploads the detected bridge-related information to the bridge monitoring platform. The bridge monitoring platform cleans and verifies the bridge-related information uploaded by the drone and the bridge monitoring information uploaded by the ground monitoring equipment, and then integrates them into multiple monitoring data.

[0047] S102: Construct a three-dimensional model of the target bridge based on the various monitoring data. The three-dimensional model is composed of a plurality of model sub-regions, wherein one model sub-region stores a plurality of monitoring data.

[0048] In the above steps, the physical meanings represented by various monitoring data are different. For example, optical images represent surface features, temperature data represent the thermal radiation characteristics of the surface and interior of the structure, and spatial data represent the three-dimensional spatial geometric features of the structure. In practical applications, optical images can accurately locate the position of surface defects, but cannot determine internal structural defects. Therefore, it is necessary to combine temperature data and spatial data to analyze the deep-seated causes of surface defects. Temperature data can locate the position of internal defects, but is easily affected by the environment, resulting in low accuracy. Therefore, it can often only assist in judging the depth of the defect or the size of the internal cavity. Spatial data can accurately measure the three-dimensional geometric features of the structure and has strong anti-interference ability, but due to the lack of surface texture features, the efficiency of defect positioning is low. Therefore, after determining the defect position in the optical image and temperature data, the spatial data is used for local refined analysis to improve the efficiency and accuracy of defect detection. Therefore, this application integrates multiple monitoring data into a three-dimensional model of the bridge based on their physical significance for bridge defect detection. The three-dimensional model is then divided into multiple model sub-regions of equal size. At this time, the model sub-regions contain multiple monitoring data based on the structural regions to which they correspond on the bridge. For example, the model sub-region corresponding to the bridge surface structure may contain image data, temperature data, and spatial data, while the model sub-region corresponding to the bridge internal structure may contain temperature data, spatial data, and ultrasonic data. By constructing a three-dimensional model of the target bridge, the consistency of the multiple monitoring data and the spatial position of the bridge structure is ensured, preventing data misalignment in time and space.

[0049] In one possible implementation, in a real bridge monitoring environment, it is not guaranteed that all types of monitoring equipment have suitable monitoring conditions. Therefore, the quality of monitoring data from various monitoring devices varies. In order to improve the data quality of low-quality monitoring data, this application uses high-quality monitoring data as a benchmark to adjust the low-quality monitoring data, thereby improving the accuracy of the structural feature expression of the three-dimensional model of the target bridge, thereby providing reliable data support for subsequent defect identification; specifically:

[0050] Taking the first model sub-region storing multiple monitoring data as an example, first, the signal quality of the multiple monitoring data is evaluated to obtain a signal quality score, wherein the evaluation method can be determined by calculating the signal-to-noise ratio of the multiple monitoring data; then the monitoring data with the highest signal quality score is selected as the benchmark monitoring data to provide an adjustment range for other monitoring data with low data quality to prevent data distortion caused by excessive adjustment; then the multiple monitoring data of the first model sub-region are converted into gradient values ​​to obtain gradient maps of the multiple monitoring data, thereby unifying the structural feature descriptions of the region by the multiple monitoring data. It can be understood that the monitoring data with high data quality has a high accuracy in structural feature description, and the monitoring data with low data quality has a low accuracy in structural feature description; based on this characteristic, the present application uses the gradient map corresponding to the benchmark monitoring data as the standard, and calculates the gradient similarity of the gradient maps of the remaining other monitoring data with the gradient map corresponding to the benchmark monitoring data, thereby determining the adjustment range of the remaining monitoring data. For monitoring data with higher gradient similarity, its signal quality is also higher, and its adjustment range is also smaller; wherein, the specific adjustment range calculation method is as follows:

[0051]

[0052] Wherein, T is the adjusted monitoring data, T0 is the second monitoring data, S1 is the signal quality score of the baseline monitoring data, S2 is the signal quality score of the second monitoring data, and sim is the gradient similarity between the baseline monitoring data and the second monitoring data.

[0053] In the above formula, the lower the gradient similarity between the current monitoring data and the benchmark monitoring data, the greater the difference between the change trend and change amplitude of the current monitoring data and the benchmark monitoring data, which further indicates that the data quality of the current monitoring data is relatively low, and thus a larger adjustment amplitude is required to restore its signal quality to a certain extent; in this process, since the adjustment amplitude is affected by the benchmark monitoring data, when the signal quality score of the benchmark monitoring data itself is also very low, it cannot effectively guide the adjustment amplitude of the remaining other monitoring data. Therefore, the signal quality score of the benchmark monitoring data in the above formula is also greater than or equal to the preset signal quality score threshold.

[0054] S103: Calculate the comprehensive signal quality scores of the multiple model sub-areas and update them to the three-dimensional model of the target bridge.

[0055] In the above steps, the typical defects of the bridge at different structural locations are different. For example, the typical defects of the main beam are bending cracks, rust, etc., and the typical defects of the piers are uneven settlement, etc.; and the contribution of different monitoring data to the identification of these typical defects is different. For example, the defect identification of the main beam is mainly obtained based on image data detection, and the defect identification of the pier is mainly obtained based on spatial data detection; therefore, for different model sub-areas, when calculating the comprehensive quality score, the present application sets the functional weights of the various monitoring data in the model sub-area according to the structural area corresponding to the model sub-area on the bridge. It can be understood that the greater the functional weight of the monitoring data, the greater the contribution of the monitoring data to the typical determination of the identification; among which, the method for determining the functional weight can be calculated by using the hierarchical analysis method on the historical defect data, which will not be elaborated here; finally, the signal quality scores of the various monitoring data in the model sub-area are weighted averaged with the functional weights of the multiple monitoring data to obtain the comprehensive signal quality score of the model sub-area.

[0056] In one possible implementation, since some monitoring data are correlated, for example, temperature data and spatial data can both characterize the internal structure of the bridge. At this time, when the signal quality of one of them is higher and the signal quality of the other is lower, this correlation can be used to repair the monitoring data with low signal quality during subsequent defect identification, thereby improving the accuracy of defect identification. Therefore, for monitoring data with low signal quality scores, if there are monitoring data with higher correlation, its signal quality score needs to be compensated to maintain the stability of the comprehensive score and reduce the possibility of missed or misjudgment. Specifically: the Pearson correlation coefficient is used to calculate the collaborative correlation of the historical data of the two monitoring data. If the collaborative correlation of the two monitoring data is greater than or equal to the preset correlation threshold, the signal quality score of the monitoring data with low signal quality score is compensated according to the monitoring data with high signal quality score and the collaborative correlation. Specifically, it can be calculated using the following formula:

[0057]

[0058] Among them, S is the signal quality score after the monitoring data with low signal quality score is compensated, is the signal quality score of the monitoring data with low signal quality score before compensation, p is the collaborative correlation degree, is the signal quality score of the monitoring data associated with the monitoring data with a low signal quality score.

[0059] In the above formula, high-quality monitoring data compensates the signal quality score of low-quality monitoring data in proportion to the proportion of collaborative correlation. Specifically, Reflects the gap ratio between low-quality data and high-quality data, among which, The larger the gap, the more space needs to be compensated. In addition, the higher the collaborative correlation degree p, the greater the compensation intensity, so as to avoid over-compensation with weakly correlated data.

[0060] S104. According to a preset signal quality score threshold, the proportion of abnormal model sub-areas in the three-dimensional model of the target bridge is counted.

[0061] S105: When the proportion of the abnormal model sub-areas is less than or equal to a preset first proportion threshold, defect identification is performed on the three-dimensional model of the target bridge to obtain defect information of the target bridge.

[0062] In steps S104 and S105, after determining the comprehensive signal quality scores of the multiple model subregions, the multiple model subregions are then labeled as abnormal model subregions and normal model subregions based on a preset signal quality score threshold. Model subregions with comprehensive signal quality scores greater than or equal to the preset signal quality score threshold are labeled as normal model subregions, while model subregions with comprehensive signal quality scores less than the preset signal quality score threshold are labeled as abnormal model subregions. The proportion of abnormal model subregions in the entire three-dimensional model area is then calculated. When the proportion of abnormal model subregions is less than or equal to a preset first proportion threshold, it indicates that the overall data quality is high and defect identification can be performed. At this point, the three-dimensional model of the target bridge is input into the defect identification model to obtain a defect signal for the target bridge, thereby avoiding missed or misjudgment caused by uneven data quality. Defect information includes, but is not limited to, defect location, defect type, severity, and hazard level.

[0063] In one possible implementation, different types of bridges have different functional attributes. For example, for urban viaducts, their main function is to bear urban traffic loads. Therefore, their bridge spans are relatively short, and their structures are mostly continuous supports of multiple span beams. Their stress is concentrated in the mid-span area of ​​the main beam. At this time, in order to ensure the normal operation of the bridge, defect detection in the mid-span area of ​​the main beam is more important than in other areas. However, when identifying defects in bridges, this functional difference is often ignored, which leads to the possibility of misjudgment. For example, in the three-dimensional model of the target bridge, if most of the abnormal model sub-areas are concentrated in important bridge areas, this will lead to the possibility of misjudgment of defects in important areas. Therefore, in order to avoid this problem, before identifying the defects of the three-dimensional model of the target bridge, the present application also needs to divide the three-dimensional model of the target bridge into key monitoring areas and non-key monitoring areas according to the functional attributes of the target bridge, and then identify the proportion of normal model sub-areas in the key monitoring areas. When the proportion of normal model sub-areas is greater than the preset second proportion threshold, it means that the signal quality of the key monitoring area is high. At this time, defect identification of the three-dimensional model of the target bridge can reduce the possibility of misjudgment or missed detection.

[0064] Reference Figure 2 The present application also provides an air-ground integrated multi-source data fusion monitoring system, which is a bridge monitoring platform. The bridge monitoring platform includes an acquisition module 1, a processing module 2, and an output module 3, wherein:

[0065] Acquisition module 1, used to acquire various monitoring data of the target bridge;

[0066] Processing module 2 is configured to construct a three-dimensional model of the target bridge based on the various monitoring data, the three-dimensional model being composed of multiple model sub-regions, wherein each model sub-region stores multiple monitoring data; calculate the comprehensive signal quality scores of the multiple model sub-regions and update them to the three-dimensional model of the target bridge; and calculate the proportion of abnormal model sub-regions in the three-dimensional model of the target bridge based on a preset signal quality score threshold;

[0067] The output module 3 is used to identify defects in the three-dimensional model of the target bridge and obtain defect information of the target bridge when the proportion of the abnormal model sub-area is less than or equal to a preset first proportion threshold.

[0068] In one possible implementation, constructing a three-dimensional model of a target bridge based on a variety of monitoring data may further include:

[0069] Calculating signal quality scores corresponding to multiple monitoring data in a first model sub-region, and using the monitoring data with the highest signal quality score as the benchmark monitoring data, where the first model sub-region is any one of the multiple model sub-regions;

[0070] converting a plurality of monitoring data of the first model sub-region into gradient values ​​to obtain a plurality of gradient maps;

[0071] Taking the gradient map of the first monitoring data as the reference gradient map, and calculating the gradient similarity between the gradient map of the first monitoring data and the gradient map of the second monitoring data, the first monitoring data is the reference monitoring data, and the second monitoring data is any one of the multiple monitoring data in the first model sub-region except the first monitoring data;

[0072] The second monitoring data is adjusted according to the gradient similarity to obtain adjusted monitoring data, and is updated into the first model sub-region.

[0073] In a possible implementation, the second monitoring data is adjusted according to the gradient similarity to obtain adjusted monitoring data, specifically:

[0074]

[0075] Wherein, T is the adjusted monitoring data, T0 is the second monitoring data, S1 is the signal quality score of the baseline monitoring data, S2 is the signal quality score of the second monitoring data, and sim is the gradient similarity between the baseline monitoring data and the second monitoring data.

[0076] In one possible implementation, the comprehensive signal quality scores of the multiple model sub-regions are calculated as follows:

[0077] identifying a bridge structure partition of a second model subregion, the second model subregion being any one of the plurality of model subregions;

[0078] determining functional weights of a plurality of monitoring data in the second model sub-region according to the bridge structure partition of the second model sub-region;

[0079] According to the functional weights and signal quality scores of the multiple monitoring data in the second model sub-area, a comprehensive signal quality score of the second model sub-area is obtained by weighted average.

[0080] In a possible implementation, before obtaining a comprehensive signal quality score for the second model sub-region by weighted averaging the functional weights and signal quality scores of the plurality of monitoring data in the second model sub-region, the method further includes:

[0081] Calculating a collaborative correlation degree between the third monitoring data and the fourth monitoring data, where the third monitoring data and the fourth monitoring data are any two of the plurality of monitoring data in the second model sub-region;

[0082] If the cooperative correlation is greater than or equal to the preset correlation threshold, the signal quality score of the fourth monitoring data is compensated according to the signal quality score of the third monitoring data and the cooperative correlation.

[0083] In a possible implementation, when the proportion of the abnormal model sub-region is less than or equal to a preset first proportion threshold, defect identification is performed on the three-dimensional model of the target bridge to obtain defect information of the target bridge, which specifically includes:

[0084] According to the functional attributes of the target bridge, the 3D model of the target bridge is divided into key monitoring areas and non-key monitoring areas;

[0085] Identify the proportion of normal model sub-areas within the key monitoring area;

[0086] When the proportion of the normal model sub-area is greater than a preset second proportion threshold, defect identification is performed on the three-dimensional model of the target bridge to obtain defect information of the target bridge.

[0087] It should be noted that the above embodiments provide devices that implement their functions using only the division of the above functional modules as examples. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiments are based on the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0088] This application also discloses an electronic device. Figure 3 , Figure 3 The electronic device 300 may include: at least one processor 301 , at least one network interface 304 , a user interface 303 , a memory 305 , and at least one communication bus 302 .

[0089] The communication bus 302 is used to implement the connection and communication between these components.

[0090] The user interface 303 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 303 may also include a standard wired interface and a wireless interface.

[0091] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0092] The processor 301 may include one or more processing cores. Using various interfaces and circuits, the processor 301 connects to various components within the server. It executes instructions, programs, code sets, or instruction sets stored in the memory 305, as well as accesses data stored in the memory 305, to perform various server functions and process data. Optionally, the processor 301 may be implemented using at least one of the following hardware forms: a digital signal processing (DSP), a field-programmable gate array (FPGA), or a programmable logic array (PLA). The processor 301 may integrate one or a combination of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. The CPU primarily processes the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing content displayed on the display screen; and the modem handles wireless communications. It is understood that the modem may not be integrated into the processor 301 but implemented as a separate chip.

[0093] Among them, the memory 305 may include a random access memory (RAM) or a read-only memory (Read-Only Memory). Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 305 may also optionally be at least one storage device located away from the aforementioned processor 301. Refer to Figure 3 , as a computer storage medium, the memory 305 may include an operating system, a network communication module, a user interface module, and an application program for an air-ground integrated multi-source data fusion monitoring method.

[0094] exist Figure 3In the electronic device 300 shown, the user interface 303 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 301 can be used to call the application program of an air-ground integrated multi-source data fusion monitoring method stored in the memory 305. When executed by one or more processors 301, the electronic device 300 executes one or more of the methods described in the above embodiments. It should be noted that for the aforementioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should know that this application is not limited to the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for this application.

[0095] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0096] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are merely schematic, such as the division of units, which is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interface, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0097] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0098] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0099] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of this application, or the portion that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the method of this application. The aforementioned memory includes various media that can store program code, such as USB flash drives, mobile hard drives, magnetic disks, or optical disks.

[0100] The foregoing is merely an exemplary embodiment of the present disclosure and is not intended to limit the scope of the present disclosure. In other words, any equivalent variations and modifications made in accordance with the teachings of the present disclosure are still within the scope of the present disclosure. Those skilled in the art will readily conceive of other embodiments of the present disclosure after considering the disclosure and the practical implications thereof.

[0101] This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art not described herein. The description and examples are to be considered as exemplary only, and the scope and spirit of the present disclosure are to be defined by the claims.

Claims

1. An air-ground integrated multi-source data fusion monitoring method, characterized in that: Applied to a bridge monitoring platform, the method includes: Obtain various monitoring data of the target bridge; constructing a three-dimensional model of the target bridge based on the plurality of monitoring data, wherein the three-dimensional model is composed of a plurality of model sub-regions, wherein a plurality of monitoring data are stored in one model sub-region; Calculating comprehensive signal quality scores of a plurality of the model sub-areas and updating the scores to the three-dimensional model of the target bridge; According to a preset signal quality score threshold, counting the proportion of abnormal model sub-areas in the three-dimensional model of the target bridge; When the proportion of the abnormal model sub-area is less than or equal to a preset first proportion threshold, defect identification is performed on the three-dimensional model of the target bridge to obtain defect information of the target bridge, wherein: The step of constructing a three-dimensional model of the target bridge based on the plurality of monitoring data further includes: Calculating signal quality scores corresponding to multiple monitoring data in a first model subregion, and using the monitoring data with the highest signal quality score as the benchmark monitoring data, wherein the first model subregion is any one of the multiple model subregions; converting the plurality of monitoring data of the first model sub-area into gradient values ​​to obtain a plurality of gradient maps; Taking a gradient map of first monitoring data as a reference gradient map, and calculating a gradient similarity between the gradient map of the first monitoring data and the gradient map of second monitoring data, wherein the first monitoring data is the reference monitoring data, and the second monitoring data is any one of the multiple monitoring data in the first model subregion except the first monitoring data; According to the gradient similarity, the second monitoring data is adjusted to obtain adjusted monitoring data, and updated to the first model sub-region, which is specifically: ； Wherein, T is the adjusted monitoring data, T0 is the second monitoring data, S1 is the signal quality score of the baseline monitoring data, S2 is the signal quality score of the second monitoring data, and sim is the gradient similarity between the baseline monitoring data and the second monitoring data.

2. The method according to claim 1, characterized in that The calculating of the comprehensive signal quality scores of the plurality of model sub-regions is specifically as follows: identifying a bridge structure partition of a second model sub-region, the second model sub-region being any one of the plurality of model sub-regions; determining, according to the bridge structure partition of the second model sub-area, functional weights of a plurality of monitoring data in the second model sub-area; According to the functional weights and signal quality scores of the plurality of monitoring data in the second model sub-region, a comprehensive signal quality score of the second model sub-region is obtained by weighted averaging.

3. The method according to claim 2, characterized in that Before obtaining a comprehensive signal quality score of the second model sub-area by weighted averaging the functional weights and signal quality scores of the plurality of monitoring data in the second model sub-area, the method further includes: calculating a collaborative correlation degree between third monitoring data and fourth monitoring data, where the third monitoring data and the fourth monitoring data are any two of the plurality of monitoring data in the second model sub-region; If the cooperative correlation is greater than or equal to a preset correlation threshold, the signal quality score of the fourth monitoring data is compensated according to the signal quality score of the third monitoring data and the cooperative correlation.

4. The method according to claim 1, wherein When the proportion of the abnormal model sub-area is less than or equal to a preset first proportion threshold, defect identification is performed on the three-dimensional model of the target bridge to obtain defect information of the target bridge, which specifically includes: Dividing the three-dimensional model of the target bridge into a key monitoring area and a non-key monitoring area according to the functional attributes of the target bridge; Identify the proportion of normal model sub-areas within the key monitoring area; When the proportion of the normal model sub-area is greater than a preset second proportion threshold, defect identification is performed on the three-dimensional model of the target bridge to obtain defect information of the target bridge.

5. An air-ground integrated multi-source data fusion monitoring system, characterized by: The system is a bridge monitoring platform, which includes an acquisition module, a processing module, and an output module, wherein: The acquisition module is used to acquire various monitoring data of the target bridge; The processing module is used to construct a three-dimensional model of the target bridge based on the multiple monitoring data, wherein the three-dimensional model is composed of multiple model sub-areas, wherein one model sub-area stores multiple monitoring data; calculate the comprehensive signal quality scores of the multiple model sub-areas and update them to the three-dimensional model of the target bridge; and count the proportion of abnormal model sub-areas in the three-dimensional model of the target bridge according to a preset signal quality score threshold, wherein The step of constructing a three-dimensional model of the target bridge based on the plurality of monitoring data further includes: Calculating signal quality scores corresponding to multiple monitoring data in a first model subregion, and using the monitoring data with the highest signal quality score as the benchmark monitoring data, wherein the first model subregion is any one of the multiple model subregions; converting the plurality of monitoring data of the first model sub-area into gradient values ​​to obtain a plurality of gradient maps; Taking a gradient map of first monitoring data as a reference gradient map, and calculating a gradient similarity between the gradient map of the first monitoring data and the gradient map of second monitoring data, wherein the first monitoring data is the reference monitoring data, and the second monitoring data is any one of the multiple monitoring data in the first model subregion except the first monitoring data; According to the gradient similarity, the second monitoring data is adjusted to obtain adjusted monitoring data, and updated to the first model sub-region, which is specifically: ； Wherein, T is the adjusted monitoring data, T0 is the second monitoring data, S1 is the signal quality score of the baseline monitoring data, S2 is the signal quality score of the second monitoring data, and sim is the gradient similarity between the baseline monitoring data and the second monitoring data; The output module is configured to perform defect identification on the three-dimensional model of the target bridge to obtain defect information of the target bridge when the proportion of the abnormal model sub-area is less than or equal to a preset first proportion threshold.

6. An electronic device, characterized in that: The electronic device (300) comprises a processor (301), a memory (305), a user interface (303) and a network interface (304), wherein the memory (305) is used to store instructions, the user interface (303) and the network interface (304) are used to communicate with other devices, and the processor (301) is used to execute the instructions stored in the memory (305) so that the electronic device (300) executes the method according to any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that The computer-readable storage medium stores instructions, and when the instructions are executed, the method according to any one of claims 1 to 4 is performed.

Images