Highway traffic safety supervision method and system based on big data analysis

Abstract

The invention provides an expressway traffic safety supervision method and system based on big data analysis, and the method comprises the steps: calculating the speed of a vehicle based on the information of time points when the vehicle passes through two roadside units, and judging whether the vehicle is overspeed; determining a vehicle standard load based on the vehicle identity information, and determining whether the vehicle is overloaded based on the vehicle weight information and the vehicle standard load; determining a vehicle standard passenger number on the basis of the vehicle identity information, recognizing the number of passengers in the vehicle by using an image recognition model on the basis of the vehicle image information, and judging whether the vehicle is overloaded on the basis of the vehicle standard passenger number and the number of passengers in the vehicle; the total driving duration of the vehicle is determined based on the time point information of the vehicle passing through the plurality of roadside units, whether fatigue driving occurs is determined based on the stay duration of the vehicle in the service area and the total driving duration, and if overspeed, overload or fatigue driving occurs, an alarm is sent to the vehicle-mounted unit through the roadside units. And if the alarm time length is greater than the preset time length, sending a notification to the management end.

Description

Technical Field

[0001] The present invention relates to the field of vehicle supervision technology, and in particular to a high-speed road traffic safety supervision method and system based on big data analysis. Background Art

[0002] The importance of safe driving is self-evident. It is directly related to the life safety and family happiness of every traffic participant. In the fast-paced modern life, road traffic has become an indispensable part of people's daily travel, and safe driving is the basis for ensuring the smooth progress of this process. Safe driving can significantly reduce the incidence of traffic accidents. Traffic accidents are often accompanied by serious consequences such as casualties and property losses, which bring heavy burdens to individuals, families and even society.

[0003] At present, unsafe driving behaviors are mainly screened manually, and the screening efficiency is low. Summary of the invention

[0004] In view of this, an embodiment of the present invention provides a method for monitoring highway traffic safety based on big data analysis to eliminate or improve one or more defects existing in the prior art.

[0005] One aspect of the present invention provides a method for supervising highway traffic safety based on big data analysis, the method comprising the steps of:

[0006] Based on the data interaction between the roadside unit and the vehicle-mounted unit, the vehicle information is obtained, wherein the vehicle information includes the time point information of the vehicle passing through each roadside unit, the vehicle identity information, the vehicle image information and the vehicle weight information;

[0007] Calculating the vehicle speed based on the time point information when the vehicle passes through two roadside units, and determining whether the vehicle is speeding based on the vehicle speed;

[0008] Determine the standard load of the vehicle based on the vehicle identity information, and determine whether the vehicle is overloaded based on the vehicle weight information and the standard load of the vehicle;

[0009] Determine the standard number of passengers in the vehicle based on the vehicle identity information, identify the number of passengers in the vehicle using an image recognition model based on the vehicle image information, and determine whether the vehicle is overloaded based on the standard number of passengers and the number of passengers in the vehicle;

[0010] Determine the total driving time of the vehicle based on the time point information of the vehicle passing through multiple roadside units, and determine whether there is fatigue driving based on the length of time the vehicle stays in the service area and the total driving time;

[0011] If speeding, overloading or fatigue driving occurs, an alarm will be sent to the on-board unit through the roadside unit. If the alarm duration is longer than the preset time length, a notification will be sent to the management end.

[0012] By adopting the above scheme, this scheme obtains the vehicle information of the vehicle through the interaction between the vehicle's on-board unit and the roadside unit, and can automatically determine whether the vehicle has unsafe driving behavior based on the vehicle information. This scheme does not require human assistance and can complete the behavior determination only through automated interaction, reducing the manual demand in the determination process and improving the efficiency of detecting unsafe behaviors.

[0013] In some embodiments of the present invention, in the step of calculating the vehicle speed based on the time point information when the vehicle passes through two roadside units, and determining whether the vehicle is speeding based on the vehicle speed, the time point information when the vehicle passes through two adjacent roadside units and the distance information between the two roadside units are obtained, the vehicle speed is calculated based on the distance information between the two roadside units and the time point information when the vehicle passes through two adjacent roadside units, the vehicle speed is compared with a threshold speed, and a determination is made as to whether the vehicle is speeding.

[0014] In some embodiments of the present invention, in the steps of determining the standard load of the vehicle based on the vehicle identity information and determining whether the vehicle is overloaded based on the vehicle weight information and the vehicle standard load, the vehicle model is determined based on the vehicle identity information, the vehicle standard load is matched based on the vehicle model, and the vehicle standard load is compared with the vehicle weight information to determine whether the vehicle is overloaded.

[0015] In some embodiments of the present invention, in the steps of determining the standard number of passengers in the vehicle based on vehicle identity information, identifying the number of people in the vehicle using an image recognition model based on vehicle image information, and determining whether the vehicle is overloaded based on the standard number of passengers in the vehicle and the number of people in the vehicle, the vehicle model is determined based on the vehicle identity information, the standard number of passengers in the vehicle is matched based on the model, the number of people in the vehicle is identified based on the image recognition model, the identified number of people in the vehicle is compared with the standard number of passengers in the vehicle to determine whether the vehicle is overloaded.

[0016] In some embodiments of the present invention, in the step of identifying the number of people in the vehicle based on the image recognition model, faces in the captured vehicle image are marked based on the image recognition model, and the number of people in the vehicle is determined based on the number of marked faces.

[0017] In some embodiments of the present invention, in the step of determining the total driving time of the vehicle based on the time point information of the vehicle passing through multiple roadside units, and determining whether there is fatigue driving based on the length of time the vehicle stays in the service area and the total driving time:

[0018] The time point information when the vehicle enters the highway and passes the first roadside unit is taken as the starting time point, and the time point information when the vehicle currently passes the last roadside unit is taken as the ending time point, and the total driving time is calculated based on the starting time point and the ending time point;

[0019] The vehicle's stay time in the service area is calculated based on the gantries at the entrance and exit of the service area, and fatigue driving is determined based on the vehicle's total driving time and the stay time in the service area.

[0020] In some embodiments of the present invention, the step of determining the total driving time of the vehicle based on the time point information of the vehicle passing through multiple roadside units, and determining whether there is fatigue driving based on the vehicle's stay time in the service area and the total driving time also includes:

[0021] Based on the vehicle images collected by the gantries at the entrance and exit of the service area, the driver profile images at the entrance and exit are extracted respectively, and based on the driver profile images, it is determined whether to change the driver. If the driver is changed, the total driving time is recalculated.

[0022] In some embodiments of the present invention, in the step of extracting driver profile images at the entrance and exit based on vehicle images collected by gantries at the entrance and exit of the service area, and determining whether to change the driver based on the driver profile images:

[0023] Marking the driver's outline based on a preset first neural network model, and cutting the driver's outline from the vehicle image to obtain a driver outline image;

[0024] The driver profile images at the entrance and the exit are both driven into the second neural network model, and the second neural network model outputs a similarity value, and determines whether to change the driver based on the similarity value.

[0025] In some embodiments of the present invention, in the step of marking the driver's profile based on a preset first neural network model, cropping the driver's profile from a vehicle image, and obtaining a driver profile image, the driver's profile cropped from the vehicle image is pasted into a preset template image to obtain a driver profile image.

[0026] The second aspect of the present invention also provides a highway traffic safety supervision system based on big data analysis, the system includes a computer device, the computer device includes a processor and a memory, the memory stores computer instructions, the processor is used to execute the computer instructions stored in the memory, when the computer instructions are executed by the processor, the system implements the steps implemented by the method described above.

[0027] The third aspect of the present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps implemented by the aforementioned method for highway traffic safety supervision based on big data analysis.

[0028] Additional advantages, purposes, and features of the present invention will be described in part in the following description, and will become apparent to those skilled in the art after studying the following, or may be learned from the practice of the present invention. The purposes and other advantages of the present invention can be specifically pointed out and obtained in the specification and the accompanying drawings.

[0029] Those skilled in the art will appreciate that the objectives and advantages that can be achieved with the present invention are not limited to the above specific description, and the above and other objectives that can be achieved by the present invention will be more clearly understood from the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The drawings described herein are used to provide a further understanding of the present invention, constitute a part of this application, and do not constitute a limitation of the present invention.

[0031] Figure 1 A schematic diagram of an implementation method of a highway traffic safety supervision method based on big data analysis of the present invention;

[0032] Figure 2 This is a schematic diagram of the information release architecture of the highway traffic safety supervision method based on big data analysis of the present invention;

[0033] Figure 3 It is a schematic diagram of the overall architecture of the present invention. DETAILED DESCRIPTION

[0034] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the embodiments and the accompanying drawings. Here, the illustrative embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0035] It should also be noted that, in order to avoid obscuring the present invention due to unnecessary details, only structures and / or processing steps closely related to the solutions according to the present invention are shown in the accompanying drawings, while other details that are not closely related to the present invention are omitted.

[0036] like Figure 1 As shown, the present invention proposes a method for supervising highway traffic safety based on big data analysis, the steps of which include:

[0037] Step S100, based on the data interaction between the roadside unit and the vehicle-mounted unit, obtaining vehicle information, wherein the vehicle information includes time point information of the vehicle passing through each roadside unit, vehicle identity information, vehicle image information and vehicle weight information;

[0038] In the specific implementation process, OBU (On-Board Unit): vehicle-mounted unit, installed on vehicles, used to communicate with RSU, obtain traffic information and provide location services. In ETC (Electronic Toll Collection System), OBU is a key device for identifying vehicles, recording traffic information, sending and receiving data, and processing transactions.

[0039] RSU (Roadside Unit): Roadside unit, installed beside the road, used to communicate with OBU, collect traffic information, control traffic lights, etc. It is a communication device deployed along the road, capable of receiving and sending wireless signals and communicating with passing vehicles in real time.

[0040] The interaction between OBU and RSU is mainly carried out in the following two ways:

[0041] Internet of Vehicles Communications:

[0042] With the help of mobile communication networks such as 4G and 5G, communication between OBU and RSU is achieved. The on-board equipment is connected to the mobile communication network through a SIM card and communicates with the RSU through the Internet. This communication method has high speed and reliability and is suitable for long-distance communication.

[0043] Radio Frequency Communications:

[0044] OBU and RSU communicate via radio signals, independent of mobile communication networks, and can use technologies such as Bluetooth, Wi-Fi, and DSRC (Dedicated Short-Range Communications) for communication. This communication method is suitable for short-range communication and has a lower transmission rate but higher real-time performance.

[0045] Step S210, calculating the vehicle speed based on the time point information when the vehicle passes through two roadside units, and determining whether the vehicle is speeding based on the vehicle speed;

[0046] Step S220, determining the standard load of the vehicle based on the vehicle identity information, and determining whether the vehicle is overloaded based on the vehicle weight information and the standard load of the vehicle;

[0047] Step S230, determining the standard number of passengers in the vehicle based on the vehicle identity information, identifying the number of passengers in the vehicle using an image recognition model based on the vehicle image information, and determining whether the vehicle is overloaded based on the standard number of passengers and the number of passengers in the vehicle;

[0048] Step S240, determining the total driving time of the vehicle based on the time point information of the vehicle passing through multiple roadside units, and determining whether there is fatigue driving based on the length of time the vehicle stays in the service area and the total driving time;

[0049] Step S300: If speeding, overloading or fatigue driving occurs, an alarm is sent to the vehicle-mounted unit through the roadside unit. If the alarm duration is longer than the preset time length, a notification is sent to the management end.

[0050] In the specific implementation process, the warning method can be a voice broadcast method, and the preset time length can be 30 minutes.

[0051] During the specific implementation process, if any of speeding, overloading or fatigue driving is found, an alarm will be started until the speeding, overloading or fatigue driving situation no longer exists and then the alarm will be stopped.

[0052] During the implementation process, a notification is sent to the management side, which can stop the illegal behavior through offline intervention.

[0053] By adopting the above scheme, this scheme obtains the vehicle information of the vehicle through the interaction between the vehicle's on-board unit and the roadside unit, and can automatically determine whether the vehicle has unsafe driving behavior based on the vehicle information. This scheme does not require human assistance and can complete the behavior determination only through automated interaction, reducing the manual demand in the determination process and improving the efficiency of detecting unsafe behaviors.

[0054] In some embodiments of the present invention, in the step of calculating the vehicle speed based on the time point information when the vehicle passes through two roadside units, and determining whether the vehicle is speeding based on the vehicle speed, the time point information when the vehicle passes through two adjacent roadside units and the distance information between the two roadside units are obtained, the vehicle speed is calculated based on the distance information between the two roadside units and the time point information when the vehicle passes through two adjacent roadside units, the vehicle speed is compared with a threshold speed, and a determination is made as to whether the vehicle is speeding.

[0055] During the specific implementation process, if the vehicle speed is greater than the threshold speed, the vehicle is determined to be speeding, the speeding situation is recorded corresponding to the identity information of the vehicle, and communication is performed with the vehicle's on-board unit to issue a warning to the vehicle, and the vehicle's driving speed is monitored via satellite. When the vehicle's driving speed is no greater than the threshold speed, the vehicle warning is stopped.

[0056] By adopting the above scheme, the present scheme can monitor the speeding situation of the vehicle in real time, and issue a warning if the speeding situation occurs, thereby ensuring the driving safety of the vehicle.

[0057] In some embodiments of the present invention, in the steps of determining the standard load of the vehicle based on the vehicle identity information and determining whether the vehicle is overloaded based on the vehicle weight information and the vehicle standard load, the vehicle model is determined based on the vehicle identity information, the vehicle standard load is matched based on the vehicle model, and the vehicle standard load is compared with the vehicle weight information to determine whether the vehicle is overloaded.

[0058] In a specific implementation process, the vehicle identity information is obtained through the interaction between the on-board unit and the roadside unit.

[0059] In some embodiments of the present invention, in the steps of determining the standard number of passengers in the vehicle based on vehicle identity information, identifying the number of people in the vehicle using an image recognition model based on vehicle image information, and determining whether the vehicle is overloaded based on the standard number of passengers in the vehicle and the number of people in the vehicle, the vehicle model is determined based on the vehicle identity information, the standard number of passengers in the vehicle is matched based on the model, the number of people in the vehicle is identified based on the image recognition model, the identified number of people in the vehicle is compared with the standard number of passengers in the vehicle to determine whether the vehicle is overloaded.

[0060] In the specific implementation process, the image recognition model is a pre-trained convolutional neural network model (Convolutional Neural Network, CNN).

[0061] By adopting the above scheme, the present scheme can directly determine the number of people in the vehicle through the image recognition model, and can be used as an auxiliary method to determine whether the vehicle is overcrowded.

[0062] In some embodiments of the present invention, in the step of identifying the number of people in the vehicle based on the image recognition model, faces in the captured vehicle image are marked based on the image recognition model, and the number of people in the vehicle is determined based on the number of marked faces.

[0063] During the specific implementation process, a laser window-through overcrowding detection system can also be used to detect the number of people in the vehicle. The laser window-through overcrowding detection system is an advanced system that combines laser window-through technology, high-definition smart cameras and artificial intelligence automatic detection methods. It is mainly used for real-time detection, locking and capturing of vehicles and people in the vehicle to identify whether there is abnormal behavior such as overcrowding.

[0064] In some embodiments of the present invention, in the step of determining the total driving time of the vehicle based on the time point information of the vehicle passing through multiple roadside units, and determining whether there is fatigue driving based on the length of time the vehicle stays in the service area and the total driving time:

[0065] The time point information when the vehicle enters the highway and passes the first roadside unit is taken as the starting time point, and the time point information when the vehicle currently passes the last roadside unit is taken as the ending time point, and the total driving time is calculated based on the starting time point and the ending time point;

[0066] The vehicle's stay time in the service area is calculated based on the gantries at the entrance and exit of the service area, and fatigue driving is determined based on the vehicle's total driving time and the stay time in the service area.

[0067] In the specific implementation process, if the total driving time is greater than the first preset time and the service area stay time is less than the second preset time, it is determined that fatigue driving occurs.

[0068] Specifically, the first preset time length is 4 hours, and the second preset time length is 20 minutes.

[0069] By adopting the above scheme, the time point when the vehicle enters the highway and passes the first roadside unit is used as the starting time point, the driving time is accumulated, and the vehicle's stay time in the service area is used. This scheme can automatically and accurately identify fatigue driving conditions and ensure vehicle safety.

[0070] In some embodiments of the present invention, the step of determining the total driving time of the vehicle based on the time point information of the vehicle passing through multiple roadside units, and determining whether there is fatigue driving based on the vehicle's stay time in the service area and the total driving time also includes:

[0071] Based on the vehicle images collected by the gantries at the entrance and exit of the service area, the driver profile images at the entrance and exit are extracted respectively, and based on the driver profile images, it is determined whether to change the driver. If the driver is changed, the total driving time is recalculated.

[0072] In the specific implementation process, it is determined whether to change the driver based on the driver profile image. If the driver is changed, the total driving time is recalculated. If the total driving time is recalculated, the total driving time is accumulated again from 0s.

[0073] By adopting the above scheme, since multiple drivers are often arranged in one vehicle during actual long-distance driving, and the driver replacement is often completed in the service area, this scheme can extract the driver profile images at the entrance and exit respectively based on the vehicle images collected by the gantries at the entrance and exit of the service area, determine whether to replace the driver based on the driver profile image, and identify the situation of driver replacement, which solves the problem of difficulty in determining the situation of driver replacement and further ensures the accuracy of determining fatigue driving conditions.

[0074] In some embodiments of the present invention, in the step of extracting driver profile images at the entrance and exit based on vehicle images collected by gantries at the entrance and exit of the service area, and determining whether to change the driver based on the driver profile images:

[0075] Marking the driver's outline based on a preset first neural network model, and cutting the driver's outline from the vehicle image to obtain a driver outline image;

[0076] In the specific implementation process, the first neural network model is a pre-trained convolutional neural network model (Convolutional Neural Network, CNN).

[0077] The driver profile images at the entrance and the exit are both driven into the second neural network model, and the second neural network model outputs a similarity value, and determines whether to change the driver based on the similarity value.

[0078] In the specific implementation process, the second neural network model is a pre-trained Siamese neural network model (Siamese Network).

[0079] During the specific implementation process, the twin neural network model outputs high-dimensional vectors corresponding to the two images, and calculates the Euclidean distance or cosine similarity of the two high-dimensional vectors as the similarity value.

[0080] By adopting the above scheme, the present scheme can realize the determination of the similarity of two images through two neural network models. If the similarity is lower than the preset similarity threshold, it is determined to replace the driver.

[0081] In some embodiments of the present invention, in the step of marking the driver's profile based on a preset first neural network model, cropping the driver's profile from a vehicle image, and obtaining a driver profile image, the driver's profile cropped from the vehicle image is pasted into a preset template image to obtain a driver profile image.

[0082] In some embodiments of the present invention, the method further includes predicting the vehicle's driving route based on the vehicle's current driving route to obtain a predicted driving route.

[0083] During the specific implementation process, the duration of the vehicle warning is calculated in real time. If the warning duration is greater than the preset market threshold, the vehicle information, the vehicle's current driving route and the predicted driving route are sent to the management side. The management side can track the vehicle based on the predicted driving route to avoid dangerous situations.

[0084] In a specific implementation process, the coordinate information of the current driving route of the vehicle is input into a preset Markov model, and the driving route is predicted by the Markov model.

[0085] like Figure 2 and 3 As shown, in the specific implementation process, data from each terminal and business system is collected, the collected data is stored and analyzed, and when abnormal behavior occurs, the information is published to the RSU, which is then sent to the OBU through the RSU to broadcast and remind the public of the abnormal behavior. After the broadcast is completed, the abnormal behavior is continuously monitored. If it lasts for more than 30 minutes, the information is sent to the management business system for disposal. The management end determines that it is an illegal vehicle through continuous monitoring, and sends the disposal information to the mobile terminal of the section manager to complete the offline disposal.

[0086] The information release module sends speeding information, overloading information, overcrowding information, and fatigue driving information to the RSU (Road Test Unit). The RSU that sends the information selects the current road section of the vehicle. After receiving the information, the RSU forwards the alarm information to the vehicles on the road through the on-board unit OBU. The on-board unit OBU cooperates with the main control unit through the voice processing module to convert text information into voice signals and broadcast them through the voice player.

[0087] The information is sent to the violation handling system through the information release module, including the license plate number, violation event, violation start time, violation end time, violation duration, and vehicle trajectory location prediction. The information is sent to the mobile terminal through the information release module, including the license plate number, violation event, violation start time, violation end time, violation duration, vehicle trajectory location prediction, and handling methods.

[0088] By adopting the above solution, data from various terminals and business systems are collected and stored in the database. Through big data analysis technology, abnormal vehicle behavior is analyzed and monitored in real time. When vehicle speeding, overloading, overcrowding and fatigue driving information appear, the information monitoring module generates an alarm and reminds the driver to control the speed, take rest and control the load through the voice contact terminal. After voice contact, continuous monitoring is carried out until the alarm ends. When the alarm duration exceeds 30 minutes, active road control instructions are issued and personnel intervene offline to complete the closed-loop management of highway safety.

[0089] In summary, through this technical solution, it is possible to monitor the abnormal behavior of highway vehicles, use big data technology to calculate in real time whether highway vehicles have abnormal behavior, and then send the information to the road test unit RSU through the information release module to reach the vehicle OBU, reminding the driver to pay attention to traffic safety. At the same time, when the alarm behavior continues to occur, the road management unit will actively intervene offline to realize the analysis and active management of abnormal highway traffic behavior, which is conducive to improving highway traffic safety.

[0090] An embodiment of the present invention also provides a highway traffic safety supervision system based on big data analysis, the system comprising a computer device, the computer device comprising a processor and a memory, the memory storing computer instructions, the processor being used to execute the computer instructions stored in the memory, and when the computer instructions are executed by the processor, the system implements the steps implemented by the method described above.

[0091] The embodiment of the present invention also provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the steps implemented by the aforementioned method for highway traffic safety supervision based on big data analysis are implemented. The computer-readable storage medium can be a tangible storage medium, such as a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a floppy disk, a hard disk, a removable storage disk, a CD-ROM, or any other form of storage medium known in the technical field.

[0092] It should be understood by those skilled in the art that the exemplary components, systems and methods described in conjunction with the embodiments disclosed herein can be implemented in hardware, software or a combination of the two. Whether it is performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present invention are programs or code segments used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link via a data signal carried in a carrier.

[0093] It should be clear that the present invention is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present invention is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present invention.

[0094] In the present invention, features described and / or illustrated for one embodiment may be used in the same or similar manner in one or more other embodiments, and / or combined with features of other embodiments or replace features of other embodiments.

[0095] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the embodiments of the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for monitoring highway traffic safety based on big data analysis, characterized in that: The steps of the method include: Based on the data interaction between the roadside unit and the vehicle-mounted unit, the vehicle information is obtained, wherein the vehicle information includes the time point information of the vehicle passing through each roadside unit, the vehicle identity information, the vehicle image information and the vehicle weight information; Calculating the vehicle speed based on the time point information when the vehicle passes through two roadside units, and determining whether the vehicle is speeding based on the vehicle speed; Determine the standard load of the vehicle based on the vehicle identity information, and determine whether the vehicle is overloaded based on the vehicle weight information and the standard load of the vehicle; Determine the standard number of passengers in the vehicle based on the vehicle identity information, identify the number of passengers in the vehicle using an image recognition model based on the vehicle image information, and determine whether the vehicle is overloaded based on the standard number of passengers and the number of passengers in the vehicle; Determine the total driving time of the vehicle based on the time point information of the vehicle passing through multiple roadside units, and determine whether there is fatigue driving based on the length of time the vehicle stays in the service area and the total driving time; If speeding, overloading or fatigue driving occurs, an alarm will be sent to the on-board unit through the roadside unit. If the alarm duration is longer than the preset time length, a notification will be sent to the management end.

2. The method for monitoring highway traffic safety based on big data analysis according to claim 1 is characterized in that: In the step of calculating the vehicle speed based on the time point information when the vehicle passes through two roadside units, and determining whether the vehicle is speeding based on the vehicle speed, the time point information when the vehicle passes through two adjacent roadside units and the distance information between the two roadside units are obtained, the vehicle speed is calculated based on the distance information between the two roadside units and the time point information when the vehicle passes through two adjacent roadside units, the vehicle speed is compared with a threshold speed, and it is determined whether the vehicle is speeding.

3. The highway traffic safety supervision method based on big data analysis according to claim 1 is characterized in that: In the steps of determining the standard load of the vehicle based on the vehicle identity information and determining whether the vehicle is overloaded based on the vehicle weight information and the standard load of the vehicle, the vehicle model is determined based on the vehicle identity information, the vehicle standard load is matched based on the vehicle model, and the vehicle standard load is compared with the vehicle weight information to determine whether the vehicle is overloaded.

4. The method for monitoring highway traffic safety based on big data analysis according to claim 1 is characterized in that: In the steps of determining the standard number of passengers in the vehicle based on the vehicle identity information, identifying the number of people in the vehicle using an image recognition model based on the vehicle image information, and determining whether the vehicle is overloaded based on the standard number of passengers and the number of people in the vehicle, the vehicle model is determined based on the vehicle identity information, the standard number of passengers in the vehicle is matched based on the model, the number of people in the vehicle is identified based on the image recognition model, the identified number of people in the vehicle is compared with the standard number of passengers in the vehicle to determine whether the vehicle is overloaded.

5. The method for monitoring highway traffic safety based on big data analysis according to claim 4 is characterized in that: In the step of identifying the number of people in the vehicle based on the image recognition model, faces in the captured vehicle image are marked based on the image recognition model, and the number of people in the vehicle is determined based on the number of marked faces.

6. The method for monitoring highway traffic safety based on big data analysis according to any one of claims 1 to 5, characterized in that: In the step of determining the total driving time of the vehicle based on the time point information of the vehicle passing through a plurality of roadside units, and determining whether there is fatigue driving based on the length of time the vehicle stays in the service area and the total driving time: The time point information when the vehicle enters the highway and passes the first roadside unit is taken as the starting time point, and the time point information when the vehicle currently passes the last roadside unit is taken as the ending time point, and the total driving time is calculated based on the starting time point and the ending time point; The vehicle's stay time in the service area is calculated based on the gantries at the entrance and exit of the service area, and fatigue driving is determined based on the vehicle's total driving time and the stay time in the service area.

7. The method for monitoring highway traffic safety based on big data analysis according to claim 6 is characterized in that: The step of determining the total driving time of the vehicle based on the time point information of the vehicle passing through the plurality of roadside units, and determining whether there is fatigue driving based on the length of time the vehicle stays in the service area and the total driving time also includes: Based on the vehicle images collected by the gantries at the entrance and exit of the service area, the driver profile images at the entrance and exit are extracted respectively, and based on the driver profile images, it is determined whether to change the driver. If the driver is changed, the total driving time is recalculated.

8. The method for monitoring highway traffic safety based on big data analysis according to claim 7 is characterized in that: In the step of extracting driver profile images at the entrance and exit based on vehicle images collected by gantries at the entrance and exit of the service area, and determining whether to change the driver based on the driver profile images: Marking the driver's outline based on a preset first neural network model, and cutting the driver's outline from the vehicle image to obtain a driver outline image; The driver profile images at the entrance and the exit are both driven into the second neural network model, and the second neural network model outputs a similarity value, and determines whether to change the driver based on the similarity value.

9. The method for monitoring highway traffic safety based on big data analysis according to claim 8 is characterized in that: In the step of marking the driver's profile based on a preset first neural network model, cropping the driver's profile from the vehicle image, and obtaining a driver profile image, the driver's profile cropped from the vehicle image is pasted into a preset template image to obtain a driver profile image.

10. A highway traffic safety supervision system based on big data analysis, characterized in that: The system includes a computer device, which includes a processor and a memory. The memory stores computer instructions. The processor is used to execute the computer instructions stored in the memory. When the computer instructions are executed by the processor, the system implements the steps implemented by the method as described in any one of claims 1 to 9.

Images