An intelligent reflective signboard system based on adaptive light regulation

Abstract

The present application relates to a kind of intelligent reflectorized sign based on adaptive light regulation, it is related to the technical field of the accessory of road.The system includes: meteorological sensor, road surface sensor, optical perception module, light regulation module are connected with processor communication, the processor is used to execute the following steps: meteorological data, road surface data, optical data are respectively obtained by the meteorological sensor, the road surface sensor, the optical perception module;According to the meteorological data, the road surface data, the optical data determine the risk prediction result of current road;According to the risk prediction result, the meteorological data and the road surface data determine the display brightness, display chroma of intelligent reflectorized sign;Display brightness, display chroma are transmitted to the light regulation module, so that light regulation module according to the display brightness, the display chroma control the brightness and chroma of the intelligent reflectorized sign.

Description

Technical Field

[0001] This invention relates to the field of road ancillary facilities technology, and in particular to an intelligent reflective sign system based on adaptive light control. Background Technology

[0002] Traffic signs are road facilities that use text or symbols to convey guidance, restrictions, warnings, and instructions. Most traffic signs are reflective, allowing them to be seen by people at a greater distance. They serve to manage traffic, indicate driving directions, and provide traffic information, ensuring smooth traffic flow and driving safety. At the same time, due to their simplicity, clarity, and eye-catching advantages, they have been widely used on highways, urban roads, and all special-purpose roads.

[0003] Currently, traffic signs are fixed and cannot be adaptively adjusted according to weather, traffic conditions, etc., resulting in poor display quality. Summary of the Invention

[0004] The present invention aims to provide an intelligent reflective sign system based on adaptive light control to overcome the shortcomings of the existing technology. The technical problem to be solved by the present invention is achieved through the following technical solution.

[0005] This invention provides an intelligent reflective sign system based on adaptive light control. The system includes: a weather sensor, a road surface sensor, an optical sensing module, and a light control module, all communicatively connected to a processor. The processor is used to perform the following steps:

[0006] Meteorological data, road surface data, and optical data are acquired through the meteorological sensor, the road surface sensor, and the optical sensing module, respectively.

[0007] The risk prediction result for the current road is determined based on the meteorological data, the road surface data, and the optical data; the risk prediction result is used to indicate the risk level of the current road.

[0008] The display brightness and color of the intelligent reflective sign are determined based on the risk prediction results, the meteorological data, and the road surface data.

[0009] The display brightness and display chromaticity are transmitted to the light control module, so that the light control module controls the brightness and chromaticity of the smart reflective sign according to the display brightness and display chromaticity.

[0010] In an optional embodiment, determining the current road risk prediction result based on the meteorological data, the road surface data, and the optical data includes:

[0011] The meteorological data, the road surface data, and the optical data are fused to obtain fused feature data;

[0012] The fused feature data is input into the road risk prediction model to obtain the risk prediction result. The road risk prediction model is trained based on the fused feature sample data and the corresponding risk level.

[0013] In an optional embodiment, the step of fusing the meteorological data, the road surface data, and the optical data to obtain fused feature data includes:

[0014] Meteorological data features are obtained by characterizing the air visibility, icing index, rainfall intensity, and snowfall intensity in the meteorological data.

[0015] Road data features are determined based on the road surface data and the optical data, and vehicle data features are determined based on the optical data;

[0016] The meteorological data features, road data features, and vehicle data features are fused to obtain fused feature data.

[0017] In an optional embodiment, the fusion of the meteorological data features, the road data features, and the vehicle data features to obtain fused feature data includes:

[0018] Cross-feature enhancement is performed on the meteorological data features, the road data features, and the vehicle data features to obtain the first fused feature data;

[0019] The meteorological data features, the road data features, and the vehicle data features are weighted and fused to obtain the second fused feature data;

[0020] The first fused feature data and the second fused feature data are spliced ​​together to determine the fused feature data.

[0021] In an optional embodiment, determining road data features based on the road surface data and the optical data, and determining vehicle data features based on the optical data, includes:

[0022] Based on the road surface data and the optical data, determine the standard deviation of vehicle speed, average vehicle speed, lane occupancy rate, lane occupancy rate change rate, count of sudden deceleration events, number of abnormal stops, road slip risk index, and proportion of high-risk vehicles;

[0023] Road data characteristics are determined by the standard deviation of vehicle speed, average vehicle speed, lane occupancy rate, lane occupancy rate change rate, count of sudden deceleration events, number of abnormal stops, road slip risk index, and proportion of high-risk vehicles.

[0024] The proportion of vehicles with emergency lights on, average headlight intensity, and average vehicle speed are determined based on the optical data, and vehicle data characteristics are determined based on the proportion of vehicles with emergency lights on, average headlight intensity, and average vehicle speed.

[0025] In an optional embodiment, the determination of road data characteristics through vehicle speed standard deviation, average vehicle speed, lane occupancy rate, lane occupancy rate change rate, count of sudden deceleration events, number of abnormal stops, road slippage risk index, and proportion of high-risk vehicles includes:

[0026] Outlier filtering and data standardization were performed on the standard deviation of vehicle speed, average vehicle speed, lane occupancy rate, lane occupancy rate change rate, count of sudden deceleration events, number of abnormal stops, road slip risk index, and proportion of high-risk vehicles, respectively.

[0027] The standard deviation of vehicle speed, average vehicle speed, lane occupancy rate, lane occupancy rate change rate, count of sudden deceleration events, number of abnormal stops, road slip risk index, and proportion of high-risk vehicles after outlier filtering and data standardization are converted into feature vectors.

[0028] The vehicle data features are obtained by combining all the feature vectors.

[0029] In an optional embodiment, determining the current road risk prediction result based on the meteorological data, the road surface data, and the optical data includes:

[0030] In an optional embodiment, determining the display brightness and color chromaticity of the intelligent reflective sign based on the risk prediction result, the meteorological data, and the road surface data includes:

[0031] The display brightness of the intelligent reflective sign is calculated based on the risk prediction results, the meteorological data, and the road surface data.

[0032] The display color of the intelligent reflective sign is determined based on the risk prediction results and the meteorological data.

[0033] In an optional embodiment, calculating the display brightness of the smart reflective sign based on the risk prediction result, the meteorological data, and the road surface data includes:

[0034] Calculate the base brightness based on the meteorological data and the road surface data;

[0035] Risk brightness compensation is calculated based on the risk prediction results, the meteorological data, and the baseline brightness.

[0036] Glare protection correction is applied to the aforementioned risk brightness compensation to obtain the display brightness of the intelligent reflective sign.

[0037] In an optional embodiment, the step of calculating risk brightness compensation based on the risk prediction result, the meteorological data, and the baseline brightness includes:

[0038] The embodiments of the present invention have the following advantages:

[0039] This invention provides an intelligent reflective sign system based on adaptive light control. The system includes a meteorological sensor, a road surface sensor, an optical sensing module, and a light control module, all communicatively connected to a processor. The processor performs the following steps: acquiring meteorological data, road surface data, and optical data through the meteorological sensor, road surface sensor, and optical sensing module, respectively; determining a risk prediction result for the current road based on the meteorological data, road surface data, and optical data; determining the display brightness and chromaticity of the intelligent reflective sign based on the risk prediction result, the meteorological data, and the road surface data; and transmitting the display brightness and chromaticity to the light control module, so that the light control module controls the brightness and chromaticity of the intelligent reflective sign according to the display brightness and chromaticity. Compared to existing fixed traffic signs, the intelligent reflective sign of this application can adaptively adjust its display brightness and chromaticity based on the acquired meteorological data, road surface data, and optical data, thereby improving the display effect of traffic signs. Attached Figure Description

[0040] Figure 1 This is a flowchart of an intelligent reflective sign method based on adaptive light control provided by an embodiment of the present invention;

[0041] Figure 2 This is a flowchart illustrating the determination of display brightness and display chromaticity of an intelligent reflective sign provided in an embodiment of the present invention;

[0042] Figure 3 This is a schematic diagram of the structure of an intelligent reflective sign system based on adaptive light control provided in an embodiment of the present invention. Detailed Implementation

[0043] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0044] An intelligent reflective sign system based on adaptive light control is provided as an embodiment of the present invention. The system includes: a meteorological sensor, a road surface sensor, an optical sensing module, and a light control module, all communicatively connected to a processor. Please refer to [link to relevant documentation]. Figure 1 The processor is used to execute a smart reflective sign method based on adaptive light modulation, the method comprising the following steps:

[0045] S101, meteorological data, road surface data, and optical data are acquired through the meteorological sensor, the road surface sensor, and the optical sensing module, respectively.

[0046] The meteorological data may include rainfall, precipitation, visibility, road icing index, and ambient light intensity; the road data may include potholes, abnormal parking, and road flooding. The optical sensing module includes an infrared-illuminated camera and a millimeter-wave radar. The infrared-illuminated camera detects vehicle lighting status, such as whether fog lights / hazard lights are on. The millimeter-wave radar monitors traffic speed and density. In this embodiment, the optical data may include average vehicle speed, the number of vehicles with fog lights / hazard lights on, lane occupancy rate, etc., but this embodiment does not impose specific limitations on these data.

[0047] Specifically, this embodiment can acquire road surface data through a multispectral road surface monitor, acquire lane status (lane occupancy rate, vehicle presence) through a geomagnetic sensor array, acquire vehicle speed, speed standard deviation, and headway through millimeter-wave radar, and acquire vehicle type, license plate information, etc. through a high-definition smart camera.

[0048] S102, determine the current road risk prediction result based on the meteorological data, the road surface data, and the optical data.

[0049] The risk prediction results are used to indicate the current risk level of the road, which can be divided into three levels: normal (L0), warning (L1), and critical (L2).

[0050] In one optional embodiment provided in this application, determining the current road risk prediction result based on the meteorological data, the road surface data, and the optical data includes:

[0051] S1021, perform data fusion on the meteorological data, the road surface data, and the optical data to obtain fused feature data.

[0052] In this embodiment, the process of fusing the meteorological data, the road surface data, and the optical data to obtain fused feature data includes:

[0053] S10211, The air visibility, icing index, rainfall intensity, and snowfall intensity in the meteorological data are characterized to obtain meteorological data features.

[0054] S10212, determine road data features based on the road surface data and the optical data, and determine vehicle data features based on the optical data.

[0055] In this embodiment, determining road data features based on the road surface data and the optical data, and determining vehicle data features based on the optical data, includes: determining the standard deviation of vehicle speed, average vehicle speed, lane occupancy rate, lane occupancy rate change rate, count of sudden deceleration events, number of abnormal stops, road skid risk index, and proportion of high-risk vehicles based on the road surface data and the optical data; determining road data features using the standard deviation of vehicle speed, average vehicle speed, lane occupancy rate, lane occupancy rate change rate, count of sudden deceleration events, number of abnormal stops, road skid risk index, and proportion of high-risk vehicles; determining the proportion of vehicles with emergency lights on, average headlight intensity, and average vehicle speed based on the optical data, and determining vehicle data features based on the proportion of vehicles with emergency lights on, average headlight intensity, and average vehicle speed.

[0056] S10213, The meteorological data features, the road data features, and the vehicle data features are fused to obtain fused feature data.

[0057] Specifically, the process of fusing the meteorological data features, road data features, and vehicle data features to obtain fused feature data includes: performing cross-feature enhancement on the meteorological data features, road data features, and vehicle data features to obtain first fused feature data; performing weighted fusion on the meteorological data features, road data features, and vehicle data features to obtain second fused feature data; and concatenating the first fused feature data and the second fused feature data to determine the fused feature data.

[0058] In this embodiment, the first fused feature data can be obtained using the following formula:

[0059]

[0060] Among them, F cross For the first fused feature data, F w For meteorological data characteristics, F e For road data features, F o For vehicle data characteristics.

[0061] Specifically, in this embodiment, adaptive weighted fusion can be used to obtain the second fused data feature:

[0062]

[0063] Among them, F i Let F be the characteristic transformation matrix, where the subscript i∈{w,e,o} corresponds to F. i These represent the meteorological feature transformation matrix, the road feature transformation matrix, and the vehicle feature transformation matrix, respectively, ω i For gating weights, u iLet u be the weight vector, where i ∈ {w, e, o}. i These represent the weight vectors for meteorological features, road features, and vehicle features, respectively, and exp is an exponential function.

[0064] The final fused feature data is as follows This is a vector concatenation operation.

[0065] S1022, input the fused feature data into the road risk prediction model to obtain the risk prediction result.

[0066] The road risk prediction model is trained based on fused feature sample data and the corresponding risk level.

[0067] In another embodiment provided in this application, determining the risk prediction result of the current road based on the meteorological data, the road surface data, and the optical data includes: determining the road risk value of the current road based on the meteorological data and the road surface data; and determining the risk prediction result of the current road based on the road risk value and the accident risk value. Specifically, this embodiment can obtain the risk prediction result of the current road by weighted calculation of the road risk value and the accident risk value. The road risk value includes the road surface risk value and the road meteorological risk value. The road surface risk value can be obtained through multispectral road surface monitoring instruments, vehicle-mounted detection systems, inspection drones, etc. For example, the size of potholes and the length of cracks can be obtained through inspection drones to determine the road surface condition risk. The road meteorological risk value can be obtained based on meteorological data; for example, if visibility decreases by more than 30% per minute, a fog warning can be issued.

[0068] In this embodiment, the risk prediction result of the current road can be calculated using the following formula:

[0069]

[0070] Where v is visibility in meters, with lower values ​​indicating higher risk; φ is the icing index (ranging from 0 to 1, where 0 indicates no ice and 1 indicates complete icing); r is rainfall or snowfall intensity (mm / h); k1, k2, and k3 are meteorological risk weighting coefficients, such as k1 = 0.85, k2 = 1.1, and k3 = 0.7 in this embodiment; σ s Let μ be the standard deviation of vehicle speed. s For the average vehicle speed, σ s μ s ρ is the vehicle speed variation coefficient, which reflects the degree of traffic flow turbulence; ρ is the lane occupancy rate; and λ is the proportion of vehicles with emergency lights on.

[0071] To improve the accuracy of risk prediction results, this embodiment can also perform weighted calculation or average calculation on the risk prediction results obtained from the road risk prediction model and the road risk prediction model calculated by the above formula to obtain the current road risk prediction results.

[0072] S103, determine the display brightness and color of the intelligent reflective sign based on the risk prediction results, the meteorological data, and the road surface data.

[0073] like Figure 2 As shown, in one optional embodiment, determining the display brightness and color chromaticity of the intelligent reflective sign based on the risk prediction results, the meteorological data, and the road surface data includes:

[0074] S1031, Calculate the display brightness of the intelligent reflective sign based on the risk prediction results, the meteorological data, and the road surface data.

[0075] Specifically, calculating the display brightness of the intelligent reflective sign based on the risk prediction result, the meteorological data, and the road surface data includes: calculating a base brightness based on the meteorological data and the road surface data; calculating a risk brightness compensation based on the risk prediction result, the meteorological data, and the base brightness; and applying glare protection correction to the risk brightness compensation to obtain the display brightness of the intelligent reflective sign. The risk brightness compensation determines the magnitude of the brightness enhancement.

[0076] In this embodiment, the risk brightness compensation can be calculated using the following formula:

[0077] B risk =B base ×(1+η k ·C m )

[0078] C m =βf+γp

[0079] B base =α·ln(E v +0.01)+B min

[0080] Among them, B base Based on luminance, B min To ensure minimum guaranteed brightness (200 cd / m²) 2 E v Ambient light intensity is obtained via photodiodes; α is the road type coefficient (120 for urban roads, 90 for highways); η kHere, represents the compensation coefficient corresponding to the risk prediction results (0.0 for normal, 0.3 for warning, and 0.6 for critical), f represents the fog level (0-4, 0 for no fog, 4 for dense fog), which is converted from visibility, p represents the rain level (0-3, 0 for no rain, 3 for heavy rain), and the rain level can be obtained through a raindrop spectrometer, C m γ represents the meteorological compensation factor. β is the fog compensation factor (0.08 / fog level), and γ is the rain compensation factor (0.05 / rainfall level).

[0081]

[0082] In this embodiment, glare protection correction for risk brightness compensation can be achieved using the following formula:

[0083]

[0084] Among them, B final To correct the display brightness of the intelligent reflective sign, B risk For risk brightness compensation, I h The intensity of the vehicle's headlights is obtained through a directional light sensor.

[0085] It should be noted that in this embodiment, glare protection has a higher priority than risk-driven adjustment. Even if risk prediction requires high brightness output (such as L2 state), when I... h Brightness reduction is still forced even when the value is >3000. Glare protection directly reads the raw data from the light sensor. h Without a risk prediction model, the risk prediction result L k It does not affect the glare protection threshold.

[0086] For example, a visibility of v = 50m and σ were detected. s μ s >0.7, based on prediction L k =0.92=L2, i.e., output L2 signal: requiring red flashing + brightness increase of 60%. Calculate the base degree B. base =850cd / m 2 ,

[0087] Overlapping risk compensation: B risk =850×(1+0.6×0.4)=1054, detecting oncoming truck high beam I. h =5000, execute brightness reduction B final =1054×min(1,2000 / 5000)=422.

[0088] Specifically, the comparison of the effects of glare protection with and without is shown in Table 1 below:

[0089] Table 1

[0090] mechanism Glare-free protection Glare protection Output brightness <![CDATA[1054cd / m 2 ]]> <![CDATA[422cd / m 2 ]]> Driver's experience High risk of glare from strong light Maintain visibility without glare Risk warning effect The red flashing light is visible but glaring. The red flashing is soft and clear.

[0091] S1032, Determine the display color of the intelligent reflective sign based on the risk prediction results and the meteorological data.

[0092] The displayed color can include: normal, amber, and red. Specifically, normal is white light (560nm), warning is amber (590nm), and emergency is red (630nm).

[0093] S104, the display brightness and the display chromaticity are transmitted to the light control module, so that the light control module controls the brightness and chromaticity of the smart reflective sign according to the display brightness and the display chromaticity.

[0094] This embodiment provides a method for intelligent reflective signs based on adaptive light control. The method acquires meteorological data, road surface data, and optical data through a meteorological sensor, a road surface sensor, and an optical sensing module, respectively. Based on the meteorological data, road surface data, and optical data, a risk prediction result for the current road is determined. The display brightness and chromaticity of the intelligent reflective sign are determined based on the risk prediction result, the meteorological data, and the road surface data. The display brightness and chromaticity are transmitted to the light control module, which then controls the brightness and chromaticity of the intelligent reflective sign according to these parameters. Compared to existing fixed traffic signs, the intelligent reflective sign in this application can adaptively adjust its display brightness and chromaticity based on the acquired meteorological data, road surface data, and optical data, thereby improving the display effect of traffic signs.

[0095] It should be understood that the sequence number of each step in the above embodiments does not imply 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 invention.

[0096] In one embodiment, an intelligent reflective sign system based on adaptive light control is provided. For example... Figure 3 As shown, the system includes: a meteorological sensor 10, a road surface sensor 20, an optical sensing module 30, and a light control module 40, all of which are communicatively connected to the processor. The functional modules of the processor 50 are described in detail below:

[0097] The acquisition module 51 is used to acquire meteorological data, road surface data, and optical data through the meteorological sensor, the road surface sensor, and the optical sensing module, respectively.

[0098] The determining module 52 is used to determine the risk prediction result of the current road based on the meteorological data, the road surface data, and the optical data; the risk prediction result is used to represent the risk level of the current road.

[0099] The determination module 52 is used to determine the display brightness and display color of the intelligent reflective sign based on the risk prediction results, the meteorological data, and the road surface data.

[0100] The transmission module 53 is used to transmit the display brightness and the display chromaticity to the light control module, so that the light control module controls the brightness and chromaticity of the smart reflective sign according to the display brightness and the display chromaticity.

[0101] In an optional embodiment, the determining module 52 is specifically used for:

[0102] The meteorological data, the road surface data, and the optical data are fused to obtain fused feature data;

[0103] The fused feature data is input into the road risk prediction model to obtain the risk prediction result. The road risk prediction model is trained based on the fused feature sample data and the corresponding risk level.

[0104] In an optional embodiment, the determining module 52 is specifically used for:

[0105] Meteorological data features are obtained by characterizing the air visibility, icing index, rainfall intensity, and snowfall intensity in the meteorological data.

[0106] Road data features are determined based on the road surface data and the optical data, and vehicle data features are determined based on the optical data;

[0107] The meteorological data features, road data features, and vehicle data features are fused to obtain fused feature data.

[0108] In an optional embodiment, the determining module 52 is specifically used for:

[0109] Cross-feature enhancement is performed on the meteorological data features, the road data features, and the vehicle data features to obtain the first fused feature data;

[0110] The meteorological data features, the road data features, and the vehicle data features are weighted and fused to obtain the second fused feature data;

[0111] The first fused feature data and the second fused feature data are spliced ​​together to determine the fused feature data.

[0112] In an optional embodiment, the determining module 52 is specifically used for:

[0113] Based on the road surface data and the optical data, determine the standard deviation of vehicle speed, average vehicle speed, lane occupancy rate, lane occupancy rate change rate, count of sudden deceleration events, number of abnormal stops, road slip risk index, and proportion of high-risk vehicles;

[0114] Road data characteristics are determined by the standard deviation of vehicle speed, average vehicle speed, lane occupancy rate, lane occupancy rate change rate, count of sudden deceleration events, number of abnormal stops, road slip risk index, and proportion of high-risk vehicles.

[0115] The proportion of vehicles with emergency lights on, average headlight intensity, and average vehicle speed are determined based on the optical data, and vehicle data characteristics are determined based on the proportion of vehicles with emergency lights on, average headlight intensity, and average vehicle speed.

[0116] In an optional embodiment, the determining module 52 is specifically used for:

[0117] The road data characteristics are determined by the standard deviation of vehicle speed, average vehicle speed, lane occupancy rate, lane occupancy rate change rate, count of sudden deceleration events, number of abnormal stops, road skid risk index, and proportion of high-risk vehicles, including:

[0118] Outlier filtering and data standardization were performed on the standard deviation of vehicle speed, average vehicle speed, lane occupancy rate, lane occupancy rate change rate, count of sudden deceleration events, number of abnormal stops, road slip risk index, and proportion of high-risk vehicles, respectively.

[0119] The standard deviation of vehicle speed, average vehicle speed, lane occupancy rate, lane occupancy rate change rate, count of sudden deceleration events, number of abnormal stops, road slip risk index, and proportion of high-risk vehicles after outlier filtering and data standardization are converted into feature vectors.

[0120] The vehicle data features are obtained by combining all the feature vectors.

[0121] In an optional embodiment, the determining module 52 is specifically used to calculate the risk prediction result of the current road using the following formula:

[0122]

[0123] Where v is visibility, φ is the icing index, r is the intensity of rainfall or snowfall, and k1, k2, and k3 are meteorological risk weighting coefficients; σ s Let μ be the standard deviation of vehicle speed. s For the average vehicle speed, σ s μ s ρ is the vehicle speed variation coefficient, ρ is the lane occupancy rate, and λ is the proportion of vehicles with emergency lights on.

[0124] In an optional embodiment, the determining module 52 is specifically used for:

[0125] The display brightness of the intelligent reflective sign is calculated based on the risk prediction results, the meteorological data, and the road surface data.

[0126] The display color of the intelligent reflective sign is determined based on the risk prediction results and the meteorological data.

[0127] In an optional embodiment, the determining module 52 is specifically used for:

[0128] Calculate the base brightness based on the meteorological data and the road surface data;

[0129] Risk brightness compensation is calculated based on the risk prediction results, the meteorological data, and the baseline brightness.

[0130] Glare protection correction is applied to the aforementioned risk brightness compensation to obtain the display brightness of the intelligent reflective sign.

[0131] In an optional embodiment, the determining module 52 is specifically used for:

[0132] Risk brightness compensation is calculated using the following formula:

[0133] B risk =B base ×(1+η k ·C m )

[0134] C m =βf+γp

[0135] Among them, B base Based on luminance, η k Here, f represents the compensation coefficient corresponding to the risk prediction result, p represents the fog level, and C represents the rain level. m β is the meteorological compensation factor, β is the fog compensation factor, and γ is the rain compensation factor.

[0136] It should be noted that the above detailed descriptions are exemplary and intended to provide further explanation of this application. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains.

[0137] For specific limitations regarding the intelligent reflective sign system based on adaptive light control, please refer to the limitations of the intelligent reflective sign system based on adaptive light control mentioned above, and will not be repeated here. Each module in the above-mentioned device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of the computer device in hardware form or independent of it, or stored in the memory of the computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0138] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above.

[0139] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. An intelligent reflective sign system based on adaptive light control, characterized in that, The system includes: a meteorological sensor, a road surface sensor, an optical sensing module, and a light control module, all communicatively connected to a processor. The processor is used to perform the following steps: Meteorological data, road surface data, and optical data are acquired through the meteorological sensor, the road surface sensor, and the optical sensing module, respectively. The risk prediction result for the current road is determined based on the meteorological data, the road surface data, and the optical data; the risk prediction result is used to indicate the risk level of the current road. The display brightness and color of the intelligent reflective sign are determined based on the risk prediction results, the meteorological data, and the road surface data. The display brightness and display chromaticity are transmitted to the light control module, so that the light control module controls the brightness and chromaticity of the smart reflective sign according to the display brightness and display chromaticity; The step of determining the current road risk prediction result based on the meteorological data, the road surface data, and the optical data includes: The meteorological data, the road surface data, and the optical data are fused to obtain fused feature data; The fused feature data is input into a road risk prediction model to obtain a risk prediction result. The road risk prediction model is trained based on the fused feature sample data and the corresponding risk level. The process of fusing the meteorological data, the road surface data, and the optical data to obtain fused feature data includes: Meteorological data features are obtained by characterizing the air visibility, icing index, rainfall intensity, and snowfall intensity in the meteorological data. Road data features are determined based on the road surface data and the optical data, and vehicle data features are determined based on the optical data; The meteorological data features, road data features, and vehicle data features are fused to obtain fused feature data; The step of determining road data features based on the road surface data and the optical data, and determining vehicle data features based on the optical data, includes: Based on the road surface data and the optical data, determine the standard deviation of vehicle speed, average vehicle speed, lane occupancy rate, lane occupancy rate change rate, count of sudden deceleration events, number of abnormal stops, road slip risk index, and proportion of high-risk vehicles; Road data characteristics are determined by the standard deviation of vehicle speed, average vehicle speed, lane occupancy rate, lane occupancy rate change rate, count of sudden deceleration events, number of abnormal stops, road slip risk index, and proportion of high-risk vehicles. Based on the optical data, determine the proportion of vehicles with emergency lights on, the average headlight intensity, and the average vehicle speed; and determine vehicle data characteristics based on the proportion of vehicles with emergency lights on, the average headlight intensity, and the average vehicle speed. The road data characteristics are determined by the standard deviation of vehicle speed, average vehicle speed, lane occupancy rate, lane occupancy rate change rate, count of sudden deceleration events, number of abnormal stops, road skid risk index, and proportion of high-risk vehicles, including: Outlier filtering and data standardization were performed on the standard deviation of vehicle speed, average vehicle speed, lane occupancy rate, lane occupancy rate change rate, count of sudden deceleration events, number of abnormal stops, road slip risk index, and proportion of high-risk vehicles, respectively. The standard deviation of vehicle speed, average vehicle speed, lane occupancy rate, lane occupancy rate change rate, count of sudden deceleration events, number of abnormal stops, road slip risk index, and proportion of high-risk vehicles after outlier filtering and data standardization are converted into feature vectors. The vehicle data features are obtained by combining all the feature vectors.

2. The system according to claim 1, characterized in that, The process of fusing the meteorological data features, the road data features, and the vehicle data features to obtain fused feature data includes: Cross-feature enhancement is performed on the meteorological data features, the road data features, and the vehicle data features to obtain the first fused feature data; The meteorological data features, the road data features, and the vehicle data features are weighted and fused to obtain the second fused feature data; The first fused feature data and the second fused feature data are spliced ​​together to determine the fused feature data.

3. The system according to claim 1, characterized in that, The step of determining the current road risk prediction result based on the meteorological data, the road surface data, and the optical data includes: Calculate the risk prediction results for the current road.

4. The system according to claim 1 or 3, characterized in that, The step of determining the display brightness and color chromaticity of the intelligent reflective sign based on the risk prediction results, the meteorological data, and the road surface data includes: The display brightness of the intelligent reflective sign is calculated based on the risk prediction results, the meteorological data, and the road surface data. The display color of the intelligent reflective sign is determined based on the risk prediction results and the meteorological data.

5. The system according to claim 4, characterized in that, The calculation of the display brightness of the intelligent reflective sign based on the risk prediction results, the meteorological data, and the road surface data includes: Calculate the base brightness based on the meteorological data and the road surface data; Risk brightness compensation is calculated based on the risk prediction results, the meteorological data, and the baseline brightness. Glare protection correction is applied to the aforementioned risk brightness compensation to obtain the display brightness of the intelligent reflective sign.

6. The system according to claim 5, characterized in that, The calculation of risk brightness compensation based on the risk prediction results, the meteorological data, and the baseline brightness includes: Calculate risk brightness compensation.

Images