A bridge pavement crack detection system

Abstract

The present invention discloses a bridge pavement crack detection system, which relates to the technical field of bridge pavement detection. The system discloses a depth crack partitioning module, a partition detection module, and an impact detection module. By setting the depth crack partitioning module and the partition detection module, the depth cracks on the bridge pavement are managed and detected in a partitioned manner, and the changes in the depth cracks of each partition on the bridge pavement can be analyzed more accurately, which is convenient for subsequent accurate evaluation and analysis of each partition on the bridge pavement. The impact detection module is set, and after the core crack partition appears on the bridge pavement, the remaining partitions within the crack influence range can be further analyzed, and the partitions with potential hidden dangers of deep cracks on the bridge pavement are analyzed, so that measures can be taken in advance for the deep cracks in the corresponding partitions.

Description

Technical Field

[0001] The invention relates to the technical field of bridge pavement detection, and more specifically, to a bridge pavement crack detection system. Background Art

[0002] The bridge pavement is a key component of the bridge project. It carries the weight of vehicles, pedestrians and other means of transportation. The bridge pavement is usually a concrete pavement. In order to ensure the long-term safe use of the bridge pavement, after the construction of the bridge pavement is completed, the bridge pavement needs to be regularly inspected for surface cracks. When cracks are detected on the surface of the bridge pavement, the cracks will be treated accordingly. However, there are many reasons for the formation of surface cracks in the bridge pavement. Some cracks are caused by surface stress. The degree of damage to the bridge pavement is not high, and the cracks can be eliminated by surface repair. Some cracks first appear inside the concrete and gradually extend from the inside to the surface. The degree of damage to the bridge pavement is high, and the cracks need to be repaired by grouting and other methods. The current surface detection method can only detect cracks in the bridge pavement caused by surface stress, and cannot prevent deep cracks in the bridge pavement. Summary of the invention

[0003] In view of the deficiencies in the prior art, an object of the present invention is to provide a bridge pavement crack detection system.

[0004] To achieve the above object, the present invention provides the following technical solutions:

[0005] A bridge pavement crack detection system, comprising a depth crack partitioning module, a partition detection module, and an impact detection module;

[0006] The deep crack partitioning module is used to divide the bridge pavement into bridge pavement partitions, and detect the deep cracks of each bridge pavement partition every c time length;

[0007] The partition detection module is used to obtain the detection impact value of each bridge pavement partition, and based on the comparison result between the detection impact value and its threshold value, mark the bridge pavement partition as a core crack partition or a common crack partition;

[0008] The impact detection module is used to divide the crack impact range after the core crack partition appears, and analyze whether there is a core impact partition in the crack impact range.

[0009] Furthermore, the bridge pavement is divided into zones, and the depth cracks of each bridge pavement zone are detected every c time duration. Specifically, the bridge pavement is divided into equal areas to obtain multiple bridge pavement zones, and the bridge pavement zones are subjected to acoustic wave detection every c time duration. When new deep cracks appear in the bridge pavement zones, the deep cracks are numbered and the depth crack detection records of each depth crack are generated synchronously.

[0010] Furthermore, the deep crack detection record includes a number, a deep crack analysis value, and a detection time.

[0011] Furthermore, the specific steps of acoustic wave detection are as follows: perform acoustic wave detection on each position of the bridge pavement partition to obtain acoustic wave data of each position, convert the acoustic wave data of each position to obtain multiple acoustic wave spectrograms, perform feature recognition on the multiple acoustic wave spectrograms to obtain multiple acoustic wave features, use each acoustic wave feature as input data of a deep crack analysis model to obtain multiple deep crack analysis values. When the depth crack analysis value is equal to 0, it indicates that there is no deep crack at that position. The larger the depth crack analysis value, the more serious the crack state is.

[0012] Furthermore, the detection influence value of each bridge pavement partition is obtained, and based on the comparison result between the detection influence value and its threshold, the bridge pavement partition is marked as a core crack partition or an ordinary crack partition. Specifically, the detection influence value of each bridge pavement partition is obtained every c time period, and a detection influence threshold is set. When the detection influence value of the bridge pavement partition is greater than or equal to the detection influence threshold, the bridge pavement partition is marked as a core crack partition; when the detection influence value of the bridge pavement partition is less than the detection influence threshold, the bridge pavement partition is marked as an ordinary crack partition.

[0013] Furthermore, the detection impact value of the bridge pavement partition is obtained by the following method: the total number of deep cracks in the bridge pavement partition is obtained and marked as Sk, the partition impact value of all deep cracks in the bridge pavement partition is obtained, all partition impact values ​​are summed up to obtain the partition impact value and marked as Cb, and the formula is used to calculate the total impact value of the partition. The detection influence value Te of the bridge pavement partition is obtained, where b1 is the total number coefficient of deep cracks and b2 is the partition influence coefficient.

[0014] Furthermore, the partition influence value of the deep crack is obtained by the following method:

[0015] Get all the deep crack detection records of the depth crack with the number before the current time of the system, mark the total number of deep crack detection records as AGT, sort all the deep crack detection records in the order of detection time, calculate the difference between the depth crack analysis values ​​of the two adjacent deep crack detection records after sorting, get the depth crack change value, set the depth crack change threshold, when the depth crack change value is greater than or equal to the depth crack change threshold, increase the number of abnormal crack changes by one, and mark the adjacent and later deep crack detection records as crack mutation records, sum the number of abnormal crack changes to get the total number of abnormal crack changes, and mark it as TWS, sort all the crack mutation records in the order of detection time, calculate the time difference between the detection time of the two adjacent crack mutation records after sorting, get the crack mutation interval, sum all the crack mutation intervals and take the average, get the average crack mutation interval, and mark it as MSZ, use the formula The partition impact value YDR of the deep crack is obtained, where a1 is the coefficient of the number of deep crack detection records, a2 is the coefficient of the total number of abnormal crack changes, and a3 is the average crack change interval coefficient.

[0016] Furthermore, after the core crack partition appears, the crack influence range is divided out, and it is analyzed whether there is a core influence partition within the crack influence range. Specifically, when the bridge pavement partition is marked as a core crack partition, a circle with a preset radius and the midpoint of the core crack partition as the center is drawn to obtain the crack influence range, and the remaining ordinary crack partitions within the crack influence range are marked as crack re-inspection areas. The total number of influence anomalies and the total number of cracks of the same degree in the core crack partition are obtained and marked as [Y1, Y2]. The total number of influence anomalies and the total number of cracks of the same degree in the crack re-inspection area are obtained and marked as [Z1, Z2]. The cosine similarity algorithm is used to calculate the influence synchronization value of the core crack partition and the crack re-inspection area, and an influence synchronization threshold is set. When the influence synchronization value is greater than or equal to the influence synchronization threshold, the crack re-inspection area is marked as a core influence partition. When the influence synchronization value is less than the influence synchronization threshold, the crack re-inspection area is marked back to an ordinary crack partition.

[0017] Furthermore, the total number of influencing abnormal waves is obtained in the following manner: obtain n detection influence values ​​of the bridge pavement partition before the current time of the system, sort all the detection influence values ​​in the order of acquisition time, calculate the difference between the two adjacent detection influence values ​​after sorting, and obtain the detection influence fluctuation value, set the detection influence fluctuation threshold, and when the detection influence fluctuation value is greater than or equal to the detection influence fluctuation threshold, increase the number of shadow fluctuations by one, sum the number of shadow fluctuations, and obtain the total number of shadow fluctuations.

[0018] Furthermore, the total number of cracks of the same degree is obtained by the following method: all the depth cracks in the bridge pavement partition are compared in pairs, the influence difference between every two depth cracks is obtained, and the influence threshold difference is set. When the influence difference is less than the influence threshold difference, the number of cracks of the same degree is increased once, and the number of cracks of the same degree is summed to obtain the total number of cracks of the same degree;

[0019] The influence difference of two deep cracks is obtained in the following way: the difference of the partition influence values ​​of the two deep cracks is calculated and the absolute value is taken to obtain the influence difference.

[0020] Compared with the prior art, the present invention has the following beneficial effects:

[0021] 1. Set up a deep crack partitioning module and a partition detection module to manage and detect the deep cracks on the bridge pavement by partitioning, which can more accurately analyze the changes in the deep cracks in each partition on the bridge pavement, and facilitate the subsequent accurate evaluation and analysis of each partition on the bridge pavement;

[0022] 2. An impact detection module is set up to further analyze the remaining partitions within the crack impact range after the core crack partition appears on the bridge pavement, and analyze the partitions with potential hidden dangers of deep cracks in the bridge pavement, so as to take measures in advance for the deep cracks in the corresponding partitions. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 A flowchart for marking bridge pavement zones as core crack zones or common crack zones;

[0024] Figure 2 A flowchart for analyzing whether there is a core impact zone within the crack impact range. DETAILED DESCRIPTION

[0025] Reference Figure 1 to Figure 2

[0026] A bridge pavement crack detection system comprises a depth crack partitioning module, a partition detection module and an impact detection module.

[0027] Deep crack partitioning module: The bridge pavement is divided into equal areas to obtain multiple bridge pavement partitions. The bridge pavement partitions are subjected to acoustic wave detection every c time (the acoustic wave detection equipment can detect whether there are cracks inside the bridge pavement partition, and the crack length and crack depth can be obtained at the same time). When new deep cracks appear in the bridge pavement partitions, the deep cracks are numbered and the deep crack detection records of each deep crack are generated synchronously. The deep crack detection records include the number (each deep crack corresponds to an independent and unique number), the depth crack analysis value, and the detection time.

[0028] Partition detection module: The detection impact value of each bridge pavement partition is obtained every c time duration, and a detection impact threshold is set. When the detection impact value of a bridge pavement partition is greater than or equal to the detection impact threshold, the bridge pavement partition is marked as a core crack partition.

[0029] When the detection influence value of a bridge pavement partition is less than the detection influence threshold, the bridge pavement partition is marked as a common crack partition.

[0030] The detection impact value of the bridge pavement partition is obtained by the following method: obtain the total number of deep cracks in the bridge pavement partition and mark it as Sk, obtain the partition impact value of all deep cracks in the bridge pavement partition, sum up all the partition impact values, obtain the partition impact value, and mark it as Cb, and use the formula The detection influence value Te of the bridge pavement partition is obtained, where b1 is the total number coefficient of deep cracks, b2 is the partition influence coefficient, the value of b1 is 0.35, and the value of b2 is 0.42.

[0031] The partition influence value of deep cracks is obtained by the following method:

[0032] Get all the depth crack detection records of the depth crack with the number before the current time of the system, mark the total number of depth crack detection records as AGT, sort all the depth crack detection records in the order of detection time, and perform difference calculation on the depth crack analysis values ​​of the two adjacent depth crack detection records after sorting (difference between the depth crack analysis values ​​of the adjacent and later depth crack detection records after sorting and the depth crack analysis values ​​of the front depth crack detection records), and obtain the depth crack change value (the depth crack change value only exists when it is greater than or equal to 0, and when it is equal to 0, it means that the depth crack has not changed), set the depth crack change threshold, which is the system set threshold, and can be calculated based on the actual The demand is modified. When the depth crack change value is greater than or equal to the depth crack change threshold, the number of abnormal crack changes is increased once, and the adjacent and subsequent deep crack detection records are marked as crack mutation records. When the depth crack change value is less than the depth crack change threshold, no corresponding processing is performed. The number of abnormal crack changes is summed to obtain the total number of abnormal crack changes and marked as TWS. All crack mutation records are sorted in the order of detection time. The detection time of the two adjacent crack mutation records after sorting is calculated to obtain the crack mutation interval. All crack mutation intervals are summed and averaged to obtain the average crack mutation interval, which is marked as MSZ. The formula is used The partition influence value YDR of the deep crack is obtained, where a1 is the coefficient of the number of deep crack detection records, a2 is the coefficient of the total number of abnormal crack changes, and a3 is the coefficient of the average crack abnormal change interval. The value of a1 is 0.72, the value of a2 is 1.81, and the value of a3 is 0.69.

[0033] The specific steps of acoustic wave detection are as follows: perform acoustic wave detection on each position of the bridge pavement partition to obtain acoustic wave data of each position, convert the acoustic wave data of each position to obtain multiple acoustic wave spectrograms, perform feature recognition on the multiple acoustic wave spectrograms to obtain multiple acoustic wave features, use each acoustic wave feature as input data of the deep crack analysis model to obtain multiple deep crack analysis values. When the deep crack analysis value is equal to 0, it means that there is no deep crack at that position. The larger the deep crack analysis value, the deeper the crack is (for example, factors such as the longer the crack, the wider the crack, and the deeper the crack will result in a larger deep crack analysis value).

[0034] The deep crack analysis model is obtained in the following way: obtain multiple acoustic wave features, use the acoustic wave features as training data for the neural network model, assign a deep crack analysis value to the training data, the value of the deep crack analysis value is greater than or equal to 0, divide the training data into a training set and a validation set according to a set ratio, perform iterative neural network training on the training data through the training set and the validation set, and obtain the deep crack analysis model.

[0035] By setting up a deep crack zoning module and a zoning detection module, the deep cracks on the bridge pavement are managed and detected by zoning. This can more accurately analyze the changes in the depth cracks in each zone on the bridge pavement, facilitating the subsequent accurate evaluation of each zone on the bridge pavement.

[0036] Impact detection module: After the bridge pavement partition is marked as a core crack partition, a circle is drawn with the midpoint of the core crack partition as the center and a preset radius to obtain the crack influence range. The remaining common crack partitions within the crack influence range are marked as crack re-inspection areas. The total number of impact anomalies and the total number of cracks of the same degree in the core crack partition are obtained and marked as [Y1, Y2]. Y1 is the total number of impact anomalies in the core crack partition, and Y2 is the total number of cracks of the same degree in the core crack partition. The total number of impact anomalies and the total number of cracks of the same degree in the crack re-inspection area are obtained and marked as [Z1, Z2]. Z1 is the total number of impact anomalies in the crack re-inspection area, and Z2 is the total number of cracks of the same degree in the crack re-inspection area. The cosine similarity algorithm is used to calculate the impact synchronization value of the core crack partition and the crack re-inspection area, and an impact synchronization threshold is set. The impact synchronization threshold is a system-set threshold and can be modified according to actual needs. When the impact synchronization value is greater than or equal to the impact synchronization threshold, the crack re-inspection area is marked as a core impact partition. When the impact synchronization value is less than the impact synchronization threshold, the crack re-inspection area is marked back to an ordinary crack partition. The core crack zone represents the area with serious deep cracks in the bridge pavement, and the core impact zone is the area with potential hidden dangers of deep cracks. The core crack zone has the potential to affect the core impact zone, and the same measures can be taken to deal with the deep cracks in these two areas in advance.

[0037]

[0038] The total number of influencing abnormal waves is obtained in the following way: obtain n detection influence values ​​of the bridge pavement partition before the current time of the system, sort all the detection influence values ​​in the order of acquisition time, calculate the difference between the two adjacent detection influence values ​​after sorting (the difference between the latter detection influence value and the former detection influence value), and obtain the detection influence fluctuation value, set the detection influence fluctuation threshold, the detection influence fluctuation threshold is the system setting threshold, which can be modified according to actual needs, when the detection influence fluctuation value is greater than or equal to the detection influence fluctuation threshold, increase the number of shadow fluctuations by one, and sum the number of shadow fluctuations to obtain the total number of shadow fluctuations.

[0039] The total number of cracks of the same degree is obtained in the following way: all the depth cracks in the bridge pavement partition are compared pairwise to obtain the impact difference between every two depth cracks, and the impact threshold difference is set. The impact threshold difference is the system set threshold and can be modified according to actual needs. When the impact difference is greater than or equal to the impact threshold difference, no corresponding processing is performed. When the impact difference is less than the impact threshold difference, the number of cracks of the same degree is increased once, and the number of cracks of the same degree is summed to obtain the total number of cracks of the same degree.

[0040] The influence difference of two deep cracks is obtained in the following way: the difference of the partition influence values ​​of the two deep cracks is calculated and the absolute value is taken to obtain the influence difference.

[0041] By setting up an impact detection module, after the core crack zone appears in the bridge pavement, the remaining zones within the crack impact range can be further analyzed to identify the zones with potential hidden dangers of deep cracks in the bridge pavement, so as to take measures in advance for the deep cracks in the corresponding zones.

[0042] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0043] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0044] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0045] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0046] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0047] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0048] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0049] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A bridge pavement crack detection system, characterized in that: It includes a deep crack partitioning module, a partition detection module, and an impact detection module; The deep crack partitioning module is used to divide the bridge pavement into bridge pavement partitions, and detect the deep cracks of each bridge pavement partition every c time length; The partition detection module is used to obtain the detection impact value of each bridge pavement partition, and based on the comparison result between the detection impact value and its threshold value, mark the bridge pavement partition as a core crack partition or a common crack partition; The impact detection module is used to divide the crack impact range after the core crack partition appears, and analyze whether there is a core impact partition within the crack impact range; Divide the bridge pavement into zones, and detect the deep cracks of each bridge pavement zone every c time duration, specifically: divide the bridge pavement into equal areas to obtain multiple bridge pavement zones, perform acoustic wave detection on the bridge pavement zones every c time duration, and when new deep cracks appear in the bridge pavement zones, number the deep cracks, and simultaneously generate deep crack detection records of each deep crack; Obtain the detection influence value of each bridge pavement partition, and based on the comparison result between the detection influence value and its threshold, mark the bridge pavement partition as a core crack partition or a common crack partition, specifically: obtain the detection influence value of each bridge pavement partition every c time duration, set the detection influence threshold, when the detection influence value of the bridge pavement partition is greater than or equal to the detection influence threshold, mark the bridge pavement partition as a core crack partition, when the detection influence value of the bridge pavement partition is less than the detection influence threshold, mark the bridge pavement partition as a common crack partition; The detection impact value of the bridge pavement partition is obtained by the following method: obtain the total number of deep cracks in the bridge pavement partition and mark it as Sk, obtain the partition impact value of all deep cracks in the bridge pavement partition, sum up all the partition impact values, obtain the partition impact value, and mark it as Cb, and use the formula The detection influence value Te of the bridge pavement partition is obtained, where b1 is the total number coefficient of deep cracks and b2 is the partition influence coefficient; The partition influence value of deep cracks is obtained by the following method: Get all the deep crack detection records of the depth crack with the number before the current time of the system, mark the total number of deep crack detection records as AGT, sort all the deep crack detection records in the order of detection time, calculate the difference between the depth crack analysis value of the adjacent and later deep crack detection records after sorting and the depth crack analysis value of the front deep crack detection record to obtain the depth crack change value, set the depth crack change threshold, when the depth crack change value is greater than or equal to the depth crack change threshold, increase the number of abnormal crack changes by one, and mark the adjacent and later deep crack detection records as crack mutation records, sum the number of abnormal crack changes to obtain the total number of abnormal crack changes, and mark it as TWS, sort all the crack mutation records in the order of detection time, calculate the time difference between the detection times of the two adjacent crack mutation records after sorting to obtain the crack mutation interval, sum all the crack mutation intervals and take the average to obtain the average crack mutation interval, and mark it as MSZ, use the formula The partition impact value YDR of the deep crack is obtained, where a1 is the coefficient of the number of deep crack detection records, a2 is the coefficient of the total number of abnormal crack changes, and a3 is the average crack change interval coefficient.

2. A bridge pavement crack detection system according to claim 1, characterized in that: The deep crack detection record includes the deep crack number, deep crack analysis value, and detection time.

3. A bridge pavement crack detection system according to claim 1, characterized in that: The specific steps of acoustic wave detection are as follows: perform acoustic wave detection on each position of the bridge pavement partition to obtain acoustic wave data of each position, convert the acoustic wave data of each position to obtain multiple acoustic wave spectrograms, perform feature recognition on the multiple acoustic wave spectrograms to obtain multiple acoustic wave features, use each acoustic wave feature as input data of the deep crack analysis model to obtain multiple deep crack analysis values. When the deep crack analysis value is equal to 0, it indicates that there is no deep crack at that position. The larger the depth crack analysis value, the more serious the crack state is.

4. A bridge pavement crack detection system according to claim 1, characterized in that: After the core crack partition appears, the crack influence range is divided, and it is analyzed whether there is a core influence partition within the crack influence range. Specifically, when the bridge pavement partition is marked as the core crack partition, the midpoint of the core crack partition is used as the center, and a circle with a preset radius is drawn to obtain the crack influence range. The remaining common crack partitions within the crack influence range are marked as crack re-inspection areas. The total number of abnormal waves and the total number of cracks of the same degree in the core crack partition are obtained and marked as , obtain the total number of abnormal waves affecting the crack re-inspection area and the total number of cracks of the same degree, and mark them as , the cosine similarity algorithm is used to calculate the influence synchronization value of the core crack partition and the crack re-inspection area, and the influence synchronization threshold is set. When the influence synchronization value is greater than or equal to the influence synchronization threshold, the crack re-inspection area is marked as the core influence partition. When the influence synchronization value is less than the influence synchronization threshold, the crack re-inspection area is marked back to the ordinary crack partition.

5. A bridge pavement crack detection system according to claim 4, characterized in that: The total number of influencing abnormal waves is obtained in the following way: obtain n detection influence values ​​of the bridge pavement partition before the current time of the system, sort all the detection influence values ​​in the order of acquisition time, calculate the difference between the two adjacent detection influence values ​​after sorting, and obtain the detection influence fluctuation value, set the detection influence fluctuation threshold, when the detection influence fluctuation value is greater than or equal to the detection influence fluctuation threshold, increase the number of shadow fluctuations by one, sum the number of shadow fluctuations, and obtain the total number of shadow fluctuations.

6. A bridge pavement crack detection system according to claim 4, characterized in that: The total number of cracks of the same degree is obtained by the following method: all the cracks of different depths in the bridge pavement partition are compared in pairs, the influence difference between every two cracks of different depths is obtained, and the influence threshold difference is set. When the influence difference is less than the influence threshold difference, the number of cracks of the same degree is increased once, and the number of cracks of the same degree is summed to obtain the total number of cracks of the same degree. The influence difference of two deep cracks is obtained in the following way: the difference of the partition influence values ​​of the two deep cracks is calculated and the absolute value is taken to obtain the influence difference.

Images