Intelligent management and control method and system for cement concrete pavement cracks

Abstract

The invention discloses an intelligent management and control method and system for cement concrete pavement cracks, and belongs to the field of road engineering.The method comprises the steps that sensitive switching parameters are set; the method comprises the following steps: controlling a collection traveling vehicle to move, pre-collecting road surface data, and constructing an initial reference data set; initializing a decision-making unit, inputting the initial reference data set into the decision-making unit, and outputting decision-making data; selecting an infrared sensor and / or an imaging sensor to carry out image data acquisition, and constructing an image data set; performing defect identification on the image data set, and recording abnormal coordinates and a disease feature set according to an identification result; and calling the pavement file, carrying out maintenance strategy matching, and carrying out intelligent management and control on the pavement according to a matching result. The technical problem that intelligent and precise detection and maintenance cannot be performed on the pavement crack in the prior art is solved, and the technical effect of intelligent management and control of the pavement crack through sensor acquisition, intelligent analysis and precise matching is achieved.

Description

Technical Field

[0001] The present invention relates to the field of road engineering, and in particular to an intelligent control method and system for cracks in a cement concrete pavement. Background Art

[0002] With the development of social economy, people have higher and higher requirements for road quality. How to detect and evaluate road conditions in real time and accurately and realize intelligent maintenance and management of roads is an important issue in urban construction. For cement concrete roads, cracks are one of the main diseases. At present, the detection of pavement cracks mainly relies on manual inspections. This method is highly subjective and inefficient. In addition, the detection of pavement cracks also has problems such as low detection accuracy, inability to distinguish and identify different types of cracks, and inability to match intelligent maintenance strategies accordingly, which limits the efficiency and intelligence level of cement concrete pavement crack control. Summary of the invention

[0003] The present application provides an intelligent control method and system for cement concrete pavement cracks, aiming to solve the technical problem that the prior art cannot perform intelligent and accurate detection and maintenance of pavement cracks.

[0004] In view of the above problems, the present application provides an intelligent control method and system for cracks in cement concrete pavement.

[0005] The first aspect disclosed in the present application provides an intelligent control method for cracks in a cement concrete pavement, the method comprising: setting a sensitive switching parameter, the sensitive switching parameter being a switching response parameter for pavement acquisition, the sensitive switching parameter being set by acquiring basic data of an infrared sensor and an imaging sensor; controlling the movement of an acquisition vehicle by a predetermined speed, and pre-acquiring pavement data by a pre-acquisition unit to construct an initial reference data set, wherein a decision unit, a pre-acquisition unit, an infrared sensor, and an imaging sensor are arranged on the acquisition vehicle and are communicatively connected with each other; initializing the decision unit by the sensitive switching parameter, inputting the initial reference data set into the decision unit, and outputting decision data; selecting an infrared sensor and / or an imaging sensor to acquire image data by the decision data, and constructing an image data set; identifying defects in the image data set by the decision unit, and recording abnormal coordinates and a disease feature set according to the identification results; calling a pavement archive, matching maintenance strategies by the pavement archive and the abnormal coordinates and the disease feature set, and performing intelligent control of the pavement according to the matching results.

[0006] Another aspect disclosed in the present application provides an intelligent management and control system for cracks in cement concrete pavement, the system comprising: a sensitive switching parameter module, used to set a sensitive switching parameter, the sensitive switching parameter is a switching response parameter for pavement collection, and the sensitive switching parameter is set by collecting basic data of infrared sensors and imaging sensors; an initial reference data module, used to control the movement of a collection vehicle by a predetermined speed, and pre-collect pavement data by a pre-collection unit to construct an initial reference data set, and the decision unit, the pre-collection unit, the infrared sensor and the imaging sensor are arranged on the collection vehicle and are communicatively connected with each other; a decision data output module, used to initialize the decision unit by the sensitive switching parameter, input the initial reference data set into the decision unit, and output decision data; an image data acquisition module, used to select an infrared sensor and / or an imaging sensor to collect image data by decision data, and construct an image data set; a data defect recognition module, used to identify defects in the image data set by the decision unit, and record abnormal coordinates and disease feature sets according to the recognition results; a pavement intelligent management and control module, used to call pavement archives, match maintenance strategies by the pavement archives and abnormal coordinates and disease feature sets, and perform intelligent management and control of the pavement according to the matching results.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0008] The sensitive switching parameters are set by collecting basic data of infrared sensors and imaging sensors to achieve precise switching control of sensors; the movement of the moving vehicle is collected by controlling the predetermined speed, and the road surface data is pre-collected by the pre-collection unit set on the collecting moving vehicle to construct an initial reference data set for subsequent decision analysis; the decision unit is initialized by the set sensitive switching parameters, and the constructed initial reference data set is input into the decision unit, and the decision unit outputs decision data to guide subsequent image acquisition; according to the instructions of the decision data, infrared sensors and / or imaging sensors are selected for image acquisition to construct an image data set to provide data support for crack identification; the image data set is analyzed by the decision unit to achieve accurate identification of the position coordinates and disease characteristics of road cracks; the road archive database is called, and the archive is matched and analyzed with the identification results to formulate corresponding maintenance strategies, and the technical solution for intelligent control of cement concrete road cracks is completed, which solves the technical problem that road cracks cannot be intelligently and accurately detected and maintained in the existing technology, and achieves the technical effect of realizing intelligent control of road cracks through sensor acquisition, intelligent analysis and precise matching.

[0009] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 A flow chart of an intelligent control method for cracks in a cement concrete pavement is provided for an embodiment of the present application;

[0011] Figure 2 A flowchart of determining abnormal coordinates and disease feature sets in an intelligent control method for cracks in a cement concrete pavement is provided for an embodiment of the present application;

[0012] Figure 3 A structural schematic diagram of an intelligent management and control system for cracks in a cement concrete pavement is provided for an embodiment of the present application.

[0013] Explanation of the reference numerals: sensitive switching parameter module 11 , initial reference data module 12 , decision data output module 13 , image data acquisition module 14 , data defect identification module 15 , road surface intelligent management and control module 16 . DETAILED DESCRIPTION

[0014] The overall idea of ​​the technical solution provided by this application is as follows:

[0015] The embodiment of the present application provides an intelligent control method and system for cement concrete pavement cracks, which realizes the full-process intelligent detection and treatment of cement concrete pavement cracks. First, by setting sensitive switching parameters, accurate control of the acquisition sensor is achieved to improve the detection efficiency of pavement cracks; then, various sensor acquisition devices set on the acquisition vehicle are used to build an initial reference data set and image data set to provide data support for subsequent intelligent analysis; then, the decision-making unit is used to realize automatic identification of the location and characteristics of pavement cracks; finally, through matching analysis with pavement archives, corresponding maintenance strategies are formulated to complete the treatment of pavement cracks, effectively solving the technical problem that pavement cracks cannot be intelligently controlled in the existing technology, and achieving intelligent and refined pavement maintenance and management.

[0016] After introducing the basic principles of the present application, various non-limiting implementation methods of the present application will be specifically described below in conjunction with the drawings in the specification.

[0017] Embodiment 1

[0018] like Figure 1 As shown, the embodiment of the present application provides an intelligent control method for cracks in a cement concrete pavement, the method comprising:

[0019] Setting a sensitive switching parameter, wherein the sensitive switching parameter is a switching response parameter for road surface collection, and the sensitive switching parameter is set by collecting basic data of the infrared sensor and the imaging sensor;

[0020] In the embodiment of the present application, the sensitive switching parameter refers to the switching response parameter for collecting images of the road surface, which is used to determine the switching use of the infrared sensor or the imaging sensor, and is determined by the basic sensor data, so that the infrared sensor and the imaging sensor can be actively switched according to the actual road surface conditions to obtain a better road surface image collection effect. Among them, the infrared sensor is an infrared night vision device that can form an infrared image of the road surface in an environment without visible light; the imaging sensor is an image acquisition device that can obtain image information within the visible light range of the road surface.

[0021] First, use imaging sensors and infrared sensors to collect images of the road surface, and obtain basic image data of the two sensors under different light conditions. Secondly, analyze the collected image data to determine the intervals in which the imaging sensor and infrared sensor can each obtain the best image quality under different light intensity ranges. For example, the imaging sensor works well under strong light, and the infrared sensor works well under weak light. Then, based on the best applicable intervals of the two sensors, set the corresponding relationship between the light intensity range and the sensor type as the sensitive switching parameter. In subsequent acquisitions, the sensitive switching parameter is used to determine the best sensor or sensor combination currently in use based on the light intensity.

[0022] By setting sensitive switching parameters, the optimal collaborative working mode of the two sensors can be dynamically determined according to the data acquisition capabilities of the infrared sensor and the image sensor, thereby achieving accurate and efficient collection of road image information.

[0023] The movement of the collection vehicle is controlled by a predetermined speed, and the road surface data is pre-collected by a pre-collection unit to construct an initial reference data set, and the decision unit, the pre-collection unit, the infrared sensor and the imaging sensor are arranged on the collection vehicle and are communicatively connected with each other;

[0024] In the embodiment of the present application, the collection vehicle is a vehicle equipped with a road data collection device, which can travel along the road at a predetermined speed. The pre-collection unit is a road data pre-collection device installed on the vehicle, such as a light sensor, etc., which is used to collect road light intensity data in real time during the vehicle's driving. The decision unit, pre-collection unit, infrared sensor and imaging sensor are all installed on the collection vehicle, and data transmission connection is realized to work together.

[0025] During the road surface data collection process, first, the collection vehicle is controlled to drive steadily at a predetermined speed set according to the actual road surface conditions. At the same time, the pre-collection unit starts to work, collects data such as road surface light in advance, obtains initial road surface data, and constructs an initial reference data set, which contains light intensity information at different locations on the road surface. Since each unit is set on the same vehicle and connected, real-time transmission and sharing of data can be performed. During the collection process, the units are connected to each other through communication, such as 5G network, Bluetooth, wired transmission, etc., to achieve collaborative work such as information exchange and command transmission, which is conducive to the subsequent accurate collection of road surface images.

[0026] Initializing the decision unit through the sensitive switching parameter, inputting the initial reference data set into the decision unit, and outputting decision data;

[0027] Furthermore, this step specifically includes:

[0028] After the initial reference data set is input into the decision unit, a lighting evaluation sub-network is used to perform light evaluation on the initial reference data set;

[0029] generating light intensity evaluation data, and using the light intensity evaluation data as first decision data;

[0030] generating light uniformity evaluation data, and using the light uniformity evaluation data as second decision data;

[0031] The first decision data and the second decision data are sent to the decision unit, and the decision data is output.

[0032] In a feasible implementation, the decision unit is first initialized using predefined sensitive switching parameters, and the parameters are loaded into the unit to configure the decision unit. Secondly, the pre-collected initial reference data set is input into the decision unit to provide road light environment information. When the pre-collected initial reference data set is input into the decision unit, the decision unit will automatically trigger the start of the lighting evaluation subnetwork. This subnetwork is a network module for light analysis set in the decision unit, which is a convolutional neural network that can extract and analyze the light data in the input initial reference data set to perform light evaluation.

[0033] Then, the subnetwork extracts the light intensity value of each road surface collection point in the initial reference data set, determines the light intensity distribution of the entire road surface, and calculates the statistical parameters of the light intensity at different positions on the road surface. Based on these statistical parameters, the light intensity level of the entire road surface corresponding to the initial reference data set is comprehensively evaluated, that is, whether the light intensity is generally sufficient, to form evaluation result data representing the light intensity level. The light intensity evaluation data will be used as the first decision data of the decision unit to determine which image sensor or sensor combination to use for subsequent fine image acquisition.

[0034] At the same time, the lighting evaluation subnetwork detects and evaluates the light uniformity of the initial reference data set. Specifically, the subnetwork analyzes the distribution range and change trend of the light intensity values ​​at each acquisition point on the road surface. If the light intensity changes very little on the entire road surface and is evenly distributed, the light uniformity is evaluated to be good. On the contrary, if the light difference is large, the uniformity is evaluated to be poor. Thus, an evaluation result representing the light uniformity level of the road surface of the initial data set is generated, that is, the light uniformity evaluation data. The evaluation data is used as the second decision data of the decision unit, and is used together with the light intensity evaluation data to determine which image sensor or combination to use for fine acquisition.

[0035] Subsequently, the first decision data and the second decision data are sent to the decision unit together. The decision unit uses an integrated learning algorithm to comprehensively consider the two factors of light intensity and uniformity to perform decision calculations. Among them, the first decision data is the light intensity evaluation result generated by the lighting evaluation subnetwork, which reflects the overall light intensity level of the initial reference data set; the second decision data is the light uniformity evaluation result generated by the subnetwork, which reflects the uniformity of light on the road surface. Finally, the decision unit outputs a set of decision data, which gives the choice of which image sensor or

[0036] Selecting the infrared sensor and / or the imaging sensor to collect image data based on the decision data to construct an image data set;

[0037] Furthermore, this step specifically includes:

[0038] If the decision data is that the imaging sensor works independently, then performing light intensity median calculation on the first decision data;

[0039] The light intensity median calculation result is sent to the imaging sensor as an auxiliary control parameter;

[0040] The auxiliary control parameter is used as a light measurement reference to control the imaging sensor to complete image data acquisition.

[0041] Furthermore, this step also includes:

[0042] If the decision data is for mixed operation with an imaging sensor, a data segmentation instruction is generated;

[0043] Performing two-level data segmentation on the first decision data according to the data segmentation instruction;

[0044] The average value of the high brightness level in the two-level segmentation result is used as an imaging photometry reference, and the average value of the low brightness level in the two-level segmentation result is used as an infrared control reference to control the infrared sensor and the imaging sensor to complete image data acquisition.

[0045] In a preferred embodiment, based on the decision data, it is determined to select an infrared sensor or an imaging sensor to perform image acquisition. When performing image acquisition, in order to obtain more complete and detailed image data, the sensor will scan and collect the road surface at a certain frequency. That is to say, during the movement of the vehicle, the sensor will acquire an image every time a certain distance interval is passed, and there will be a certain overlapping area between two adjacent acquisitions to ensure that they can be spliced ​​into a complete image. Through continuous and frequent acquisition, the sensor acquires multiple sets of image data with a certain degree of repeatability. Finally, these image data containing repeated areas are spliced ​​using image processing algorithms to construct a high-quality image data set with continuous content and rich details.

[0046] First, determine whether the decision data is to enable only the imaging sensor for image acquisition, that is, whether the decision data only contains an instruction to select the imaging sensor to work independently. If so, extract the first decision data, and perform median calculation on the light intensity statistics of the multiple acquisition points contained therein, that is, count the light intensity values ​​of all acquisition points, find the median of these light intensity values, that is, the representative light intensity value between the maximum and minimum values, to provide a basis for the subsequent parameter optimization of the imaging sensor. Then, send the calculated median light intensity as an auxiliary control parameter to the imaging sensor. After receiving the auxiliary control parameter, the imaging sensor uses it as a reference for photometry and configures the exposure time, aperture size and other parameters of the imaging sensor accordingly. Under this parameter configuration, the imaging sensor is controlled to collect image information of the road surface, obtain the best image data under given lighting conditions, and complete image data acquisition.

[0047] If the decision data indicates that the infrared sensor and the imaging sensor should be enabled to work in combination, a data segmentation instruction is generated accordingly, which is used to perform two-level segmentation on the light intensity statistics in the generated first decision data (light intensity evaluation data), that is, to segment them into two data sets of high brightness level and low brightness level. For example, the light intensity evaluation data is clustered into two data clusters using the K-means clustering analysis algorithm. Then, the light intensity average value of the high brightness cluster is calculated as the photometric reference parameter of the imaging sensor; and the light intensity average value of the low brightness cluster is calculated as the control reference parameter of the infrared sensor. Subsequently, the corresponding parameters are sent to the two sensors, and the parameters are configured separately. The imaging sensor uses the high brightness average value for photometric control, and the infrared sensor uses the low brightness average value as a reference for image processing. Finally, the two sensors are controlled simultaneously to perform image acquisition according to their respective optimized parameters to obtain high-quality image data combined with the two.

[0048] Performing defect recognition on the image data set by the decision unit, and recording abnormal coordinates and disease feature sets according to recognition results;

[0049] Further, such as Figure 2 As shown, this step specifically includes:

[0050] If the image data set is a two-layer data set, a segmentation contour line is generated according to the two-level segmentation results to determine a standard image area and an infrared image area;

[0051] Using the calibrated grayscale value of the road surface as the central comparison grayscale, binary comparisons are performed on the standard image area and the infrared image area, respectively, and the abnormal area is determined;

[0052] Performing a convolution kernel traversal of the image on the abnormal area, wherein the convolution kernel is an abnormal convolution kernel constructed by using big data;

[0053] Determine the abnormal coordinates and disease feature set based on the traversal results.

[0054] In a preferred embodiment, a decision unit is used to identify defects in the collected image data set. The decision unit scans and analyzes the image data set position by position to identify various road surface defects such as cracks, potholes, etc. For each abnormal defect identified, its corresponding coordinate position in the image, i.e., abnormal coordinates, is accurately recorded. At the same time, feature information of the defect, such as shape, size, density, etc., is extracted to form a feature set about the defect. This process is repeated to record the coordinates and feature sets corresponding to each abnormality, to complete comprehensive defect identification and feature extraction of the image data set, and the abnormal coordinates and feature set data formed provide a basis for subsequent processing and analysis.

[0055] If the decision unit chooses to use both the infrared sensor and the imaging sensor, the image data set finally obtained will contain two layers of data, namely infrared data and standard image data. In this case, the obtained two-level segmentation results are used to generate a segmentation contour line. This contour line represents the boundary between the infrared image data area and the standard imaging data area. Then, based on the segmentation contour line, the area covered by the infrared data in the image data set, namely the infrared image area, is determined and annotated; at the same time, the standard image area other than the infrared area is annotated. In this way, the two types of areas in the image data are clearly annotated, providing a basis for differential processing of the two types of areas.

[0056] The calibrated grayscale value of the road standard image is pre-set to represent the typical grayscale features of a normal road surface. In addition, since the infrared image and the standard image are different, an independent contrast grayscale value is also set for the infrared image. Subsequently, the calibrated grayscale value of the standard image is used as the central contrast grayscale for abnormal detection in the standard image area. For each point in the standard image area, the difference between its grayscale value and the central contrast grayscale is compared. If the difference exceeds the preset threshold, the point is marked as a candidate abnormal point. For the infrared image area, a similar comparison is performed using the corresponding infrared central contrast grayscale to obtain the abnormal candidate points of the infrared image. The abnormal candidate points of the standard image and the infrared image are combined to form an abnormal area. The difference comparison is performed based on the characteristics of the two types of image data to improve the accuracy of abnormal recognition.

[0057] Next, the constructed abnormal convolution kernel is used to traverse the determined abnormal area to accurately identify the abnormality. The abnormal convolution kernel is an image feature extraction tool constructed by using the convolutional neural network algorithm and a large number of abnormal image samples for training, which can capture the characteristic information of various abnormalities. For the acquired abnormal area, the abnormal convolution kernel is used to traverse it comprehensively and calculate the convolution response value. If the convolution result responds strongly, it is confirmed to be a real abnormality; if the response is weak, it is excluded as a false alarm. Through the accurate identification of the abnormal convolution kernel, a large number of false alarms can be filtered out, and only the real abnormal area is retained, thereby improving the detection accuracy.

[0058] After the convolution kernel traverses the candidate abnormal area, the convolution response analysis results of the abnormal area are obtained. For those areas with strong traversal responses, they are confirmed as real abnormal areas, and the coordinate positions of these abnormal areas in the original image data set are recorded as abnormal coordinates. At the same time, for each confirmed abnormal area, a feature extraction algorithm is used to obtain the specific feature information of its appearance, such as the shape, size, distribution, etc. of the disease, to form a feature set that describes the abnormality. Integrating all the abnormal coordinate information and the corresponding disease feature set realizes the accurate judgment, positioning and feature extraction of the abnormality, laying the foundation for the precise matching of subsequent maintenance strategies.

[0059] The pavement archive is called, and a maintenance strategy is matched through the pavement archive, the abnormal coordinates, and the disease feature set, and intelligent management and control of the pavement is performed according to the matching result.

[0060] Furthermore, the embodiment of the present application also includes:

[0061] Analyze the pavement file to obtain construction record information and environmental record information;

[0062] Using the abnormal coordinates as mapping comparison nodes, performing correlation analysis on the construction record information, environmental record information and disease feature set, and constructing a correlation identifier;

[0063] Maintenance strategy matching is performed using the disease feature set as basic data and the association identifier as constraint data.

[0064] In a preferred embodiment, the pavement archive exists in the form of a structured digital database and is stored in a cloud server. The system accesses the pavement archive database through a high-speed network connection, and sends an access request using the unique identification code of the pavement that needs to be analyzed as a query parameter. After receiving the request, the server searches the database for the pavement archive corresponding to the location based on the pavement identification code, and returns the found pavement archive data to the management and control system via the network connection.

[0065] After receiving the returned pavement archive data, natural language processing technology is used to parse the archive text data, and sentences related to words such as "construction" and "repair" are identified in the text data; similarly, sentences related to words such as "climate", "temperature" and "rainfall" are identified, thereby forming a structured construction record and environmental record data set to provide a basis for subsequent decision-making analysis. Among them, the construction record information is information such as the construction time of the road surface and the content of the road surface repairs that have been carried out; the environmental record information is information such as past climate conditions, temperature changes, and rainfall.

[0066] Subsequently, the damage distribution map formed by the abnormal coordinates is marked on the map, and the construction activity distribution in the construction record is marked on the same map. Next, the image registration algorithm is used to realize the alignment mapping of the two distribution maps, compare the spatial overlap of the two maps, determine the correlation between the damage distribution and the historical construction activities, and perform the association identification of the construction activities on the pavement damage. At the same time, the time distribution of the environmental records is compared with the damage distribution, and the correlation analysis method is used to calculate the correlation coefficient between different factors and the current damage distribution. According to the correlation coefficient, the correlation between the environmental factors and the damage distribution is determined, and the environmental factors are associated with the pavement damage.

[0067] Then, a strategy knowledge base is constructed, in which a large number of encoding vectors of maintenance strategies are pre-stored. The data in the disease feature set is encoded into a structured digital vector as the basic vector input for strategy matching; at the same time, each factor in the association identifier is encoded into a constraint vector. Then, according to the basic vector input, the candidate strategy set closest to it is searched in the strategy vector space, and the candidate set is screened item by item according to the constraints, and the non-compliant strategies are filtered out. Then, the matching degree of each candidate strategy with the basic vector is compared, and the maintenance strategy with the most similar semantics to the basic vector and satisfying the constraints is selected as the best matching result.

[0068] After that, the best matching result is converted into the corresponding maintenance operation instructions, such as which processes need to be carried out, what equipment and materials are used, etc. The maintenance operation instructions are then transmitted to the management and control system. The management system arranges the actual maintenance operations according to the instructions, such as allocating equipment, personnel and purchasing materials. The operators arrive at the designated section with the required equipment and materials for precise maintenance. After the maintenance operation is completed, the operation data is uploaded to the management system to achieve closed-loop control.

[0069] Furthermore, the embodiment of the present application also includes:

[0070] performing outlier analysis based on the disease feature set;

[0071] If there are abnormal values ​​that meet the preset requirements of the disease characteristics, a repeated collection instruction is generated according to the abnormal coordinates corresponding to the disease characteristics;

[0072] The enrichment acquisition is re-executed by the repeat acquisition instruction.

[0073] In a preferred embodiment, an abnormal value detection is performed on the extracted disease feature set to determine whether the feature value has features that meet the preset abnormal conditions, such as abnormal values ​​such as size exceeding the range and atypical shape. If such abnormal features exist, it means that the corresponding position needs to be collected again to obtain richer information. At this time, according to the coordinates corresponding to the abnormal features, a repeated collection instruction for the position is generated. The instruction will be transmitted to the corresponding sensor to repeatedly scan the coordinate position in the instruction. Finally, richer and multi-angle image data is obtained for further decision analysis.

[0074] In summary, the intelligent control method for cement concrete pavement cracks provided in the embodiments of the present application has the following technical effects:

[0075] Set sensitive switching parameters, which are switching response parameters for road surface acquisition. Sensitive switching parameters are set by collecting basic data of infrared sensors and imaging sensors to achieve precise control of sensors and improve detection efficiency. The movement of the acquisition vehicle is controlled by a predetermined speed, and the road surface data is pre-collected by the pre-collection unit to construct an initial reference data set. The decision unit, pre-collection unit, infrared sensor and imaging sensor are set on the acquisition vehicle and communicate with each other to provide basic data for subsequent analysis. The decision unit is initialized by sensitive switching parameters, and the initial reference data set is input into the decision unit, and decision data is output to provide support for controlling the sensor to collect images. Infrared sensors and / or imaging sensors are selected by decision data to collect image data, and image data sets are constructed to provide information for intelligent identification of road surface defects. Defects are identified in the image data set by the decision unit, and abnormal coordinates and disease feature sets are recorded according to the identification results to provide a basis for road surface control. Call up the pavement archive, match the maintenance strategy with the pavement archive, abnormal coordinates, and disease feature sets, and perform intelligent management and control of the pavement based on the matching results, to achieve intelligent management and control of the entire process from collection and detection to governance decision-making, making pavement crack detection and maintenance more intelligent and precise, and improving the quality of cement concrete pavement and driving experience.

[0076] Embodiment 2

[0077] Based on the same inventive concept as the intelligent control method for cement concrete pavement cracks in the aforementioned embodiment, Figure 3 As shown, the embodiment of the present application provides an intelligent management and control system for cracks in cement concrete pavement, the system comprising:

[0078] A sensitive switching parameter module 11 is used to set a sensitive switching parameter, wherein the sensitive switching parameter is a switching response parameter collected for road surface data, and the sensitive switching parameter is set by collecting basic data of infrared sensors and imaging sensors;

[0079] The initial reference data module 12 is used to control the movement of the collection vehicle by a predetermined speed, and to pre-collect the road surface data by a pre-collection unit to construct an initial reference data set, and the decision unit, the pre-collection unit, the infrared sensor and the imaging sensor are arranged on the collection vehicle and are in communication connection with each other;

[0080] A decision data output module 13, configured to initialize the decision unit through the sensitive switching parameter, input the initial reference data set into the decision unit, and output decision data;

[0081] An image data acquisition module 14 is used to select the infrared sensor and / or the imaging sensor to acquire image data according to the decision data, and to construct an image data set;

[0082] A data defect recognition module 15, configured to perform defect recognition on the image data set through the decision unit, and record abnormal coordinates and a disease feature set according to the recognition result;

[0083] The pavement intelligent management and control module 16 is used to call the pavement archive, match the maintenance strategy through the pavement archive, the abnormal coordinates, and the disease feature set, and perform intelligent management and control of the pavement according to the matching result.

[0084] Furthermore, the decision data output module 13 includes the following execution steps:

[0085] After the initial reference data set is input into the decision unit, a lighting evaluation sub-network is used to perform light evaluation on the initial reference data set;

[0086] generating light intensity evaluation data, and using the light intensity evaluation data as first decision data;

[0087] generating light uniformity evaluation data, and using the light uniformity evaluation data as second decision data;

[0088] The first decision data and the second decision data are sent to the decision unit, and the decision data is output.

[0089] Furthermore, the decision data output module 13 also includes the following execution steps:

[0090] Determining whether the decision data is for the imaging sensor to work independently;

[0091] If the decision data is that the imaging sensor works independently, then performing light intensity median calculation on the first decision data;

[0092] The light intensity median calculation result is sent to the imaging sensor as an auxiliary control parameter;

[0093] The auxiliary control parameter is used as a light measurement reference to control the imaging sensor to complete image data acquisition.

[0094] Furthermore, the decision data output module 13 also includes the following execution steps:

[0095] If the decision data is for mixed operation with an imaging sensor, a data segmentation instruction is generated;

[0096] Performing two-level data segmentation on the first decision data according to the data segmentation instruction;

[0097] The average value of the high brightness level in the two-level segmentation result is used as an imaging photometry reference, and the average value of the low brightness level in the two-level segmentation result is used as an infrared control reference to control the infrared sensor and the imaging sensor to complete image data acquisition.

[0098] Furthermore, the data defect identification module 15 includes the following execution steps:

[0099] If the image data set is a two-layer data set, a segmentation contour line is generated according to the two-level segmentation results to determine a standard image area and an infrared image area;

[0100] Using the calibrated grayscale value of the road surface as the central comparison grayscale, binary comparisons are performed on the standard image area and the infrared image area, respectively, and the abnormal area is determined;

[0101] Performing a convolution kernel traversal of the image on the abnormal area, wherein the convolution kernel is an abnormal convolution kernel constructed by using big data;

[0102] Determine the abnormal coordinates and disease feature set based on the traversal results.

[0103] Furthermore, the road intelligent management and control module 16 includes the following execution steps:

[0104] Analyze the pavement file to obtain construction record information and environmental record information;

[0105] Using the abnormal coordinates as mapping comparison nodes, performing correlation analysis on the construction record information, environmental record information and disease feature set, and constructing a correlation identifier;

[0106] Maintenance strategy matching is performed using the disease feature set as basic data and the association identifier as constraint data.

[0107] Furthermore, the embodiment of the present application also includes a repeated acquisition instruction module, which includes the following execution steps:

[0108] performing outlier analysis based on the disease feature set;

[0109] If there are abnormal values ​​that meet the preset requirements of the disease characteristics, a repeated collection instruction is generated according to the abnormal coordinates corresponding to the disease characteristics;

[0110] The enrichment acquisition is re-executed by the repeat acquisition instruction.

[0111] Any step of the method described above can be stored as a computer instruction or program in an unlimited computer memory, and can be called and recognized by an unlimited computer processor to implement any method in the embodiments of the present application, without any unnecessary restrictions.

[0112] Furthermore, the first or second mentioned above may not only represent an order relationship, but may also represent a specific concept, and / or refer to multiple elements that can be selected individually or in full. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. An intelligent control method for cement concrete pavement cracks, characterized in that: The method comprises: Setting a sensitive switching parameter, wherein the sensitive switching parameter is a switching response parameter for road surface collection, and the sensitive switching parameter is set by collecting basic data of the infrared sensor and the imaging sensor; The movement of the collection vehicle is controlled by a predetermined speed, and the road surface data is pre-collected by a pre-collection unit to construct an initial reference data set, and the decision unit, the pre-collection unit, the infrared sensor and the imaging sensor are arranged on the collection vehicle and are communicatively connected with each other; Initializing the decision unit through the sensitive switching parameter, inputting the initial reference data set into the decision unit, and outputting decision data; Selecting the infrared sensor and / or the imaging sensor to collect image data based on the decision data to construct an image data set; Perform defect recognition on the image data set by the decision unit, and record abnormal coordinates and disease feature sets according to the recognition results; The pavement archive is called, and a maintenance strategy is matched through the pavement archive, the abnormal coordinates, and the disease feature set, and intelligent management and control of the pavement is performed according to the matching result.

2. The method according to claim 1, characterized in that The method further comprises: After the initial reference data set is input into the decision unit, a lighting evaluation sub-network is used to perform light evaluation on the initial reference data set; generating light intensity evaluation data, and using the light intensity evaluation data as first decision data; generating light uniformity evaluation data, and using the light uniformity evaluation data as second decision data; The first decision data and the second decision data are sent to the decision unit, and the decision data is output.

3. The method according to claim 2, characterized in that The method further comprises: Determining whether the decision data is for the imaging sensor to work independently; If the decision data is that the imaging sensor works independently, then performing light intensity median calculation on the first decision data; The light intensity median calculation result is sent to the imaging sensor as an auxiliary control parameter; The auxiliary control parameter is used as a light measurement reference to control the imaging sensor to complete image data acquisition.

4. The method according to claim 3, characterized in that The method further comprises: If the decision data is for mixed operation with an imaging sensor, a data segmentation instruction is generated; Performing two-level data segmentation on the first decision data according to the data segmentation instruction; The average value of the high brightness level in the two-level segmentation result is used as an imaging photometry reference, and the average value of the low brightness level in the two-level segmentation result is used as an infrared control reference to control the infrared sensor and the imaging sensor to complete image data acquisition.

5. The method according to claim 4, characterized in that The method further comprises: If the image data set is a two-layer data set, a segmentation contour line is generated according to the two-level segmentation results to determine a standard image area and an infrared image area; Using the calibrated grayscale value of the road surface as the central comparison grayscale, binary comparisons are performed on the standard image area and the infrared image area, respectively, and the abnormal area is determined; Performing a convolution kernel traversal of the image on the abnormal area, wherein the convolution kernel is an abnormal convolution kernel constructed by using big data; Determine the abnormal coordinates and disease feature set based on the traversal results.

6. The method according to claim 1, characterized in that The method further comprises: Analyze the pavement file to obtain construction record information and environmental record information; Using the abnormal coordinates as mapping comparison nodes, performing correlation analysis on the construction record information, environmental record information and disease feature set, and constructing a correlation identifier; Maintenance strategy matching is performed using the disease feature set as basic data and the association identifier as constraint data.

7. The method according to claim 1, characterized in that The method further comprises: performing outlier analysis based on the disease feature set; If there are abnormal values ​​that meet the preset requirements of the disease characteristics, a repeated collection instruction is generated according to the abnormal coordinates corresponding to the disease characteristics; The enrichment acquisition is re-executed by the repeat acquisition instruction.

8. An intelligent management and control system for cement concrete pavement cracks, characterized in that: A method for intelligently controlling cracks in a cement concrete pavement according to any one of claims 1 to 7, the method comprising: A sensitive switching parameter module, which is used to set sensitive switching parameters, which are switching response parameters collected from road surfaces, and which are set by collecting basic data from infrared sensors and imaging sensors; An initial reference data module, which is used to control the movement of the collection vehicle by a predetermined speed, and to pre-collect road surface data by a pre-collection unit to construct an initial reference data set, and the decision unit, the pre-collection unit, the infrared sensor and the imaging sensor are arranged on the collection vehicle and are in communication connection with each other; A decision data output module, the decision data output module is used to initialize the decision unit through the sensitive switching parameter, input the initial reference data set into the decision unit, and output decision data; An image data acquisition module, wherein the image data acquisition module is used to select the infrared sensor and / or the imaging sensor to acquire image data according to the decision data, and to construct an image data set; A data defect recognition module, the data defect recognition module is used to identify defects in the image data set through the decision unit, and record abnormal coordinates and disease feature sets according to the recognition results; The pavement intelligent management and control module is used to call the pavement archive, match the maintenance strategy through the pavement archive, the abnormal coordinates, and the disease feature set, and perform intelligent management and control of the pavement according to the matching result.

Images