Highway dense fog grading identification method and device, terminal and storage medium

Abstract

The invention discloses an expressway dense fog grading identification method and device, a terminal and a storage medium in the technical field of traffic meteorology, and aims to solve the problem of low fine degree of dense fog grading early warning caused by sparse monitoring density of traffic meteorological station networks and video monitoring points along an expressway in the prior art. The method comprises the following steps: acquiring the visibility level of each unit by using an optimal interpolation method according to unitized highway network information, the visibility level of each traffic weather station and the visibility level of each video monitoring point; acquiring a data set according to the visibility level of each unit; according to the method, the visibility level of each unit is obtained by using the optimal interpolation method, so that the highway dense fog classification accurate identification is realized under the condition that the traffic weather station and the video monitoring point are insufficient in density, and a reference is provided for the safe operation scheduling and management and control of the highway.

Description

Technical Field

[0001] The present invention relates to a method, device, terminal and storage medium for classifying and identifying thick fog on expressways, and belongs to the technical field of traffic meteorology. Background Art

[0002] An expressway, also known as a highway, is a road specifically designed for high-speed vehicle travel. Due to the high-speed travel of vehicles on expressways, it is necessary to monitor meteorological factors that may affect vehicle traffic on expressways. With the rapid expansion of the expressway network, the problem of traffic safety under complex meteorological conditions has become increasingly prominent. Thick fog weather, characterized by a sudden drop in visibility and strong suddenness, has become the main cause of serious accidents such as multi-vehicle chain-rear-end collisions. Usually, traffic meteorological stations and video monitoring points along the expressway are required to monitor thick fog.

[0003] In the prior art, due to the sparse monitoring density of the traffic meteorological station network and video monitoring points along the expressway, it is impossible to support refined thick fog classification and early warning, resulting in low refinement of thick fog classification and early warning, which affects the safe operation, dispatching and control of expressways. Summary of the Invention

[0004] The purpose of the present invention is to overcome the deficiencies in the prior art and provide a method, device, terminal and storage medium for classifying and identifying thick fog on expressways, which fully utilize the expressway network information, traffic meteorological station information and video monitoring point information along the expressway, and use the optimal interpolation method to obtain the visibility level of each unit, so as to achieve accurate identification of thick fog classification on expressways in the case of insufficient density of traffic meteorological stations and video monitoring points, and provide a reference for the safe operation, dispatching and control of expressways.

[0005] To solve the above technical problems, the present invention is implemented by the following technical solutions: In a first aspect, the present invention provides a method for classifying and identifying thick fog on expressways, including the following steps: Obtain expressway network information; Unitize the expressway network information to obtain the unitized expressway network information; wherein, the unitized expressway network information includes multiple units; According to the expressway network information, obtain the traffic meteorological station information and video monitoring point information along the expressway; According to the information of each traffic meteorological station, obtain the visibility level of each traffic meteorological station; According to the information of each video monitoring point, obtain pictures of each video monitoring point, input the pictures of the video monitoring points into a pre-constructed and trained hybrid model, and output the visibility level of each video monitoring point; According to the unitized highway network information, the visibility levels of each traffic meteorological station, and the visibility levels of each video surveillance point, the visibility level of each unit is obtained by using the optimal interpolation method; According to the visibility levels of each unit, a data set is obtained; Based on a preset filling scheme, the data set is filled to obtain a highway thick fog grading early warning map, and the highway thick fog grading recognition work is completed.

[0006] Further, the highway network information includes the longitude and latitude of the highway network and the starting point and ending point of the highway network. According to the starting point and ending point of the highway network, the mileage of the highway network is obtained.

[0007] Further, the unitization of the highway network information to obtain the unitized highway network information specifically includes: According to the starting point and ending point of the highway network, the highway network information is unitized at preset intervals by using Arcgis software to obtain multiple units.

[0008] Further, the obtaining of the visibility level of each traffic meteorological station according to each traffic meteorological station information specifically includes: According to each traffic meteorological station information, the visibility of each traffic meteorological station is obtained; Based on the visibility grading standard, the visibility level of each traffic meteorological station is obtained according to the visibility of each traffic meteorological station.

[0009] Further, the hybrid model is a hybrid model of a convolutional neural network and a transformer.

[0010] Further, the obtaining of the visibility level of each unit by using the optimal interpolation method specifically includes: Obtain the actual visibility data within the preset grid points; According to the actual visibility data within the preset grid points, obtain the visibility grid point values; According to the unitized highway network information, the traffic meteorological station information along the highway, and the video surveillance point information, use the bilinear interpolation method to interpolate the visibility grid point values to each unit, each traffic meteorological station, and each video surveillance point; Let the initial estimated value of the visibility grid point values interpolated to each unit, each traffic meteorological station, and each video surveillance point be graded as ; Judge whether there is a traffic meteorological station or a video surveillance point within the unit. If so, use the visibility level of this traffic meteorological station or the visibility level of this video surveillance point as the visibility level of this unit; If it does not exist, calculate the visibility level of this unit through the following formula: ; ; In the formula: is the output result; is the floor operation; is the visibility level of this unit; W is the preset weight; is the visibility level of the traffic meteorological station or the visibility level of the video surveillance point closest to this unit in the starting direction of the highway road network; is the visibility level of the traffic meteorological station or the visibility level of the video surveillance point closest to this unit in the ending direction of the highway road network; The acquisition specifically includes: According to the highway road network information, obtain the location information of each unit; According to the location information of each unit, the traffic meteorological station information along the highway, and the video surveillance point information, obtain the traffic meteorological station information or the video surveillance point information closest to this unit in the starting direction of the highway road network; According to the traffic meteorological station information or the video surveillance point information, obtain the visibility level of the corresponding traffic meteorological station or the visibility level of the corresponding video surveillance point; The acquisition specifically includes: According to the location information of each unit, the traffic meteorological station information along the highway, and the video surveillance point information, obtain the traffic meteorological station information or the video surveillance point information closest to this unit in the ending direction of the highway road network; According to the traffic meteorological station information or the video surveillance point information, obtain the visibility level of the corresponding traffic meteorological station or the visibility level of the corresponding video surveillance point.

[0011] Furthermore, the obtaining of the data set according to the visibility level of each unit specifically includes: According to the unitized highway road network information and the starting point and ending point of the highway road network, arrange the visibility levels of each unit in sequence to obtain the data set; The filling of the data set based on the preset filling scheme specifically includes: The preset filling scheme includes multiple colors corresponding one-to-one to the visibility level; According to the visibility level of each unit, fill the unit with the color corresponding to the visibility level.

[0012] Second aspect, the present invention provides a freeway heavy fog grading and recognition device, specifically including: Collection module: used to obtain freeway road network information; Unitization module: used to unitize the freeway road network information to obtain the unitized freeway road network information; wherein, the unitized freeway road network information includes multiple units; First calculation module: used to obtain traffic meteorological station information and video monitoring point information along the freeway according to the freeway road network information; obtain the visibility level of each traffic meteorological station according to each traffic meteorological station information; obtain pictures of each video monitoring point according to each video monitoring point information, input the pictures of the video monitoring points into a pre-constructed and trained hybrid model, and output the visibility level of each video monitoring point; Second calculation module: used to obtain the visibility level of each unit by using the optimal interpolation method according to the unitized freeway road network information, the visibility level of each traffic meteorological station, and the visibility level of each video monitoring point; Recognition module: used to obtain a data set according to the visibility level of each unit; fill the data set based on a preset filling scheme to obtain a freeway heavy fog grading early warning map, and complete the freeway heavy fog grading and recognition work.

[0013] Third aspect, the present invention provides a terminal, including a processor and a storage medium; The storage medium is used to store instructions; The processor is used to operate according to the instructions to execute the steps of the method according to the first aspect.

[0014] Fourth aspect, a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, it implements the steps of the method according to the first aspect.

[0015] Compared with the prior art, the beneficial effects achieved by the present invention: This freeway heavy fog grading and recognition method makes full use of the freeway road network information, the traffic meteorological station information along the freeway, and the video monitoring point information, and uses the optimal interpolation method to obtain the visibility level of each unit, so as to realize the accurate recognition of freeway heavy fog grading in the case of insufficient density of traffic meteorological stations and video monitoring points, and provide a reference for the safe operation scheduling and control of freeways. Description of the drawings

[0016] Figure 1 is a flowchart of a freeway heavy fog grading and recognition method provided according to an embodiment of the present invention; Figure 2It is a schematic flowchart of a freeway thick fog grading recognition device provided according to an embodiment of the present invention; Figure 3 It is a structural diagram of the cTrans-Net network model provided according to an embodiment of the present invention; Figure 4 It is a freeway thick fog grading early warning map of the dataset provided according to an embodiment of the present invention. Detailed implementation manners

[0017] The technical solution of the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific features in the embodiments of the present invention are detailed descriptions of the technical solution of the present invention, rather than limitations on the technical solution of the present invention. Without conflict, the technical features in the embodiments of the present invention and the embodiments can be combined with each other.

[0018] The term "and / or" is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " generally represents an "or" relationship between the associated objects before and after. Embodiment 1:

[0019] As Figure 1 shown, the present invention provides a freeway thick fog grading recognition method, including the following steps: Obtain freeway road network information; Among them, the freeway road network information includes the longitude and latitude of the freeway road network and the starting point and ending point of the freeway road network. According to the starting point and ending point of the freeway road network, the mileage of the freeway road network is obtained.

[0020] Unitize the freeway road network information to obtain the unitized freeway road network information; among them, the unitized freeway road network information includes multiple units; According to the freeway road network information, obtain the traffic meteorological station information and video monitoring point information along the freeway; According to the information of each traffic meteorological station, obtain the visibility level of each traffic meteorological station; According to the information of each video monitoring point, obtain the pictures of each video monitoring point, and input the pictures of the video monitoring points into a pre-constructed and trained hybrid model to output the visibility level of each video monitoring point; According to the unitized freeway road network information, the visibility levels of each traffic meteorological station and the visibility levels of each video monitoring point, use the optimal interpolation method to obtain the visibility level of each unit; According to the visibility levels of each unit, obtain a dataset; Based on a preset filling scheme, fill the dataset to obtain a freeway thick fog grading warning map, and complete the freeway thick fog grading recognition work.

[0021] In one embodiment, unitize the freeway road network information to obtain the unitized freeway road network information, which specifically includes: According to the starting point and ending point of the freeway road network, use Arcgis software to unitize the freeway road network information at preset intervals to obtain multiple units.

[0022] Specifically, take the starting point of the freeway as S0 and the first integer mileage point as the initial point S1. Use Arcgis software to unitize each freeway at an interval of 1 KM. If the freeway is n KM long, start from the freeway starting point and label each unit in sequence as S1, S2, S3... Sn. According to the obtained freeway road network information, the specific location information of each unit can be obtained.

[0023] In one embodiment, to obtain the visibility level of each traffic meteorological station according to the information of each traffic meteorological station, it specifically includes: Obtain the visibility of each traffic meteorological station according to the information of each traffic meteorological station; Based on the visibility grading standard, obtain the visibility level of each traffic meteorological station according to the visibility of each traffic meteorological station, so that the visibility level of each traffic meteorological station corresponds to the respective traffic meteorological station information.

[0024] Specifically, the visibility grading standard is shown in Table 1:

[0025] In one embodiment, according to the information of each video monitoring point, obtain the pictures of each video monitoring point, and input the pictures of the video monitoring points into a pre-constructed and trained hybrid model, and output the visibility level of each video monitoring point. The hybrid model is a hybrid model of a convolutional neural network and a transformer.

[0026] Specifically, collect the video monitoring pictures along the freeway to construct a dataset for model training and testing. The historical data is graded and labeled according to the traffic station observation data. Normalize the video monitoring pictures, utilize the ability of the convolutional neural network (CNN) to learn local features and the ability of the Transformer (a neural network architecture based on self-attention mechanism) to learn global features, build a CNN + Transformer hybrid model (cTrans-Net), and use the hybrid model to carry out visibility grading recognition.

[0027] An embodiment, wherein the visibility level of each unit is obtained by using the optimal interpolation method, specifically including: Obtain the actual visibility data within the preset grid points; wherein, the preset grid points are 5*5KM grid points; Obtain the visibility grid point values according to the actual visibility data within the preset grid points; According to the unitized highway road network information, highway along - line traffic meteorological station information, and video monitoring point information, use the bilinear interpolation method to interpolate the visibility grid point values to each unit, each traffic meteorological station, and each video monitoring point; Let the initial estimated values of the visibility grid point values interpolated to each unit, each traffic meteorological station, and each video monitoring point be classified as ; Judge whether there is a traffic meteorological station or a video monitoring point within the unit. If so, use the visibility level of this traffic meteorological station or the visibility level of this video monitoring point as the visibility level of this unit; If not, calculate the visibility level of this unit through the following formula: ; ; In the formula: is the output result; is the floor operation; is the visibility level of this unit; W is the preset weight; is the visibility level of the traffic meteorological station or the visibility level of the video monitoring point closest to this unit in the starting - point direction of the highway road network; is the visibility level of the traffic meteorological station or the visibility level of the video monitoring point closest to this unit in the ending - point direction of the highway road network; The obtaining specifically includes: Obtain the location information of each unit according to the highway road network information; According to the location information of each unit, highway along - line traffic meteorological station information, and video monitoring point information, obtain the information of the traffic meteorological station or the video monitoring point closest to this unit in the starting - point direction of the highway road network; According to the traffic meteorological station information or the video monitoring point information, obtain the visibility level of the corresponding traffic meteorological station or the visibility level of the corresponding video monitoring point; The obtaining specifically includes: According to the location information of each unit, the traffic meteorological station information along the highway, and the video surveillance point information, obtain the traffic meteorological station information or video surveillance point information closest to the end direction of the highway road network from this unit; According to the traffic meteorological station information or video surveillance point information, obtain the visibility level of the corresponding traffic meteorological station or the visibility level of the corresponding video surveillance point.

[0028] An embodiment, the obtaining of the data set according to the visibility level of each unit specifically includes: According to the unitized highway road network information, the starting point and the end point of the highway road network, arrange the visibility levels of each unit in sequence to obtain a data set; The filling of the data set based on a preset filling scheme specifically includes: The preset filling scheme includes a variety of colors corresponding one-to-one with the visibility level; According to the visibility level of each unit, fill the unit with the color corresponding to the visibility level.

[0029] Specifically, using the data set, fill the colors according to the road network unit levels. The road network cells with a visibility of level 0 are filled with red, the road network cells with a visibility of level 1 are filled with orange, the road network cells with a visibility of level 2 are filled with yellow, the road network cells with a visibility of level 3 are filled with blue, and the road network cells with a visibility of level 4 do not need to be filled, completing the color filling work of each unit, thereby realizing the hierarchical recognition of heavy fog on the highway.

[0030] An embodiment, obtain the longitude and latitude information of a certain highway within the jurisdiction, with the starting mileage being K1508 and the ending mileage being K1630. Take K1508 as the starting point S0 of the highway, and the mileage of the first integer mileage point as the initial point S1 is K1509. Use Arcgis software to unitize each highway at an interval of 1 KM. The length of the highway is 122 KM. Starting from the starting point of the highway, each unit is sequentially marked as S1, S2, S3... Sn; Obtain the information of 4 traffic meteorological stations and 8 video surveillance points along the highway; According to the information of each traffic meteorological station, obtain the visibility level of each traffic meteorological station; According to the information of each video surveillance point, obtain the pictures of each video surveillance point, input the pictures of the video surveillance points into a pre-constructed and trained hybrid model, and output the visibility level of each video surveillance point; After evaluation, the cTrans-Net model, such as Figure 3As described above, the accuracy (Acc) is 0.8917, the recall rate (Rec) is 0.8947, the precision rate (Pre) is 0.8942, the area under the receiver operating characteristic curve (AUC) is 0.9822, and the F1 score is 0.8942, indicating that cTrans-Net can not only accurately identify positive samples, but also effectively distinguish positive and negative samples, with high comprehensive classification ability; the recognition accuracy of the visibility levels L0-4 of the test samples is 92.31% for L0, 85.97% for L1, 90.66% for L2, 87.95% for L3, and 90.45% for L4, indicating that cTrans-Net can achieve accurate classification of different samples.

[0031] Use the cTrans-Net model to output the pictures of all video monitoring points along the highway at a certain moment. The classification recognition results of the video pictures are shown in Table 2:

[0032] Then use the optimal interpolation method to obtain the visibility levels of each unit. According to the visibility levels of each unit, obtain a data set. The visibility levels of each unit are shown in Table 3:

[0033] Finally, based on the preset filling scheme, fill the data set to obtain a highway heavy fog classification warning map, and complete the highway heavy fog classification recognition work, as Figure 4 shown.

[0034] The present invention makes full use of the highway road network information, the traffic meteorological station information along the highway, and the video monitoring point information, and uses the optimal interpolation method to obtain the visibility levels of each unit, so as to achieve accurate recognition of highway heavy fog classification in the case of insufficient density of traffic meteorological stations and video monitoring points, and provide a reference for the safe operation scheduling and control of highways. Embodiment 2:

[0035] As Figure 2 shown, the present invention provides a highway heavy fog classification recognition device, which specifically includes: Acquisition module: used to obtain highway road network information; Unitization module: used to unitize the highway road network information to obtain the unitized highway road network information; wherein, the unitized highway road network information includes multiple units; The first calculation module: is used to obtain traffic meteorological station information and video monitoring point information along the highway according to the highway road network information; obtain the visibility levels of each traffic meteorological station according to each traffic meteorological station information; obtain pictures of each video monitoring point according to each video monitoring point information, input the pictures of the video monitoring points into a pre-constructed and trained hybrid model, and output the visibility levels of each video monitoring point; The second calculation module: is used to obtain the visibility level of each unit by using the optimal interpolation method according to the unitized highway road network information, the visibility levels of each traffic meteorological station, and the visibility levels of each video monitoring point; The recognition module: is used to obtain a data set according to the visibility levels of each unit; fill the data set based on a preset filling scheme to obtain a highway thick fog grading early warning map, and complete the highway thick fog grading recognition work. Embodiment 3:

[0036] An embodiment of the present invention further provides a terminal, including a processor and a storage medium; The storage medium is used to store instructions; The processor is used to operate according to the instructions to execute the steps of the method described in Embodiment 1. Embodiment 4:

[0037] An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, it implements the steps of the method described in Embodiment 1.

[0038] Since the storage medium provided by the embodiment of the present invention can execute the method provided by Embodiment 1 of the present invention, it has the corresponding functional modules and beneficial effects of the execution method.

[0039] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0040] This application is described with reference to the flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processors of general-purpose computers, special-purpose computers, embedded processors, or other programmable data processing devices to generate a machine, such that the instructions executed by the processors of the computer or other programmable data processing devices produce means for implementing the functions specified in the flow Figure 1 one or more flows and / or blocks Figure 1 or means for implementing the functions specified in a block or multiple blocks.

[0041] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufactured article including instruction means that implement the functions specified in the flow Figure 1 one or more flows and / or blocks Figure 1 or means for implementing the functions specified in a block or multiple blocks.

[0042] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operating steps are executed on the computer or other programmable device to generate a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in the flow Figure 1 one or more flows and / or blocks Figure 1 or means for implementing the functions specified in a block or multiple blocks.

[0043] The above is only the preferred embodiment of the present invention. It should be noted that for those of ordinary skill in the art of the present technology, without departing from the technical principle of the present invention, several improvements and modifications can be made, and these improvements and modifications should also be regarded as the protection scope of the present invention.

Claims

1. A method for classifying and identifying thick fog on expressways, characterized in that, Including the following steps: Obtain the expressway road network information; Unitize the expressway road network information to obtain the unitized expressway road network information; wherein, the unitized expressway road network information includes multiple units; According to the expressway road network information, obtain the traffic meteorological station information and video monitoring point information along the expressway; According to the information of each traffic meteorological station, obtain the visibility level of each traffic meteorological station; According to the information of each video monitoring point, obtain the pictures of each video monitoring point, input the pictures of the video monitoring points into a pre-constructed and trained hybrid model, and output the visibility level of each video monitoring point; According to the unitized expressway road network information, the visibility levels of each traffic meteorological station and the visibility levels of each video monitoring point, use the optimal interpolation method to obtain the visibility level of each unit; According to the visibility levels of each unit, obtain a data set; Based on a preset filling scheme, fill the data set to obtain an expressway thick fog grading early warning map, and complete the expressway thick fog grading recognition work.

2. The freeway thick fog grading and recognition method according to claim 1, characterized in that, The expressway road network information includes the longitude and latitude of the expressway road network and the starting point and ending point of the expressway road network. According to the starting point and ending point of the expressway road network, obtain the mileage of the expressway road network.

3. The freeway heavy fog grading and recognition method according to claim 2, characterized in that The unitization of the expressway road network information to obtain the unitized expressway road network information specifically includes: According to the starting point and ending point of the expressway road network, use Arcgis software to unitize the expressway road network information at preset intervals to obtain multiple units.

4. The freeway heavy fog grading and recognition method according to claim 1, characterized in that The obtaining of the visibility level of each traffic meteorological station according to the information of each traffic meteorological station specifically includes: According to the information of each traffic meteorological station, obtain the visibility of each traffic meteorological station; Based on the visibility grading standard, according to the visibility of each traffic meteorological station, obtain the visibility level of each traffic meteorological station.

5. The freeway thick fog grading and recognition method according to claim 1, wherein The hybrid model is a hybrid model of a convolutional neural network and a transformer.

6. The freeway thick fog grading and recognition method according to claim 1, characterized in that The obtaining of the visibility level of each unit by using the optimal interpolation method specifically includes: Obtain the visibility actual situation data within the preset grid points; According to the visibility actual situation data within the preset grid points, obtain the visibility grid point values; According to the unitized expressway road network information, the traffic meteorological station information along the expressway and the video monitoring point information, use the bilinear interpolation method to interpolate the visibility grid point values to each unit, each traffic meteorological station and each video monitoring point; The initial estimated values of visibility grid points inserted into each unit, each traffic meteorological station, and each video monitoring point are classified as ; Judge whether there is a traffic meteorological station or a video monitoring point within the unit. If so, use the visibility level of this traffic meteorological station or the visibility level of this video monitoring point as the visibility level of this unit; If not, calculate the visibility level of this unit through the following formula: ； ； Wherein: is the output result; is the floor operation; is the visibility level of this unit; W is the preset weight; is the visibility level of the traffic meteorological station or the visibility level of the video monitoring point closest to this unit in the starting direction of the highway road network; is the visibility level of the traffic meteorological station or the visibility level of the video monitoring point closest to this unit in the ending direction of the highway road network; The said obtaining specifically includes: According to the expressway road network information, obtain the position information of each unit; According to the position information of each unit, the traffic meteorological station information along the expressway and the video monitoring point information, obtain the traffic meteorological station information or video monitoring point information closest to this unit in the starting point direction of the expressway road network; Obtain the visibility level of the corresponding traffic meteorological station or the visibility level of the corresponding video surveillance point according to the traffic meteorological station information or video surveillance point information; The said obtaining specifically includes: Obtain the traffic meteorological station information or video surveillance point information of the traffic meteorological station closest to this unit in the end direction of the highway road network according to the location information of each unit, the traffic meteorological station information along the highway, and the video surveillance point information; Obtain the visibility level of the corresponding traffic meteorological station or the visibility level of the corresponding video surveillance point according to the traffic meteorological station information or video surveillance point information.

7. The freeway heavy fog grading and recognition method according to claim 2, wherein The obtaining of the data set according to the visibility level of each unit specifically includes: Arrange the visibility levels of each unit in sequence according to the unitized highway road network information and the starting point and ending point of the highway road network to obtain a data set; The filling of the data set based on a preset filling scheme specifically includes: The preset filling scheme includes multiple colors corresponding one-to-one to the visibility levels; Fill the unit with the color corresponding to the visibility level according to the visibility level of each unit.

8. An expressway thick fog grading recognition device, characterized in that, Specifically includes: Acquisition module: used to obtain highway road network information; Unitization module: used to unitize the highway road network information to obtain unitized highway road network information; wherein, the unitized highway road network information includes multiple units; First calculation module: used to obtain traffic meteorological station information and video surveillance point information along the highway according to the highway road network information; obtain the visibility level of each traffic meteorological station according to each traffic meteorological station information; obtain pictures of each video surveillance point according to each video surveillance point information, and input the video surveillance point pictures into a pre-constructed and trained hybrid model to output the visibility level of each video surveillance point; Second calculation module: used to obtain the visibility level of each unit by using the optimal interpolation method according to the unitized highway road network information, the visibility level of each traffic meteorological station, and the visibility level of each video surveillance point; Recognition module: used to obtain a data set according to the visibility level of each unit; fill the data set based on a preset filling scheme to obtain a highway thick fog grading early warning map, and complete the highway thick fog grading recognition work.

9. A terminal, characterized in that, Includes a processor and a storage medium; The storage medium is used to store instructions; The processor is used to operate according to the instructions to execute the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images