WO2020061766A1

WO2020061766A1 - Vehicle event detection apparatus and method, and computer program product and computer-readable medium

Info

Publication number: WO2020061766A1
Application number: PCT/CN2018/107405
Authority: WO
Inventors: 孙芃
Original assignee: 西门子股份公司; 孙芃
Priority date: 2018-09-25
Filing date: 2018-09-25
Publication date: 2020-04-02

Abstract

A vehicle event detection apparatus and method, and a computer program product and a computer-readable medium. The detection method comprises the following steps: acquiring a group of pictures, arranged in chronological order, of a vehicle within a time period (S101); identifying, from the group of pictures, a change over time in the shape of the vehicle within the time period (S102); determining whether the identified change is the same as a predefined mode of a change over time in one vehicle shape (S103); and if the two are the same, determining that a mode-defined event has occurred to the vehicle (S104).

Description

Vehicle event detection device, method, computer program product and computer-readable medium

Technical field

The present invention relates to the technical field of traffic management, and in particular, to a device, a method, a computer program product, and a computer-readable medium for detecting a vehicle event.

Background technique

In the field of traffic management technology, there are many application scenarios related to the detection of vehicle events. For example: detecting whether a vehicle has stopped illegally in a parking space for loading and unloading, or two vehicles collided.

At present, most cities also use manual methods to detect vehicle incidents. Every day, a large amount of manpower is required to monitor the video captured by the camera, and manually report when an abnormal situation is found.

Summary of the Invention

In view of this, embodiments of the present invention provide a device, a method, a computer program product, and a computer-readable medium for detecting a vehicle event, which are used to realize automatic detection of a vehicle event, which can save a lot of manpower, and have accurate and timely detection advantage.

In a first aspect, a method for detecting a vehicle event is provided, including: acquiring a set of pictures sorted by time of a vehicle within a time period; and identifying, from the set of pictures, a vehicle's Changes in shape over time; determining whether the identified change is the same as a pattern of a vehicle shape that changes over time that is defined in advance; if the pattern is the same, it is determined that the vehicle has an event defined by the pattern.

By identifying the change of the shape of the vehicle capacity over time, the change is compared with a predefined pattern of the vehicle shape changing over time. Since the pattern of the vehicle shape changing over time corresponds to a vehicle event, it can be based on the vehicle shape over time Changes determine what kind of vehicle incident has occurred.

In the field of transportation, there are many types of vehicle events and complex scenes. In the embodiment of the present invention, the change of the shape of the vehicle when the vehicle event occurs and the positional relationship between the vehicle and the passengers or goods related to the vehicle are defined in advance. Multiple vehicle shape changes over time. When the identified change in vehicle shape over time matches a certain pattern, it can be easily determined that a vehicle event defined by the pattern has occurred.

Since the solution is simple and easy, does not require a large amount of storage space for storing pictures or videos, and does not require complicated algorithms, the embodiments of the present invention can be implemented on a vehicle event detection device deployed at a traffic scene, further ensuring event detection. Real-time performance, and through edge computing and processing, also reduces the processing load of the central node.

Optionally, when the change of the shape of the vehicle in the time period from the set of pictures is recognized over time, for each of the set of pictures, the changeable shape of the vehicle may be identified. At least one part; determining a change in shape of each part identified in each picture that is changeable over time within the time period. Specifically, the occupant of the vehicle may be identified for each of the group of pictures, and the positional relationship between the occupant of the vehicle and at least one part of the vehicle that can be changed is identified in each picture And, for each of the set of pictures, identifying the cargo of the vehicle; determining a positional relationship between the cargo of the vehicle identified in each of the pictures and at least one part of the vehicle that can be changed.

By identifying the changeable parts of each shape of the vehicle and the positional relationship between them, it is easier and more accurate to determine the law of the shape change of the vehicle, and the result of matching the predefined pattern is more accurate.

Optionally, before judging whether the identified change is the same as a predefined pattern of a vehicle shape changing with time, it further includes: identifying the type of the vehicle from the set of pictures; judging the identified all Whether the change is the same as a pre-defined mode of vehicle shape changing with time, and includes: comparing the identified change with at least one mode of vehicle shape changing over time corresponding to the identified type of the vehicle .

In this way, the calculation amount of the pattern matching can be further reduced, and the accuracy of the pattern matching can be further improved by first identifying the type of the vehicle.

According to a second aspect, a vehicle event detection device is provided, including:

A picture acquisition module for obtaining a set of pictures sorted by time of a vehicle within a time period;

A shape change detection module, configured to identify, from the set of pictures, a change in shape of the vehicle over time in the time period;

A pattern matching module, configured to determine whether the identified change is the same as a predefined pattern of a vehicle shape changing with time;

An event judging module, if the change is the same as a predefined pattern of a vehicle shape changing with time, determining that the vehicle has an event defined by the pattern.

By identifying the change of the shape of the vehicle capacity over time, the change is compared with a predefined pattern of the shape of the vehicle over time. Since the pattern of the shape of the vehicle over time corresponds to a vehicle event, it can be based on the shape of the vehicle over time. Changes determine what kind of vehicle incident has occurred.

Optionally, the shape change detection module is specifically configured to: for each of the group of pictures, identify at least a part where the shape of the vehicle is changeable; determine that the shape recognized in each picture is changeable The shape of each of the parts changes over time during the time period. Specifically, the shape change detection module may identify the occupant of the vehicle for each of the set of pictures; and determine that the occupants of the vehicle and the changeable of the vehicle are identified in each of the pictures. Position relationship of at least one part of; and for each of the set of pictures, identifying the goods of the vehicle; determining at least one of the pictures identifying the goods of the vehicle and the changeable of the vehicle in each picture Partial positional relationship.

Optionally, the device further includes: a vehicle type recognition module, configured to identify from the set of pictures before determining whether the identified change is the same as a predefined pattern of a vehicle shape changing with time. The type of the vehicle; the pattern matching module is specifically configured to compare the identified change with at least one pattern of vehicle shape changes over time corresponding to the identified type of the vehicle.

According to a third aspect, a vehicle event detection device is provided, including: at least one memory for storing computer-readable code; and at least one processor for calling the computer-readable code to execute the first aspect or the first aspect Method provided by any of the possible implementations.

Among them, the ERP system device provided by the second aspect, any possible implementation manner of the second aspect, the third aspect, or any possible implementation manner of the third aspect may be deployed at a traffic site to perform edge computing.

In a third aspect, a computer program product is provided that is tangibly stored on a computer-readable medium and includes computer-executable instructions that, when executed, cause at least one processor to execute a first The method provided by one aspect or any possible implementation manner of the first aspect.

According to a fourth aspect, a computer-readable medium is provided. The computer-readable medium stores computer-readable instructions, and the computer-readable instructions, when executed by a processor, cause the processor to execute the first aspect, or The method provided in any possible implementation of the first aspect.

In any of the above aspects or any possible implementation manner of any aspect, the judged event includes one of the following types: vehicle side door opened; vehicle side door closed; vehicle tail door opened; vehicle tail door closed; vehicle occupant Get on; get off the vehicle; load; unload.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG. 1 is a schematic structural diagram of a traffic management system according to a first embodiment of the present invention.

FIG. 2a is a flowchart of a method for detecting a vehicle event according to a second embodiment of the present invention.

FIG. 2b is a flowchart of a method for detecting a vehicle event according to a third embodiment of the present invention.

FIG. 3 is a schematic structural diagram of a vehicle event detection device according to a fourth embodiment of the present invention.

FIG. 4 is a schematic structural diagram of a vehicle event detection device according to a fifth embodiment of the present invention.

FIG. 5 is a schematic structural diagram of a vehicle event detection device according to a sixth embodiment of the present invention.

6 to 8 are schematic diagrams of detecting a shape change of a vehicle in each embodiment of the present invention.

FIG. 9 and FIG. 11 are schematic diagrams of detecting a vehicle occupant getting off event according to an embodiment of the present invention.

FIG. 10 is a schematic diagram of detecting a boarding event of a vehicle occupant according to an embodiment of the present invention.

FIG. 12 is a schematic diagram of detecting an unloading event in an embodiment of the present invention.

FIG. 13 is a schematic diagram of detecting a loading event in an embodiment of the present invention.

List of reference signs:

100：交通管理系统100: Traffic Management System	10：摄像头10: Camera	20：云20: Cloud
30：车辆事件的检测装置30: Vehicle event detection device	40：客户端40: Client	Zh
S101：获取图片序列S101: Obtain a picture sequence	S102：识别车辆形状变化S102: Recognize changes in vehicle shape	S103：车辆形状变化模式匹配S103: Vehicle shape change pattern matching
S104：确定发生的车辆事件S104: Determine the occurrence of a vehicle event	Zh	Zh
S201：获取图片序列S201: Obtaining a picture sequence	S202：识别车辆形状变化S202: Identify vehicle shape changes	S202’：识别车辆类型S202 ’: Identify the type of vehicle
S203：车辆形状变化模式匹配S203: Vehicle shape change pattern matching	S204：确定发生的车辆事件S204: Determine the occurrence of a vehicle event	Zh
301：图片获取模块301: Picture acquisition module	302：形状变化检测模块302: Shape change detection module	303：模式匹配模块303: Pattern matching module
304：事件判断模块304: Event judgment module	302’：车辆类型识别模块302 ’: Vehicle type identification module	Zh
305：存储器305: Memory	306：处理器306: Processor	307：通信模块307: Communication module

detailed description

In order to realize the automatic detection of vehicle events, in the embodiment of the present invention, by identifying the change of the shape of the vehicle capacity with time, the change is compared with a predefined pattern of the shape of the vehicle with time. As the shape of the vehicle changes with time, The mode corresponds to vehicle events, so you can determine what kind of vehicle event has occurred based on changes in vehicle shape over time.

[Example 1]

FIG. 1 shows a traffic management system 100 according to an embodiment of the present invention. Among them, the camera 10 is used to capture pictures or videos, and the vehicle event detection device 30 is used to perform image processing on the pictures or videos captured by the camera 10, and determine whether a vehicle event has occurred and what kind of vehicle has occurred according to the results of the image processing. event. The judgment results and related pictures or videos can be stored in the vehicle event detection device 20 or the cloud 20 side, and the client 40 (computer or mobile terminal) can log in to the cloud 20 side to obtain the detection results of the vehicle event, and can obtain related Pictures or videos, and further, various applications and the like running on the client 40 can be implemented according to the detection result of the vehicle event.

The vehicle event detection device 30 may be deployed at a traffic scene, and may be integrated with the camera 10 on the same hardware device in hardware implementation, or may be implemented by a separate hardware device.

The vehicle event detection process implemented by the vehicle event detection device 30 may refer to the second embodiment and the third embodiment described below.

[Example 2]

As shown in FIG. 2a, the method for detecting a vehicle event provided in the second embodiment may include the following steps:

S101: Acquire a picture sequence.

In this step, the vehicle event detection device 30 can capture the video or picture at the traffic scene through the camera 10. It should be noted that if the video is captured, multiple pictures ordered by time can be intercepted from the video; if If you are taking pictures, you need to mark the time of taking each picture to ensure that you get a set of pictures ordered by time.

S102: Identify a change in the shape of the vehicle.

In this step, for each of the group of pictures, at least one part of the vehicle shape that can be changed, such as a side door, a tail door, a occupant of the vehicle, a cargo of the vehicle, and the like can be identified; The shape of each part can change over time during a period of time.

Referring to FIG. 8, the camera 10 captures the upper left and upper right pictures in FIG. 8. Through target recognition, a bounding box can be used to frame the target car in the two pictures. As shown in the lower left picture and the lower right picture, the shape of the tail gate of the vehicle that can be changed is also bounded by the bounding box, then the change in the shape of the tail gate of the vehicle can be determined.

Wherein, if the occupant of the vehicle is identified from the set of pictures, the positional relationship between the occupant of the vehicle and at least one part of the vehicle that can be changed in each of the pictures can be further determined. If the cargo of the vehicle is identified from the set of pictures, the positional relationship between the identified cargo of the vehicle and at least one part of the vehicle that can be changed can be further determined.

Referring to FIG. 9, FIG. 10, and FIG. 11, the camera 10 has taken three pictures from left to right, and can recognize the changeable shape of the side door of the vehicle and the occupant of the vehicle through target recognition, and can identify the vehicle Relationship between the occupants and the side doors of the vehicle.

Referring to FIG. 12 and FIG. 13, the camera has taken three pictures from left to right, and can recognize the changeable shapes of the rear door of the vehicle, the occupant of the vehicle, and the cargo of the vehicle through target recognition, and can identify The positional relationship between the occupant of the vehicle and the tailgate of the vehicle, the positional relationship between the cargo of the vehicle and the tailgate of the vehicle, and the positional relationship between the occupant of the vehicle and the acquisition of the vehicle of the vehicle.

After the above-mentioned shape change and positional relationship are identified, the pattern matching can be performed through the following step S103 and then the vehicle event that has occurred can be determined through step S104.

S103: Match the vehicle shape change pattern.

In this step, it is determined whether the change identified in step S102 is the same as a pattern of a shape of a vehicle that changes over time in advance.

S104: If the change identified in step S102 is the same as a predefined pattern of a vehicle shape changing with time, it is determined that the vehicle has an event defined by the pattern.

The pattern of the vehicle shape changing with time, and the correspondence between the events defined by the pattern can be shown in the following table.

Optionally, a machine vision algorithm can be used to trigger an event by identifying changes in the shape of the vehicle over time. Since the machine vision algorithm does not require high processing capabilities, the above process can be deployed by edge devices deployed at the traffic site That is, the vehicle event detection device 30 is implemented. In addition, an artificial intelligence algorithm may be used to perform the above steps S103 and S104 for pattern matching and event determination.

Taking "vehicle occupants get off" shown in Figure 9 as an example, the artificial intelligence algorithm can identify the following steps:

1) As shown on the left, the vehicle is parked on the side of the road.

2) As shown in the middle figure, the side door is opened (the profile of the side of the vehicle changes). Optionally, although not shown in the figure, it is also possible to detect the vehicle occupant getting off (the boundary of the vehicle occupant) The frame is adjacent to or partially overlaps the bounding box of the vehicle, that is, the positional relationship between the occupant of the vehicle and the part where the shape of the vehicle can be changed).

3) As shown on the right, the side door is closed.

In addition, additional steps can be added to the finite state machine to improve the calculation accuracy. Various different finite state machines can be defined to support more application scenarios. Taking the "unloading" event shown in Figure 12 as an example, the finite state machine can identify the following steps:

1) As shown on the left, the vehicle is parked on the side of the road.

2) As shown in the middle figure, the tailgate is opened (the outline of the side of the vehicle changes), and a cargo is detected in the vehicle (the bounding box of the cargo overlaps with the bounding box of the vehicle).

3) As shown in the figure on the right, the tailgate opens, and passengers and cargo are detected outside the vehicle.

[Example 3]

As shown in FIG. 2b, steps S201, S202, S203, and S204 included in the method for detecting a vehicle event provided in the third embodiment may refer to the foregoing steps S101, S102, S103, and S104, respectively. Different from the second embodiment, in the third embodiment, between steps S202 and S203, when performing target recognition on the group of pictures, the type of the vehicle can be further identified. In step S203, the identified change may be compared with at least one pattern of vehicle shape changes over time corresponding to the identified type of vehicle. This can reduce the number of pattern matching and reduce the amount of calculation.

In addition, when the target is identified in the picture, the target type may be further identified, such as: a vehicle, a side door of the vehicle, a tail door of the vehicle, a cargo, a passenger of the vehicle, and the like. During pattern recognition and predefined patterns, you can define the positional relationship and timing between different types of targets, such as when the bounding box of a target of the type of the side door of the vehicle and the bounding box of the target of the type of passenger of the vehicle partially overlap , It can be determined that the passenger of the vehicle got on or off.

The process of detecting a vehicle event has been described above through the second and third embodiments. The following describes a vehicle event detection device 30 through Embodiments 4 to 6.

[Example 4]

As shown in FIG. 3, the vehicle event detection device 30 provided in the fourth embodiment may include:

A picture acquisition module 301, for obtaining a set of pictures sorted by time of a vehicle within a time period;

A shape change detection module 302, for identifying the change of the shape of the vehicle over time from a set of pictures;

A pattern matching module 303, configured to determine whether the identified change is the same as a predefined pattern of a vehicle shape changing with time;

An event judging module 304 determines that the vehicle has an event defined by the mode if the change is the same as a predefined pattern of a vehicle shape changing with time.

Optionally, the shape change detection module 302 is specifically configured to:

For each of a set of pictures, identifying at least one part of which the shape of the vehicle can vary;

Determine the change in shape of each part of the shape that can be identified in each picture over time.

Further, the shape change detection module 302 may be specifically configured to: for each of a group of pictures, identify the occupant of the vehicle; determine the identities of the vehicle and the changeable at least one part of the vehicle in each of the pictures. Positional relationship; and for each of a set of pictures, identifying the cargo of the vehicle; determining the positional relationship of the cargo of the identified vehicle in each of the pictures and at least one part of the vehicle that can be changed.

Optionally, the event determined by the event determination module 304 includes one of the following types: vehicle side door open, vehicle side door closed, vehicle tail door opened, vehicle tail door closed, vehicle occupant getting on, vehicle occupant getting off, loading Cargo, unloading.

For other optional implementations of the device, reference may be made to the second embodiment. The picture acquisition module 301 may be used to complete the foregoing step S101, the shape change detection module 302 may be used to complete the foregoing step S102, and the pattern matching module 303 may be used to complete the foregoing In step S103, the event determination module 304 may be used to complete the foregoing step S104.

[Example 5]

Different from the fourth embodiment, the vehicle event detection device 30 provided in the fifth embodiment may further include a vehicle type recognition module 302 'for determining whether the recognized change is different from a predefined shape of the vehicle over time. Before the patterns are the same, the type of the vehicle is identified from a set of pictures; and the pattern matching module 303 is specifically configured to compare the identified change with at least one pattern of the shape of the vehicle that changes over time corresponding to the identified type of vehicle. .

[Example 6]

FIG. 5 is a schematic structural diagram of a vehicle event detection device 30 according to an eighth embodiment. As shown in FIG. 5, the device may include:

At least one memory 305, configured to store computer-readable code;

At least one processor 306 is configured to call a computer-readable code to execute a method for detecting a vehicle event provided by the foregoing embodiments.

The at least one memory 305 and the at least one processor 306 may be connected through a bus. In addition, the device may further provide at least one communication interface 307 for communicating with the camera 10 and the cloud 20, and transmitting pictures and picture information. The communication interface 307 and the memory 305 and the processor 306 can also communicate through a bus.

It should be noted that the modules and the like included in the vehicle event detection device 30 in Embodiments 5 to 6 can be regarded as program modules in computer-readable codes stored in at least one memory 305 shown in FIG. 5. At least one processor 306 calls to execute a method for detecting a vehicle event provided by an embodiment of the present invention. The program module may be included in the computing device in the form of an operating system, an application program module, and other program modules, and may also be physically stored in several known memory devices. The program module may include, but is not limited to, a routine, a subroutine, a program, an object, a component, and a data structure for performing a specific operation or a type of specific abstract data to be described in accordance with the present invention.

In addition, the above-mentioned modules can also be regarded as various functional modules implemented by a combination of hardware and software, and various functions involved in the vehicle event detection device 30 when executing the vehicle event detection method. The above-mentioned modules can also be regarded as various functional modules implemented by hardware, which are used to implement various functions involved in the vehicle event detection device 30 when performing the vehicle event detection method, such as the methods involved in the vehicle event detection method in advance. The control logic of each process is burned into, for example, a Field-Programmable Gate Array (FPGA) chip or a Complex Programmable Logic Device (CPLD), and these chips or devices execute the above modules The specific functions and implementation methods may depend on engineering practice.

In addition, an embodiment of the present invention further provides a computer-readable medium. The computer-readable medium stores computer-readable instructions. When the computer-readable instructions are executed by a processor, the method for detecting a processor vehicle event. Examples of computer-readable media include floppy disks, hard disks, magneto-optical disks, optical disks (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD + RW), magnetic tape, non- Volatile memory card and ROM. Alternatively, the computer-readable instructions may be downloaded from a server computer or the cloud by a communication network.

In summary, embodiments of the present invention provide a method, a device, a computer-readable medium, a computer program product, and a traffic management system for detecting a vehicle event. By identifying the change of the shape of the vehicle capacity over time, the change is compared with a predefined pattern of the shape of the vehicle over time. Since the pattern of the shape of the vehicle over time corresponds to a vehicle event, it can be based on the shape of the vehicle over time. Changes automatically determine what kind of vehicle event has occurred.

It should be noted that not all steps and modules in the above processes and system structure diagrams are necessary, and some steps or modules can be ignored according to actual needs. The execution order of each step is not fixed and can be adjusted as needed. The system structure described in the above embodiments may be a physical structure or a logical structure, that is, some modules may be implemented by the same physical entity, or some modules may be implemented by multiple physical entities, or may be implemented by multiple Some components in separate devices are implemented together.

Claims

A method for detecting a vehicle event, including:

Get a set of pictures sorted by time of a vehicle in a time period;

Identifying changes in the shape of the vehicle over the period of time from the set of pictures;

Determining whether the identified change is the same as a predefined pattern of a vehicle shape changing with time;

If they are the same, it is determined that the vehicle has an event defined by the mode.
The method of claim 1, wherein identifying the change in shape of the vehicle over the time period from the set of pictures includes:

For each of the set of pictures, identifying at least a portion of which the shape of the vehicle is changeable;

It is determined that the shape of each part of the shape that can be changed in each picture is changed over time within the time period.
The method according to claim 2, wherein identifying the change of the shape of the vehicle in the time period from the set of pictures with time further comprises:

For each of the set of pictures, identifying a occupant of the vehicle;

A positional relationship between an occupant of the vehicle and at least a changeable part of the vehicle is identified in each picture.
The method according to claim 2, wherein identifying the change of the shape of the vehicle in the time period from the set of pictures with time further comprises:

For each of the set of pictures, identifying the cargo of the vehicle;

A positional relationship between the cargo of the vehicle and at least a changeable part of the vehicle is identified in each picture.
The method according to any one of claims 1 to 4, wherein

Before determining whether the identified change is the same as a predefined pattern of a vehicle shape changing with time, the method further includes: identifying the type of the vehicle from the set of pictures;

Judging whether the identified change is the same as a predefined pattern of a vehicle shape changing with time, including: comparing the identified change with at least one vehicle shape corresponding to the identified type of the vehicle over time Compare the patterns of change.
The method according to any one of claims 1 to 5, wherein the event comprises one of the following types:

Vehicle side doors open;

Vehicle side door closed;

The tailgate of the vehicle is open;

Vehicle tailgate closed;

Vehicle occupants board;

Vehicle occupants get off;

Loading

discharge.
The vehicle event detection device (30) is characterized in that it comprises:

A picture acquisition module (301) for obtaining a set of pictures sorted by time of a vehicle within a time period;

A shape change detection module (302), configured to identify, from the set of pictures, a change in shape of the vehicle over time in the time period;

A pattern matching module (303), configured to determine whether the identified change is the same as a predefined pattern of a vehicle shape changing with time;

An event judging module (304), if the change is the same as a predefined pattern of a vehicle shape changing with time, determining that the vehicle has an event defined by the pattern.
The device (30) according to claim 7, wherein the shape change detection module (302) is specifically configured to:

For each of the set of pictures, identifying at least a portion of which the shape of the vehicle is changeable;

It is determined that the shape of each part of the shape that can be changed in each picture is changed over time within the time period.
The device (30) according to claim 8, wherein the shape change detection module (302) is specifically configured to:

Identify each occupant of the vehicle for each of the set of pictures;

A positional relationship between an occupant of the vehicle and at least a changeable part of the vehicle is identified in each picture.
The device (30) according to claim 8, wherein the shape change detection module (302) is specifically configured to:

For each of the set of pictures, identifying the cargo of the vehicle;

A positional relationship between the cargo of the vehicle and at least a changeable part of the vehicle is identified in each picture.
The device (30) according to any one of claims 7 to 10, further comprising: a vehicle type identification module (302 ') for determining whether the identified change is different from a predefined one Before the vehicle shape changes in time with the same pattern, identifying the type of the vehicle from the set of pictures;

The pattern matching module (303) is specifically configured to compare the identified change with at least one pattern of vehicle shape changes over time corresponding to the identified type of the vehicle.
The device (30) according to any one of claims 7 to 11, wherein the event judged by the event judgment module (304) includes one of the following types:

Vehicle side doors open;

Vehicle side door closed;

The tailgate of the vehicle is open;

Vehicle tailgate closed;

Vehicle occupants board;

Vehicle occupants get off;

Loading

discharge.
The vehicle event detection device (30) is characterized in that it comprises:

At least one memory (305) for storing computer-readable code;

At least one processor (306), configured to call the computer-readable code and execute the method according to any one of claims 1 to 6.
The device (30) according to any one of claims 7 to 13, which is deployed at a traffic site.
A computer program product tangibly stored on a computer-readable medium and including computer-executable instructions that, when executed, cause at least one processor to perform any of claims 1 to 6 Item.
A computer-readable medium, wherein computer-readable instructions are stored on the computer-readable medium, and when the computer-readable instructions are executed by a processor, the processor causes the processor to execute claims 1 to 6. The method of any one.