CN109835348B - Screening method and device for road traffic dangerous scene - Google Patents
Screening method and device for road traffic dangerous scene Download PDFInfo
- Publication number
- CN109835348B CN109835348B CN201910075575.2A CN201910075575A CN109835348B CN 109835348 B CN109835348 B CN 109835348B CN 201910075575 A CN201910075575 A CN 201910075575A CN 109835348 B CN109835348 B CN 109835348B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- dangerous
- scene
- target object
- rel
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Landscapes
- Traffic Control Systems (AREA)
Abstract
The invention discloses a method and a device for screening road traffic dangerous scenes, electronic equipment and a storage medium, relates to the technical field of road traffic, and is used for quickly and effectively screening out the traffic dangerous scenes from a large amount of road traffic data. The screening method of the road traffic dangerous scene comprises the following steps: determining a dangerous object according to the driving area range of the vehicle in the road traffic data; and when the vehicle has a collision danger with the dangerous target object at the current speed, confirming that the scene is a traffic danger scene.
Description
Technical Field
The invention belongs to the technical field of road traffic, and particularly relates to a method and a device for screening a road traffic dangerous scene.
Background
The road traffic scene is the basis and the key for carrying out the research and development verification of Advanced Driver Assistance System (ADAS) technology and automatic driving technology of vehicles. The road traffic dangerous scene is the most concerned content of developers in the road traffic scene because the road traffic dangerous scene directly relates to the road safety problem of vehicles. However, in the open road test process, most processes are normal and non-dangerous states, and screening dangerous traffic scenes from massive open road drive test data is complicated and complicated, so that the difficulty of developing testers is already caused.
Since the host vehicle generally decelerates suddenly before a dangerous scene occurs, the current main screening method for dangerous scenes is to use the deceleration a of the host vehicle to perform threshold-triggered screening. However, in the dangerous scene screening using the deceleration threshold, there are many cases where the scene is mistakenly screened, such as when the vehicle passes through a deceleration strip or turns, the scene is easily screened as a dangerous scene, and there are many cases where the screening is missed, such as when the driver is not attentive, the vehicle almost collides with another object, but the vehicle is not decelerated.
At present, the technical problem to be solved is how to quickly and effectively screen out traffic danger scenes from a large amount of road traffic data.
Disclosure of Invention
In view of this, the present invention is directed to a method, an apparatus, an electronic device and a storage medium for screening a traffic hazard scene on a road, which can quickly and effectively screen the traffic hazard scene from a large amount of road traffic data.
In order to achieve the purpose, the technical scheme of the invention is realized as follows:
a screening method of a road traffic dangerous scene is characterized in that a dangerous target object is confirmed in road traffic data according to a vehicle driving area range;
when the vehicle has a collision danger with a dangerous target object at the current speed, determining that the scene is a traffic danger scene; the step of determining the dangerous object according to the driving area range of the vehicle in the road traffic data comprises the following steps:
identifying objects within the driving area of the vehicle as potentially dangerous objects;
and sequencing the potential dangerous target objects according to the distance, and taking the potential dangerous target object closest to the potential dangerous target object as the dangerous target object.
Further, the driving area of the vehicle is within a range that the left and right sides of the driving track do not exceed a predetermined distance, the driving track is considered to be a straight line when the vehicle drives on a straight road, and the driving track is considered to be a curved line when the vehicle drives on a curved road.
Further, when the vehicle has a collision risk with the dangerous target object at the current vehicle speed, confirming that the scene is a traffic danger scene includes:
calculating the collision time and/or safe braking deceleration of the vehicle with the dangerous target object at the current vehicle speed;
and when the collision time is smaller than a first preset threshold value and/or the safety braking deceleration is smaller than a second preset threshold value, the scene is determined to be a traffic danger scene.
Further, the first preset threshold value changes along with the relative speed of the vehicle and the dangerous target object, and the smaller the relative speed of the vehicle and the dangerous target object is, the larger the first preset threshold value is;
first predetermined threshold value TTC0The calculation formula of (2) is as follows:
-15km/h<vrel≤0km/h，TTC0＝-0.0533*vrel；
-20km/h<vrel≤-15km/h，TTC0＝0.8s；
vrel≤-20km/h，TTC0＝0.002*vrel+0.84s；
wherein v isrelThe relative speed of the vehicle and the dangerous target object.
Further, the second preset threshold value changes along with the relative speed of the vehicle and the dangerous target object, and the smaller the relative speed of the vehicle and the dangerous target object is, the smaller the second preset threshold value is;
second preset threshold asafe0The calculation formula of (2) is as follows:
-10km/h<vrel≤0km/h，asafe0＝-2m/s2；
-30km/h≤vrel<-10km/h，asafe0＝0.225*vrel+0.25；
-40km/h≤vrel<-30km/h，asafe0＝-6.5m/s2；
vrel<-40km/h，asafe0＝-0.2*vrel-14.5；
wherein v isrelThe relative speed of the vehicle and the dangerous target object.
A screening method for road traffic dangerous scenes comprises the following steps of when a vehicle has collision danger with a dangerous target object under the current speed, confirming that the scene is a traffic dangerous scene: deconstructing the traffic danger scene for constructing a traffic danger scene library; deconstructing a traffic hazard scenario includes: and deconstructing the dangerous scene state points into a traffic dangerous scene with the forming and developing processes, wherein the traffic dangerous scene comprises the type of the dangerous target object, the speed, the track and the relative position information of the vehicle and the dangerous target object in the preset time periods before and after the dangerous scene state points.
Further, the first confirming module is used for confirming the dangerous object according to the driving area range of the vehicle in the road traffic data; the second confirming module is used for confirming that the scene is a traffic danger scene when the vehicle has collision danger with the dangerous target object at the current speed;
the first confirmation module includes: the first confirming submodule is used for confirming the objects in the range of the driving area of the vehicle as potential dangerous objects; the sequencing submodule is used for sequencing the potential dangerous target objects according to the distance and taking the potential dangerous target object closest to the potential dangerous target object as a dangerous target object;
the driving area range of the vehicle is that the left side and the right side of the driving track do not exceed a preset distance, when the vehicle drives on a straight road, the driving track is considered to be a straight line, and when the vehicle drives on a curve, the driving track is considered to be a curve;
the second confirmation module includes: the calculation submodule is used for calculating the collision time and/or safe braking deceleration of the vehicle with the dangerous target object at the current vehicle speed; the second confirming submodule is used for confirming that the scene is a traffic danger scene when the collision time is smaller than a first preset threshold value and/or the safety braking deceleration is smaller than a second preset threshold value;
the first preset threshold value changes along with the relative speed of the vehicle and the dangerous target object, and the smaller the relative speed of the vehicle and the dangerous target object is, the larger the first preset threshold value is;
the screening device also comprises a deconstruction module which is used for deconstructing the traffic danger scene so as to construct a traffic danger scene library; and the deconstruction module is further used for deconstructing the dangerous scene state points into a traffic dangerous scene with a forming and developing process, wherein the traffic dangerous scene comprises the type of the dangerous target object, the speed, the track and the relative position information of the vehicle and the dangerous target object in the preset time period before and after the dangerous scene state points.
Further, the first preset threshold value TTC0The calculation formula of (2) is as follows:
-15km/h<vrel≤0km/h，TTC0＝-0.0533*vrel；
-20km/h<vrel≤-15km/h，TTC0＝0.8s；
vrel≤-20km/h，TTC0＝0.002*vrel+0.84s；
wherein v isrelThe relative speed of the vehicle and the dangerous target object is obtained;
the second preset threshold value changes along with the relative speed of the vehicle and the dangerous target object, and the smaller the relative speed of the vehicle and the dangerous target object is, the smaller the second preset threshold value is;
second preset threshold asafe0The calculation formula of (2) is as follows:
-10km/h<vrel≤0km/h，asafe0＝-2m/s2；
-30km/h≤vrel<-10km/h，asafe0＝0.225*vrel+0.25；
-40km/h≤vrel<-30km/h，asafe0＝-6.5m/s2；
vrel<-40km/h，asafe0＝-0.2*vrel-14.5；
wherein v isrelThe relative speed of the vehicle and the dangerous target object is obtained;
an electronic device, the electronic device comprising: the device comprises a shell, a processor, a memory, a circuit board and a power circuit, wherein the circuit board is arranged in a space enclosed by the shell, and the processor and the memory are arranged on the circuit board; a power supply circuit for supplying power to each circuit or device of the electronic apparatus; the memory is used for storing executable program codes; the processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, and is used for executing the screening method of the road traffic dangerous scene.
A computer readable storage medium storing one or more programs, the one or more programs being executable by one or more processors, for performing the method for screening a dangerous scene of road traffic.
Compared with the prior art, the screening method and the screening device for the road traffic dangerous scene have the following advantages:
according to the screening method and device for the road traffic dangerous scene, firstly, a dangerous target object is confirmed in road traffic data according to the driving area range of a vehicle, then when the vehicle and the dangerous target object are in collision danger at the current speed, the scene is confirmed to be the traffic dangerous scene, and the traffic dangerous scene can be screened out quickly and effectively from a large amount of road traffic data through the confirmation of the dangerous target object and the evaluation of the dangerous state.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate an embodiment of the invention and, together with the description, serve to explain the invention and not to limit the invention.
In the drawings:
FIG. 1 is a flowchart of a first embodiment of a method for screening dangerous scenes of road traffic according to the present invention;
FIG. 2 is a flowchart of a second embodiment of the method for screening dangerous scenes of road traffic according to the present invention;
FIG. 3 is a schematic diagram illustrating the confirmation of dangerous objects in a second embodiment of the method for screening dangerous scenes of road traffic according to the present invention;
FIG. 4 is a schematic view illustrating scene risk status evaluation in a second embodiment of the method for screening a dangerous scene of road traffic according to the present invention;
FIG. 5 is a flowchart of a third embodiment of the method for screening dangerous scenes of road traffic according to the present invention;
FIG. 6 is a schematic view illustrating deconstruction of a traffic hazard scene in a third embodiment of the method for screening a road traffic hazard scene according to the present invention;
FIG. 7 is a schematic diagram of a traffic hazard scene screening method according to a third embodiment of the present invention;
FIG. 8 is a diagram of a traffic hazard scene screening model structure according to a third embodiment of the method for screening a road traffic hazard scene of the present invention;
FIG. 9 is a schematic structural diagram of a first screening apparatus for a dangerous scene of road traffic according to an embodiment of the present invention;
FIG. 10 is a schematic structural diagram of a second screening apparatus for a dangerous scene of road traffic according to the present invention;
FIG. 11 is a schematic structural diagram of a third screening apparatus for a dangerous scene of road traffic according to the present invention;
fig. 12 is a schematic structural diagram of an embodiment of an electronic device according to the present invention.
Detailed Description
It should be noted that the embodiments and features of the embodiments may be combined with each other without conflict.
In the description of the present invention, it is to be understood that the terms "center", "longitudinal", "lateral", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", and the like, indicate orientations or positional relationships based on those shown in the drawings, and are used only for convenience in describing the present invention and for simplicity in description, and do not indicate or imply that the referenced devices or elements must have a particular orientation, be constructed and operated in a particular orientation, and thus, are not to be construed as limiting the present invention. Furthermore, the terms "first", "second", etc. are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first," "second," etc. may explicitly or implicitly include one or more of that feature. In the description of the present invention, "a plurality" means two or more unless otherwise specified.
In the description of the present invention, it should be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meaning of the above terms in the present invention can be understood by those of ordinary skill in the art through specific situations.
The present invention will be described in detail below with reference to the embodiments with reference to the attached drawings.
As shown in fig. 1, the present embodiment provides a method for screening a road traffic hazard scene, including:
step 101: determining a dangerous object according to the driving area range of the vehicle in the road traffic data;
in this step, the road traffic data is mainly acquired by the environment sensors such as the millimeter wave radar and the camera mounted on the vehicle, and mainly includes the motion information of the vehicle and the perception information of the environment. The road traffic data may be data that has been collected and stored in a database, or may be data that is acquired in real time.
Step 102: and when the vehicle has a collision danger with the dangerous target object at the current speed, confirming that the scene is a traffic danger scene.
When a traffic danger scene is screened in the step, the road traffic data are judged one by one according to the time sequence, once the collision danger between the vehicle and a dangerous target object at the current speed is found, the scene is determined to be the traffic danger scene, otherwise, the scene is not determined to be the traffic danger scene.
According to the method, firstly, the dangerous target object is confirmed according to the driving area range of the vehicle in the road traffic data, then when the vehicle has collision danger with the dangerous target object under the current speed, the scene is confirmed to be a traffic dangerous scene, and the traffic dangerous scene can be screened out quickly and effectively in a large amount of road traffic data through the confirmation of the dangerous target object and the evaluation of the dangerous state.
Fig. 2 is a flowchart of a second embodiment of the method for screening a dangerous road traffic scene, as shown in fig. 2, the method of this embodiment may include:
step 201: identifying objects within the driving area of the vehicle as potentially dangerous objects;
in this step, a plurality of objects often exist in front of the vehicle when the vehicle is running, not all the objects are in danger of colliding with the vehicle, and only the objects within the driving area of the vehicle are considered as potential dangerous target objects. Preferably, the vehicle driving area ranges are such that the left and right sides of the driving path do not exceed a predetermined distance, for example, the vehicle driving area ranges are such that the left and right sides of the driving path do not exceed Δ0Only objects within this range will be identified as potentially dangerous targets.
When the vehicle runs on a straight road, the track of the vehicle is considered as a straight line, and whether a front object is a potential dangerous target object or not can be confirmed by judging the transverse distance delta between the object and the running track of the vehicle, if the absolute value of delta is less than or equal to delta0Then the object is a potentially dangerous target. The lateral distance Δ is generally given directly by the environmental sensor, or calculated from the distance l between the object and the vehicle and the included angle θ, i.e., Δ ═ l × sin (θ).
In particular, Δ0The selection of (2) may be related to the vehicle width, for example, first taking a half W/2 of the vehicle width, and adding 20cm, i.e. delta, to the half of the vehicle width to include the target in small overlapping relation with the vehicle0＝W/2+20cm。
When the vehicle runs on a curve, the vehicle track is considered as a curve, the vehicle transverse track displacement can be calculated according to the formula (1), and then the transverse distance y between an object and the vehicle is calculated2Transverse trajectory displacement y from the vehicle1The difference calculation is performed, as shown in equation (2), and likewise, if | Δ ≦ Δ |0Then the object is a potentially dangerous target.
Δ＝|y2-y1| (2)
y2＝l×sin(θ) (4)
Where k represents the curvature of the vehicle's path of travel, w represents the yaw rate of the vehicle, v represents the vehicle's speed, x1Indicating the displacement of the longitudinal trajectory of the vehicle, wherein the lateral distance y of the object from the vehicle2Given directly by the environmental sensor or calculated according to equation (4), where l represents the distance of the object from the vehicle and θ represents the angle of the object from the vehicle.
Since the environmental perception sensor collects dozens of target objects at the same time, not all the target objects may collide with the vehicle, only the target objects within the driving area of the vehicle may be considered as potential dangerous target objects, and in the embodiment, the left and right of the driving track of the vehicle are set not to exceed Δ0Objects within the range are potential dangerous objects, specifically, as shown in fig. 3, the vehicle a runs on a straight road in the left image, 4 objects including T1, T2, T3 and T4 are provided in the front detection area, wherein T1 and T2 are 2 objects closer to the vehicle, and T3 and T4 are 2 objects farther from the vehicle, but only T3 and T4 are determined as potential dangerous objects when determining the objects because they are located at the left and right 2 Δ of the running track of the vehicle0In the region, there is a risk of collision; in the right image, the vehicle B runs on a curved road, the transverse displacement of the running track of the vehicle is judged according to the formula (1) of the vehicle curved track, and further, the target T0 is judged to be located in the running area of the vehicle and is a potential dangerous target object of the vehicle B.
Step 202: sequencing the potential dangerous target objects according to the distance, and taking the potential dangerous target object closest to the potential dangerous target object as a dangerous target object;
in this step, the potential dangerous target objects within the driving track range of the vehicle need to be further confirmed as dangerous target objects, and at this time, the potential dangerous target objects are sorted according to distance, and the target object closest to the vehicle is taken as the dangerous target object, so that the dangerous target object confirmation is completed.
For example, in the example shown in fig. 3, the host vehicle a is traveling in a straight lane in which the vehicles T3 and T4 are confirmed as potentially dangerous target objects, and since T3 is close to the host vehicle, T3 is confirmed as a dangerous target object; the host vehicle B is traveling in a curve, and the vehicle T0 is both a potentially dangerous target object and a dangerous target object.
It should be noted that the potential dangerous target object may be a vehicle located in the own lane (e.g., T3 in fig. 3) or a vehicle changing lanes from an adjacent lane (e.g., T4 in fig. 3), and therefore the potential dangerous target object can be accurately determined by the way of the vehicle travel area.
Step 203: calculating the collision time and/or safe braking deceleration of the vehicle with the dangerous target object at the current vehicle speed;
after the confirmation of the dangerous target object is completed, the dangerous state of the dangerous target object and the host vehicle needs to be evaluated. In the present embodiment, the collision time may be used alone, or the safety braking deceleration (the safety braking deceleration is a value obtained by considering conditions such as braking safety distance, braking comfort, etc.) may be used alone, but it is preferable to use a combination of the both to evaluate the traffic risk state.
Specifically, as shown in fig. 4, the time to collision TTC and the safe braking deceleration a may be estimated from the relative distance, the relative speed, and the relative angle between the dangerous target object and the host vehicle, in addition to the host vehicle speed, the longitudinal acceleration, and other informationsafe. If at a certain vehicle speed vegoTTC is less than a set threshold and/or asafeIf the value is less than the set threshold value, the collision danger exists at the moment, namely the scene is determined to be a traffic dangerous scene, and at the moment, the traffic scene elements can be recorded together.
The time to collision TTC can be calculated according to equation (5), where arel，vrel，drelThe relative acceleration, the relative speed and the relative distance of the vehicle and the target object are respectively directly given by the environment perception sensor, and t in the formula isRepresenting the time to collision TTC.
Safety braking deceleration asafeThe minimum deceleration required by the vehicle to avoid collision in the current state can be calculated according to the formula (6), asafeIs a signed value, and the generally calculated safe braking deceleration is a negative value. Wherein a isobjRepresenting target acceleration; v. ofrelAnd drelRespectively showing the relative speed and the relative distance between the vehicle and the target object; dsafeThe safe distance represents the safe distance when the vehicle and the target object keep the same speed, and the safe distance is defined by the researcher.
Step 204: and when the collision time is smaller than a first preset threshold value and/or the safety braking deceleration is smaller than a second preset threshold value, the scene is determined to be a traffic danger scene.
In this step, when the calculated collision time is less than a first preset threshold and/or the safety braking deceleration is less than a second preset threshold, it is determined that the vehicle is in a traffic hazard scene when there is a risk of collision with a dangerous target object at the current vehicle speed, and otherwise, the vehicle is not determined to be the traffic hazard scene.
In this example, asafeIs a signed value, and the calculated safe braking deceleration is generally a negative value, such as a calculated at a certain vehicle speed according to the above equation (6)safeIs-7 m/s2The second predetermined threshold is correspondingly negative, e.g., -6m/s at the same vehicle speed2At this time, -7m/s2<-6m/s2We consider that the threshold is exceeded and there is a risk of collision.
In order to more accurately estimate the traffic risk state in consideration of the difference in the degree of collision risk in the case of different vehicle speeds, it is preferable that both the first preset threshold and the second preset threshold vary with the relative speed of the host vehicle and the dangerous target object, and the smaller the relative speed of the host vehicle and the dangerous target object is, the larger the first preset threshold is, the smaller the second preset threshold is.
Specifically, the calculation formulas of the first preset threshold and the second preset threshold may be as follows:
(1) first preset threshold TTC corresponding to time to collision TTC0With relative velocity vrelCorrelation, namely:
-15km/h<vrel≤0km/h，TTC0＝-0.0533*vrel；
-20km/h<vrel≤-15km/h，TTC0＝0.8s；
vrel≤-20km/h，TTC0＝0.002*vrel+0.84s；
(2) safety braking deceleration asafeCorresponding second preset threshold asafe0Is related to the relative velocity vrelA related quantity, namely:
-10km/h<vrel≤0km/h，asafe0＝-2m/s2；
-30km/h≤vrel<-10km/h，asafe0＝0.225*vrel+0.25；
-40km/h≤vrel<-30km/h，asafe0＝-6.5m/s2；
vrel<-40km/h，asafe0＝-0.2*vrel-14.5；
wherein v isrelThe relative speed of the vehicle and the dangerous target object.
When a road traffic danger scene is screened, the evaluation of the vehicle motion danger state needs to be added, and the factors are used for directly reflecting the traffic danger state of the vehicle. The embodiment is based on the principle, when a road traffic dangerous scene is screened, the vehicle motion dangerous state evaluation factor is directly added into the model, then the traffic dangerous scene is screened by a model-based method, namely, the traffic dangerous state is judged by comprehensively judging the position, the motion form, the dangerous state and other information of a front target relative to the vehicle, and if the road traffic data is judged to be dangerous in the established dangerous traffic scene screening model, the traffic scene is the traffic dangerous scene.
Fig. 5 is a flowchart of a third embodiment of the method for screening a dangerous road traffic scene, as shown in fig. 5, the method of this embodiment may include:
step 301: identifying objects within the driving area of the vehicle as potentially dangerous objects;
step 302: sequencing the potential dangerous target objects according to the distance, and taking the potential dangerous target object closest to the potential dangerous target object as a dangerous target object;
step 303: calculating the collision time and/or safe braking deceleration of the vehicle with the dangerous target object at the current vehicle speed;
step 304: when the collision time is smaller than a first preset threshold and/or the safety braking deceleration is smaller than a second preset threshold, determining that the scene is a traffic hazard scene;
step 305: and deconstructing the traffic danger scene for constructing a traffic danger scene library.
After the confirmation of the dangerous target object and the evaluation of the dangerous state are completed, the current scene can be confirmed to be a traffic dangerous scene, and the current moment is a dangerous scene state point, but the traffic dangerous scene is a dynamic process, and can be effectively used for developing and researching and developing a driving scene only by having a complete dangerous forming and developing process. The dangerous scene deconstruction is to deconstruct the dangerous scene state points into a traffic dangerous scene with the forming and developing processes, and mainly comprises object classification, scene element extraction and scene state point expansion.
As shown in fig. 6-7, the information collected by the environmental sensor may be specifically used to classify dangerous objects and extract scene elements, for example, the type of the object is an urban SUV, the dangerous collision with the vehicle is in the form of straight driving at the intersection of the vehicle, and the dangerous object rushes to turn left; recording kinematic information of two vehicles, such as the vehicle speed, the acceleration, the relative distance, the relative speed, the turning angle, the track and the like, in the front 3s and the rear 2s within a preset time period before and after the dangerous scene state point. The speed, the track and the relative position information of the vehicle and the dangerous target object in the 5s form a complete traffic dangerous scene, and the deconstruction of the traffic dangerous scene is completed.
On the basis of the second embodiment, the third embodiment adds a step of deconstructing the traffic hazard scene, so that the third embodiment can be more conveniently used for constructing a traffic hazard scene library.
In essence, the traffic hazard scene screening may adopt a scene screening method based on model driving, wherein the hazardous target object confirmation model, the hazardous state assessment model and the traffic hazard scene deconstruction model may all be modeled in Matlab-Simulink, and a specific model architecture may refer to fig. 8.
In summary, the screening method for the road traffic hazard scene provided by the embodiment of the invention fully considers the possibility of collision accidents in road traffic, and can find the most valuable, most dangerous and most significant traffic hazards in the massive road data.
In addition, the method fully considers the complexity of big data scene screening, wastes time and labor in manually screening scenes, can automatically screen traffic dangerous scenes in road data quickly, efficiently and qualitatively, and lays a foundation for constructing a scene library.
The driving scene library is a basic resource for researching, developing and testing the ADAS and the automatic driving system, and the traffic danger scene is a scene library resource with the highest safety value in the driving scene library. The method provided by the embodiment of the invention is used as an important ring for dangerous driving scene library construction, can obviously reduce the workload of scene researchers, and can screen out the required scene with high quality, high efficiency and high speed.
Fig. 9 is a schematic structural diagram of a first screening apparatus for a dangerous road traffic scene according to the present invention, as shown in fig. 9, the apparatus of the present embodiment may include:
a first identification module 11, configured to identify a dangerous object according to a vehicle driving area range in road traffic data;
and the second confirming module 12 is used for confirming that the scene is a traffic danger scene when the vehicle has collision danger with the dangerous target object at the current speed.
The apparatus of this embodiment may be used to implement the technical solution of the method embodiment shown in fig. 1, and the implementation principle and the technical effect are similar, which are not described herein again.
Fig. 10 is a schematic structural diagram of a second screening apparatus for a dangerous road traffic scene according to the present invention, as shown in fig. 10, the apparatus of the present embodiment may include:
a first confirming submodule 21 for confirming an object within a range of a vehicle driving area as a potentially dangerous object;
the sequencing submodule 22 is used for sequencing the potential dangerous target objects according to the distance, and taking the potential dangerous target object closest to the potential dangerous target object as a dangerous target object;
the calculation submodule 23 is used for calculating the collision time and/or safe braking deceleration of the vehicle with the dangerous target object at the current vehicle speed;
and the second confirming submodule 24 is used for confirming that the scene is a traffic danger scene when the collision time is smaller than the first preset threshold value and/or the safe braking deceleration is smaller than the second preset threshold value.
Preferably, the vehicle driving area ranges are such that the left and right sides of the trajectory do not exceed a predetermined distance, and the trajectory is considered to be a straight line when the vehicle is driving on a straight road and a curve when the vehicle is driving on a curved road.
The apparatus of this embodiment may be used to implement the technical solution of the method embodiment shown in fig. 2, and the implementation principle and the technical effect are similar, which are not described herein again.
In order to more accurately estimate the traffic risk state in consideration of the difference in the degree of collision risk in the case of different vehicle speeds, it is preferable that both the first preset threshold and the second preset threshold vary with the relative speed of the host vehicle and the dangerous target object, and the smaller the relative speed of the host vehicle and the dangerous target object is, the larger the first preset threshold is, the smaller the second preset threshold is.
In particular, a first preset threshold TTC0The calculation formula of (2) is as follows:
-15km/h<vrel≤0km/h，TTC0＝-0.0533*vrel；
-20km/h<vrel≤-15km/h，TTC0＝0.8s；
vrel≤-20km/h，TTC0＝0.002*vrel+0.84s；
wherein v isrelThe relative speed of the vehicle and the dangerous target object.
Second preset threshold asafe0The calculation formula of (2) is as follows:
-10km/h<vrel≤0km/h，asafe0＝-2m/s2；
-30km/h≤vrel<-10km/h，asafe0＝0.225*vrel+0.25；
-40km/h≤vrel<-30km/h，asafe0＝-6.5m/s2；
vrel<-40km/h，asafe0＝-0.2*vrel-14.5；
wherein v isrelThe relative speed of the vehicle and the dangerous target object.
Fig. 11 is a schematic structural diagram of a third screening apparatus for a dangerous road traffic scene according to the present invention, as shown in fig. 11, the apparatus of the present embodiment may include:
a first confirming submodule 21 for confirming an object within a range of a vehicle driving area as a potentially dangerous object;
the sequencing submodule 22 is used for sequencing the potential dangerous target objects according to the distance, and taking the potential dangerous target object closest to the potential dangerous target object as a dangerous target object;
the calculation submodule 23 is used for calculating the collision time and/or safe braking deceleration of the vehicle with the dangerous target object at the current vehicle speed;
the second confirming submodule 24 is used for confirming that the scene is a traffic hazard scene when the collision time is less than a first preset threshold value and/or the safe braking deceleration is less than a second preset threshold value;
and the deconstruction module 25 is configured to deconstruct the traffic hazard scene, so as to construct a traffic hazard scene library.
Preferably, the deconstruction module is further configured to deconstruct the dangerous scene state points into a traffic dangerous scene having a forming and developing process, where the traffic dangerous scene includes a type of the dangerous target object, and speed, trajectory, and relative position information of the host vehicle and the dangerous target object in a preset time period before and after the dangerous scene state points.
The apparatus of this embodiment may be used to implement the technical solution of the method embodiment shown in fig. 5, and the implementation principle and the technical effect are similar, which are not described herein again.
An embodiment of the present invention further provides an electronic device, as shown in fig. 12, which can implement the processes of the method embodiments shown in fig. 1, 2, and 5 of the present invention, and the electronic device may include: the device comprises a shell 41, a processor 42, a memory 43, a circuit board 44 and a power circuit 45, wherein the circuit board 44 is arranged inside a space enclosed by the shell 41, and the processor 42 and the memory 43 are arranged on the circuit board 44; a power supply circuit 45 for supplying power to each circuit or device of the electronic apparatus; the memory 43 is used for storing executable program code; the processor 42 runs a program corresponding to the executable program code by reading the executable program code stored in the memory 43 for performing any of the method embodiment methods described above.
For the specific execution process of the above steps by the processor 42 and the steps further executed by the processor 42 by running the executable program code, reference may be made to the description of the embodiments of the method shown in fig. 1, 2 and 5 of the present invention, and no further description is given here.
The electronic device exists in a variety of forms, including but not limited to:
(1) a mobile communication device: such devices are characterized by mobile communications capabilities and are primarily targeted at providing voice, data communications. Such terminals include: smart phones (e.g., iphones), multimedia phones, functional phones, and low-end phones, among others.
(2) Ultra mobile personal computer device: the equipment belongs to the category of personal computers, has calculation and processing functions and generally has the characteristic of mobile internet access. Such terminals include: PDA, MID, and UMPC devices, etc., such as ipads.
(3) A portable entertainment device: such devices can display and play multimedia content. This type of device comprises: audio, video players (e.g., ipods), handheld game consoles, electronic books, and smart toys and portable car navigation devices.
(4) A server: the device for providing the computing service comprises a processor, a hard disk, a memory, a system bus and the like, and the server is similar to a general computer architecture, but has higher requirements on processing capacity, stability, reliability, safety, expandability, manageability and the like because of the need of providing high-reliability service.
(5) And other electronic equipment with data interaction function.
The embodiment of the present invention further provides a computer-readable storage medium, in which a computer program is stored, and the computer program, when executed by a processor, implements the method steps of any of the above-mentioned method embodiments.
Embodiments of the present invention also provide an application program, which is executed to implement the method provided by any one of the method embodiments of the present invention.
The present invention is not limited to the above preferred embodiments, and any modifications, equivalent substitutions, improvements, etc. within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (8)
1. A screening method for road traffic dangerous scenes is characterized by comprising the following steps: determining a dangerous object according to the driving area range of the vehicle in the road traffic data;
when the vehicle has a collision danger with the dangerous target object at the current speed, determining that the scene is a traffic danger scene; the step of identifying the dangerous object according to the driving area range of the vehicle in the road traffic data comprises the following steps:
identifying objects within the driving area of the vehicle as potentially dangerous objects;
sequencing the potential dangerous target objects according to the distance, and taking the potential dangerous target object closest to the potential dangerous target object as the dangerous target object;
the driving area range of the vehicle is that the left side and the right side of a driving track do not exceed a preset distance, when the vehicle drives on a straight road, the driving track is considered to be a straight line, and when the vehicle drives on a curve, the driving track is considered to be a curve;
when the vehicle runs on a straight road, the track of the vehicle is considered as a straight line, and whether a front object is a potential dangerous target object or not can be confirmed by judging the transverse distance delta between the object and the running track of the vehicle, if the absolute value of delta is less than or equal to delta0Then the object is a potentially dangerous target; the transverse distance delta is directly given by an environment perception sensor or calculated by the distance l between an object and the vehicle and the included angle theta, namely delta is l multiplied by sin (theta);
Δ0the selection of (2) can be related to the vehicle width, firstly, half W/2 of the vehicle width is taken, and in order to include the target which is in small overlapping relation with the vehicle, 20cm, namely delta, is added on the basis of the half of the vehicle width0＝W/2+20cm；
When the vehicle runs on a curve, the vehicle track is considered as a curve, the vehicle transverse track displacement can be calculated according to the formula (1), and then the transverse distance y between an object and the vehicle is calculated2Transverse trajectory displacement y from the vehicle1The difference calculation is performed, as shown in equation (2), and likewise, if | Δ ≦ Δ |0Then the object is a potentially dangerous target;
Δ＝|y2-y1| (2)
y2＝l×sin(θ) (4)
where k represents the curvature of the vehicle's path of travel, w represents the yaw rate of the vehicle, v represents the vehicle's speed, x1Indicating the displacement of the longitudinal trajectory of the vehicle, wherein the lateral distance y of the object from the vehicle2The method is directly provided by an environment sensor or calculated according to a formula (4), wherein l represents the distance between an object and a vehicle, and theta represents the included angle between the object and the vehicle;
when the vehicle has collision danger with the dangerous target object at the current speed, the step of confirming that the scene is a traffic danger scene comprises the following steps:
calculating the collision time and/or safe braking deceleration of the vehicle with the dangerous target object at the current vehicle speed;
and when the collision time is smaller than a first preset threshold value and/or the safe braking deceleration is smaller than a second preset threshold value, determining that the scene is a traffic hazard scene.
2. The method for screening road traffic hazard scenes according to claim 1, wherein:
the first preset threshold value changes along with the relative speed of the vehicle and the dangerous target object, and the smaller the relative speed of the vehicle and the dangerous target object is, the larger the first preset threshold value is;
the first preset threshold value TTC0The calculation formula of (2) is as follows:
-15km/h<vrel≤0km/h，TTC0＝-0.0533*vrel；
-20km/h<vrel≤-15km/h，TTC0＝0.8s；
vrel≤-20km/h，TTC0＝0.002*vrel+0.84s；
wherein v isrelThe relative speed of the vehicle and the dangerous target object is obtained.
3. The method for screening road traffic hazard scenes according to claim 1, wherein: the second preset threshold value changes along with the relative speed of the vehicle and the dangerous target object, and the smaller the relative speed of the vehicle and the dangerous target object is, the smaller the second preset threshold value is;
the second preset threshold asafe0The calculation formula of (2) is as follows:
-10km/h<vrel≤0km/h，asafe0＝-2m/s2；
-30km/h≤vrel<-10km/h，asafe0＝0.225*vrel+0.25；
-40km/h≤vrel<-30km/h，asafe0＝-6.5m/s2；
vrel<-40km/h，asafe0＝-0.2*vrel-14.5；
wherein v isrelThe relative speed of the vehicle and the dangerous target object is obtained.
4. The method for screening road traffic hazard scenes according to any one of claims 1 to 3, characterized in that: when the vehicle has a collision danger with the dangerous target object at the current speed, the method further comprises the following steps after confirming that the scene is a traffic danger scene: deconstructing the traffic danger scene for constructing a traffic danger scene library; the deconstructing the traffic hazard scenario comprises: and deconstructing the dangerous scene state points into a traffic dangerous scene with the forming and developing processes, wherein the traffic dangerous scene comprises the type of the dangerous target object, the speed, the track and the relative position information of the vehicle and the dangerous target object in the preset time periods before and after the dangerous scene state points.
5. The utility model provides a sieving mechanism of road traffic dangerous scene which characterized in that: the system comprises a first confirming module, a second confirming module and a third confirming module, wherein the first confirming module is used for confirming a dangerous object according to a vehicle driving area range in road traffic data; the second confirming module is used for confirming that the scene is a traffic danger scene when the vehicle has collision danger with the dangerous target object at the current speed;
the first confirmation module comprises: the first confirming submodule is used for confirming the objects in the range of the driving area of the vehicle as potential dangerous objects; the sequencing submodule is used for sequencing the potential dangerous target objects according to the distance and taking the potential dangerous target object closest to the potential dangerous target object as the dangerous target object;
the driving area range of the vehicle is that the left side and the right side of a driving track do not exceed a preset distance, when the vehicle drives on a straight road, the driving track is considered to be a straight line, and when the vehicle drives on a curve, the driving track is considered to be a curve;
the second confirmation module comprises:
the calculation submodule is used for calculating the collision time and/or safe braking deceleration of the vehicle with the dangerous target object at the current vehicle speed; the second confirming submodule is used for confirming that the scene is a traffic danger scene when the collision time is smaller than a first preset threshold value and/or the safe braking deceleration is smaller than a second preset threshold value;
the first preset threshold value changes along with the relative speed of the vehicle and the dangerous target object, and the smaller the relative speed of the vehicle and the dangerous target object is, the larger the first preset threshold value is;
the screening device also comprises a deconstruction module which is used for deconstructing the traffic danger scene so as to construct a traffic danger scene library; the deconstruction module is further used for deconstructing the dangerous scene state points into a traffic dangerous scene with a forming and developing process, wherein the traffic dangerous scene comprises the type of the dangerous target object, and the speed, the track and the relative position information of the vehicle and the dangerous target object in the preset time period before and after the dangerous scene state points.
6. The screening device for road traffic hazard scenes according to claim 5, wherein: the first preset threshold value TTC0The calculation formula of (2) is as follows:
-15km/h<vrel≤0km/h，TTC0＝-0.0533*vrel；
-20km/h<vrel≤-15km/h，TTC0＝0.8s；
vrel≤-20km/h，TTC0＝0.002*vrel+0.84s；
wherein v isrelThe relative speed of the vehicle and the dangerous target object is obtained;
the second preset threshold value changes along with the relative speed of the vehicle and the dangerous target object, and the smaller the relative speed of the vehicle and the dangerous target object is, the smaller the second preset threshold value is;
the second preset threshold asafe0The calculation formula of (2) is as follows:
-10km/h<vrel≤0km/h，asafe0＝-2m/s2；
-30km/h≤vrel<-10km/h，asafe0＝0.225*vrel+0.25；
-40km/h≤vrel<-30km/h，asafe0＝-6.5m/s2；
vrel<-40km/h，asafe0＝-0.2*vrel-14.5；
wherein v isrelThe relative speed of the vehicle and the dangerous target object is obtained.
7. An electronic device, characterized in that the electronic device comprises: the device comprises a shell, a processor, a memory, a circuit board and a power circuit, wherein the circuit board is arranged in a space enclosed by the shell, and the processor and the memory are arranged on the circuit board; a power supply circuit for supplying power to each circuit or device of the electronic apparatus; the memory is used for storing executable program codes; the processor executes a program corresponding to the executable program code by reading the executable program code stored in the memory for performing the method of any of the preceding claims 1 to 3.
8. A computer readable storage medium, characterized in that the computer readable storage medium stores one or more programs which are executable by one or more processors to implement the method of any of the preceding claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910075575.2A CN109835348B (en) | 2019-01-25 | 2019-01-25 | Screening method and device for road traffic dangerous scene |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910075575.2A CN109835348B (en) | 2019-01-25 | 2019-01-25 | Screening method and device for road traffic dangerous scene |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109835348A CN109835348A (en) | 2019-06-04 |
| CN109835348B true CN109835348B (en) | 2021-04-23 |
Family
ID=66884160
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910075575.2A Active CN109835348B (en) | 2019-01-25 | 2019-01-25 | Screening method and device for road traffic dangerous scene |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109835348B (en) |
Families Citing this family (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110775034B (en) * | 2019-11-07 | 2021-10-15 | 厦门金龙联合汽车工业有限公司 | Control method of automatic brake auxiliary system, terminal equipment and storage medium |
| CN113109055A (en) * | 2020-01-10 | 2021-07-13 | 上海汽车集团股份有限公司 | Test scene grade calculation method and device and computer storage medium |
| CN111559388B (en) * | 2020-03-26 | 2022-07-12 | 吉利汽车研究院（宁波）有限公司 | Target vehicle screening method, device, equipment and storage medium |
| CN111803065B (en) * | 2020-06-23 | 2023-12-26 | 北方工业大学 | Dangerous traffic scene identification method and system based on electroencephalogram data |
| CN111856470A (en) * | 2020-07-20 | 2020-10-30 | 中国第一汽车股份有限公司 | Target screening method, device, equipment and storage medium for automobile radar |
| CN114435356A (en) * | 2020-10-30 | 2022-05-06 | 华为技术有限公司 | Dangerous scene processing method and device |
| US11524703B2 (en) * | 2020-11-24 | 2022-12-13 | GM Global Technology Operations LLC | Method and system for interactive hypothesis estimation of multi-vehicle traffic for autonomous driving |
| CN113868875B (en) * | 2021-09-30 | 2022-06-17 | 天津大学 | Method, device and equipment for automatically generating test scene and storage medium |
| CN113778108B (en) * | 2021-10-09 | 2023-07-21 | 招商局检测车辆技术研究院有限公司 | Data acquisition system and data processing method based on road side sensing unit |
| CN113815620B (en) * | 2021-10-26 | 2023-03-14 | 中国第一汽车股份有限公司 | Method, device and equipment for evaluating safe driving of vehicle and storage medium |
| CN114104000B (en) * | 2021-12-16 | 2024-04-12 | 智己汽车科技有限公司 | Dangerous scene evaluation and processing system, method and storage medium |
| CN114132311B (en) * | 2021-12-28 | 2024-05-14 | 联创汽车电子有限公司 | Dangerous target screening method and module for automatic emergency braking of vehicle |
| CN114475614A (en) * | 2022-03-21 | 2022-05-13 | 中国第一汽车股份有限公司 | Method, device, medium and equipment for screening dangerous targets |
| CN115273539B (en) * | 2022-06-16 | 2024-01-30 | 中国第一汽车股份有限公司 | Vehicle danger early warning method and device based on V2X communication and computer readable storage medium |
| CN115524996B (en) * | 2022-09-13 | 2023-07-28 | 工业和信息化部装备工业发展中心 | Edge scene supplementing method and device for simulated scene library |
| CN115563020B (en) * | 2022-12-05 | 2023-03-28 | 深圳慧拓无限科技有限公司 | Method and system for generating danger test scene, electronic device and storage medium |
-
2019
- 2019-01-25 CN CN201910075575.2A patent/CN109835348B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN109835348A (en) | 2019-06-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109835348B (en) | Screening method and device for road traffic dangerous scene | |
| CN108062095B (en) | Object tracking using sensor fusion within a probabilistic framework | |
| CN113879295A (en) | Trajectory prediction method and apparatus | |
| US11385991B1 (en) | Collision evaluation for log-based simulations | |
| CN110910673B (en) | Method and system for reminding pedestrian to collide with vehicle, camera and mobile terminal | |
| CN111932881A (en) | Traffic intersection management method and device, terminal device and storage medium | |
| CN103210433A (en) | Vehicle behavior analysis device, vehicle behavior analysis program and drive recorder | |
| JP2019179372A (en) | Learning data creation method, learning method, risk prediction method, learning data creation device, learning device, risk prediction device, and program | |
| CN108475470B (en) | Accident probability calculation device, accident probability calculation method, and medium storing accident probability calculation program | |
| CN104773177A (en) | Aided driving method and aided driving device | |
| CN112257542B (en) | Obstacle sensing method, storage medium and electronic device | |
| CN108073893A (en) | Plant is detected using range data | |
| CN113674523A (en) | Traffic accident analysis method, device and equipment | |
| US20120155711A1 (en) | Apparatus and method for analyzing video | |
| US20230206652A1 (en) | Systems and methods for utilizing models to detect dangerous tracks for vehicles | |
| CN115877343A (en) | Man-vehicle matching method and device based on radar target tracking and electronic equipment | |
| CN112326258A (en) | Method, device and system for detecting automatic driving state and electronic equipment | |
| CN112166446A (en) | Method, system, device and computer readable storage medium for identifying trafficability | |
| CN109887321B (en) | Unmanned vehicle lane change safety judgment method and device and storage medium | |
| CN111985850A (en) | Driving risk control method, driving risk control device and computer storage medium | |
| CN114167404A (en) | Target tracking method and device | |
| CN114723903A (en) | Obstacle risk field environment modeling method and device and related products | |
| CN110758244A (en) | Method and system for automatically preventing rear-end collision of electric automobile | |
| CN114162145A (en) | Automatic vehicle driving method and device and electronic equipment | |
| CN111557026A (en) | Driving support device, driving support system, driving support method, and recording medium storing driving support program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |