ETC vehicle-road cooperation device and system

Abstract

The invention discloses an ETC vehicle-road cooperation device and system, relates to the technical field of vehicle-road cooperation, and aims to solve the technical problem that an existing vehicle-road cooperation device and system lacks an intelligent assessment and active intervention mechanism for a wet and slippery risk of a road in special weather, and the ETC vehicle-road cooperation device and system comprises a plurality of groups of road test modules which are distributed along the road at equal intervals; the central processing module is connected to the cloud processor and is used for receiving the image, speed and spacing information uploaded by the road test module, judging the slippery condition of the road, calculating the length of the slippery road, the quantized value of the slippery degree of the road and the slip risk level and sending the slip risk level to the cloud processor; the slip risk level, the wet and slippery road length information and the distance information between the vehicle and the wet and slippery road are sent to the ETC vehicle-mounted equipment; and the ETC vehicle-mounted equipment is mounted on the automobile and is used for receiving the information sent by the central processing module and performing voice broadcast. The method has the advantages of intelligent assessment and active intervention for the wet and slippery risk of the road in special weather.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle-road cooperation, and more specifically, to an ETC vehicle-road cooperation device and system. Background Art

[0002] The ETC vehicle-road cooperation device and system is a new generation of intelligent transportation solution that integrates electronic toll collection technology and vehicle-road cooperation technology, aiming to improve traffic efficiency, safety, and service experience through information interaction between vehicles and road infrastructure.

[0003] In the prior art, road slipperiness detection mainly relies on manual inspections or single-point sensor devices, making it difficult to achieve real-time monitoring and dynamic warning of the entire high-speed road section. The traditional vehicle anti-skid system only judges the local road conditions through in-vehicle sensors and cannot predict the slippery area ahead in advance. At the same time, the existing vehicle-road cooperation technologies mostly focus on traffic flow guidance and toll management, lacking an intelligent evaluation and active intervention mechanism for road slipperiness risks under special weather conditions.

[0004] In view of this, we propose an ETC vehicle-road cooperation device and system. Summary of the Invention

[0005] The purpose of the present invention is to provide an ETC vehicle-road cooperation device and system to solve the technical problem that the existing vehicle-road cooperation devices and systems lack an intelligent evaluation and active intervention mechanism for road slipperiness risks under special weather conditions.

[0006] To solve the above technical problems, the present invention provides the following technical solution: An ETC vehicle-road cooperation device and system, comprising: A roadside detection module, provided with several groups, evenly distributed along the road; A central processing module, connected to a cloud processor, for receiving the image, speed, and spacing information uploaded by the roadside detection module, judging the road slipperiness situation, calculating the length of the slippery road, the quantification value of the road slipperiness degree, and the skidding risk level, and sending the skidding risk level, the slippery road length information, and the vehicle-to-slippery road spacing information to the ETC in-vehicle device; An ETC in-vehicle device, installed on a vehicle, for receiving the information sent by the central processing module and performing voice broadcasts; The roadside detection module includes: A video acquisition module, for acquiring road image information and transmitting it to the central processing module; A speed acquisition module, for detecting the driving speed of passing vehicles and uploading it to the central processing module; A positioning module, for determining the distance between the vehicle position and the slippery road and sending it to the central processing module.

[0007] Preferably, the video acquisition module is a high-definition camera with high resolution, low illuminance, and wide dynamic range, equipped with an intelligent anti-shake function, and at the same time equipped with an image enhancement algorithm to automatically optimize the contrast, brightness, and color saturation of the image. Based on the histogram equalization algorithm, the gray histogram of the image is equalized. Let the gray value of the original image be , and the gray value after histogram equalization is calculated by the formula: ; where is the total number of gray levels of the image, is the total number of pixels of the image, is the number of pixels with gray value ; The speed acquisition module is a radar speedometer. Based on the Doppler effect principle, when the vehicle moves at a speed , the frequency of the reflected wave received by the radar and the frequency of the transmitted wave are related as follows: ; where is the speed of light, is the angle between the radar wave and the vehicle's moving direction. By measuring the frequency difference , the speed of the vehicle can be calculated: .

[0008] Preferably, when the vehicle travels to the roadside module, the positioning module determines its position coordinates. Let the position coordinates of the vehicle determined by the positioning module be . The central processing module judges the road wetness condition through the roadside modules at both ends of the wet road and determines the starting point coordinates and the ending point coordinates of the wet road, and calculates the distance from the vehicle position to the starting point of the wet road. Its calculation formula is: .

[0009] Preferably, after receiving the image information of the video acquisition module, the central processing module uses the deep learning image recognition algorithm and, based on the neural network model, intelligently analyzes the road surface texture, reflection characteristics, and water accumulation area in the image to judge the road wetness condition. The specific method is as follows: Let the input image be . After being processed by the convolutional layer, pooling layer, and fully connected layer, the output wetness state judgment result is . Its calculation formula is: ; Among them, and are the weight matrix and bias vector of the th layer respectively, is the activation function, ; When it is determined that the road is slippery, the central processing module immediately determines the number of roadside modules on the slippery road through the positioning module. Given that the distance between each roadside module is a fixed value , then the length of the slippery road is calculated by the following formula: ; Among them, is the number of roadside modules on the slippery road.

[0010] Preferably, the calculation method of the road slipperiness quantification value is as follows: First, identify the number of pixels in the slippery area and the total number of pixels in the image through an image recognition algorithm to obtain the proportion of the slippery area ; At the same time, according to the analysis of the reflectivity of the image, calculate the reflectivity quantification value by comparing the average brightness of the reflective area in the image with the average brightness of the normal road surface; Let the average brightness of the normal road surface be , and the average brightness of the reflective area be , then ; Then the calculation formula of the road slipperiness quantification value is: , where and are weight coefficients, and .

[0011] Preferably, the calculation method of the skidding risk level is: After receiving the current driving speed information of the vehicle uploaded by the speed acquisition module, establish a skidding risk assessment model, considering factors such as road slipperiness, vehicle driving speed, and vehicle type, and calculate the skidding risk level of the current vehicle when driving on the slippery road in the future; Let the vehicle driving speed be , the vehicle type coefficient be , and the skidding risk level The calculation formula is: ; Among them, , and is the weight coefficient, is the constant term; The skidding risk level is divided into three levels: low, medium, and high, and each level corresponds to a different risk threshold range; When it is a low risk level; When it is a medium risk level; When it is a high risk level.

[0012] Preferably, after receiving the spacing information between the vehicle position determined by the positioning module and the slippery road, the central processing module integrates and packages the skidding risk level, the slippery road length information, and the spacing information between the vehicle position and the slippery road, and sends them to the on-vehicle ETC device through a wireless communication link.

[0013] Preferably, after receiving the information from the central processing module, the on-vehicle ETC device broadcasts it through the built-in voice synthesis engine in a clear, loud, and moderate-speed voice. The broadcast content includes the skidding risk level at the current vehicle speed, the slippery road length information, and the spacing information between the current vehicle position and the slippery road.

[0014] Compared with the prior art, the beneficial effects of the present invention are: 1. Through multiple groups of roadside modules evenly distributed along the road, combined with video acquisition, speed detection, and positioning modules, the present invention realizes continuous monitoring of the slippery state of the entire road section. Based on the deep learning image recognition algorithm, the central processing module can accurately judge the range of the slippery area, solving the problem of limited detection range in the prior art.

[0015] 2. The present invention innovatively constructs a skidding risk assessment model including the quantification value of the slippery degree , vehicle speed and vehicle type coefficient , realizing accurate calculation of the risk level, and thus dynamically analyzing the skidding risk at the current speed according to the vehicle driving speed, which has higher prediction accuracy compared with the traditional evaluation method that only relies on a single parameter.

[0016] 3. The present invention also designs an on-vehicle ETC device, integrates and packages the skidding risk level, the slippery road length information, and the spacing information between the vehicle position and the slippery road, and sends them to the on-vehicle ETC device through a wireless communication link, and broadcasts them through the built-in voice synthesis engine of the on-vehicle ETC device, which is beneficial to providing information about the slippery road surface to the driver and playing an early warning effect. Description of the Drawings

[0017] Figure 1Schematic diagram of the system framework of the present invention. Detailed implementation manners

[0018] For the convenience of those skilled in the art to understand the technical solution of the present invention, the technical solution of the present invention will be further described below with reference to the accompanying drawings of the specification.

[0019] Embodiment 1: As Figure 1 shown, the present invention provides an ETC vehicle-road collaborative device and system, including: A plurality of roadside modules are provided and evenly distributed along the road; A central processing module is connected to a cloud processor, and is configured to receive image, speed, and spacing information uploaded by the roadside module, judge the road wetness condition, calculate the length of the wet road, the quantization value of the road wetness degree, and the skidding risk level, and send the skidding risk level, the wet road length information, and the vehicle-wet road spacing information to the ETC on-vehicle device; The ETC on-vehicle device is installed on a vehicle and is configured to receive the information sent by the central processing module and perform voice broadcast; The roadside module includes: A video acquisition module is configured to acquire road image information and transmit it to the central processing module; A speed acquisition module is configured to detect the driving speed of passing vehicles and upload it to the central processing module; A positioning module is configured to determine the spacing between the vehicle position and the wet road and send it to the central processing module.

[0020] In the embodiment of the present invention, the video acquisition module is a high-definition camera with high resolution, low illumination, and wide dynamic range, with an intelligent anti-shake function, and at the same time is equipped with an image enhancement algorithm to automatically optimize the contrast, brightness, and color saturation of the image. Based on the histogram equalization algorithm, the gray histogram of the image is equalized. Let the gray value of the original image be , and the gray value after histogram equalization is calculated by the formula: ; wherein, is the total number of gray levels of the image, is the total number of pixels of the image, is the number of pixels with a gray value of ; The speed acquisition module is a radar speedometer. Based on the Doppler effect principle, when the vehicle moves at a speed , the relationship between the frequency of the reflected wave received by the radar and the frequency of the transmitted wave is: ; Among them, is the speed of light, is the angle between the radar wave and the vehicle's moving direction. By measuring the frequency difference the vehicle speed can be calculated : .

[0021] In the embodiment of the present invention, when the vehicle travels to the roadside module, the positioning module determines its position coordinates. Let the vehicle position coordinates determined by the positioning module be , and the central processing module judges the road wetness condition, and determines the starting point coordinates and the ending point coordinates of the wet road through the roadside modules at both ends of the wet road, and calculates the distance from the vehicle position to the starting point of the wet road and the distance to the ending point. The calculation formula is: .

[0022] In the embodiment of the present invention, after receiving the image information from the video acquisition module, the central processing module uses the deep learning image recognition algorithm, based on the neural network model, to intelligently analyze the road surface texture, reflection characteristics, and water accumulation area in the image to judge the road wetness condition. The specific method is: Let the input image be , after being processed by the convolutional layer, pooling layer, and fully connected layer, the output wetness state judgment result is , and the calculation formula is: ; Among them, and are the weight matrix and bias vector of the th layer respectively, is the activation function, ; When it is judged that the road is wet, the central processing module immediately determines the number of roadside modules on the wet road through the positioning module. It is known that the distance between each roadside module is a fixed value , then the length of the wet road is calculated by the following formula: ; Among them, is the number of roadside modules on the wet road.

[0023] In the embodiment of the present invention, the calculation method of the road wetness degree quantization value is: First, use an image recognition algorithm to identify the number of pixels in the slippery area of the image and the total number of pixels in the image , and obtain the proportion of the slippery area ; At the same time, based on the analysis of the reflection intensity of the image, calculate the quantified value of the reflection intensity by comparing the average brightness of the reflective area in the image with the average brightness of the normal road surface ; Let the average brightness of the normal road surface be , and the average brightness of the reflective area be , then ; Then the calculation formula for the quantified value of the road slipperiness is: , where and are weight coefficients, obtained through a large amount of experimental data and machine learning algorithms training, and .

[0024] In the embodiment of the present invention, the calculation method of the skidding risk level is: After receiving the current driving speed information of the vehicle uploaded by the speed acquisition module, establish a skidding risk assessment model, consider factors such as road slipperiness, vehicle driving speed, and vehicle type, and calculate the skidding risk level of the current vehicle when driving on a slippery road surface in the future; Let the vehicle driving speed be , the vehicle type coefficient be , and the skidding risk level The calculation formula is: ; Among them, , and are weight coefficients, obtained through a large amount of experimental data and machine learning algorithms training, is a constant term; Divide the skidding risk level into three levels: low, medium, and high, and each level corresponds to a different risk threshold range; When , it is a low risk level; When , it is a medium risk level; When , it is a high risk level; and It is a threshold determined through actual accident data and simulation tests. This model uses machine learning technology and continuously optimizes and adjusts according to actual accident data and vehicle driving data to make the risk assessment results more in line with the actual situation. At the same time, the model also has an adaptive adjustment function, which can automatically adjust the weight coefficients according to the road characteristics and traffic conditions in different regions to improve the accuracy of the assessment.

[0025] In an embodiment of the present invention, after receiving the spacing information between the vehicle position determined by the positioning module and the slippery road, the central processing module integrates and packages the skidding risk level, the slippery road length information, and the spacing information between the vehicle position and the slippery road, and sends them to the ETC on-vehicle device through a wireless communication link; The wireless communication link uses channel coding and modulation technologies to split the high-speed data stream into multiple low-speed sub-data streams, modulate them onto different subcarriers for transmission respectively, and assume the transmitted signal is , and the signal after modulation is: ; wherein, is the symbol period, is the subcarrier spacing, is the number of subcarriers, is the start time.

[0026] In an embodiment of the present invention, after receiving the information from the central processing module, the ETC on-vehicle device broadcasts it through the built-in voice synthesis engine in a clear, loud and moderate-speed voice. The broadcast content includes the skidding risk level at the current vehicle speed, the slippery road length information, and the spacing information between the current vehicle position and the slippery road.

[0027] The embodiments disclosed in the present invention are preferred embodiments, but are not limited thereto. Those of ordinary skill in the art can easily understand the spirit of the present invention according to the above embodiments and make different extensions and changes. However, as long as they do not depart from the spirit of the present invention, they are within the protection scope of the present invention.

Claims

1. An ETC vehicle-road cooperative device and system, characterized in that: include: The road test module is provided in several groups and is evenly distributed along the road; The central processing module is connected to the cloud processor and is used to receive the image, speed and distance information uploaded by the road test module, determine the slippery condition of the road, calculate the length of the slippery road, the quantitative value of the slippery degree of the road and the slippery risk level, and send the slippery risk level, slippery road length information and the distance between the vehicle and the slippery road to the ETC on-board device; ETC on-board equipment, installed on the car, is used to receive information sent by the central processing module and make voice broadcasts; The drive test module comprises: Video acquisition module, used to obtain road image information and transmit it to the central processing module; Speed ​​acquisition module, used to detect the speed of passing vehicles and upload it to the central processing module; The positioning module is used to determine the distance between the vehicle position and the slippery road and send it to the central processing module.

2. An ETC vehicle-road cooperative device and system according to claim 1, characterized in that: The video acquisition module is a high-definition camera with high resolution, low illumination and wide dynamic range, with intelligent anti-shake function, and equipped with image enhancement algorithm, which automatically optimizes the contrast, brightness and color saturation of the image. Based on the histogram equalization algorithm, the grayscale histogram of the image is uniformly processed, and the grayscale value of the original image is set to , the gray value after histogram equalization The calculation formula is: ； in, is the total number of gray levels of the image, is the total number of pixels in the image, The gray value is The number of pixels; The speed acquisition module is a radar speedometer. Based on the Doppler effect principle, when a vehicle is moving at a speed of When moving, the frequency of the reflected wave received by the radar The frequency of the transmitted wave The relationship between them is: ； in, is the speed of light, is the angle between the radar wave and the direction of vehicle movement. The speed of the vehicle can be calculated : 。 3. An ETC vehicle-road cooperative device and system according to claim 2, characterized in that: The positioning module determines the position coordinates of the vehicle when the vehicle drives to the road test module, and the vehicle position coordinates determined by the positioning module are set to The central processing module determines the slippery condition of the road, and the road test modules at both ends of the slippery road determine the starting coordinates of the slippery road. and the end point coordinates , and calculate the distance from the vehicle position to the starting point of the slippery road , and its calculation formula is: 。 4. An ETC vehicle-road cooperative device and system according to claim 3, characterized in that: After receiving the image information from the video acquisition module, the central processing module uses a deep learning image recognition algorithm based on a neural network model to perform intelligent analysis on the road surface texture, reflective properties, and water accumulation area in the image to determine the slippery condition of the road. The specific method is as follows: Assume the input image is After being processed by the convolutional layer, pooling layer, and fully connected layer, the output slippery state judgment result is , and its calculation formula is: ； in, and Respectively The weight matrix and bias vector of the layer, is the activation function, ; When it is determined that the road is slippery, the central processing module immediately determines the number of road test modules on the slippery road through the positioning module. It is known that the distance between each road test module is a fixed value. , then the length of the slippery road Calculated by the following formula: ； in, is the number of road test modules on slippery roads.

5. An ETC vehicle-road cooperative device and system according to claim 4, characterized in that: Quantitative value of the road slipperiness The calculation method is: First, the image recognition algorithm is used to identify the number of pixels in the wet area of ​​the image. and the total number of pixels in the image , and the percentage of slippery area is obtained ; At the same time, according to the reflection intensity analysis of the image, the reflection intensity quantification value is calculated by comparing the average brightness of the reflection area in the image with the average brightness of the normal road surface. ; Assume that the average brightness of normal road surface is , the average brightness of the reflective area is ,but ; The quantitative value of road slipperiness The calculation formula is: ,in, and is the weight coefficient, and .

6. An ETC vehicle-road cooperative device and system according to claim 5, characterized in that: The calculation method of the slip risk level is: After receiving the current driving speed information of the car uploaded by the speed acquisition module, a skidding risk assessment model is established, taking into account factors such as the degree of slippery road, vehicle speed and vehicle model, to calculate the skidding risk level of the current vehicle when it subsequently drives on a slippery road; Assume the vehicle speed is , the model coefficient is , Slip risk level The calculation formula is: ； in, , and is the weight coefficient, is a constant term; The skid risk level is divided into three levels: low, medium and high, and each level corresponds to a different risk threshold range; when The risk level is low. when The risk level is medium. when It is a high risk level.

7. An ETC vehicle-road cooperative device and system according to claim 6, characterized in that: After receiving the distance information between the vehicle position and the slippery road determined by the positioning module, the central processing module integrates and packages the skidding risk level, slippery road length information and the distance information between the vehicle position and the slippery road, and sends it to the ETC on-board device through a wireless communication link.

8. An ETC vehicle-road cooperative device and system according to claim 7, characterized in that: After receiving the information from the central processing module, the ETC on-board device broadcasts it in a clear, loud and moderately fast voice through the built-in speech synthesis engine. The broadcast content includes the skidding risk level at the current vehicle speed, the length of the slippery road, and the distance information between the current position of the vehicle and the slippery road.

Images