Bridge detection method and system for collaborative operation of vehicle-mounted unmanned aerial vehicle cluster

Abstract

The invention discloses a bridge detection method and system for collaborative operation of a vehicle-mounted unmanned aerial vehicle cluster, and relates to the field of bridge detection. The method is applied to a vehicle-mounted control system and comprises the following steps: acquiring vibration data of a target sling on a suspension bridge; according to the vibration data, the number of unmanned aerial vehicles for detecting the target sling and a detection strategy of the multiple unmanned aerial vehicles are determined, and the detection strategy comprises shooting frequency and detection speed; after the plurality of unmanned aerial vehicles complete detection according to the respective detection strategies, obtaining detection images of the plurality of unmanned aerial vehicles; and performing defect analysis on the plurality of detection images to obtain a defect result of the target sling on the suspension bridge. By implementing the technical scheme provided by the invention, the problem that the defect detection precision of the sling of the suspension bridge is relatively low at present is solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of bridge detection, and in particular to a bridge detection method and system based on vehicle-mounted UAV cluster cooperative operation. BACKGROUND

[0002] As a key component of traffic infrastructure, the structural health state of a bridge is directly related to traffic safety and transportation efficiency. Therefore, it is crucial to regularly carry out bridge defect detection. With the development of science and technology, unmanned aerial vehicles (UAVs) can greatly improve the detection efficiency in the detection of large bridges due to their small size, strong maneuverability, and low-altitude flight characteristics.

[0003] Currently, when detecting defects of a large suspension bridge, the sling, as the main load-bearing structure of the suspension bridge, is often the focus of detection. Therefore, according to the structural characteristics of the sling, the UAV detects the sling by capturing surface images of the sling in a stable shooting posture along the direction of the sling, thereby capturing subtle crack defects of the sling.

[0004] However, the sling of a suspension bridge will vibrate violently under the influence of vehicle traffic, which can cause the images captured by the UAV to be blurred. Therefore, some denoising algorithms are generally used to enhance image features. However, due to unstable traffic on the bridge, the vibration pattern of the sling is complex, which results in unsatisfactory enhancement of image features by the denoising algorithm, and thus reduces the defect detection accuracy of the sling. SUMMARY

[0005] To solve the problem of low defect detection accuracy of the sling of a suspension bridge, the present application provides a bridge detection method and system based on vehicle-mounted UAV cluster cooperative operation.

[0006] In a first aspect, the present application provides a bridge detection method based on vehicle-mounted UAV cluster cooperative operation, applied to a vehicle-mounted control system, the method comprising: obtaining vibration data of a target sling on a suspension bridge; determining the number of UAVs for detecting the target sling and the detection strategy of the plurality of UAVs according to the vibration data, the detection strategy including a shooting frequency and a detection speed; obtaining detection images of the plurality of UAVs after the plurality of UAVs complete detection according to their respective detection strategies; performing defect analysis on the plurality of detection images to obtain a defect result of the target sling on the suspension bridge.

[0007] Optionally, before determining the number of UAVs for detecting the target sling and the detection trajectory of the plurality of UAVs according to the vibration data, the method further comprises: calculating the signal-to-noise ratio of the vibration data; When the signal-to-noise ratio of the vibration data is less than a preset signal-to-noise ratio threshold, traffic flow data passing through the target sling is obtained, the traffic flow data including traffic composition and traffic flow; According to the traffic flow data passing through the target sling, the vibration data is corrected.

[0008] Optionally, according to the vibration data, the number of unmanned aerial vehicles detecting the target sling is determined, specifically including: The vibration data is subjected to Fourier transform to obtain a plurality of main frequency components of the vibration data; The energy proportion of a plurality of the main frequency components is calculated; The energy proportion of a plurality of the main frequency components is compared with a preset energy proportion threshold respectively to determine a plurality of effective main frequency components; The number of a plurality of the effective main frequency components is determined as the number of unmanned aerial vehicles detecting the target sling.

[0009] Optionally, the number of a plurality of the effective main frequency components is determined as the number of unmanned aerial vehicles detecting the target sling, specifically further including: The vibration mode and the main frequency of a plurality of effective main frequency components are identified; According to the vibration mode and the main frequency of a plurality of the effective main frequency components, a plurality of the main frequency components are subjected to cluster analysis to obtain a plurality of cluster clusters; The number of a plurality of the cluster clusters is determined as the number of unmanned aerial vehicles detecting the target sling.

[0010] Optionally, the detection strategy includes shooting frequency and detection speed, and according to the vibration data, the detection strategy of a plurality of unmanned aerial vehicles detecting the target sling is determined, specifically: According to the time interval between the node and the loop of the first main frequency component, the shooting frequency of the unmanned aerial vehicle corresponding to the first main frequency component is determined, the first main frequency component being any one of a plurality of the main frequency components; According to the vibration period of the first main frequency component, the detection speed of the unmanned aerial vehicle corresponding to the first main frequency component is determined.

[0011] Optionally, the defect analysis of a plurality of the detection images is performed to obtain the defect result of the target sling of the suspension bridge, specifically: Based on a plurality of the detection images, a plurality of spatial coordinates of a plurality of structure points of the target sling are extracted, wherein a plurality of spatial coordinates of each structure point are respectively extracted from a plurality of the detection images; A plurality of the detection images are subjected to quality evaluation to obtain a quality score of each of a plurality of the detection images; According to the quality scores of the detection images, a fusion weight corresponding to each of the spatial coordinates of the to-be-fused structure point is determined, the to-be-fused structure point being any one of the structure points; Based on the fusion weights corresponding to the spatial coordinates of the to-be-fused structure point, the spatial coordinates of the to-be-fused structure point are fused to obtain target spatial coordinates of the to-be-fused structure point. The target spatial coordinates of the structure points are input into a bridge defect detection model to obtain a defect result of the target sling of the suspension bridge.

[0012] Optionally, the quality of the detection images is evaluated to obtain the quality scores of the detection images, specifically as follows: Defects in the detection images are pre-identified to obtain defect distribution in the detection images; The imaging quality of the defect distribution of the detection images is evaluated to obtain first quality scores of the detection images; The distribution similarity of the defect distribution of the detection images is calculated to obtain second quality scores of the detection images; The quality scores of the detection images are calculated according to the first quality scores and the second quality scores of the detection images.

[0013] In a second aspect, the present application provides a bridge detection system for vehicle-mounted UAV cluster cooperative operation, the system being a vehicle-mounted control system, the vehicle-mounted control system comprising an acquisition module, a processing module and an output module, wherein: The acquisition module is configured to acquire vibration data of a target sling of a suspension bridge. The processing module is configured to determine the number of UAVs for detecting the target sling and a detection strategy of the UAVs according to the vibration data. The acquisition module is further configured to acquire detection images of the UAVs after the UAVs complete detection according to the respective detection strategies. The output module is configured to analyze defects in the detection images to obtain a defect result of the target sling of the suspension bridge.

[0014] In a third aspect, the present application provides an electronic device comprising a processor, a memory, a user interface and a network interface, the memory being configured to store instructions, the user interface and the network interface being configured to communicate with other devices, and the processor being configured to execute the instructions stored in the memory to enable the electronic device to perform the method of any one of the first aspect.

[0015] In a fourth aspect, the present application provides a computer-readable storage medium storing instructions that, when executed, perform the method of any of the first aspect.

[0016] To sum up, the one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: The present application determines the interference situation of the target cable to be detected by acquiring the vibration data of the target cable of the suspension bridge, then assigns an unmanned aerial vehicle to each main vibration mode in the vibration data based on the vibration data, and matches the shooting frequency and detection speed of the unmanned aerial vehicle with the corresponding main vibration mode, thereby splitting the cable image originally fused with multiple vibration interferences into multiple cable images of single vibration dimension, finally, complementing and fusing the multiple cable images of single vibration dimension, and finally synthesizing a comprehensive and accurate cable image, at this time, inputting the fused high-precision cable image into the bridge defect detection model can greatly improve the analysis accuracy of defect analysis, thereby effectively solving the problem of low defect detection accuracy of the cable of the suspension bridge. BRIEF DESCRIPTION OF DRAWINGS

[0017] Figure 1 is a flowchart of a bridge detection method of a vehicle-mounted unmanned aerial vehicle cluster cooperative operation provided by the embodiments of the present application.

[0018] Figure 2 is a structural schematic diagram of a bridge detection system of a vehicle-mounted unmanned aerial vehicle cluster cooperative operation provided by the embodiments of the present application.

[0019] Figure 3 is a structural schematic diagram of an electronic device provided by the embodiments of the present application.

[0020] BRIEF DESCRIPTION OF DRAWINGS DETAILED DESCRIPTION

[0021] To make the objectives, technical solutions and advantages of the present application clearer, the technical solutions in the present application will be described clearly and completely below with reference to the drawings in the present application. Obviously, the described embodiments are some embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0022] The present application provides a bridge detection method of a vehicle-mounted unmanned aerial vehicle cluster cooperative operation, which is applied to a vehicle-mounted control system, such as Figure 1As shown, the method comprises steps S101 to S104, which are as follows: S101, obtaining vibration data of a target suspension cable of a suspension bridge.

[0023] In the above step, the vehicle-mounted control system connects the sensing network of the suspension bridge, then reads the real-time detection data of the vibration sensor installed on the target suspension cable, and then pre-processes the real-time detection data to obtain the vibration data of the target suspension cable.

[0024] In an embodiment, the vibration data pit may be affected by electromagnetic interference in the environment, resulting in serious noise interference in the vibration data obtained by the vehicle-mounted control system. Therefore, before analyzing the vibration data, the application calculates the signal-to-noise ratio of the vibration data. If the signal-to-noise ratio of the vibration data is less than a preset signal-to-noise ratio threshold, it means that the reliability of the current vibration data is low. At this time, in order to improve the reliability of the vibration data, the application considers that the vibration of the suspension cable is caused by the load vibration of the vehicle driving on the bridge deck, and its vibration law is closely related to the traffic flow data. Therefore, the application obtains the traffic flow data through the target suspension cable, wherein the traffic flow data includes the traffic composition and the traffic flow. It should be noted that when the vehicle drives on the bridge deck, the load vibration of the vehicle itself will be transmitted to the suspension cable. As the traffic flow on the bridge deck increases, the vibration transmitted to the suspension cable will become stronger. In addition, under the same traffic flow, if the traffic composition is different, the vibration transmitted to the suspension cable will also be different. Then, according to the traffic flow data through the target suspension cable, the vibration data is corrected, wherein the traffic flow data reflects the distribution form of various vibration frequencies in the vibration data. Specifically, the traffic composition in the traffic flow data reflects the vibration frequency composition in the vibration data, and the traffic flow in the traffic flow data reflects the vibration intensity of the vibration frequency. At this time, the traffic flow data can be used to establish a prior model of the suspension cable vibration, and then a matched filter is generated based on the prior model to filter the original vibration data. The noise components that do not match the prior model are filtered out to highlight the true vibration characteristics, thereby improving the reliability of the vibration data.

[0025] S102, according to the vibration data, determining the number of unmanned aerial vehicles for detecting the target suspension cable and the detection strategy of the plurality of unmanned aerial vehicles, the detection strategy including the shooting frequency and the detection speed.

[0026] In the above step, the vibration data is subjected to Fourier transform to obtain the vibration of the target sling in the frequency domain, at this time, a plurality of main frequency components are extracted to obtain a plurality of vibration modes of the target sling, then one unmanned aerial vehicle is assigned for each vibration mode for independent detection of the target sling, and a corresponding detection strategy is configured according to the vibration mode, the detection strategy including shooting frequency and detection speed, thereby splitting the sling image originally fused with multiple vibration interferences into a plurality of sling images of single vibration dimension, so as to reduce the analysis difficulty of subsequent sling defect analysis and improve the analysis accuracy.

[0027] In a possible implementation, in an actual scene, all vibration frequency components of the sling can be theoretically obtained by Fourier transform of the vibration data, however, in addition to strong signal components reflecting main structural vibration, a large number of secondary components with weak energy caused by environmental interference are also included in the vibration spectrum, the secondary components will not have a great impact on the sling vibration, at this time, if the unmanned aerial vehicles are assigned for the secondary components, the unmanned aerial vehicle cluster resources will be greatly wasted, thereby reducing the bridge detection efficiency, therefore, after obtaining a plurality of main frequency components of the vibration data, the energy proportion of each main frequency component in the total energy of the vibration signal is calculated, the energy proportion calculation method of the main frequency component is a conventional technical means in the field, which will not be described here, then the energy proportions of the plurality of main frequency components are compared with a preset energy proportion threshold, if the energy proportion of the main frequency component is greater than or equal to the preset energy proportion threshold, the main frequency component is determined as an effective main frequency component, thereby screening a plurality of effective main frequency components from the plurality of main frequency components, finally, the number of the plurality of effective main frequency components is counted and used as the number of unmanned aerial vehicles dispatched in the target sling defect detection process.

[0028] In a possible implementation, after the vibration data is converted into frequency domain data, different harmonic components may exist in the main frequency components, but these harmonic components actually originate from the same physical vibration mode, at this time, in order to avoid the problem that multiple harmonic components of the same physical vibration mode are assigned multiple unmanned aerial vehicles, thereby causing waste of cluster resources, the application first identifies a plurality of effective main frequency components, then performs modal analysis on the effective main frequency components to determine the vibration mode of the sling corresponding to the main frequency component, wherein the vibration mode includes a plurality of types, for example, first-order bending type, second-order bending type, torsion type, etc., then a clustering algorithm is used to perform clustering analysis by taking the vibration mode and the main frequency as the clustering feature vector and taking the vibration mode consistency and the frequency harmonic as the clustering rule, to obtain a plurality of clustering clusters, wherein the vibration modes of any two clustering feature vectors in the same clustering cluster are consistent, and the main frequencies are the same or integer multiples. Finally, the number of the plurality of clustering clusters is counted and used as the number of unmanned aerial vehicles dispatched in the target sling defect detection process.

[0029] After determining the detection unmanned aerial vehicle for each vibration mode, in order to adapt to the vibration mode, the unmanned aerial vehicle needs to be configured with a corresponding detection strategy, so as to ensure the effectiveness of the unmanned aerial vehicle detection result. Specifically: For the shooting frequency, the application determines the shooting frequency of the unmanned aerial vehicle corresponding to each main frequency component according to the time interval between the antinode point and the node point of each main frequency component. Specifically, the antinode point is the position of the maximum sling vibration displacement, and the node point is the position of the sling vibration displacement of 0. The surface defect of the sling changes most significantly when the sling vibration displacement is maximum. Therefore, the time interval between the antinode point and the node point is used as the time interval of the shooting frequency of the unmanned aerial vehicle, which can effectively capture the sling surface defect, thereby improving the accuracy of subsequent defect analysis.

[0030] For the detection speed, the application determines the detection speed of the unmanned aerial vehicle corresponding to each main frequency component according to the vibration period of each main frequency component. Specifically: the essence of sling vibration is periodic deformation along the length direction, and the vibration period of the main frequency component is the time for the sling to complete one complete deformation. During the movement detection of the unmanned aerial vehicle along the length direction of the sling, if the detection speed of the unmanned aerial vehicle is too fast, it may pass through a certain section before the sling completes one vibration period, resulting in that the key mode of the section in vibration is not photographed. If the detection speed of the unmanned aerial vehicle is too slow, the same section will be repeatedly photographed, resulting in a large amount of repeated data. Therefore, the detection speed of the unmanned aerial vehicle is determined according to the vibration period of the main frequency component and the length covered by one vibration period on the sling. For example, if the vibration period T of the main frequency component is 1 second, and the length of the sling covered by the vibration period is 3 meters, the detection speed needs to be controlled at 3 meters / second, so as to completely capture all possible defect deformations within one vibration period.

[0031] S103, after the multiple unmanned aerial vehicles complete the detection according to the respective detection strategies, the detection images of the multiple unmanned aerial vehicles are acquired.

[0032] S104, defect analysis is performed on the multiple detection images to obtain the defect result of the target sling on the suspension bridge.

[0033] In the above steps S103 to S104, after the detection strategies of the multiple unmanned aerial vehicles are determined, the multiple unmanned aerial vehicles are dispatched to completely photograph the images of the target sling along the sling direction. After the photographing task is completed, the multiple unmanned aerial vehicles send the detection images to the vehicle-mounted control system. The vehicle-mounted control system performs defect analysis on the multiple detection images at this time to obtain the defect result of the target sling on the suspension bridge. Specifically: Firstly, structural features of the target sling in the plurality of detection images are extracted, and then the structural features are converted into spatial coordinates of a plurality of structural points on a preset target sling model in a three-dimensional coordinate space. It should be explained that each detection image contains complete structural features of the target sling, and therefore each structural point stores a plurality of spatial coordinates, wherein one spatial coordinate corresponds to one detection image. Then, the plurality of detection images are quality evaluated to obtain respective quality scores of the plurality of detection images. The higher the quality score is, the clearer the structural features of the target sling in the image are, and the higher the reliability is. Therefore, the respective quality scores of the plurality of detection images are normalized to obtain respective fusion weights of the plurality of spatial coordinates of the plurality of structural points. Finally, the plurality of spatial coordinates of each structural point are weighted and fused based on the respective fusion weights of the plurality of spatial coordinates of each structural point, so as to obtain more accurate target spatial coordinates of each structural point. At this time, the target spatial coordinates are more accurate in describing the structural features of the target sling. Therefore, the target spatial coordinates of the plurality of structural points are input into the bridge defect detection model for defect analysis, so as to realize the effect of improving the accuracy of the defect detection result of the target sling on the suspension bridge, wherein the bridge defect detection model is a deep learning network model trained from the correspondence between spatial information and defect information.

[0034] In a possible implementation, when the plurality of detection images are quality evaluated, in order to improve the analysis accuracy of defects, the application first performs defect pre-recognition on the plurality of detection images to obtain defect distribution in the plurality of detection images. Specifically, the spatial coordinates of the plurality of structural points corresponding to each of the plurality of detection images are input into the bridge defect detection model to obtain the defect distribution in the plurality of detection images. Then, the imaging quality of the defect area of the plurality of detection images is evaluated to obtain first quality scores of the plurality of detection images. Then, since the unmanned aerial vehicle may be affected by some instantaneous environmental interference (for example, water droplets, sandstone falling and shielding the sling) when shooting the sling image, these environmental interference may appear as defect features in the image, which may cause misjudgment in subsequent defect analysis. Therefore, the distribution similarity of the defect distribution of the plurality of detection images is calculated to obtain second quality scores of the plurality of detection images, so as to judge the consistency of the defect distribution area in the plurality of detection images. Finally, the first quality scores and the second quality scores of the plurality of detection images are weighted and summed to calculate the quality scores of the plurality of detection images. Since the first quality score directly reflects the imaging clarity and reliability of the defect features, the weight of the first quality score is greater than the weight of the second quality score.

[0035] Reference Figure 2The application also provides a bridge detection system for a vehicle-mounted UAV cluster cooperative operation, the system being a vehicle-mounted control system, the vehicle-mounted control system comprising an acquisition module 1, a processing module 2 and an output module 3, wherein: The acquisition module 1 is configured to acquire vibration data of a target sling cable of a suspension bridge. The processing module 2 is configured to determine the number of UAVs for detecting the target sling cable and a detection strategy of the plurality of UAVs according to the vibration data. The acquisition module 1 is further configured to acquire detection images of the plurality of UAVs after the plurality of UAVs complete the detection according to the respective detection strategies. The output module 3 is configured to perform defect analysis on the plurality of detection images to obtain a defect result of the target sling cable of the suspension bridge.

[0036] In a possible implementation, before determining the number of UAVs for detecting the target sling cable and the detection trajectory of the plurality of UAVs according to the vibration data, the method further comprises: calculating a signal-to-noise ratio of the vibration data; when the signal-to-noise ratio of the vibration data is less than a preset signal-to-noise ratio threshold, acquiring vehicle flow data passing through the target sling cable, the vehicle flow data comprising vehicle flow composition and vehicle flow; correcting the vibration data according to the vehicle flow data passing through the target sling cable.

[0037] In a possible implementation, the number of UAVs for detecting the target sling cable is determined according to the vibration data, and specifically comprises: performing Fourier transform on the vibration data to obtain a plurality of main frequency components of the vibration data; calculating energy proportions of the plurality of main frequency components; comparing the energy proportions of the plurality of main frequency components with preset energy proportion thresholds respectively to determine a plurality of effective main frequency components; determining the number of the plurality of effective main frequency components as the number of UAVs for detecting the target sling cable.

[0038] In a possible implementation, the number of UAVs for detecting the target sling cable is determined according to the vibration data, and specifically comprises: identifying vibration modes and main frequencies of the plurality of effective main frequency components; performing cluster analysis on the plurality of main frequency components according to the vibration modes and the main frequencies of the plurality of effective main frequency components to obtain a plurality of cluster clusters; determining the number of the plurality of cluster clusters as the number of UAVs for detecting the target sling cable.

[0039] In a possible implementation, the detection strategy comprises a shooting frequency and a detection speed, and the detection strategy of the plurality of UAVs for detecting the target sling cable is determined according to the vibration data, and specifically comprises: determine a shooting frequency of the unmanned aerial vehicle corresponding to the first main frequency component according to a time interval between a node and a loop of the first main frequency component, the first main frequency component being any one of the plurality of main frequency components; determine a detection speed of the unmanned aerial vehicle corresponding to the first main frequency component according to a vibration period of the first main frequency component.

[0040] In a possible implementation, the plurality of detection images are subjected to defect analysis to obtain a defect result of the target suspension cable of the suspension bridge, specifically: Based on the plurality of detection images, a plurality of spatial coordinates of a plurality of structure points of the target suspension cable are extracted, wherein the plurality of spatial coordinates of each structure point are respectively extracted from the plurality of detection images; The plurality of detection images are subjected to quality evaluation to obtain a quality score of each of the plurality of detection images; According to the quality score of each of the plurality of detection images, a fusion weight corresponding to each of the plurality of spatial coordinates of the to-be-fused structure point is determined, the to-be-fused structure point being any one of the plurality of structure points; Based on the fusion weight corresponding to each of the plurality of spatial coordinates of the to-be-fused structure point, the plurality of spatial coordinates of the to-be-fused structure point are subjected to weighted fusion to obtain a target spatial coordinate of the to-be-fused structure point; The target spatial coordinates of the plurality of structure points are input into the bridge defect detection model to obtain the defect result of the target suspension cable of the suspension bridge.

[0041] In a possible implementation, the plurality of detection images are subjected to quality evaluation to obtain a quality score of each of the plurality of detection images, specifically: The plurality of detection images are subjected to defect pre-recognition to obtain a defect distribution in the plurality of detection images; The imaging quality of the defect distribution of the plurality of detection images is evaluated to obtain a first quality score of the plurality of detection images; The distribution similarity of the defect distribution of the plurality of detection images is calculated to obtain a second quality score of the plurality of detection images; The quality score of the plurality of detection images is calculated according to the first quality score and the second quality score of the plurality of detection images.

[0042] It should be noted that: the apparatus provided in the above embodiments is only used as an example to divide the above functional modules, and in actual application, the above functions can be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the apparatus and method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process is described in detail in the method embodiments, which will not be repeated here.

[0043] The application also discloses an electronic device. Refer to Figure 3 , Figure 3 is a structural schematic diagram of an electronic device disclosed by the embodiment of the application. The electronic device 300 can 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.

[0044] The communication bus 302 is configured to realize the connection and communication between the components.

[0045] The user interface 303 can include a display and a camera. Optionally, the user interface 303 can further include a standard wired interface and a wireless interface.

[0046] The network interface 304 can optionally include a standard wired interface and a wireless interface (such as a WI-FI interface).

[0047] The processor 301 can include one or more processing cores. The processor 301 is connected to various parts of the server through various interfaces and lines, and performs various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 305, and calling data stored in the memory 305. Optionally, the processor 301 can be implemented in at least one of a hardware form of a digital signal processing (DSP), a field-programmable gate array (FPGA), and a programmable logic array (PLA). The processor 301 can be integrated with a combination of one or more of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. The CPU is mainly used to process an operating system, a user interface, and an application program. The GPU is used to render and draw the content to be displayed on the display. The modem is used to process wireless communication. It can be understood that the above-mentioned modem can also not be integrated into the processor 301, but can be realized by a separate chip.

[0048] The memory 305 can include a random access memory (RAM) and a read-only memory (ROM). 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 can include a program storage area and a data storage area, where the program storage area can store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing the various method embodiments described above, etc.; and the data storage area can store data involved in the various method embodiments described above, etc. The memory 305 can also be at least one storage device located away from the processor 301. For reference Figure 3 , the memory 305 as a computer storage medium can include an operating system, a network communication module, a user interface module, and an application program of the bridge detection method for the cluster cooperative operation of the vehicle-mounted unmanned aerial vehicle.

[0049] In Figure 3 , the user interface 303 is mainly used to provide an interface for user input and obtain data input by the user; and the processor 301 can be used to call the application program of the bridge detection method for the cluster cooperative operation of the vehicle-mounted unmanned aerial vehicle stored in the memory 305, and when executed by one or more processors 301, the electronic device 300 performs the method described in one or more of the above embodiments. It should be noted that, for the above-mentioned method embodiments, in order to simply describe, they are all expressed as a series of action combinations, but those skilled in the art should know that the application is not limited by the described action sequence, because according to the application, some steps can be performed in other order or simultaneously. Secondly, those skilled in the art should know that the embodiments described in the specification all belong to preferred embodiments, and the actions and modules involved are not necessarily required by the application.

[0050] In the above embodiments, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the relevant description of other embodiments.

[0051] In several embodiments provided in the present application, it should be understood that the disclosed apparatus can be implemented in other manners. For example, the division of the apparatus embodiments is merely illustrative, and the division of units can be changed according to actual conditions, such as a combination or integration of some units, or a deletion of some features, or an addition of some features. In addition, the coupling or direct coupling or communication connection between the shown or discussed units can be indirect coupling or communication connection through some interfaces, devices or units, and can be in electrical, mechanical or other forms.

[0052] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one place or distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0053] In addition, the functional units in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0054] If the integrated unit is realized in the form of 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 solutions of the present application essentially or the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a memory and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the embodiments of the present application. The aforementioned memory includes: a U disk, a mobile hard disk, a magnetic disk or an optical disk, and various media that can store program codes.

[0055] The above is only exemplary embodiments of the present disclosure, which cannot limit the scope of the present disclosure. Any equivalent changes 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 easily think of other embodiments of the present disclosure after considering the specification and the true disclosure.

[0056] The present application is intended to cover any variations, uses or adaptive changes of the present disclosure that follow the general principles of the present disclosure and include common knowledge or conventional technical means in the technical field not disclosed in the present disclosure. The specification and examples are only considered as exemplary, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A bridge detection method based on a vehicle-mounted UAV cluster cooperative operation, characterized in that, The method is applied to a vehicle-mounted control system, and comprises the following steps: Obtaining vibration data of a target suspension cable of a suspension bridge; According to the vibration data, determining the number of unmanned aerial vehicles for detecting the target suspension cable and a detection strategy of the unmanned aerial vehicles, the detection strategy comprising a shooting frequency and a detection speed; After the unmanned aerial vehicles complete the detection according to the respective detection strategies, obtaining detection images of the unmanned aerial vehicles; Performing defect analysis on the detection images to obtain a defect result of the target suspension cable of the suspension bridge. 2.The bridge detection method of claim 1, wherein, Before determining the number of unmanned aerial vehicles for detecting the target suspension cable and a detection trajectory of the unmanned aerial vehicles according to the vibration data, the method further comprises the following steps: Calculating a signal-to-noise ratio of the vibration data; When the signal-to-noise ratio of the vibration data is less than a preset signal-to-noise ratio threshold, obtaining vehicle flow data passing through the target suspension cable, the vehicle flow data comprising vehicle flow composition and vehicle flow; According to the vehicle flow data passing through the target suspension cable, correcting the vibration data. 3.The bridge detection method of claim 1, wherein, According to the vibration data, determining the number of unmanned aerial vehicles for detecting the target suspension cable, specifically comprising the following steps: Performing Fourier transform on the vibration data to obtain a plurality of main frequency components of the vibration data; Calculating energy proportions of the main frequency components; Comparing the energy proportions of the main frequency components with preset energy proportion thresholds respectively to determine a plurality of effective main frequency components; Determining the number of the effective main frequency components as the number of unmanned aerial vehicles for detecting the target suspension cable. 4.The bridge detection method of claim 3, wherein, Determining the number of the effective main frequency components as the number of unmanned aerial vehicles for detecting the target suspension cable, specifically comprising the following steps: Identifying vibration modes and main frequencies of the effective main frequency components; According to the vibration modes and main frequencies of the effective main frequency components, performing cluster analysis on the main frequency components to obtain a plurality of cluster clusters; Determining the number of the cluster clusters as the number of unmanned aerial vehicles for detecting the target suspension cable. 5.The bridge detection method of claim 3, wherein, The detection strategy comprises a shooting frequency and a detection speed, and according to the vibration data, determining a detection strategy of a plurality of unmanned aerial vehicles for detecting the target suspension cable, specifically comprising the following steps: According to a time interval between a node and an anti-node of a first main frequency component, determining a shooting frequency of an unmanned aerial vehicle corresponding to the first main frequency component, the first main frequency component being any one of the main frequency components; According to a vibration period of the first main frequency component, determining a detection speed of the unmanned aerial vehicle corresponding to the first main frequency component. 6.The bridge detection method of claim 1, wherein, The defect analysis on the detection images to obtain the defect result of the target suspension cable of the suspension bridge, specifically comprising the following steps: Based on the detection images, extracting a plurality of spatial coordinates of a plurality of structure points of the target suspension cable, wherein the spatial coordinates of each structure point are extracted from the detection images respectively; Performing quality evaluation on the detection images to obtain respective quality scores of the detection images; According to the respective quality scores of the detection images, determining respective fusion weights of spatial coordinates of to-be-fused structure points, the to-be-fused structure points being any one of the structure points; The plurality of spatial coordinates of the to-be-fused structure point are fused by weighting according to the fusion weights corresponding to the plurality of spatial coordinates of the to-be-fused structure point, to obtain target spatial coordinates of the to-be-fused structure point; The target spatial coordinates of the plurality of structure points are input into a bridge defect detection model to obtain a defect result of the target sling on the suspension bridge. 7.The bridge detection method of claim 6, wherein, The quality of the plurality of detection images is evaluated to obtain a quality score of each of the plurality of detection images, specifically: Defects in the plurality of detection images are pre-identified to obtain defect distribution in the plurality of detection images; The imaging quality of the defect distribution of the plurality of detection images is evaluated to obtain a first quality score of the plurality of detection images; The distribution similarity of the defect distribution of the plurality of detection images is calculated to obtain a second quality score of the plurality of detection images; The quality score of the plurality of detection images is calculated according to the first quality score and the second quality score of the plurality of detection images. 8.A bridge detection system based on a vehicle-mounted UAV cluster cooperative operation, characterized in that, The system is a vehicle-mounted control system, and the vehicle-mounted control system comprises an acquisition module (1), a processing module (2), and an output module (3), wherein: The acquisition module (1) is configured to acquire vibration data of a target sling on a suspension bridge. The processing module (2) is configured to determine the number of unmanned aerial vehicles for detecting the target sling and a detection strategy of a plurality of unmanned aerial vehicles according to the vibration data. The acquisition module (1) is further configured to acquire detection images of the plurality of unmanned aerial vehicles after the plurality of unmanned aerial vehicles complete detection according to the respective detection strategies. The output module (3) is configured to analyze defects in the plurality of detection images to obtain a defect result of the target sling on the suspension bridge.

9. An electronic device, comprising: The electronic device (300) comprises a processor (301), a memory (305), a user interface (303), and a network interface (304). The memory (305) is configured to store instructions. The user interface (303) and the network interface (304) are configured to communicate with other devices. The processor (301) is configured to execute the instructions stored in the memory (305) to enable the electronic device (300) to perform the bridge detection method of the vehicle-mounted unmanned aerial vehicle cluster cooperative operation according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions that, when executed, perform the bridge detection method of the vehicle-mounted unmanned aerial vehicle cluster cooperative operation according to any one of claims 1 to 7.

Images