CN115273545A

CN115273545A - Safety early warning method and equipment for auxiliary road driving scene

Info

Publication number: CN115273545A
Application number: CN202210839628.5A
Authority: CN
Inventors: 李和安
Original assignee: Mercedes Benz Group AG
Current assignee: Mercedes Benz Group AG
Priority date: 2022-07-18
Filing date: 2022-07-18
Publication date: 2022-11-01
Also published as: DE102023002802A1

Abstract

The present invention relates to the field of safe driving of vehicles. The invention provides a safety early warning method for a road-assisting driving scene, which comprises the following steps: s1: identifying a driving behavior of the vehicle on a secondary road parallel to the main road; s2: in response to identifying the driving behavior, detecting whether a vehicle is approaching a predefined category of point of risk, the point of risk being located between a main road and a secondary road; and, S3: in case it is detected that the vehicle is approaching said point of risk, a warning is issued to the driver of the vehicle and/or to the surroundings of the vehicle. The invention also provides a device for safety early warning of a road-assisting driving scene and a machine-readable storage medium. According to the method and the device, the early warning scenes are screened by considering the type of the road on which the vehicle runs, so that unnecessary information push and the number of false alarms can be reduced, and a more accurate and efficient early warning triggering mechanism is realized.

Description

Safety early warning method and equipment for auxiliary road driving scene

Technical Field

The invention relates to a safety early warning method for a secondary driving scene, and also relates to equipment for safety early warning of the secondary driving scene and a machine-readable storage medium.

Background

With the development of traffic industry and the improvement of national economic level, the quantity of vehicles kept is steadily increased, however, the quantity of traffic accidents is increased. Statistical studies show that the frequency of traffic accidents when vehicles run on the side road is high, and the accidents are mainly caused by the great complexity and uncertainty brought by the mixed running mechanism of motor vehicles and non-motor vehicles. In addition, some countries and regions may build bus stations at the junctions of main roads and auxiliary roads, which means that the passengers of the bus must cross the auxiliary roads to enter or leave the station platform when getting on or off the bus. In many cases, the passengers may not observe the vehicle coming from behind due to the blind area of the viewing angle, and the vehicle may also not be able to timely detect the passengers getting off the vehicle suddenly, thereby causing a collision between the vehicle and the pedestrian.

For this purpose, it is proposed in the prior art to notify the surrounding vehicles before the bus stops, so that the vehicles can immediately recognize the occurring dangerous situation and react to it.

A method for non-motor vehicle riding alert is also known in order to alert a rider when there are dangerous environmental elements around the rider, such as bus stops, road zebra crossings, etc.

However, the solutions known so far still have a number of disadvantages, in particular, at present, only the identification and detection of the hazard site itself is focused on, but the vehicle driving scene is not filtered, so that excessive false alarms are easily caused, which may cause unnecessary mental stress to the driver and intervene in the normal driving of the surrounding road participants.

In this context, it is desirable to provide an improved vehicle early warning scheme, which aims to improve the safety of a vehicle in a road-following driving scene through a more precise triggering mechanism.

Disclosure of Invention

The invention aims to provide a method for safety precaution of a secondary driving scene, a device for safety precaution of a secondary driving scene and a machine-readable storage medium, so as to solve at least part of problems in the prior art.

According to a first aspect of the present invention, a method for safety precaution in a secondary driving scenario is provided, the method comprising the steps of:

s1: identifying a driving behavior of the vehicle on a secondary road parallel to the main road;

s2: in response to identifying the driving behavior, detecting whether a vehicle is approaching a predefined category of point of risk, the point of risk being located between a main road and a secondary road; and

s3: in case it is detected that the vehicle is approaching said point of risk, a warning is issued to the driver of the vehicle and/or to the surroundings of the vehicle.

The invention comprises in particular the following technical concepts: when the potential risks are identified, not only are specific point location types which possibly cause dangers considered, but also the traffic environment where the vehicle is located is screened in advance, so that the early warning triggering scene is accurately limited under the condition that the vehicle runs on the side road. In general, the number of unnecessary information push and wrong alarms is reduced, and the driving safety of the vehicle on the side road section is improved.

Optionally, the point of risk relates to the following position between the main road and the auxiliary road: at said location crossing behaviour of the secondary road by at least one traffic object occurs with a predefined risk.

Thereby, the following technical advantages are achieved: due to the particularity of the traffic rules applicable in the secondary road, the phenomenon that pedestrians cross the road may frequently occur under the condition that the traffic signal lamp is not used for controlling the driving authority. By giving important consideration to the positions with higher crossing risks in the safety strategy, the vehicle can obtain more reliable and effective early warning.

Optionally, the point of risk includes:

the bus station is arranged at a road edge between the main road and the auxiliary road; and/or

The inlet channel and/or the outlet channel of the overpass are arranged at the curb between the main road and the auxiliary road.

Thereby, the following technical advantages are achieved: it is recognized that the frequent crossing of the side roads by the passengers is usually to reach the bus station or the overpass, and if the source positions causing the potential safety hazards are considered in an important way, the collision accidents can be avoided more pertinently.

Optionally, in step S3, in the case that it is detected that the vehicle is approaching the point of risk, the warning is issued to the surroundings of the vehicle only when crossing behavior of the at least one traffic object on the secondary road is occurring at the point of risk and/or there is crossing intention of the at least one traffic object on the secondary road.

Thereby, the following technical advantages are achieved: unnecessary early warning scenes can be further filtered out, and therefore the acceptance of the early warning function is improved.

Optionally, in the case where the point of risk relates to a bus stop, when the bus is entering or has stopped at the bus stop, it is confirmed that the crossing behavior of the at least one traffic object with respect to the secondary road is being recognized at the point of risk and/or there is a crossing intention of the at least one traffic object with respect to the secondary road.

Thereby, the following technical advantages are achieved: if a bus is entering a station or has stopped, it usually means that there is a higher probability that a passenger is getting on/off the bus. With the help of the recognition of the bus, the difficulty of recognizing the intention or the behavior of the pedestrian can be reduced, and therefore the reliability of the whole scheme is improved.

Optionally, detecting whether the vehicle is approaching a point of risk comprises:

acquiring an image of the surroundings of the vehicle, identifying predefined categories of point of risk in the image by means of a trained object classifier and/or an artificial neural network; and/or

And receiving the information of the risk point positions within the preset range around the vehicle by means of vehicle-to-vehicle and/or vehicle-to-infrastructure communication.

Thereby, the following technical advantages are achieved: based on the image recognition technology, the surrounding environment of the vehicle can be identified with higher accuracy, and a reliable data base is provided for the correct triggering of the alarm. Furthermore, even in the case of a vehicle not carrying a high-precision camera or in-vehicle cameras being unavailable, additional possibilities for detecting points of risk can be provided by means of vehicle communication technology.

Optionally, the method further comprises the steps of:

acquiring a current position of a vehicle and a digital map of a surrounding environment of the vehicle;

the driving behavior of the vehicle on a side road parallel to the main road is identified based on the localization information of the current position of the vehicle in the digital map, and/or a plausibility check is performed on the detection result regarding the point of risk in step S2 based on the localization information of the current position of the vehicle in the digital map.

Thereby, the following technical advantages are achieved: by fully utilizing the digital map information, the auxiliary road driving scene can be more accurately deduced based on lane recognition. In addition, the rich content of the digital map can also be used for supplementing or verifying the image identification result, so that the detection accuracy of the point of risk is further improved.

Optionally, issuing an early warning to a driver of the vehicle and/or to a surrounding of the vehicle comprises:

informing the driver that the vehicle is approaching the risk point on a vehicle-mounted display unit and/or through voice broadcast;

triggering an emergency braking function of the vehicle; and/or

Controlling the lamp of the vehicle to flash and/or controlling the horn of the vehicle to sound so as to send out an optical alarm signal and/or an acoustic alarm signal with warning content to the surrounding environment of the vehicle.

Thereby, the following technical advantages are achieved: by controlling the alarm sending mode, the driver can be made aware of the emergency danger in advance, and the brake can be automatically completed when the driver does not react in time. Further, by issuing an alarm to the surroundings of the vehicle, it is possible to make a pedestrian who intends to cross the road notice the approach of the vehicle.

According to a second aspect of the present invention, there is provided a device for safety precaution in a secondary driving scenario, the device being configured to perform the method according to the first aspect of the present invention, the device comprising:

an identification module configured to be able to identify a driving behavior of a vehicle on a secondary road parallel to a main road;

a detection module configured to be able to detect whether a vehicle is approaching a predefined category of point of risk located between the primary and secondary roads in response to identifying the driving behaviour; and

a control module configured to issue a warning to a driver of the vehicle and/or to the surroundings of the vehicle in the event that the vehicle is detected to be approaching the point of risk.

According to a third aspect of the present invention, there is provided a machine-readable storage medium having stored thereon a computer program for performing the method according to the first aspect of the present invention when run on a computer.

Drawings

The principles, features and advantages of the present invention may be better understood by describing the invention in more detail below with reference to the accompanying drawings. The drawings comprise:

fig. 1 shows a block diagram of a device for safety precaution for a secondary driving scenario according to an exemplary embodiment of the present invention;

FIG. 2 shows a flow diagram of a method for safety precaution for a secondary driving scenario, according to an exemplary embodiment of the present invention;

fig. 3 shows a flow chart of a method for safety precaution for a secondary driving scenario according to another exemplary embodiment of the present invention;

FIG. 4 shows a schematic diagram of the use of the method according to the invention in an exemplary application scenario; and

fig. 5 shows a schematic representation of the use of the method according to the invention in a further exemplary application scenario.

Detailed Description

In order to make the technical problems, technical solutions and advantageous effects of the present invention more apparent, the present invention will be described in further detail with reference to the accompanying drawings and exemplary embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and do not limit the scope of the invention.

Fig. 1 shows a block diagram of a device for safety precaution for a secondary driving scenario according to an exemplary embodiment of the present invention.

As shown in fig. 1, a vehicle 100 comprises a device 1 according to the invention. Here, the vehicle 100 further includes a panoramic vision sensing system including a front-view camera 11, a left-view camera 12, a rear-view camera 13, and a right-view camera 14, a radar sensor 15, and a lidar sensor 16, for example. With these vehicle-mounted environment sensors, the vehicle 100 can perform various functions such as back-up assistance, obstacle detection, road structure recognition, and the like to support partially autonomous traveling or fully autonomous traveling, for example. Furthermore, the vehicle 100 for example also comprises a communication interface 17 based on car networking technology and a positioning navigation unit 18. By means of the communication interface 17, it is possible to receive traffic information from other traffic participants, infrastructure and/or road supervision platforms and also to share the traffic information collected by the vehicle 100 to the other traffic participants. By means of the positioning and navigation unit 18, the position of the vehicle in the digital map can be determined in real time and the landmark information around the vehicle can be known therefrom. It should be noted herein that the vehicle 100 may include other types and numbers of sensors besides the sensors shown in fig. 1, and the present invention is not particularly limited thereto.

For safety precaution in a road-side driving scenario, the device 1 comprises, for example, an identification module 10, a detection module 20 and a control module 30, which are connected to one another in terms of communication technology.

The recognition module 10 is used to recognize the driving behavior of the vehicle 100 on a secondary road parallel to the main road. To this end, the identification module 10 may for example be connected to a panoramic visual perception system of the vehicle 100 in order to receive images of the road ahead and/or to the sides of the vehicle 100. In the recognition module 10, road morphology (including, for example, the number of lanes, lane width, lane marking morphology, lane boundary position, street lamp position, curb position, sidewalk position, etc.) around the vehicle is recognized from these images by means of a trained machine learning model, then classification is performed on the traffic scene in which the vehicle 100 is currently located based on the road morphology, and it is checked whether the current traffic scene matches one or more preset scenes. In addition or alternatively, the recognition module 10 can also be connected to a positioning navigation unit 18, for example, so that a lane-level positioning of the vehicle 100 can be obtained, in combination with the road information stored in the digital map, it being likewise possible to determine whether the vehicle 100 is currently driving on a secondary road parallel to the main road.

The recognition module 10 is connected to the detection module 20 and is adapted to provide recognition results regarding the traffic scene in which the vehicle is located to the detection module 20. If it has been identified that the vehicle 100 is traveling in a secondary road scenario, the detection module 20 initiates detection of a point of risk in the vehicle's surroundings and checks whether the vehicle is approaching the point of risk. For this purpose, the detection module 20 is likewise connected to the forward-looking camera 11 of the vehicle 100, for example, and receives images of the road environment in front of the vehicle 100, and with the aid of a suitable image recognition algorithm, the detection module 20 is able to recognize the characteristic features of the risk points from the captured images, so that the presence of the risk points can be recognized well. Furthermore, the detection module 20 can also receive information from other surrounding traffic participants/infrastructure, for example, by means of the communication interface 17, so that the image recognition result can be supplemented or verified, for example, by means of over-the-horizon information.

With the control module 30, a warning may be issued to the driver of the vehicle 100 and/or to the surroundings of the vehicle 100 in the event that it is confirmed that the vehicle 100 is approaching a point of risk. Such a warning can be issued, for example, visually and/or audibly to the driver or to the surroundings of the vehicle. As an example, the control module 30 may be connected to a display unit 41 of the vehicle 100, for example, so that a warning prompt may be displayed on the display unit 41 when the point of risk is approached. Furthermore, in this exemplary embodiment, the control module 30 is also connected, for example, to the horn 42 of the vehicle 100, so that the control module 30 can, if necessary, prompt the horn of the vehicle 100 to sound in order to immediately draw the attention of surrounding traffic.

It should be noted here that although the

individual sub-modules

10, 20, 30 of the device 1 are shown in fig. 1 as communication interfaces and connected to individual sensors or actuators, it is also possible for these

modules

10, 20, 30 to be constructed directly as or to comprise the above-described on-board sensors and actuators.

Fig. 2 shows a flowchart of a method for safety precaution for a secondary driving scenario according to an exemplary embodiment of the present invention. In the embodiment shown in fig. 2, the method exemplarily comprises steps S1-S3 and may for example be implemented in case of using the device 1 shown in fig. 1.

In step S1, a driving behavior of the vehicle on a side road parallel to the main road is identified.

In this context, a main road, which is also synonymously referred to as a "main road," for example, usually only allows motor vehicles to travel, while a secondary road allows mixed traffic of motor vehicles, non-motor vehicles and pedestrians. Both road types will generally occur simultaneously, however, in some narrower sections only one of the two types may occur alone.

The invention aims to: and screening out traffic scenes in which the auxiliary road and the main road exist simultaneously, and responding to the possible risks in the special scene. In order to distinguish the sub road driving scene from the main road driving scene and the like, it is necessary not only to perform the determination in terms of the road type in terms of the lane width/lane line shape, but also to verify the rationality of the recognition result of the road type based on the directional characteristic of at least one visual road feature and the presence of a special marker, for example.

In order to avoid an erroneous parking of the vehicle on the side of the auxiliary road, it is furthermore possible to additionally detect the movement state of the vehicle and to carry out the recognition of the road type only when the vehicle speed is greater than zero or only when the vehicle is in the ignition state.

Additionally or alternatively, the driving behavior of the vehicle on a side road parallel to the main road can also be inferred comprehensively in conjunction with the GPS coordinates of the vehicle or information received by means of the communication interface.

In step S2, in response to identifying a driving behavior of the vehicle traveling on a secondary road parallel to the primary road, it is detected whether the vehicle is approaching a predefined class of point of risk located between the primary road and the secondary road.

In the sense of the present invention, a "point of risk" is understood to be located between the main road and the secondary road in the following positions: at which crossing behavior of the secondary road by the at least one traffic object occurs at a predefined risk.

Such points of risk include, for example, bus stops and entrances and/or exits to overpasses. It should be noted, however, that not all bus stops, and overpass entrances and/or exits, etc., are equally important in risk assessment. In this context, particular attention is paid to the entrance and/or exit passages of bus stops and overpasses which are arranged at the borders between main roads and auxiliary roads and which must be traversed by persons if they need to arrive at or leave such locations, which therefore represent a very large potential risk. In addition, other types of risk points can be considered according to the specific traffic rules and cultural characteristics of the country and/or region, so that the early warning behavior of the vehicle is suitable for different use scenes.

Advantageously, the presence check of the point of risk and the estimation of the proximity of the vehicle are initiated only when it has been identified that the vehicle is on a secondary road parallel to the primary road, thereby greatly reducing the overhead with respect to the detection and identification of the point of risk. In addition, for example, instead of additionally capturing an image of the surroundings of the vehicle solely for detecting the risk point, the image that has been acquired in step S1 at the stage of identifying the type of road in which the vehicle is located is directly used, and the image identification result that has been performed in step S1 is fully utilized in detecting the risk point, thereby further saving computational overhead.

In step S3, in case it is detected that the vehicle is approaching a point of risk, a warning is issued to the driver of the vehicle and/or to the surroundings of the vehicle. In this step, for example, at least one of the following measures can be taken:

triggering an emergency braking function of the vehicle; and/or

Furthermore, it is also conceivable to perform these warning measures in a certain order. For example, the image of the driver can be shot by a personnel monitoring camera in the vehicle cabin, whether the driver reacts to the triggered alarm is checked, and if the driver does not react, the vehicle is controlled to automatically take emergency braking.

Fig. 3 shows a flowchart of a method for safety precaution for a secondary driving scenario according to another exemplary embodiment of the invention. Step S1 in fig. 2 for example comprises sub-steps S11-S13, step S2 for example comprises sub-steps S21-S23, and step S3 for example comprises sub-steps S31-S32.

In step S11, images of the surroundings of the vehicle are continuously recorded by means of the onboard camera and analyzed by means of the trained machine learning model and the traffic scene or road type in which the vehicle is located is identified.

Since the machine learning model has been pre-trained with a large number of image samples, the machine learning model is able to automatically distinguish which type of road the vehicle is driving on when a predefined type of visual road feature appears in the image.

For determining the road type, one comparison with one or more reference features by means of the visual road feature may be sufficient, or a plurality of comparisons may also be performed. For example, 3 to 5 positive comparisons may be required.

In step S12, the current GPS position of the vehicle is acquired, and the traffic scene or road type in which the vehicle is located is determined in the digital map carried by the vehicle. Specifically, for example, the lane type in which the vehicle is currently traveling may be read directly from the positioning information of the vehicle in the digital map.

In step S13, it is comprehensively determined whether the vehicle is located on a secondary road parallel to the main road based on the image recognition result and the positioning information of the vehicle in the digital map.

For example, the detected lane width in which the vehicle is located may be compared with a standard lane width of a side road, and it may be determined whether the current road type relates to the side road. On this basis, such a decision can also be performed by identifying directional characteristics of road features around the vehicle, for example, it can be checked whether the sidewalk or the isolation structure between the main road and the auxiliary road is located on the left or right side of the vehicle.

It is also conceivable to confirm this only when it is concluded that the vehicle is traveling on a secondary road parallel to the main road based on both the image recognition result and the positioning information.

If it is determined in step S13 that the vehicle is not traveling on a secondary road parallel to the main road, the early warning function is not triggered in step S32. At the same time, such assessment of aspects of the traffic scenario may continue to be performed.

If it has been confirmed that the vehicle is traveling on a secondary road parallel to the main road, it is further checked in step S21 whether the vehicle is approaching at least one bus stop provided on a curb located between the main road and the secondary road. As an example, it can be checked with the aid of the image recognition result whether a bus stop of the type described above can be observed in the road environment ahead of the vehicle.

For example, if landmark features such as a stop board at a bus stop, a structural outline of a overpass, and a barrier gap between a main road and a side road are recognized in an image captured by a vehicle-mounted camera, it is confirmed that a vehicle is approaching a point of risk. Additionally, for example, the distance between the relevant risk point and the vehicle can be deduced in terms of the size, shape and position of various road elements in the captured image, so that the risk size can be further measured in terms of distance, and a foundation is laid for more accurate early warning.

Next, the presence of the identified bus stops is checked based on the information of the digital map in step S22, thereby performing a reliability check on the detection result of the point of risk.

For example, if it is found in conjunction with the digital map information that there is no bus stop within a range of 20 meters ahead of the vehicle, the early warning function is not triggered in step S32. This may indicate that there is an error in the image recognition result, or that a bus stop opposite to the road is erroneously recognized as a point of risk.

In contrast, if the bus stop is not only identified in the image taken with the vehicle-mounted camera, but also verified in the digital map, it indicates that the vehicle is indeed approaching a point of risk in the side road scene. In this case, the check in step S23 may continue: whether a bus is approaching a station, or whether a bus is parked at the bus station.

If no bus is found near the bus stop, it indicates that there is a behavior or intention of a person to cross the road with a low probability near the point of risk, and therefore, no warning may be issued temporarily in step S32.

If it is found that there is already a parked bus at the bus stop, indicating that the getting-on and getting-off behavior of the passenger is taking place with a high probability, the passenger who has got off will gather near the bus stop and may walk through the side at some point in the future. At this time, a warning may be issued to the driver of the vehicle and/or to the surroundings of the vehicle in step S31.

Fig. 4 shows a schematic representation of the use of the method according to the invention in an exemplary application scenario.

In the scenario shown in fig. 4, the vehicle 100 is traveling on a side road 502 in a certain direction and is about to arrive at a bus stop 310, where a waiting area dedicated to waiting and a bus sign 320 are provided at the bus stop 310. Note also that a main road 501 is laid alongside a secondary road 502, the main road 501 and the secondary road 502 extending parallel to each other and being separated from each other by a curb 300.

In fig. 4, the main road 501 has two lanes, and only vehicles are allowed to travel on each lane. A mixed passage of motor vehicles and non-motor vehicles and pedestrians is permitted on the secondary road 502, for example, the outer side of the secondary road 502 being delimited by the sidewalk 400, and the secondary road 502 being delimited on the side adjacent to the main road 501 by a curb 300, which curb 300 is configured, for example, as a green belt. Notably, bus stops 310 are constructed on curb 300 between main road 501 and secondary road 502.

In order to implement early warning in a secondary driving scene, the vehicle 100 detects the road environment ahead by means of the vehicle-mounted camera, and recognizes: a bus stop 310 exists a short distance ahead, and the bus 200 has stopped at the bus stop 310. It can be seen that several passengers 401 have descended from bus 200 and are ready to traverse side road 502 to the opposite sidewalk 400. In addition, some passengers 402 are attempting to cross the secondary road 502 from the sidewalk 400 to the platform 310 in order to ride the bus 200. In this case, it may be determined that the vehicle 100 is approaching the point of risk 310, and that there is a crossing intention of the pedestrian for the sub-road 502 at the point of risk 310. In order to avoid collision between the vehicle 100 and the suddenly appearing

pedestrians

401 and 402, the vehicle 100 may be controlled to warn the pedestrians in advance (for example, when the vehicle 100 is 5 m away from the bus stop 310) by whistling or causing the headlights to blink, and the driver may be notified of the imminent passing of the dangerous area inside the vehicle 100 in the form of voice, text, or the like.

In the scenario shown in fig. 5, the vehicle 100 is also traveling on a side road 502 in a certain direction, and a main road 501 of two lanes is laid side by side beside the side road 502. In the scenario shown in fig. 5, there is a street bridge 600, which street bridge 600 has, in addition to a second inlet and/or outlet channel 602 of the walkway 400 extending outside the side road 502, a first inlet and/or outlet channel 601 to the curb 300. By adding such first entrance and/or exit passageways 601 at the curb 300, passengers who would otherwise alight at nearby bus stops (not expressly shown) can more conveniently reach the overpass 600 without having to traverse the secondary roads 502. However, since the first entrance and/or exit passageway 601 and the second entrance and/or exit passageway 602 of the overpass 500 extend in opposite directions, many pedestrians walking through the overpass 600 may choose to enter and exit the first entrance and/or exit passageway 601 near the curb 300 in order to save time. This also increases the risk of a pedestrian crossing the side road 502.

To provide an early warning of this situation, the vehicle 100 first determines the type of road on which it is located. The vehicle 100 then detects the presence of the overpass 600 in front of the road, for example in conjunction with image recognition techniques, and the overpass 600 has an entrance and/or exit channel leading to the curb 300 between the main road 501 and the secondary road 502. Still further, the vehicle 100 may also determine a specific behavioral intent, for example, in conjunction with facial expression and/or motion recognition of the person. Therefore, whether the early warning function needs to be triggered or not can be determined under the condition of integrating various factors.

Although specific embodiments of the invention have been described herein in detail, they have been presented for purposes of illustration only and are not to be construed as limiting the scope of the invention. Various substitutions, alterations, and modifications may be devised without departing from the spirit and scope of the present invention.

Claims

1. A method for safety precaution in a secondary driving scenario, the method comprising the steps of:

s1: identifying a driving behavior of a vehicle (100) on a secondary road (502) parallel to a main road (501);

s2: in response to identifying the driving behavior, detecting whether a vehicle (100) is approaching a point of risk (310) of a predefined category, the point of risk (310) being located between a main road (501) and a side road (502); and

s3: in case it is detected that the vehicle (100) is approaching the point of risk (310), an early warning is issued to a driver of the vehicle (100) and/or to a surrounding of the vehicle (100).

2. The method according to claim 1, wherein the point of risk (310) relates to a position between a main road (501) and a secondary road (502) as follows: a crossing behavior of the at least one traffic object (401) to the secondary road (502) occurs at the location with a predefined risk.

3. The method according to claim 1 or 2, wherein the point of risk (310) comprises:

a bus stop arranged at a curb (300) located between a main road (501) and a secondary road (502); and/or

An entrance and/or exit channel (601) of a street bridge (600), the entrance and/or exit channel (601) of the street bridge (600) being arranged at a curb (300) located between a main road (501) and a secondary road (502).

4. Method according to any one of claims 1 to 3, wherein in step S3, in the event of detection that the vehicle (100) is approaching the point of risk (310), a warning is issued to the surroundings of the vehicle (100) only if a crossing behavior of the at least one traffic object (401) on the secondary road (502) is occurring at the point of risk (310) and/or an intention of the at least one traffic object (401) to cross the secondary road (502) is present.

5. The method according to claim 4, wherein, in the case where the point of risk (310) relates to a bus stop, when a bus (200) is entering or has stopped at the bus (200) stop, it is confirmed that a crossing behavior of at least one traffic object (401) to a secondary road (502) is occurring at the point of risk (310) and/or there is a crossing intention of at least one traffic object (401) to a secondary road (502) is identified.

6. The method of any of claims 1-5, wherein detecting whether a vehicle (100) is approaching a point of risk (310) comprises:

acquiring an image of the surroundings of the vehicle (100), identifying predefined classes of point of risk locations (310) in the image by means of a trained object classifier and/or an artificial neural network; and/or

Information of point of risk locations (310) within a preset range around the vehicle (100) is received by means of vehicle-to-vehicle and/or vehicle-to-infrastructure communication.

7. The method according to any one of claims 1 to 6, wherein the method further comprises the steps of:

acquiring a current position of the vehicle (100) and a digital map of a surrounding environment of the vehicle (100);

identifying the driving behavior of the vehicle (100) on a secondary road (502) parallel to the main road (501) based on the localization information of the current position of the vehicle (100) in the digital map, and/or performing a plausibility check on the detection result in step S2 with respect to the point of risk (310) based on the localization information of the current position of the vehicle (100) in the digital map.

8. The method according to any one of claims 1 to 7, wherein issuing an early warning to a driver of the vehicle (100) and/or to a surrounding of the vehicle (100) comprises:

informing the driver that the risk point (310) is approaching on an on-board display unit and/or by voice broadcast;

triggering an emergency braking function of the vehicle (100); and/or

Controlling the lamps of the vehicle (100) to flash and/or controlling the horn of the vehicle (100) to sound in order to emit an optical and/or acoustic warning signal with warning content to the surroundings of the vehicle (100).

9. A device (1) for safety precaution of a road traffic scenario, the device (1) being adapted to perform the method according to any one of claims 1 to 8, the device (1) comprising:

-an identification module (10), the identification module (10) being configured to be able to identify a driving behaviour of a vehicle (100) on a secondary road (502) parallel to a primary road (501);

a detection module (20), the detection module (20) being configured to be able to detect whether a vehicle (100) is approaching a predefined category of point of risk (310) in response to identifying the driving behavior, the point of risk (310) being located between the main road (501) and a secondary road (502); and

a control module (30), the control module (30) being configured to be able to issue a warning to a driver of the vehicle (100) and/or to a surrounding of the vehicle (100) in case it is detected that the vehicle (100) is approaching the point of risk (310).

10. A machine-readable storage medium, on which a computer program is stored for performing the method according to any one of claims 1 to 8 when run on a computer.