Road surface crack detection method and device based on grid model, medium and equipment

Abstract

The application provides a grid model-based road surface crack detection method, device, medium and equipment, and relates to the field of road surface crack detection.The method comprises the following steps: dividing the road surface in the intelligent road management range into equal-sized road surface grid units on a road surface intelligent monitoring map, calculating corresponding crack critical values according to the images of the road surface grid units, and presenting the crack critical values of the road surface grid units on the road surface intelligent monitoring map.Management personnel can intuitively and quickly obtain the crack conditions of all the road surfaces in the management range from the road surface intelligent monitoring map, and the first road surface grid unit with a high crack critical value is highlighted.Compared with direct image analysis and processing or manual identification, the processing efficiency of the road surface crack information can be improved, and the road surface maintenance efficiency is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of road crack detection, and in particular to a road crack detection method and device based on a grid model, a medium and equipment. BACKGROUND

[0002] With the large-scale coverage of the highway network, highway department managers need to monitor the physical state of the road in real time to ensure traffic safety and smoothness. Road conditions frequently change with increasing traffic flow and weather changes, and it is necessary to continuously check the road conditions to promptly discover and repair problems and avoid affecting traffic.

[0003] In related technologies, a UAV can periodically take pictures of the road surface, and after identifying cracks in the image, relevant personnel are notified to maintain the road surface.

[0004] However, as more and more roads are added to the scope of highway management, the road crack pictures received by highway department managers are too numerous to quickly determine which roads need priority maintenance. The low efficiency of processing road crack information can result in the road surface of some important channels not being maintained in a timely manner, or some severely damaged road surfaces not being maintained in a timely manner, resulting in low road maintenance efficiency and potentially causing more traffic accidents. SUMMARY

[0005] The present application provides a road crack detection method and device based on a grid model, which presents the condition of cracks in each road grid unit on a map through a crack critical value. Highway department managers can quickly obtain the crack conditions of all roads within the scope of management, improve the processing efficiency of road crack information, and thus improve the efficiency of road maintenance.

[0006] In a first aspect, the present application provides a road crack detection method based on a grid model, which comprises:

[0007] Dividing the road surface within the scope of intelligent highway management into road grid units of equal size on an intelligent road monitoring map;

[0008] Obtaining images of the road grid units;

[0009] Inputting the images of the road grid units into a trained road crack identification model to generate crack critical values corresponding to the images of the road grid units;

[0010] Displaying the crack critical values corresponding to the road grid units on the intelligent road monitoring map, including a first crack critical value corresponding to a first image of a first road grid unit;

[0011] when the first crack critical value is greater than a first preset critical threshold value, highlighting the first pavement grid cell on the pavement intelligent monitoring map, the first preset critical threshold value being a preset crack critical threshold value corresponding to the first pavement grid cell.

[0012] By adopting the technical solution, the crack critical value corresponding to each pavement grid cell is calculated according to the image of each pavement grid cell, and the crack critical value of each pavement grid cell is presented on the pavement intelligent monitoring map, so that the management personnel can quickly obtain the crack condition of the pavement within the supervision range from the pavement intelligent monitoring map, and the first pavement grid cell with a high crack critical value is highlighted, which can improve the processing efficiency of the pavement crack information and the maintenance efficiency of the pavement compared with directly analyzing and processing the image or manually identifying.

[0013] Optionally, the method comprises:

[0014] inputting the image of each pavement grid cell into the trained pavement crack identification model to generate the current crack critical value and the predicted crack critical value after a preset time length corresponding to the image of each pavement grid cell, wherein the second current crack critical value and the second predicted crack critical value corresponding to the second image of the second pavement grid cell are included;

[0015] displaying the current crack critical value and the predicted crack critical value corresponding to each pavement grid cell on the pavement intelligent monitoring map, wherein the second current crack critical value and the second predicted crack critical value corresponding to the second image of the second pavement grid cell are included;

[0016] when the second predicted crack critical value is greater than a second preset critical threshold value, prewarningly displaying the second pavement grid cell on the pavement intelligent monitoring map.

[0017] By adopting the technical solution, the predicted crack critical value of part of the pavement grid cells after a preset time length can be predicted, and the pavement cracks that will evolve into more serious cracks can be prewarned, so that the management personnel can discover the pavement crack condition in time, thereby further improving the maintenance efficiency.

[0018] Optionally, before the image of each pavement grid cell is inputted into the trained pavement crack identification model, the method further comprises:

[0019] obtaining the image and the crack critical value of each pavement grid cell at each time sequence;

[0020] taking the image and the crack critical value of each pavement grid cell at each time sequence as training data to train the pavement crack identification model for calculating the predicted crack critical value.

[0021] By adopting the technical scheme, the prediction accuracy of the evolution of the pavement crack information can be improved by taking the input image and the output crack critical value as the training data for calculating the predicted crack critical value, thereby further improving the maintenance efficiency.

[0022] Optionally, after the second pavement grid unit is highlighted on the pavement intelligent monitoring map when the first crack critical value is greater than the first preset critical threshold, the method further comprises:

[0023] real-time acquisition of pavement images of each time sequence of the second pavement grid unit;

[0024] If a repaired crack image of the second pavement grid unit is acquired in the pavement images within a preset time length, the second pavement grid unit is unhighlighted on the pavement intelligent monitoring map.

[0025] By adopting the technical scheme, if the second pavement grid unit is detected to be repaired within a preset time length, the second pavement grid unit is unhighlighted on the pavement intelligent monitoring map, the processing amount of data is reduced, and the efficiency of the warning is improved.

[0026] Optionally, after the first pavement grid unit is highlighted on the pavement intelligent monitoring map when the first crack critical value is greater than the first preset critical threshold, the method further comprises:

[0027] priority ranking of the first pavement grid units based on the first crack critical value, to obtain a first pavement grid unit ranking result;

[0028] planning of a maintenance route of the first pavement grid units based on the first pavement grid unit ranking result.

[0029] By adopting the technical scheme, the first pavement grid units that need to be repaired in time are priority ranked according to the size of the first crack critical value, and the maintenance route is determined based on the priority ranking result, which can improve the processing efficiency of the management personnel for the first pavement grid units that need to be repaired, thereby improving the pavement maintenance efficiency.

[0030] Optionally, after the first pavement grid unit is highlighted on the pavement intelligent monitoring map when the first crack critical value is greater than the first preset critical threshold, the method further comprises:

[0031] If a third crack critical value corresponding to the first pavement grid unit at a subsequent time is less than the first preset critical threshold;

[0032] a repair quality of the first pavement grid unit is calculated based on a difference between the first crack critical value and the third crack critical value.

[0033] By using the above technical solution, the first pavement grid unit corresponding to the first crack critical value is recorded at all times, and after detecting that the first pavement grid unit has been repaired, the repair result is judged by calculating the third preset crack critical value of the first pavement grid unit, so that the repair quality can be evaluated.

[0034] In a second aspect, the present application provides a pavement crack detection device based on a grid model, the device comprising:

[0035] a unit segmentation module configured to segment pavements within a smart highway management range into equal-sized pavement grid units on a pavement smart monitoring map;

[0036] an image acquisition module configured to acquire images of the pavement grid units;

[0037] a crack critical value generation module configured to input the images of the pavement grid units into a trained pavement crack recognition model to generate crack critical values corresponding to the images of the pavement grid units;

[0038] a crack critical value display module configured to display the crack critical values corresponding to the pavement grid units on the pavement smart monitoring map, wherein the crack critical values include a first crack critical value corresponding to a first image of a first pavement grid unit;

[0039] a highlight display module configured to highlight the first pavement grid unit on the pavement smart monitoring map when the first crack critical value is greater than a first preset critical threshold value, the first preset critical threshold value being a preset crack critical threshold value corresponding to the first pavement grid unit.

[0040] In a third aspect, the present application provides a computer storage medium storing a plurality of instructions, the instructions being adapted to be loaded and executed by a processor to perform any of the above methods.

[0041] In a fourth aspect, the present application provides an electronic device comprising a processor, a memory, and a transceiver, the memory being configured to store instructions, the transceiver being configured to communicate with other devices, and the processor being configured to execute the instructions stored in the memory to cause the electronic device to perform any of the above methods.

[0042] In summary, the technical solution of the present application has the following beneficial effects:

[0043] According to the image of each road surface grid unit, the corresponding crack critical value is calculated, and the crack critical value of each road surface grid unit is presented on the road surface intelligent monitoring map. The management personnel can intuitively and quickly obtain the crack condition of the road surface in the supervision range from the road surface intelligent monitoring map, and the first road surface grid unit with a high crack critical value is highlighted. Compared with direct image analysis and processing or manual identification, the processing efficiency of the road surface crack information can be improved, and the road surface maintenance efficiency can be improved. BRIEF DESCRIPTION OF DRAWINGS

[0044] Figure 1 is a system architecture diagram of a road surface crack detection method based on a grid model provided by an embodiment of the present application;

[0045] Figure 2 is a flowchart of a road surface crack detection method based on a grid model according to an embodiment of the present application;

[0046] Figure 3 is a scene implementation diagram of an exemplary road surface intelligent monitoring map provided by an embodiment of the present application;

[0047] Figure 4 is another exemplary scene diagram of a road surface intelligent monitoring map provided by an embodiment of the present application;

[0048] Figure 5 is a scene diagram of a repair route planning provided by an embodiment of the present application;

[0049] Figure 6 is a structural diagram of a road surface crack detection device based on a grid model provided by an embodiment of the present application;

[0050] Figure 7 is a structural diagram of an electronic device provided by an embodiment of the present application.

[0051] The reference signs are as follows: 10, unit segmentation module; 20, image acquisition module; 30, crack critical value generation module; 40, crack critical value display module; 50, highlighting module; 700, electronic device; 701, processor; 702, communication bus; 703, user interface; 704, network interface; 705, memory. DETAILED DESCRIPTION

[0052] In order for those skilled in the art to better understand the technical solutions in the specification, the technical solutions in the specification will be clearly and completely described below in conjunction with the drawings in the specification. Obviously, the described embodiments are only some of the embodiments of the present application, not all.

[0053] In the description of the embodiments of the present application, the words "exemplary", "for example", or "e.g." are used to mean serving as an example, instance, or illustration. Any embodiment or design presented as "exemplary", "for example", or "e.g." is not necessarily to be construed as preferred or advantageous over other embodiments or designs. Rather, use of the words "exemplary", "for example", or "e.g." is intended to present concepts in a concrete manner.

[0054] In the description of the embodiments of the present application, the term "a plurality of" means two or more. For example, a plurality of systems means two or more systems, and a plurality of screen terminals means two or more screen terminals. In addition, the terms "first", "second", and the like are used only for the purpose of description, and should not be construed as indicating or implying relative importance or implying the indicated technical features. Therefore, the features defined with "first", "second" can be explicitly or implicitly included one or more features. The terms "include", "contain", "have", and their variants mean "including but not limited to", unless otherwise specifically emphasized.

[0055] Referring to Figure 1 A system architecture diagram of a road surface crack detection method based on a grid model is provided in the embodiments of the present application. After the image acquisition device collects the road surface images corresponding to each road surface grid unit, the images are transmitted to the server. The server calculates the crack critical value corresponding to each road surface grid unit according to the images. The server then transmits the crack critical value to the computer device. The computer device outputs the intelligent road surface monitoring map with the crack critical value through the visualization device, and realizes the visualization of crack identification.

[0056] Referring to Figure 2 A flowchart of a road surface crack detection method based on a grid model is provided in the embodiments of the present application. The method can be realized by relying on a computer program, can be realized by relying on a single-chip microcomputer, and can also run on a grid model-based road surface crack detection device based on the von Neumann system. The computer program can be integrated in an application, or can be run as an independent tool class application. The embodiments of the present application take the server as an example to make a detailed description of the specific steps of the grid model-based road surface crack detection method.

[0057] S101, the road surface in the intelligent highway management range is divided into road surface grid units of equal size on the intelligent road surface monitoring map.

[0058] The road surface in the intelligent highway management range is the road surface in the management range of the server of the present application, i.e., the road surface area that can obtain corresponding images. The management range of the server is defined as the intelligent highway management range.

[0059] The intelligent road surface monitoring map is a satellite map within the scope of intelligent road management. The intelligent road surface monitoring map can be displayed to the management personnel in a visual manner.

[0060] The road surface grid unit is divided according to the crack critical value of each road surface unit grid in the embodiments of the present application. The road surface grid units are of the same size. The size of the road surface grid unit can be determined according to the distribution density of the cracks, the distribution density of the actual road network, and the like.

[0061] In S102, the images of the road surface grid units are obtained.

[0062] After the intelligent road surface monitoring map is divided into road surface grid units of the same size, the images of the road surface grid units are obtained. The images of the road surface grid units can be obtained by a fixedly arranged traffic camera or by aerial photography by a drone. The images need to contain the road surface information of the road surface grid units, including the crack information, and can obtain the position, shape, size, depth, and surrounding environment of the road surface cracks from the images.

[0063] In S103, the images of the road surface grid units are input into the trained road crack recognition model to generate the crack critical values corresponding to the images of the road surface grid units.

[0064] The road crack recognition model is a model trained based on a deep learning framework. The training data can be road crack images and their corresponding crack critical values. The training data can be obtained by obtaining historical road crack images and labeling the historical road crack images.

[0065] In a specific implementation, the road crack recognition model is a MobileNetV2 deep learning model. Each road surface grid unit is provided with an image processing device. The image processing device is embedded with a MobileNetV2 lightweight deep learning model to perform a computer vision task. The generated crack critical values corresponding to the images of the road surface grid units are transmitted to the server corresponding to the intelligent road surface monitoring map, so that the server corresponding to the intelligent road surface monitoring map can process and output the received crack critical values.

[0066] In S104, the corresponding crack critical values of the road surface grid units on the intelligent road surface monitoring map are displayed, including the first crack critical value corresponding to the first image of the first road surface grid unit.

[0067] Please refer to Figure 3An example scene implementation diagram of the intelligent road surface monitoring map is provided in the embodiments of the present application. The intelligent road surface monitoring map has been divided into a plurality of road surface grid cells in the above steps, and the crack critical value corresponding to the image of each road surface grid cell is displayed on the intelligent road surface monitoring map. The first crack critical value is a crack critical value exceeding the first preset critical threshold value, and the first crack critical value corresponds to the first image of the first road surface grid cell.

[0068] In S105, when the first crack critical value is greater than the first preset critical threshold value, the first road surface grid cell is highlighted on the intelligent road surface monitoring map. The first preset critical threshold value is a preset crack critical threshold value corresponding to the first road surface grid cell.

[0069] See Figure 4 Another example scene diagram of the intelligent road surface monitoring map is provided in the embodiments of the present application. The road surface grid cell with a higher grayscale in the diagram is the first road surface grid cell, which embodies the highlighting effect. After displaying each crack critical value on each road surface grid cell of the intelligent road surface monitoring map, it is determined whether the first crack critical value of each road surface grid cell is greater than the first preset critical threshold value. When the first crack critical value is greater than the first preset critical threshold value, the first road surface grid cell corresponding to the first crack critical value is highlighted. The first preset critical threshold value reflects the road crack repair demand, which can be set or adjusted according to the actual road crack. For example, the first preset critical threshold value is determined as a crack critical value of 80. The first road surface grid cells A4, B3, B4, D2, and E5 have first crack critical values of 81, 86, 88, 87, and 84, respectively.

[0070] In an implementable embodiment, the first road surface grid cells are prioritized based on the first crack critical values, and a first road surface grid cell sorting result is obtained. The repair route of the first road surface grid cell is planned based on the first road surface grid cell sorting result.

[0071] For the plurality of first road surface grid cells greater than the first preset critical threshold value, the first road surface grid cells are prioritized using the first crack critical values, that is, the first crack critical values are arranged in descending order, a corresponding first road surface grid cell sorting result is obtained, and the repair route is planned based on the sorting result. See Figure 5 A scene diagram of the repair route planning is provided in the embodiments of the present application. The priority sorting result of the first road surface grid cell is shown in the diagram, and the repair route of the first road surface grid cell is planned based on the sorting result. For example, the crack critical values are sorted as 88, 87, 86, 84, and 81. The repair route of the first road surface grid cell corresponding to the crack critical values is B4→D2→B3→E5→A4.

[0072] In one feasible implementation, if the third crack hazard value corresponding to the first pavement grid unit at a subsequent time is less than the first preset hazard threshold, then the repair quality of the first pavement grid unit is calculated based on the difference between the first crack hazard value and the third crack hazard value.

[0073] If the third crack critical value of the first road surface grid unit corresponding to the first image is less than the first preset critical threshold at a subsequent time, it indicates that the first road surface grid unit has been repaired. The third crack critical value of the repaired first road surface grid unit is obtained. By calculating the difference between the first crack critical value and the third crack critical value, the repair quality of the first road surface grid unit is evaluated. The repair quality of the road surface grid unit for cracks can be understood without introducing other calculation models for repair effects.

[0074] In another embodiment of the grid model-based pavement crack detection method of this application, the process of predicting the expected crack critical value after a period of time is described in detail to realize early warning of pavement cracks, so as to detect and repair pavement cracks in a timely manner and improve pavement maintenance efficiency.

[0075] S201 divides the road surface within the scope of intelligent highway management into equal-sized road surface grid units on the intelligent road monitoring map.

[0076] S202, acquire images of each road surface grid unit.

[0077] Steps S201 and S202 have been described in detail in the above embodiments S101 and S102, and will not be repeated here.

[0078] S203, input the images of each road surface grid unit into the trained road surface crack recognition model, and generate the current crack critical value and the expected crack critical value after a preset time corresponding to the image of each road surface grid unit.

[0079] The expected crack crisis value is obtained by inputting the image of each pavement grid unit at the current moment into the pavement crack recognition model. The model calculates the crack crisis value growth rate of the pavement grid unit, thereby calculating the expected crack crisis value after a preset time.

[0080] In one feasible implementation, images of each pavement grid unit and crack severity values ​​at each time sequence are acquired; the images of each pavement grid unit and crack severity values ​​at each time sequence are used as training data to train a pavement crack identification model for calculating the expected crack severity values.

[0081] The training data for the trained pavement crack recognition model consists of historical images of pavement grid cells and crack severity values. The model can be continuously trained and learned based on the current images of each pavement grid cell and crack severity values ​​to improve the accuracy of crack severity value and predicted crack severity value calculation.

[0082] S204, the current crack critical value and the expected crack critical value are displayed for each road grid unit on the road intelligent monitoring map, including the second current crack critical value and the second expected crack critical value corresponding to the second image of the second road grid unit.

[0083] The intelligent road surface monitoring map displays the current and expected crack severity values ​​for each road surface grid cell, enabling managers to promptly identify the grid cells requiring repair after a preset time period. This allows for timely planning of road crack repairs. The second road surface grid cell is defined as one whose current crack severity value is less than the first preset severity threshold, and whose expected crack severity value after a preset time period is greater than the second preset severity threshold.

[0084] In one feasible implementation, the intelligent road monitoring map can be switched to display the expected crack hazard value for a preset duration, or it can be switched to display the duration required for the second expected crack hazard value corresponding to each road grid unit to reach the second preset hazard threshold, so that managers can make timely plans based on the duration.

[0085] S205, when the second predicted crack critical value is greater than the second preset critical threshold, the second road surface grid unit is displayed as an early warning on the road surface intelligent monitoring map.

[0086] The pavement grid unit corresponding to the second expected crack critical value that exceeds the second preset critical threshold after a preset time period is determined as the second pavement grid unit.

[0087] In one optional implementation, road surface images of the second road surface grid unit at various time intervals are acquired in real time; if a repaired crack image of the second road surface grid unit is acquired in the road surface images within a preset time period, the warning display of the second road surface grid unit on the intelligent road surface monitoring map is canceled.

[0088] If the road surface cracks in the second road surface grid unit have been repaired within a preset time period, the warning for the second road surface grid unit will be canceled on the intelligent road surface monitoring map to improve the timeliness of warning processing within the preset time period, thereby improving the efficiency of road surface crack treatment.

[0089] The following are system embodiments of this application, which can be used to execute the method embodiments of this application. For details not disclosed in the system embodiments of this application, please refer to the method embodiments of the application.

[0090] Please see Figure 6 This illustration shows a structural schematic diagram of a pavement cracking device based on a mesh model, provided in an exemplary embodiment of this application. The device can be implemented entirely or partially through software, hardware, or a combination of both. The device includes a unit segmentation module 10, an image acquisition module 20, a crack critical value generation module 30, a crack critical value display module 40, and a highlighting module 50.

[0091] The unit segmentation module 10 is used to divide the road surface within the scope of intelligent highway management into equal-sized road surface grid units on the intelligent road monitoring map.

[0092] Image acquisition module 20 is used to acquire images of each road surface grid unit;

[0093] The crack critical value generation module 30 is used to input the images of each pavement grid unit into the trained pavement crack recognition model and generate the crack critical value corresponding to the image of each pavement grid unit.

[0094] The crack critical value display module 40 is used to display the corresponding crack critical value in each road grid cell on the road intelligent monitoring map, including the first crack critical value corresponding to the first image of the first road grid cell.

[0095] The highlighting module 50 is used to highlight the first road grid unit on the road intelligent monitoring map when the first crack critical value is greater than the first preset critical threshold. The first preset critical threshold is the preset crack critical threshold corresponding to the first road grid unit.

[0096] This application also provides a computer storage medium that can store multiple instructions, which are adapted to be loaded and executed by a processor as described above. Figures 1-5 The pavement crack detection method based on a mesh model shown in the embodiment can be found in the following documentation for its specific execution process. Figures 1-5 The specific details of the illustrated embodiments will not be elaborated here.

[0097] Please see Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 7 As shown, the electronic device 700 may include: at least one processor 701, at least one network interface 704, a user interface 703, a memory 705, and at least one communication bus 702.

[0098] The communication bus 702 is used to enable communication between these components.

[0099] The user interface 703 may include a display screen and a camera. Optionally, the user interface 703 may also include a standard wired interface and a wireless interface.

[0100] The network interface 704 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface).

[0101] The processor 701 may include one or more processing cores. The processor 701 connects to various parts of the server using various interfaces and lines, and performs various server functions and processes data by running or executing instructions, programs, code sets, or instruction sets stored in memory 705, and by calling data stored in memory 705. Optionally, the processor 701 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 701 may integrate one or a combination of several of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the content required for display; and the modem handles wireless communication. It is understood that the modem may also not be integrated into the processor 701 and may be implemented as a separate chip.

[0102] The memory 705 may include random access memory (RAM) or read-only memory. Optionally, the memory 705 may include a non-transitory computer-readable storage medium. The memory 705 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 705 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-described method embodiments, etc.; the data storage area may store data involved in the above-described method embodiments, etc. Optionally, the memory 705 may also be at least one storage device located remotely from the aforementioned processor 701. Figure 7As shown, the memory 705, which serves as a computer storage medium, may include an operating system, a network communication module, a user interface module, and an application program for a pavement crack detection method based on a mesh model.

[0103] exist Figure 7 In the electronic device 700 shown, the user interface 703 is mainly used to provide an input interface for the user and to obtain the user input data; while the processor 701 can be used to call an application program stored in the memory 705 for a road surface crack detection method based on a mesh model. When executed by one or more processors, the electronic device executes one or more methods as described in the above embodiments.

[0104] An electronic device readable storage medium stores instructions that, when executed by one or more processors, cause the electronic device to perform one or more methods as described in the above embodiments.

[0105] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0106] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0107] In the several embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the shown or discussed mutual couplings or direct couplings or communication connections may be through some service interfaces; indirect couplings or communication connections between apparatuses or units may be electrical or other forms.

[0108] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0109] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0110] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, portable hard drives, magnetic disks, or optical disks.

[0111] The above are merely exemplary embodiments of this disclosure and should not be construed as limiting the scope of this disclosure. Any equivalent changes and modifications made in accordance with the teachings of this disclosure shall still fall within the scope of this disclosure. Those skilled in the art will readily conceive of other embodiments of this disclosure upon considering the specification and the disclosure of practical truth. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not described in this disclosure. The specification and embodiments are considered exemplary only, and the scope and spirit of this disclosure are defined by the claims.

Claims

1. A method for detecting pavement cracks based on a mesh model, characterized in that, The method includes: The road surface within the scope of intelligent highway management is divided into equal-sized road surface grid units on the intelligent road monitoring map; Acquire images of each road surface grid unit; The images of each road surface grid unit are input into the trained road surface crack recognition model to generate crack severity values ​​corresponding to the images of each road surface grid unit. The road surface grid cells on the intelligent road surface monitoring map display the corresponding crack critical values, including the first crack critical value corresponding to the first image of the first road surface grid cell. When the first crack critical value is greater than the first preset critical threshold, the first road grid unit is highlighted on the intelligent road monitoring map. The first preset critical threshold is the preset crack critical threshold corresponding to the first road grid unit. Based on the first crack urgency value, the first pavement grid cells are prioritized to obtain the first pavement grid cell sorting result; Based on the sorting results of the first road surface grid unit, the maintenance route of the first road surface grid unit is planned; The method further includes: inputting the image of each road grid unit into a trained road crack recognition model to generate the current crack critical value and the expected crack critical value after a preset time corresponding to the image of each road grid unit, including the second current crack critical value and the second expected crack critical value corresponding to the second image of the second road grid unit. The road surface intelligent monitoring map displays the corresponding current crack critical value and the expected crack critical value for each road surface grid unit, including the second current crack critical value and the second expected crack critical value corresponding to the second image of the second road surface grid unit; When the second predicted crack critical value is greater than the second preset critical threshold, the second road grid cell is displayed as an early warning on the intelligent road monitoring map.

2. The method according to claim 1, characterized in that, Before inputting the images of each road surface grid unit into the trained road surface crack recognition model, the method further includes: Obtain images of each pavement grid unit and crack severity values ​​at each time step; The images of each pavement grid unit in each time series and the crack critical value are used as training data to train the pavement crack identification model for calculating the expected crack critical value.

3. The method according to claim 1, characterized in that, When the second predicted crack critical value is greater than the second preset critical threshold, after displaying the second road grid cell on the intelligent road monitoring map as a warning, the method further includes: Real-time acquisition of road surface images of the second road surface grid unit at various time intervals; If a repaired crack image of the second road surface grid unit is obtained in the road surface image within a preset time period, then the warning display of the second road surface grid unit on the intelligent road surface monitoring map will be canceled.

4. The method according to claim 1, characterized in that, After highlighting the first road grid cell on the intelligent road monitoring map when the first crack critical value is greater than the first preset critical threshold, the method further includes: If the third crack hazard value corresponding to the first road surface grid unit in a subsequent time is less than the first preset hazard threshold; The maintenance quality of the first road surface grid unit is calculated based on the difference between the first crack critical value and the third crack critical value.

5. The method according to claim 1, characterized in that, The road surface crack identification model is a MobileNetV2 deep learning model.

6. A pavement crack detection device based on a mesh model, characterized in that, The device includes: The unit segmentation module is used to divide the road surface within the scope of intelligent highway management into equal-sized road surface grid units on the intelligent road monitoring map; The image acquisition module is used to acquire images of each road surface grid unit; The crack critical value generation module is used to input the images of each pavement grid unit into the trained pavement crack recognition model and generate the crack critical value corresponding to the image of each pavement grid unit. The crack critical value display module is used to display the corresponding crack critical value in each road grid unit on the road intelligent monitoring map, including the first crack critical value corresponding to the first image of the first road grid unit. A highlighting module is used to highlight the first road grid unit on the intelligent road monitoring map when the first crack hazard value is greater than a first preset hazard threshold, wherein the first preset hazard threshold is a preset crack hazard threshold corresponding to the first road grid unit; prioritize the first road grid units based on the first crack hazard value to obtain a first road grid unit ranking result; plan the maintenance route of the first road grid unit based on the first road grid unit ranking result; input the images of each road grid unit into a trained road crack recognition model to generate the current crack hazard value and the expected crack hazard value after a preset time corresponding to the image of each road grid unit, including the second current crack hazard value and the second expected crack hazard value corresponding to the second image of the second road grid unit; display the corresponding current crack hazard value and the expected crack hazard value on the intelligent road monitoring map for each road grid unit, including the second current crack hazard value and the second expected crack hazard value corresponding to the second image of the second road grid unit; and display a warning on the intelligent road monitoring map when the second expected crack hazard value is greater than the second preset hazard threshold.

7. A computer storage medium, characterized in that, The computer storage medium stores multiple instructions, which are adapted to be loaded by a processor and executed as described in any one of claims 1 to 4.

8. An electronic device, characterized in that, The device includes a processor, a memory, and a transceiver. The memory is used to store instructions, the transceiver is used to communicate with other devices, and the processor is used to execute the instructions stored in the memory to cause the electronic device to perform the method as described in any one of claims 1 to 4.

Images