Bridge disease detection method, device and equipment, storage medium and program product

Abstract

The invention relates to a bridge disease detection method and device, equipment, a storage medium and a program product. The method comprises the following steps: controlling first detection equipment to carry out disease detection on the whole area of a target bridge according to a planned first detection path to obtain a first disease detection result; determining at least one to-be-detected disease area of the target bridge according to the first disease detection result; according to the corresponding relation between each to-be-detected disease area and the second detection equipment, the second detection equipment is controlled to carry out disease detection on each to-be-detected disease area according to a planned second detection path, at least one second disease detection result is obtained, and the first detection equipment and the second detection equipment are heterogeneous detection equipment; the detection precision of the first detection equipment is smaller than that of the second detection equipment; and generating a total disease detection result of the target bridge according to each second disease detection result. By adopting the method, both the detection efficiency and the detection accuracy during the disease detection of the bridge are considered.

Description

Technical Field

[0001] The present application relates to the technical field of bridge detection, and in particular to a bridge defect detection method, apparatus, computer equipment, computer-readable storage medium, and computer program product. Background Art

[0002] As key nodes and three-dimensional spatial carriers of transportation infrastructure, bridges play an important role in regional economic linkage, urban space expansion, and people's livelihood travel security. However, as the service life of bridges increases, under the influence of the environment and loads, bridge projects are inevitably prone to defects such as steel bar corrosion, expansion joint damage, and excessively wide bridge cracks. Therefore, it is very necessary to conduct bridge defect detection.

[0003] At present, bridge defect detection usually relies on manual visual inspection and large-scale bridge inspection equipment. However, manual visual inspection takes a lot of time and is limited by the scope of operation, making it impossible to comprehensively inspect every part of the bridge. Although large-scale bridge inspection equipment can fully cover the entire area of ​​the bridge, it has shortcomings in the degree of detection precision due to factors such as operating distance and equipment size. Therefore, it is currently impossible to take into account both detection efficiency and detection accuracy when conducting bridge defect detection. Summary of the Invention

[0004] Based on this, it is necessary to provide a bridge defect detection method, device, computer equipment, computer-readable storage medium and computer program product that take into account both detection efficiency and detection accuracy when performing bridge defect detection to address the above technical problems.

[0005] In a first aspect, the present application provides a bridge disease detection method, comprising:

[0006] Controlling the first detection device to perform a defect detection on the entire area of ​​the target bridge according to the planned first detection path to obtain a first defect detection result;

[0007] determining at least one defect area to be detected on the target bridge according to the first defect detection result;

[0008] Controlling the second detection device to perform disease detection on each of the disease areas to be detected according to a planned second detection path based on a correspondence between each of the disease areas to be detected and the second detection device, thereby obtaining at least one second disease detection result, wherein the first detection device and the second detection device are heterogeneous detection devices, and a detection accuracy of the first detection device is lower than a detection accuracy of the second detection device;

[0009] According to each of the second defect detection results, a total defect detection result of the target bridge is generated.

[0010] In one embodiment, controlling the first detection device to perform defect detection on the entire area of ​​the target bridge according to the planned first detection path to obtain a first defect detection result includes:

[0011] Obtaining an adapted shooting distance for the first detection device to shoot the entire area;

[0012] determining a plurality of first shooting position coordinates of the first detection device according to the adapted shooting distance;

[0013] Planning the first detection path for the first detection device according to the multiple first shooting position coordinates;

[0014] The first detection device is controlled to perform defect detection on the entire area of ​​the target bridge according to the first detection path to obtain the first defect detection result.

[0015] In one embodiment, obtaining an adapted shooting distance for shooting the entire area by the first detection device includes:

[0016] constructing a first objective function based on a correspondence between a detection capability parameter of the first detection device and a structural characteristic parameter of the target bridge;

[0017] An adapted shooting distance for shooting the entire area by the first detection device is detected according to the first objective function.

[0018] In one embodiment, determining at least one defect area to be detected of the target bridge based on the first defect detection result includes:

[0019] Obtaining the real-time position coordinates of the first detection device and constructing a camera posture rotation matrix corresponding to the first detection device;

[0020] Constructing a preset disease area according to the first disease detection result, and collecting first position coordinates of a plurality of regional feature points of the preset disease area;

[0021] Normalizing the plurality of first position coordinates respectively to obtain a plurality of normalized position coordinates, and converting the plurality of normalized position coordinates into second position coordinates of the plurality of regional feature points in a camera coordinate system;

[0022] Obtaining actual position coordinates corresponding to each of the plurality of regional feature points according to the camera posture rotation matrix and the plurality of second position coordinates;

[0023] Fitting is performed on a plurality of actual position coordinates to obtain at least one defect area to be detected of the target bridge.

[0024] In one embodiment, before controlling the second detection device to perform disease detection on each of the disease areas to be detected according to the correspondence between each of the disease areas to be detected and the second detection device along the planned second detection path, the method further includes:

[0025] Adjusting the multiple actual position coordinates according to a shooting safety distance of the second detection device for shooting each of the diseased areas to be detected, to obtain multiple second shooting position coordinates of the second detection device;

[0026] Determining the center coordinates of each of the diseased areas to be detected based on the multiple second shooting position coordinates;

[0027] Constructing a group of diseased areas to be detected corresponding to each of the diseased areas to be detected according to the multiple center position coordinates;

[0028] Obtaining an adapted shooting time of the second detection device for the group of diseased areas to be detected;

[0029] A corresponding relationship between each of the diseased areas to be detected and the second detection device is established according to the adapted shooting time.

[0030] In one embodiment, obtaining the adapted shooting time of the second detection device for the group of diseased areas to be detected includes:

[0031] constructing a second objective function based on the correspondence between the operating performance parameters of the second detection equipment and the spatial distribution characteristics of the detected disease area group;

[0032] According to the second objective function, the adaptive shooting time of the first detection device for the group of diseased areas to be detected is detected.

[0033] In a second aspect, the present application further provides a bridge defect detection device, comprising:

[0034] A first detection module is used to control a first detection device to perform a defect detection on the entire area of ​​the target bridge according to a planned first detection path to obtain a first defect detection result;

[0035] a determination module, configured to determine at least one defect area to be detected of the target bridge according to the first defect detection result;

[0036] The second detection module is configured to control the second detection device to detect diseases of each of the to-be-detected disease areas according to the planned second detection path, to obtain at least one second disease detection result, wherein the first detection device and the second detection device are heterogeneous detection devices, and the detection accuracy of the first detection device is less than that of the second detection device.

[0037] The generation module is configured to generate a total disease detection result of the target bridge according to the second disease detection results.

[0038] In a third aspect, the present application further provides a computer device, comprising a memory and a processor, the memory stores a computer program, and the processor realizes the following steps when executing the computer program:

[0039] controlling a first detection device to detect diseases of an overall area of a target bridge according to a planned first detection path, to obtain a first disease detection result; determining at least one to-be-detected disease area of the target bridge according to the first disease detection result; controlling a second detection device to detect diseases of each of the to-be-detected disease areas according to a planned second detection path, to obtain at least one second disease detection result, wherein the first detection device and the second detection device are heterogeneous detection devices, and the detection accuracy of the first detection device is less than that of the second detection device; and generating a total disease detection result of the target bridge according to the second disease detection results.

[0040] In a fourth aspect, the present application further provides a computer readable storage medium, which stores a computer program, and the computer program realizes the following steps when executed by a processor:

[0041] controlling a first detection device to detect diseases of an overall area of a target bridge according to a planned first detection path, to obtain a first disease detection result; determining at least one to-be-detected disease area of the target bridge according to the first disease detection result; controlling a second detection device to detect diseases of each of the to-be-detected disease areas according to a planned second detection path, to obtain at least one second disease detection result, wherein the first detection device and the second detection device are heterogeneous detection devices, and the detection accuracy of the first detection device is less than that of the second detection device; and generating a total disease detection result of the target bridge according to the second disease detection results.

[0042] In a fifth aspect, the present application further provides a computer program product, comprising a computer program, which, when executed by a processor, implements the following steps:

[0043] Control the first detection device to perform defect detection on the entire area of ​​the target bridge according to the planned first detection path to obtain a first defect detection result; determine at least one defect area to be detected of the target bridge based on the first defect detection result; control the second detection device to perform defect detection on each defect area to be detected according to the correspondence between each defect area to be detected and the second detection device according to the planned second detection path to obtain at least one second defect detection result, wherein the first detection device and the second detection device are heterogeneous detection devices, and the detection accuracy of the first detection device is less than the detection accuracy of the second detection device; generate a total defect detection result of the target bridge based on each second defect detection result.

[0044] The above-mentioned bridge defect detection method, apparatus, computer equipment, computer-readable storage medium and computer program product first control the first detection device to perform defect detection on the entire area of ​​the target bridge according to the planned first detection path to obtain a first defect detection result, and then determine at least one defect area to be detected of the target bridge through the first defect detection result, and then control the second detection device to perform defect detection on each defect area to be detected according to the planned second detection path according to the correspondence between each defect area to be detected and the second detection device to obtain at least one second defect detection result, wherein the first detection device and the second detection device are heterogeneous detection devices, and the detection accuracy of the first detection device is less than the detection accuracy of the second detection device, and finally generate the total defect detection result of the target bridge according to each second defect detection result; since the first detection device and the second detection device are heterogeneous detection devices, and the detection accuracy of the first detection device is less than the detection accuracy of the second detection device, firstly The first detection device performs defect detection on the target bridge as a whole based on the first detection path to determine at least one defect area to be detected on the target bridge, and then the second detection device performs targeted defect detection on each defect area to be detected based on the second detection path, so as to achieve the purpose of completing the defect detection of the target bridge through the collaboration of heterogeneous detection devices. At the same time, since the heterogeneous detection devices all independently complete the defect detection under the corresponding detection path, and perform overall and local defect detection on the target bridge, it is possible to effectively control the defect detection time and ensure the degree of refinement of the defect detection, overcoming the manual visual inspection method that takes a lot of time and is limited by the operating range and cannot fully inspect every part of the bridge. Although large-scale bridge inspection equipment can fully cover the entire area of ​​the bridge, it has technical defects due to factors such as operating distance and equipment volume. Therefore, it can take into account both detection efficiency and detection accuracy when performing bridge defect detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0046] Figure 1 Schematic diagram of a flow chart of a bridge disease detection method in one embodiment;

[0047] Figure 2 A schematic diagram of a bridge defect detection method in one embodiment in which a large drone performs defect detection on the entire area of ​​a target bridge;

[0048] Figure 3 A schematic diagram of a bridge defect detection method in accordance with an embodiment of the present invention in which a small drone performs defect detection on the entire area of ​​a target bridge;

[0049] Figure 4 A schematic flow chart of a bridge defect detection method in another embodiment;

[0050] Figure 5 is a structural block diagram of a bridge defect detection device in one embodiment;

[0051] Figure 6 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0053] First of all, it should be understood that bridges are very important for infrastructure construction, which brings challenges to the maintenance and management of operating bridges. As the service life of bridges increases, under the dual influence of the environment and load, related defects such as steel corrosion, expansion joint damage and excessive cracks in bridges often occur. If the defects can be discovered in time during the bridge inspection process and perfect measures can be taken, the health and safety of the bridge will be greatly improved. However, due to the untimely and non-standard inspection of target bridges and inaccurate inspection data, the health problems of bridges cannot be discovered in time. At present, the inspection work for bridges is mainly carried out manually in combination with bridge inspection equipment. Specifically, the manual inspection method is that the staff goes deep into the bottom of the bridge and uses tools such as the naked eye, steel rulers, crack measuring instruments and cameras to obtain real-time status information of the bottom of the bridge. There is no doubt that The problem is that this method requires a lot of manpower and time to complete the inspection work, which is inefficient. Moreover, due to the limited working space, this bridge inspection method requires a lot of manpower and time to complete the inspection work, which is inefficient. Moreover, due to the limited working space, inspection vehicles are often unable to reach high towers and high piers and other structural parts with large longitudinal extensions, resulting in a limited working range and an inability to fully inspect every part of the bridge. At the same time, due to the need to work at heights, there are huge safety hazards for inspectors. Although the method of using bridge inspection equipment for inspection is suitable for long-distance and high-efficiency inspection tasks, it is limited by factors such as equipment size and operating distance, and cannot ensure the degree of refinement of bridge inspection. Therefore, there is an urgent need for a bridge disease detection method that can take into account both detection efficiency and detection accuracy when inspecting bridges.

[0054] In one embodiment, Figure 1As shown, a bridge defect detection method is provided. This embodiment takes the application of this method to a terminal as an example. The terminal includes but is not limited to a personal computer, a laptop computer, a smart phone, and a tablet computer. The terminal is deployed with a control system. The control system serves as a control center for heterogeneous collaboration. Specifically, it can issue detection instructions and detection parameters to the first detection device and the second detection device, receive detection data sent back by the first detection device and the second detection device, and dynamically regulate the entire heterogeneous collaborative bridge defect detection process. The control system includes a first detection module, a determination module, a second detection module and a generation module. The first detection module is used to control the first detection device to perform defect detection on the entire area of ​​the target bridge according to the planned first detection path to obtain a first disease detection result. The determination module is used to determine at least one disease area to be detected of the target bridge based on the first disease detection result. The second detection module is used to determine the disease area to be detected based on the relationship between each disease area to be detected and the second detection device. The first detection device and the second detection device are controlled to perform disease detection on each defect area to be detected according to the planned second detection path, and obtain at least one second disease detection result. The first detection device and the second detection device are heterogeneous detection devices, and the detection accuracy of the first detection device is lower than that of the second detection device. The generation module is used to generate an overall disease detection result of the target bridge based on each second disease detection result. Through the information interaction between the first detection module, the determination module, the second detection module and the generation module, the purpose of completing the disease detection of the target bridge by coordinating the heterogeneous detection devices can be achieved. At the same time, because the heterogeneous detection devices all independently complete the disease detection under the corresponding detection path and perform overall and local disease detection on the target bridge, it is possible to effectively control the disease detection time and ensure the degree of refinement of the disease detection. Therefore, it is possible to take into account both detection efficiency and detection accuracy when performing disease detection on the bridge. It is understandable that this method can also be applied to a server, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0055] Step 202: Control the first detection device to perform a defect detection on the entire area of ​​the target bridge according to the planned first detection path to obtain a first defect detection result.

[0056] It should be noted that the first detection equipment refers to equipment that performs defect detection on the entire area of ​​the target bridge, and can specifically be a large unmanned aerial vehicle with a long flight time and large load capacity. For example, in one feasible method, the large unmanned aerial vehicle is equipped with an ultra-high-definition depth camera of an inertial navigation system IMU, a high-precision GPS positioning system, and an embedded system; the first detection path is represented by the flight trajectory planned by the first detection equipment, wherein the first detection path can be obtained by autonomous planning by the first detection equipment, and can also be planned for the first detection equipment by the control system; the target bridge represents a bridge that needs to be detected for defects, and the entire area of ​​the target bridge may include main beams, piers, cables, etc., which is not specifically limited in this embodiment; the first defect detection result is the defect condition of the entire area of ​​the target bridge detected by the first detection equipment, which can specifically be the defect area, defect type, and defect degree, etc.

[0057] It should be noted that the first detection device is mainly used to quickly perform high-altitude rapid inspections of the entire area of ​​the target bridge. It performs inspections according to the planned first detection path to gradually cover the entire bridge structure from a long distance. The process of the first detection device performing disease detection on the entire area of ​​the target bridge can be specifically implemented through deep learning algorithms, such as Faster R-CNN or UNet, and the detection models used include but are not limited to YOLOv5 network models and ResNet network models.

[0058] As an example, step 202 includes: generating a first detection path and a first control instruction corresponding to the first detection device, and based on the first control instruction, controlling the first detection device to perform defect detection on the entire area of ​​the target bridge according to the first detection path to obtain a first defect detection result.

[0059] Step 204: Determine at least one defect area to be detected on the target bridge based on the first defect detection result.

[0060] It should be noted that the defect area to be detected represents the local area on the target bridge that needs to be inspected for defects. Specifically, the defect area to be detected can be the local area that needs to be re-inspected that is screened out from the first defect detection result, wherein the defect area to be detected can be represented by a rectangle, a polygon or a three-dimensional block; it can be understood that the first detection device can adopt a fixed-point shooting method during the inspection of the target bridge. For example, assuming that the first detection device is a large drone, the ultra-high-definition depth camera carried by the large drone can capture the regional image of the entire area of ​​the target bridge, and transmit the regional image to the embedded system in real time. The embedded system can detect the entire area of ​​the target bridge by carrying a trained deep learning YOLOv5 model. Specifically, referring to Figure 2 , Figure 2This is a schematic diagram showing a large drone performing defect detection on the entire area of ​​a target bridge. The large drone first transmits the captured area image to an embedded system via a wired connection, and uses an interpolation method to resize the area image to the size required by the YOLOv5 model. It then linearly scales each pixel value of the image to map it to a specified range. After that, the processed image data is input one by one into the YOLOv5 model to complete the bridge defect detection task. Finally, the first defect detection result is returned to the control system, which can specifically be a ground station or a cloud.

[0061] As an example, step 204 includes: screening at least one defect area to be detected of the target bridge in the first defect detection result.

[0062] Step 206: Based on the correspondence between each disease area to be detected and the second detection device, control the second detection device to perform disease detection on each disease area to be detected according to the planned second detection path, and obtain at least one second disease detection result, wherein the first detection device and the second detection device are heterogeneous detection devices, and the detection accuracy of the first detection device is lower than the detection accuracy of the second detection device.

[0063] It should be noted that the second detection device refers to a device that performs disease detection on the diseased area to be detected, and can specifically be a small drone with a long flight time and a large load capacity. For example, in one feasible method, the small drone is equipped with a high-definition camera or a dedicated sensor; the second detection path is represented by the flight trajectory planned by the second detection device, wherein the second detection path can be obtained by the second detection device independently planned, and can also be planned for the second detection device by the control system; the correspondence between each diseased area to be detected and the second detection device is used to represent the task allocation logic between each diseased area to be detected and the second detection device. Since the second detection device can be one or more In the case where there is only one second detection device, the corresponding relationship may refer to the detection order of each disease area to be detected by the second detection device; in the case where there are multiple second detection devices, the corresponding relationship may refer to the one-to-one matching relationship between the multiple second detection devices and the multiple disease areas to be detected; it can be understood that the first detection device and the second detection device are heterogeneous detection devices, and the heterogeneity of the detection devices can be reflected in the performance such as load capacity, detection accuracy and coverage range. Specifically, the detection accuracy of the first detection device is less than the detection accuracy of the second detection device. The detection accuracy of different detection devices can be represented by indicators such as spatial resolution and positioning magnitude; refer to Figure 3 , Figure 3 A schematic diagram showing a small drone performing disease detection on the entire area of ​​a target bridge.

[0064] As an example, step 206 includes: generating a second detection path and a second control instruction corresponding to the second detection device, and based on the correspondence between each disease area to be detected and the second detection device and the second control instruction, controlling the second detection device to perform disease detection on each disease area to be detected according to the second detection path to obtain a second disease detection result.

[0065] Step 208: Generate a total defect detection result of the target bridge based on each second defect detection result.

[0066] It should be noted that the second defect detection result refers to the set of defect data output by the second detection device after fine-grained detection of the defect area to be detected, which may specifically include the defect type, size, location coordinates and image, etc.; it can be understood that the process of the second detection device performing defect detection on each defect area to be detected can also be specifically implemented through a deep learning algorithm, such as Faster R-CNN or UNet, and the detection models used include but are not limited to the YOLOv5 network model and the ResNet network model, etc.; the total defect detection result represents the comprehensive defect situation of the entire target bridge area after integrating all the second defect detection results and combining them with the macro detection information of the first detection device.

[0067] As an example, step 208 includes: integrating the second defect detection results into a total defect detection result of the target bridge.

[0068] The above-mentioned bridge defect detection method first controls the first detection device to perform defect detection on the entire area of ​​the target bridge according to the planned first detection path to obtain a first defect detection result, and then determines at least one defect area to be detected of the target bridge through the first defect detection result, and then controls the second detection device to perform defect detection on each defect area to be detected according to the planned second detection path according to the correspondence between each defect area to be detected and the second detection device, to obtain at least one second defect detection result, wherein the first detection device and the second detection device are heterogeneous detection devices, and the detection accuracy of the first detection device is less than the detection accuracy of the second detection device, and finally generates the total defect detection result of the target bridge according to each second defect detection result; since the first detection device and the second detection device are heterogeneous detection devices, and the detection accuracy of the first detection device is less than the detection accuracy of the second detection device, the first detection device first detects the defect based on the first detection path. The target bridge is inspected for defects as a whole by using a single detection path to determine at least one defective area to be inspected of the target bridge, and then the second detection device performs targeted defect detection on each defective area to be inspected based on the second detection path, thereby achieving the purpose of completing defect detection on the target bridge through collaborative heterogeneous detection equipment. At the same time, since the heterogeneous detection equipment all independently completes defect detection under the corresponding detection path and performs overall and local defect detection on the target bridge, it can effectively control the defect detection time and ensure the degree of refinement of the defect detection, overcoming the manual visual inspection method that takes a lot of time and is limited by the operating range and cannot fully inspect every part of the bridge. Although large-scale bridge inspection equipment can fully cover the entire area of ​​the bridge, it has technical defects due to factors such as operating distance and equipment volume. Therefore, it can take into account both detection efficiency and detection accuracy when conducting bridge defect detection.

[0069] In one embodiment, Figure 4 As shown, controlling the first detection device to perform a defect detection on the entire area of ​​the target bridge according to the planned first detection path to obtain a first defect detection result includes:

[0070] Step 302: Obtain an adaptive shooting distance for the first detection device to shoot the entire area.

[0071] It should be noted that the adaptive shooting distance represents the distance at which the first detection device can capture the entire area so that the captured image covers the target range and the image quality meets the requirements of macroscopic detection. Specifically, the preset shooting distance for capturing the target bridge can be determined based on the performance of the camera carried by the first detection device. The preset shooting distance is then adjusted using a set empirical value to obtain the adaptive shooting distance. The expression for determining the preset shooting distance can be as follows:

[0072]

[0073] in, To preset the shooting distance, is the width of the photosensitive element of the camera sensor carried by the first detection device, is the focal length, is the desired resolution, which can be expressed in pixels per meter.

[0074] As an example, step 302 includes: determining a preset shooting distance for the first detection device to shoot the entire area, and adjusting the preset shooting distance based on a set distance value to obtain an adapted shooting distance.

[0075] Step 304: Determine a plurality of first shooting position coordinates of the first detection device according to the adapted shooting distance.

[0076] It should be noted that after determining the adaptive shooting distance, multiple shooting position points and first shooting position coordinates of multiple shooting position points can be formulated according to the shooting field of view of the first detection device, so as to facilitate subsequent planning of the first detection path based on multiple first shooting position coordinates.

[0077] As an example, a plurality of first shooting position coordinates of the first detection device are located and obtained according to the adapted shooting distance.

[0078] Step 306 : Planning a first detection path for the first detection device according to the plurality of first shooting position coordinates.

[0079] As an example, a preset path planning algorithm is used to plan a first detection path of the first detection device based on a plurality of first shooting position coordinates.

[0080] Step 308: Control the first detection device to perform a defect detection on the entire area of ​​the target bridge according to the first detection path to obtain a first defect detection result.

[0081] As an example, step 308 includes: controlling the first detection device to perform a defect detection on the entire area of ​​the target bridge according to the first detection path to obtain a first defect detection result.

[0082] In the above-mentioned method of controlling the first detection device to perform defect detection on the entire area of ​​the target bridge, the optimal shooting distance for the first detection device to perform defect detection on the entire area of ​​the target bridge is first determined, and then the coordinates of multiple first shooting positions for the first detection device to shoot the entire area are obtained through the optimal shooting distance positioning, and then the first detection path is planned, and finally the defect detection of the entire area is completed relying on the first detection path. The spatial coverage model can be constructed through the optimal shooting distance to ensure that the field of view of the equipment at each shooting position can completely cover the bridge structure (such as beams, piers and supports, etc.), avoiding local overexposure due to too close distance or loss of details due to too far distance. Therefore, it lays the foundation for further improving the detection accuracy of bridge defect detection.

[0083] In one embodiment, obtaining an adapted shooting distance for shooting the entire area by the first detection device includes:

[0084] A first objective function is constructed based on the correspondence between the detection capability parameters of the first detection device and the structural characteristic parameters of the target bridge; and based on the first objective function, an adaptive shooting distance for the first detection device to shoot the entire area is detected.

[0085] It should be noted that in order to adapt to the different requirements of adaptive shooting distances in different disease detection scenarios, real-time detection of adaptive shooting distance can be performed based on the first objective function constructed based on the detection capability parameters of the first detection equipment and the structural characteristic parameters of the target bridge; the detection capability parameters represent the key indicators of the performance of the detection equipment, which are used to measure the ability of the first detection equipment to obtain the disease information of the target bridge, and may specifically include resolution, detection range and positioning accuracy, etc.; the structural characteristic parameters represent the geometric shape, structural details and disease-sensitive parts of the bridge; the first objective function is a mathematical model obtained by mapping the mapping relationship between the detection capability parameters and the structural characteristic parameters, which is used to determine the adaptive shooting distance of the first detection equipment.

[0086] As an example, a preset shooting distance of the first detection device is obtained, and the physical distance range of the film field of view at the preset shooting distance is calculated, where the physical distance range of the film field of view can be represented by DOV, and the calculation expression of the physical distance range of the film field of view can be as follows:

[0087]

[0088] in, is the first component of the physical distance range of the film field of view, is the second component of the physical distance range of the film field of view, is the width of the photosensitive element of the camera sensor carried by the first detection device, is the focal length, is the required resolution, in pixels / meter. To preset the shooting distance, the first objective function is constructed based on the correspondence between the physical distance range of the field of view of the image and the structural characteristic parameters of the target bridge. The first objective function can be expressed as , the expression of the first objective function can be shown as follows:

[0089]

[0090] in, Characterize the structural characteristic parameters of the target bridge, specifically the size of the bridge area to be detected, t is the unit time of the shooting field of view DOV, is the first weight, is the second weight, the first objective function The solution condition is Minimum positive number; according to the first objective function, detecting the adaptive shooting distance of the first detection device for shooting the entire area.

[0091] In this embodiment, the first objective function is constructed by capturing the mapping relationship between the detection capability parameters of the first detection device and the structural characteristic parameters of the target bridge. Finally, the first objective function is used to detect the adaptive shooting distance currently suitable for the first detection device to shoot the entire area, so that the unique or optimal distance solution can be obtained through mathematical optimization. Therefore, the foundation is laid for further improving the detection accuracy of bridge disease detection.

[0092] In one embodiment, determining at least one defect area to be detected on the target bridge based on the first defect detection result includes:

[0093] Acquire the real-time position coordinates of the first detection device and construct a camera attitude rotation matrix corresponding to the first detection device; construct a preset defect area based on the first defect detection result, and collect the first position coordinates of multiple regional feature points of the preset defect area; perform normalization on the multiple first position coordinates respectively to obtain multiple normalized position coordinates, and convert the multiple normalized position coordinates into second position coordinates of multiple regional feature points in the camera coordinate system; obtain the actual position coordinates corresponding to each of the multiple regional feature points based on the camera attitude rotation matrix and the multiple second position coordinates; fit the multiple actual position coordinates to obtain at least one defect area to be detected of the target bridge.

[0094] It should be noted that the real-time position coordinates refer to the real-time three-dimensional coordinates of the first detection device in space, which can be specifically expressed as ; Regional feature points are points with significant geometric features in the preset defect area (such as crack endpoints and corners), which are used for spatial coordinate fitting. Specifically, they can be regional vertices of the preset defect area; normalized coordinates refer to the conversion of image pixel coordinates into dimensionless standardized coordinates; the camera coordinate system represents a three-dimensional coordinate system with the camera optical center as the origin and the optical axis as the Z axis, which is used to describe the spatial position of the object from the camera's perspective; the actual position coordinates represent the real three-dimensional coordinates of the regional feature points in the world coordinate system, reflecting their actual position in the bridge structure.

[0095] As an example, the real-time position coordinates of the first detection device are obtained, and the camera posture rotation matrix corresponding to the first detection device is constructed; based on the first defect detection result, a preset defect area is drawn, and the first position coordinates of the four area vertices of the preset defect area are collected; the multiple first position coordinates are normalized respectively to obtain multiple normalized position coordinates, and the multiple normalized position coordinates are converted into the second position coordinates of multiple area feature points in the camera coordinate system; based on the camera posture rotation matrix and the multiple second position coordinates, the actual position coordinates corresponding to the multiple area feature points are obtained; the multiple actual position coordinates are fitted to obtain at least one defect area to be detected of the target bridge.

[0096] In one practicable manner, assuming that the first detection device is a large drone, the GPS position coordinates of the first detection device are first obtained through the positioning system of the large drone. , and the camera posture information is obtained through IMU to form a rotation matrix R; then after drawing the preset disease area based on the first disease detection result, the pixel coordinates of the four vertices of the preset disease area are extracted , that is, extract the first position coordinates; then use the following formula to normalize the extracted first position coordinates to obtain multiple normalized coordinates , where the normalization formula is as follows:

[0097]

[0098] in, is the abscissa of the principal point, is the vertical coordinate of the main point, is the first focal length, is the second focal length, which can be obtained by camera calibration; and then, according to the depth information H recorded by the depth camera and multiple normalized coordinates, the second position coordinates of different rectangular vertices in the camera coordinate system are converted. The conversion formula for obtaining the second position coordinates can be shown as follows:

[0099]

[0100] ; Then the camera posture rotation matrix R and multiple second position coordinates Input into the preset calculation formula to calculate the coordinates of different rectangle vertices in the camera coordinate system , where the preset calculation formula can be as follows:

[0101]

[0102] ; Finally, add the coordinates of the different rectangle vertices in the camera coordinate system to the world coordinates 、 and , and obtain the actual position coordinates corresponding to multiple regional feature points. The specific expression can be shown as follows:

[0103] [ x i w , y i w , z i w ] = [ x uav , y uav , z uav ] + [ x i co , y i co , z i co ] .

[0104] In this way, the defect positioning error can be improved from the pixel level to the centimeter level through coordinate system conversion and posture matrix calculation, thus laying the foundation for further improving the detection accuracy of bridge defect detection.

[0105] In one embodiment, before controlling the second detection device to perform disease detection on each disease area to be detected according to the correspondence between each disease area to be detected and the second detection device according to the planned second detection path, the method further includes:

[0106] According to the shooting safety distance of each diseased area to be detected by the second detection device, the multiple actual position coordinates are adjusted to obtain multiple second shooting position coordinates of the second detection device; based on the multiple second shooting position coordinates, the center position coordinates of each diseased area to be detected are determined; based on the multiple center position coordinates, a group of diseased areas to be detected that corresponds to each diseased area to be detected is constructed; the adaptive shooting time of the second detection device for the group of diseased areas to be detected is obtained; and based on the adaptive shooting time, a corresponding relationship between each diseased area to be detected and the second detection device is constructed.

[0107] It should be noted that the shooting safety distance represents the minimum distance threshold set by the second detection device to ensure the safety of the device (such as avoiding collision with the bridge structure) and image quality (such as avoiding distortion caused by being too close) when shooting. For example, in one feasible method, the second detection device is equipped with an ultra-high-definition camera, a high-precision GPS positioning system, and a small drone with an embedded system to accurately identify bridge defects. As a waypoint for a small drone, the waypoint rectangle vertex does not take into account the distance between the drone and the bridge pier or beam. In order to ensure the clarity and resolution of the photos taken, the shooting safety distance between the small drone and the bridge pier surface is set to ,in, Specifically, it can be 0.5m~2m. The coordinates of the expanded rectangle vertices can be obtained by increasing or decreasing the fixed value of the area vertices of the four preset diseased areas, that is, multiple second shooting position coordinates of the second device to be detected are obtained; the adapted shooting time is the optimal time window for the second detection device to shoot the diseased area group; the center position coordinates represent the geometric center coordinates of each diseased area to be detected; the diseased area group to be detected refers to a collection of multiple diseased areas to be detected.

[0108] As an example, based on the shooting safety distance of each diseased area to be detected by the second detection device, multiple actual position coordinates are added to obtain multiple second shooting position coordinates of the second detection device; the center position coordinates of each diseased area to be detected are determined based on the multiple second shooting position coordinates; and the diseased areas to be detected are sorted according to the multiple center position coordinates to form a group of diseased areas to be detected. For example, assuming that there are M diseased areas to be detected, all diseased areas to be detected are sorted according to the center position coordinates of each diseased area to be detected to obtain a group of diseased areas to be detected U, where the expression of the group of diseased areas to be detected U is as follows: U ∈ [ ( x 1 cc , y 1 cc ) , ( x 2 cc , y 2 cc ) , ( x 3 cc , y 3 cc ) , ⋯⋯ ( x M cc , y M cc ) ] ; Obtain the adaptive shooting time of the second detection device for the group of diseased areas to be detected; Based on the adaptive shooting time, construct a corresponding relationship between each diseased area to be detected and the second detection device.

[0109] In one practicable manner, it is assumed that the second detection device is a plurality of small drones, which are represented as , the M disease areas to be detected are represented as , then the corresponding relationship between each disease area to be detected and the second detection equipment can be Corresponding to , Corresponding to , Corresponding to .

[0110] In this way, by adjusting the safety distance and optimizing the time window, equipment failure and data distortion can be avoided, and the stability of the detection process can be guaranteed. At the same time, based on coordinate calibration and cluster processing, the accurate positioning of the disease characteristics and the clear collection of images can be guaranteed. On the other hand, by planning the second detection path and scheduling resources, the idle time and energy consumption of the second detection equipment can be reduced. Therefore, the foundation is laid for further taking into account the detection efficiency and detection accuracy of the bridge.

[0111] In one embodiment, obtaining the adapted shooting time of the second detection device for the diseased area group to be detected includes:

[0112] A second objective function is constructed based on the correspondence between the operating performance parameters of the second detection device and the spatial distribution characteristics of the detected diseased area group; and based on the second objective function, the adaptive shooting time of the first detection device for the diseased area group to be detected is detected.

[0113] It should be noted that in order to adapt to the different requirements of adaptive shooting time in different disease detection scenarios, real-time detection of adaptive shooting time can be performed based on the second objective function constructed based on the operating performance parameters of the second detection equipment and the spatial distribution characteristics of the detected disease area group; the operating performance parameters characterize the working ability of the second detection equipment, which can be specifically motion parameters, endurance parameters and detection parameters, etc.; the spatial distribution characteristics are used to characterize the distribution of all disease areas to be detected in space.

[0114] As an example, the operating performance parameters of the second detection device and the spatial distribution characteristics of the detected disease area group are obtained, and the second objective function is further constructed based on the corresponding relationship between the operating performance parameters of the second detection device and the spatial distribution characteristics of the detected disease area group. The second objective function can be expressed as , the expression of the first objective function can be shown as follows:

[0115]

[0116] in, Characterizes the distance from the second detection device i to the disease area j to be detected, which can be specifically determined based on the regional location coordinates and And the calculation of the drone's position coordinates, Characterizes the time required for the second detection device i to perform disease detection task j, is the variance of the completion time of bridge disease detection, which is used to measure the balance of task allocation. For the minimum flight speed of the second detection device, it can be understood that According to the first objective function, the adaptive shooting distance of the first detection device for shooting the entire area is a weight parameter for adjusting the task completion time, reasonable resource utilization and task allocation balance; the objective function The solution condition is is the minimum positive number; according to the second objective function, the adaptive shooting time of the first detection device for the diseased area group to be detected is detected.

[0117] In this way, by capturing the mapping relationship between the operating performance parameters of the second detection equipment and the spatial distribution characteristics of the group of defective areas to be detected, the second objective function is constructed. Finally, the second objective function is used to detect the adaptive shooting time that is currently suitable for the second detection equipment to shoot the group of defective areas to be detected. The purpose of obtaining a unique or optimal distance solution can be achieved through mathematical optimization. Therefore, the foundation is laid for further improving the detection accuracy of bridge defect detection.

[0118] In one feasible method, this embodiment first uses a large drone to quickly detect the bridge defect area, then calculates the area location, selects waypoints to connect into a route, and detects the entire area of ​​the target bridge according to the route to obtain a first defect detection result; then, based on the first defect detection result, at least one defect area to be detected of the target bridge is determined; then, a small drone is used to accurately identify bridge defects at close range according to the route, calculates the area location, selects waypoints to connect into a route, and detects all defect areas to be detected according to the route to obtain a second defect detection result; finally, all second defect detection results are integrated to obtain the total defect detection result of the target bridge.

[0119] This provides an efficient, high-precision, and comprehensive intelligent bridge heterogeneous drone inspection method, effectively broadening the perspective of bridge inspection. Compared with the previous bridge inspection method using manual or large-scale inspection equipment, this embodiment can greatly improve the time cost of bridge inspection, improve the efficiency of bridge inspection, and strongly support the safe operation and maintenance of bridges. At the same time, since the heterogeneous inspection equipment all independently completes the disease detection under the corresponding inspection path, and performs overall and local disease detection on the target bridge, it can effectively control the disease detection time and ensure the degree of refinement of disease detection, overcoming the manual visual inspection method that takes a lot of time and is limited by the operating range and cannot fully inspect every part of the bridge. Although large-scale bridge inspection equipment can fully cover the entire area of ​​the bridge, it has technical defects affected by factors such as operating distance and equipment volume. Therefore, it can take into account both detection efficiency and detection accuracy when performing bridge disease detection.

[0120] It should be understood that, although the steps in the flowcharts of the above embodiments are shown in sequence as indicated by the arrows, these steps are not necessarily performed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be performed in other orders. Moreover, at least a portion of the steps in the flowcharts of the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily performed at the same time, but can be performed at different times. The execution order of these steps or stages is not necessarily to be performed in sequence, but can be performed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0121] Based on the same inventive concept, embodiments of the present application also provide a bridge defect detection device for implementing the aforementioned bridge defect detection method. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations of one or more bridge defect detection device embodiments provided below can be found in the aforementioned limitations of the bridge defect detection method and will not be further elaborated here.

[0122] In an exemplary embodiment, Figure 5 As shown, a bridge defect detection device is provided, comprising: a first detection module 401, a determination module 402, a second detection module 403 and a generation module 404, wherein:

[0123] The first detection module 401 is used to control the first detection device to perform a defect detection on the entire area of ​​the target bridge according to the planned first detection path to obtain a first defect detection result;

[0124] A determination module 402 is configured to determine at least one defect area to be detected of the target bridge based on the first defect detection result;

[0125] The second detection module 403 controls the second detection device to perform disease detection on each disease area to be detected according to the planned second detection path based on the correspondence between each disease area to be detected and the second detection device, thereby obtaining at least one second disease detection result. The first detection device and the second detection device are heterogeneous detection devices, and the detection accuracy of the first detection device is lower than that of the second detection device.

[0126] The generation module 404 generates a total defect detection result of the target bridge according to each second defect detection result.

[0127] In one embodiment, the first detection module 401 is further configured to:

[0128] Obtain an adaptive shooting distance for the first detection device to shoot the entire area; determine multiple first shooting position coordinates of the first detection device based on the adaptive shooting distance; plan a first detection path for the first detection device based on the multiple first shooting position coordinates; control the first detection device to perform defect detection on the entire area of ​​the target bridge according to the first detection path, and obtain a first defect detection result.

[0129] In one embodiment, the first detection module 401 is further configured to:

[0130] A first objective function is constructed based on the correspondence between the detection capability parameters of the first detection device and the structural characteristic parameters of the target bridge; and based on the first objective function, an adaptive shooting distance for the first detection device to shoot the entire area is detected.

[0131] In one embodiment, the determining module 402 is further configured to:

[0132] Acquire the real-time position coordinates of the first detection device and construct a camera attitude rotation matrix corresponding to the first detection device; construct a preset defect area based on the first defect detection result, and collect the first position coordinates of multiple regional feature points of the preset defect area; perform normalization on the multiple first position coordinates respectively to obtain multiple normalized position coordinates, and convert the multiple normalized position coordinates into second position coordinates of multiple regional feature points in the camera coordinate system; obtain the actual position coordinates corresponding to each of the multiple regional feature points based on the camera attitude rotation matrix and the multiple second position coordinates; fit the multiple actual position coordinates to obtain at least one defect area to be detected of the target bridge.

[0133] In one embodiment, the bridge defect detection device is further used to:

[0134] According to the shooting safety distance of each diseased area to be detected by the second detection device, the multiple actual position coordinates are adjusted to obtain multiple second shooting position coordinates of the second detection device; based on the multiple second shooting position coordinates, the center position coordinates of each diseased area to be detected are determined; based on the multiple center position coordinates, a group of diseased areas to be detected that corresponds to each diseased area to be detected is constructed; the adaptive shooting time of the second detection device for the group of diseased areas to be detected is obtained; and based on the adaptive shooting time, a corresponding relationship between each diseased area to be detected and the second detection device is constructed.

[0135] In one embodiment, the bridge defect detection device is further used to:

[0136] A second objective function is constructed based on the correspondence between the operating performance parameters of the second detection device and the spatial distribution characteristics of the detected diseased area group; and based on the second objective function, the adaptive shooting time of the first detection device for the diseased area group to be detected is detected.

[0137] Each module in the bridge defect detection device described above can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in hardware form, or stored in a computer device memory in software form, allowing the processor to call and execute the corresponding operations of each module.

[0138] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 6 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface, the display unit and the input device are connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, it realizes a bridge disease detection method. Those skilled in the art can understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0139] In one embodiment, a computer device is further provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0140] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0141] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0142] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiments. In particular, any reference to memory, database, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processors involved in the various embodiments provided herein may be, but are not limited to, general-purpose processors, central processing units (CPUs), graphics processing units (GPUs), digital signal processors (DSPs), programmable logic devices (PLDs), data processing logic devices based on quantum computing, and the like.

[0143] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0144] The above embodiments merely illustrate several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art may make various modifications and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A bridge disease detection method, characterized in that: The method comprises: Controlling the first detection device to perform a defect detection on the entire area of ​​the target bridge according to the planned first detection path to obtain a first defect detection result; determining at least one defect area to be detected on the target bridge according to the first defect detection result; Controlling the second detection device to perform disease detection on each of the disease areas to be detected according to a planned second detection path based on a correspondence between each of the disease areas to be detected and the second detection device, thereby obtaining at least one second disease detection result, wherein the first detection device and the second detection device are heterogeneous detection devices, and a detection accuracy of the first detection device is lower than a detection accuracy of the second detection device; According to each of the second defect detection results, a total defect detection result of the target bridge is generated.

2. The method according to claim 1, characterized in that The controlling the first detection device to perform a defect detection on the entire area of ​​the target bridge according to the planned first detection path to obtain a first defect detection result includes: Obtaining an adapted shooting distance for the first detection device to shoot the entire area; determining a plurality of first shooting position coordinates of the first detection device according to the adapted shooting distance; Planning the first detection path for the first detection device according to the multiple first shooting position coordinates; The first detection device is controlled to perform a defect detection on the entire area of ​​the target bridge according to the first detection path to obtain the first defect detection result.

3. The method according to claim 2, characterized in that The obtaining of an adapted shooting distance for shooting the entire area by the first detection device includes: constructing a first objective function based on a correspondence between the detection capability parameters of the first detection equipment and the structural characteristic parameters of the target bridge; An adapted shooting distance for shooting the entire area by the first detection device is detected according to the first objective function.

4. The method according to claim 1, wherein The step of determining at least one defect area to be detected on the target bridge according to the first defect detection result includes: Obtaining the real-time position coordinates of the first detection device and constructing a camera posture rotation matrix corresponding to the first detection device; Constructing a preset disease area according to the first disease detection result, and collecting first position coordinates of a plurality of regional feature points of the preset disease area; Normalizing the plurality of first position coordinates respectively to obtain a plurality of normalized position coordinates, and converting the plurality of normalized position coordinates into second position coordinates of the plurality of regional feature points in a camera coordinate system; Obtaining actual position coordinates corresponding to each of the plurality of regional feature points according to the camera posture rotation matrix and the plurality of second position coordinates; Fitting is performed on a plurality of actual position coordinates to obtain at least one defect area to be detected of the target bridge.

5. The method according to claim 4, characterized in that Before controlling the second detection device to perform disease detection on each of the disease areas to be detected according to the planned second detection path based on the correspondence between each of the disease areas to be detected and the second detection device, the method further includes: Adjusting the multiple actual position coordinates according to a shooting safety distance of the second detection device for shooting each of the diseased areas to be detected, to obtain multiple second shooting position coordinates of the second detection device; Determining the center coordinates of each of the diseased areas to be detected based on the multiple second shooting position coordinates; Constructing a group of diseased areas to be detected corresponding to each of the diseased areas to be detected according to the multiple center position coordinates; Obtaining an adapted shooting time of the second detection device for the group of diseased areas to be detected; A corresponding relationship between each of the diseased areas to be detected and the second detection device is established according to the adapted shooting time.

6. The method according to claim 5, characterized in that The obtaining of the adaptive shooting time of the second detection device for the group of diseased areas to be detected includes: constructing a second objective function based on the correspondence between the operating performance parameters of the second detection equipment and the spatial distribution characteristics of the detected disease area group; According to the second objective function, the adaptive shooting time of the first detection device for the group of diseased areas to be detected is detected.

7. A bridge disease detection device, characterized in that: The device comprises: A first detection module is used to control a first detection device to perform a defect detection on the entire area of ​​the target bridge according to a planned first detection path to obtain a first defect detection result; a determination module, configured to determine at least one defect area to be detected of the target bridge according to the first defect detection result; a second detection module, configured to control the second detection device to perform disease detection on each of the disease areas to be detected according to a planned second detection path based on a correspondence between each of the disease areas to be detected and the second detection device, to obtain at least one second disease detection result, wherein the first detection device and the second detection device are heterogeneous detection devices, and a detection accuracy of the first detection device is lower than a detection accuracy of the second detection device; A generation module is used to generate an overall disease detection result of the target bridge according to each of the second disease detection results.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images