CN109835348A - A kind of screening technique and device of road traffic danger scene - Google Patents
A kind of screening technique and device of road traffic danger scene Download PDFInfo
- Publication number
- CN109835348A CN109835348A CN201910075575.2A CN201910075575A CN109835348A CN 109835348 A CN109835348 A CN 109835348A CN 201910075575 A CN201910075575 A CN 201910075575A CN 109835348 A CN109835348 A CN 109835348A
- Authority
- CN
- China
- Prior art keywords
- scene
- rel
- risk
- vehicle
- traffic
- 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.)
- Granted
Links
Abstract
The invention discloses screening technique, device, electronic equipment and the storage mediums of a kind of road traffic danger scene, are related to road traffic technical field, for fast and effeciently filtering out traffic hazard scene in a large amount of highway traffic datas.The screening technique of road traffic danger scene includes: to confirm risk object object according to vehicle driving regional scope in highway traffic data；When vehicle has risk of collision with risk object object under current vehicle speed, confirm that the scene is traffic hazard scene.
Description
Technical field
The invention belongs to road traffic technical field, a kind of screening technique more particularly, to road traffic danger scene and
Device.
Background technique
Road traffic scene is to carry out the advanced driving assistance system of vehicle (Advanced Driver Assistance
System, ADAS) technology and automatic Pilot technical research verifying basis and key.And road traffic danger scene is road
In traffic scene the most developer be concerned about content because it is directly related to the road safety issues of vehicle.But due to
In open route test process, most of processes are all normal and not dangerous states, in magnanimity open route drive test data
It is cumbersome, complicated to screen dangerous traffic scene, has become pendulum and is developing the difficulty in face of tester.
Before the generation of dangerous scene, the case where this vehicle generally will appear emergency deceleration, so the master that dangerous scene is current
Wanting screening technique is the screening that threshold triggers are carried out with the deceleration a of this vehicle.But dangerous scene is carried out using deceleration threshold
Screening has that scene is accidentally screened more, is all easy screening for dangerous scene, simultaneously when crossing deceleration strip or turning such as vehicle
There is the case where more leakage screening, when not concentrating such as driver attention, Ben Che and other targets will almost bump against, however this vehicle
There is no decelerations.
Currently, the technical issues of urgent need to resolve is how in a large amount of highway traffic datas fast and effeciently to filter out traffic
Dangerous scene.
Summary of the invention
In view of this, the present invention is directed to propose a kind of screening technique of road traffic danger scene, device, electronic equipment and
Storage medium can fast and effeciently filter out traffic hazard scene in a large amount of highway traffic datas.
In order to achieve the above objectives, the technical scheme of the present invention is realized as follows:
A kind of screening technique of road traffic danger scene, it is true according to vehicle driving regional scope in highway traffic data
Recognize risk object object；
When vehicle has risk of collision with risk object object under current vehicle speed, confirm that the scene is traffic hazard scene；
Confirm that risk object object includes: according to vehicle driving regional scope in highway traffic data
Object in vehicle driving regional scope is confirmed as potential danger object；
To potential danger object by distance sort, using apart from nearest potential danger object as risk object
Object.
Further, vehicle driving regional scope is to be no more than preset distance at left and right sides of wheelpath, when vehicle is straight
When driving, wheelpath is considered as straight line in road, and when vehicle is in negotiation of bends, wheelpath is considered as curve.
Further, when vehicle has risk of collision with risk object object under current vehicle speed, confirm that the scene is traffic
Dangerous scene includes:
Calculate vehicle under current vehicle speed with the collision time and/or safety arrestment retarded velocity of risk object object；
When collision time less than the first preset threshold and/or safety arrestment retarded velocity less than the second preset threshold when, confirmation
The scene is traffic hazard scene.
Further, the first preset threshold changes with the relative velocity of Ben Che and risk object object, Ben Che and dangerous mesh
The relative velocity for marking object is smaller, and the first preset threshold is bigger；
First preset threshold TTC0Calculation formula are 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, vrelFor the relative velocity of Ben Che and risk object object.
Further, the second preset threshold changes with the relative velocity of Ben Che and risk object object, Ben Che and dangerous mesh
The relative velocity for marking object is smaller, and the second preset threshold is smaller；
Second preset threshold asafe0Calculation formula are 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, vrelFor the relative velocity of Ben Che and risk object object.
A kind of screening technique of road traffic danger scene, when vehicle has collision to endanger under current vehicle speed with risk object object
When dangerous, confirm the scene for after traffic hazard scene further include: to deconstruct to traffic hazard scene, to be used for traffic hazard
The building of scene library；Deconstruct to traffic hazard scene includes: to deconstruct dangerous scene state point to have formation and development
The traffic hazard scene of process, the traffic hazard scene include risk object species type, Ben Che and risk object object in dangerous field
Speed, track, relative position information before and after scape state point in preset time period.
Further, the first confirmation module, for being confirmed in highway traffic data according to vehicle driving regional scope
Risk object object；Second confirmation module, for when vehicle has risk of collision with risk object object under current vehicle speed, confirmation should
Scene is traffic hazard scene；
First confirmation module includes: the first confirmation submodule, for the object in vehicle driving regional scope to be confirmed as
Potential danger object；Sorting sub-module will be apart from recently potential for sorting to potential danger object by distance
Risk object object is as risk object object；
Vehicle driving regional scope be wheelpath at left and right sides of be no more than preset distance, when vehicle straight way when driving,
Wheelpath is considered as straight line, and when vehicle is in negotiation of bends, wheelpath is considered as curve；
Second confirmation module includes: computational submodule, is touched under current vehicle speed with risk object object for calculating vehicle
Hit time and/or safety arrestment retarded velocity；Second confirmation submodule, for when collision time less than the first preset threshold and/or
When safety arrestment retarded velocity is less than the second preset threshold, confirm that the scene is traffic hazard scene；
First preset threshold changes with the relative velocity of Ben Che and risk object object, and Ben Che is opposite with risk object object
Speed is smaller, and the first preset threshold is bigger；
Screening plant further includes destructing module, for deconstructing to traffic hazard scene, to be used for traffic hazard scene
The building in library；Module is deconstructed, being further used for deconstructing dangerous scene state point is the traffic danger for having formation and development process
Dangerous scene, the traffic hazard scene include risk object species type, Ben Che and risk object object before and after dangerous scene state point
Speed, track in preset time period, relative position information.
Further, the first preset threshold TTC0Calculation formula are 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, vrelFor the relative velocity of Ben Che and risk object object；
Second preset threshold changes with the relative velocity of Ben Che and risk object object, and Ben Che is opposite with risk object object
Speed is smaller, and the second preset threshold is smaller；
Second preset threshold asafe0Calculation formula are 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, vrelFor the relative velocity of Ben Che and risk object object；
A kind of electronic equipment, electronic equipment include: shell, processor, memory, circuit board and power circuit, wherein electricity
Road plate is placed in the space interior that shell surrounds, and processor and memory setting are on circuit boards；Power circuit, for being above-mentioned
The each circuit or device of electronic equipment are powered；Memory is for storing executable program code；Processor is by reading storage
The executable program code stored in device runs program corresponding with executable program code, for executing above-mentioned road traffic
The screening technique of dangerous scene.
A kind of computer readable storage medium, computer-readable recording medium storage have one or more program, and one
Or multiple programs can be executed by one or more processor, for executing the screening side of above-mentioned road traffic danger scene
Method.
Compared with the existing technology, the present invention a kind of screening technique and device of road traffic danger scene has following excellent
Gesture:
The screening technique and device of a kind of road traffic danger scene provided by the invention, first in highway traffic data
Risk object object is confirmed according to vehicle driving regional scope, then when vehicle has collision with risk object object under current vehicle speed
When dangerous, confirm that the scene is traffic hazard scene, assessed by the confirmation of risk object object and precarious position, it can be in a large amount of roads
Traffic hazard scene is fast and effeciently filtered out in the traffic data of road.
Detailed description of the invention
The attached drawing for constituting a part of the invention is used to provide further understanding of the present invention, schematic reality of the invention
It applies example and its explanation is used to explain the present invention, do not constitute improper limitations of the present invention.
In the accompanying drawings:
Fig. 1 is the flow chart of the screening technique embodiment one of road traffic danger scene of the present invention；
Fig. 2 is the flow chart of the screening technique embodiment two of road traffic danger scene of the present invention；
Fig. 3 is the signal of risk object object confirmation in the screening technique embodiment two of road traffic danger scene of the present invention
Figure；
Fig. 4 is the signal of scene precarious position assessment in the screening technique embodiment two of road traffic danger scene of the present invention
Figure；
Fig. 5 is the flow chart of the screening technique embodiment three of road traffic danger scene of the present invention；
Fig. 6 is the signal of traffic hazard scene destructing in the screening technique embodiment three of road traffic danger scene of the present invention
Figure；
Fig. 7 is that the traffic hazard scene of the screening technique embodiment three of road traffic danger scene of the present invention screens principle
Figure；
Fig. 8 is the traffic hazard scene screening model knot of the screening technique embodiment three of road traffic danger scene of the present invention
Composition；
Fig. 9 is the structural schematic diagram of the screening plant embodiment one of road traffic danger scene of the present invention；
Figure 10 is the structural schematic diagram of the screening plant embodiment two of road traffic danger scene of the present invention；
Figure 11 is the structural schematic diagram of the screening plant embodiment three of road traffic danger scene of the present invention；
Figure 12 is the structural schematic diagram of electronic equipment one embodiment of the present invention.
Specific embodiment
It should be noted that in the absence of conflict, the feature in embodiment and embodiment in the present invention can phase
Mutually combination.
In the description of the present invention, it is to be understood that, term " center ", " longitudinal direction ", " transverse direction ", "upper", "lower",
The orientation or positional relationship of the instructions such as "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outside" is
It is based on the orientation or positional relationship shown in the drawings, is merely for convenience of description of the present invention and simplification of the description, rather than instruction or dark
Show that signified device or element must have a particular orientation, be constructed and operated in a specific orientation, therefore should not be understood as pair
Limitation of the invention.In addition, term " first ", " second " etc. are used for description purposes only, it is not understood to indicate or imply phase
To importance or implicitly indicate the quantity of indicated technical characteristic.The feature for defining " first ", " second " etc. as a result, can
To explicitly or implicitly include one or more of the features.In the description of the present invention, unless otherwise indicated, " multiple "
It is meant that two or more.
In the description of the present invention, it should be noted that unless otherwise clearly defined and limited, term " installation ", " phase
Even ", " connection " shall be understood in a broad sense, for example, it may be being fixedly connected, may be a detachable connection, or be integrally connected；It can
To be mechanical connection, it is also possible to be electrically connected；It can be directly connected, can also can be indirectly connected through an intermediary
Connection inside two elements.For the ordinary skill in the art, above-mentioned term can be understood by concrete condition
Concrete meaning in the present invention.
The present invention will be described in detail below with reference to the accompanying drawings and embodiments.
As shown in Figure 1, the present embodiment provides a kind of screening techniques of road traffic danger scene, comprising:
Step 101: risk object object being confirmed according to vehicle driving regional scope in highway traffic data；
In this step, highway traffic data mainly passes through the environment such as the millimetre-wave radar installed on vehicle, camera biography
Sensor carries out real vehicle road data and collects, mainly the motion information of this vehicle and the perception information to environment.Road traffic
Data are also possible to the data obtained in real time either the acquired data being finished and stored in database.
Step 102: when vehicle has risk of collision with risk object object under current vehicle speed, confirming the scene for traffic danger
Dangerous scene.
It when screening traffic hazard scene in this step, is judged one by one in chronological order highway traffic data, one
When denier discovery vehicle has risk of collision with risk object object under current vehicle speed, that is, confirm that the scene is traffic hazard scene, it is no
Then not think it is traffic hazard scene.
The present embodiment confirms risk object object according to vehicle driving regional scope first in highway traffic data, so
Afterwards when vehicle has risk of collision with risk object object under current vehicle speed, confirm that the scene is traffic hazard scene, this implementation
Example can fast and effeciently filter out friendship by the confirmation of risk object object and precarious position assessment in a large amount of highway traffic datas
Logical danger scene.
Fig. 2 is the flow chart of the screening technique embodiment two of road traffic danger scene of the present invention, as shown in Fig. 2, this reality
The method for applying example may include:
Step 201: the object in vehicle driving regional scope is confirmed as potential danger object；
In this step, often there are multiple objects in front when vehicle driving, and not all objects have and this Che Fasheng
The danger of collision, the only object in this vehicle traveling regional scope can just be considered potential risk object object.Preferably, vehicle
Running region range is to be no more than preset distance at left and right sides of wheelpath, for example, this vehicle traveling regional scope is driving rail
It is no more than Δ at left and right sides of mark0, object only within this range can just be confirmed to be potential danger object.
Vehicle straight way when driving, this wheel paths is considered as straight line, at this moment can pass through judgment object and vehicle driving
The lateral distance delta of track confirms whether objects in front is potential danger object, if | Δ |≤Δ0, then the object is
For potential danger object.And lateral distance delta is generally directly given by environment sensing sensor, or passes through object and vehicle
Distance l and angle theta be calculated, i.e. Δ=l × sin (θ).
Specifically, Δ0Selection can be related to this vehicle vehicle width, such as take the half W/2 of this vehicle vehicle width first, be simultaneously
It will be that the target of small overlapping relation is included, then 20cm, i.e. Δ are added the vehicle width half on the basis of with this vehicle0=W/2+
20cm。
For vehicle in negotiation of bends, this wheel paths is considered as curve, and the displacement of this vehicle transverse path can be according to formula (1)
It is calculated, then by the lateral distance y of object and this vehicle2Y is displaced with the transverse path of vehicle1Carry out difference calculating, such as formula
(2) shown in, similarly, if | Δ |≤Δ0, then the object is potential danger object.
Δ=| y2-y1| (2)
y2=l × sin (θ) (4)
Wherein k indicates that this vehicle travels trajectory tortuosity, and w indicates that this vehicle yaw velocity, v indicate this vehicle speed, x1Indicate this
Vehicle longitudinal direction trajectory displacement, wherein the lateral distance y of object and this vehicle2It is directly given by environmental sensor, or according to formula (4)
It is calculated, wherein l indicates object at a distance from vehicle, and θ indicates the angle of object and vehicle.
Since environment sensing sensor can acquire tens objects simultaneously, and not all object all can be with Ben Chefa
Raw risk of collision, the only object in this vehicle traveling regional scope can just be considered potential danger object, in this implementation
This vehicle driving trace or so is set in example no more than △0Object in range is potential danger target, as shown in figure 3, specifically
Ground, this vehicle A is travelled on linear road in left figure, there is T1, T2, T3 in the search coverage of front, T4 totally 4 objects, wherein T1
It is apart from closer 2 objects of this vehicle with T2, and T3 and T4 are but to judge mesh apart from farther away 2 objects of this vehicle
Only have T3 and T4 that can just be judged as potential danger object when marking object, because they are located at 2 △ of driving trace of this vehicle or so0
In region, it is possible to the dangerous region that collides；This vehicle B is travelled on crankcase ventilaton in right figure, according to vehicle bend rail
Trace formula (1) judges this vehicle driving trace lateral displacement, and then determines that target T0 is located in the running region of this vehicle, is this vehicle B
Potential danger object.
Step 202: to potential danger object by distance sort, using apart from nearest potential danger object as
Risk object object；
In this step, the potential danger object in this vehicle traveling footprint needs further to be confirmed as dangerous mesh
Object is marked, at this time by carrying out distance sequence to potential danger object, using the object nearest apart from this vehicle as danger
Object so far completes the confirmation of risk object object.
Such as in the example shown in Fig. 3, this vehicle A is travelled in straight way, and wherein vehicle T3 and T4 are confirmed to be potential danger
Object, since T3 is closer apart from this vehicle, therefore T3 is confirmed to be risk object object；This vehicle B is both latent in negotiation of bends, vehicle T0
It is also risk object object in risk object object.
It should be noted that potential danger object both may be the vehicle (T3 in such as Fig. 3) in this vehicle lane,
Be also likely to be from the vehicle (T4 in such as Fig. 3) that adjacent lane lane change comes, so by way of vehicle driving regional scope,
It can be accurately judged to potential danger object.
Step 203: calculating vehicle and slow down under current vehicle speed with the collision time of risk object object and/or safety arrestment
Degree；
The precarious position to risk object object and Ben Che is needed to assess after the completion of the confirmation of risk object object.The present embodiment
In both can be used alone collision time, also can be used alone safety arrestment retarded velocity (safety arrestment retarded velocity be consider system
The value that the conditions such as dynamic safe distance, braking comfort obtain), but it is preferable to use the combinations of the two to assess traffic hazard shape
State.
It specifically, as shown in figure 4, can be according to the relative distance of risk object object and this vehicle, relative velocity, relative angle
Degree, collision time TTC and safety arrestment retarded velocity a are estimated in addition combined with information such as this vehicle speed, longitudinal accelerationssafe.Such as
Fruit is in a certain speed vegoUnder, TTC is less than the threshold value and/or a of settingsafeLess than the threshold value of setting, then it is assumed that there is collision to endanger at this time
Danger confirms that the scene is traffic hazard scene, can record traffic scene element together at this time.
Collision time TTC can be calculated according to formula (5), wherein arel, vrel, drelRespectively this vehicle and object
Relative acceleration, relative velocity and relative distance, directly given by environment sensing sensor, and the t in formula means that and touches
Hit time TTC.
Safety arrestment retarded velocity asafeRefer under current state, in order to avoid colliding, minimum deceleration degree needed for this vehicle can
To be calculated according to formula (6), asafeIt is signed values, general calculated safety arrestment retarded velocity is negative value.Its
Middle aobjIndicate object acceleration；vrelAnd drelRespectively indicate the relative velocity and relative distance of Ben Che and object；dsafeTable
Show Ben Che and safe distance when object keeps same speed, this safe distance is big by researcher's self-defining its value
It is small.
Step 204: when collision time less than the first preset threshold and/or safety arrestment retarded velocity less than the second preset threshold
When, confirm that the scene is traffic hazard scene.
In this step, when calculated collision time less than the first preset threshold and/or safety arrestment retarded velocity less than
When two preset thresholds, then it is assumed that when vehicle has risk of collision with risk object object under current vehicle speed, confirm that the scene is at this time
Otherwise traffic hazard scene is not confirmed as traffic hazard scene.
In the present embodiment, asafeIt is signed values, general calculated safety arrestment retarded velocity is negative value, such as basis
The a that above-mentioned formula (6) calculates under a certain speedsafeFor -7m/s2, the second preset threshold is accordingly also negative value, such as in same vehicle
Lower second preset threshold of speed is -6m/s2, at this moment -7m/s2<-6m/s2, we are considered as being more than threshold value, there is risk of collision.
It is different in view of there is the degree of risk of collision under different vehicle speed conditions, in order to more accurately assess traffic hazard shape
State, it is preferred that the first preset threshold and the second preset threshold change, this vehicle with the relative velocity of Ben Che and risk object object
Smaller with the relative velocity of risk object object, the first preset threshold is bigger, and the second preset threshold is smaller.
Specifically, the calculation formula of the first preset threshold and the second preset threshold can be such that
(1) the corresponding first preset threshold TTC of collision time TTC0With relative velocity vrelIt is related, it may be assumed that
-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 arrestment retarded velocity asafeCorresponding second preset threshold asafe0It is and relative velocity vrelRelevant one
Amount, it may be assumed that
-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, vrelFor the relative velocity of Ben Che and risk object object.
It needs to be added in the screening of road traffic danger scene and vehicle movement precarious position is assessed, it is direct with these factors
Reflect the traffic hazard state of vehicle.The present embodiment is based on this principle, directly will in the screening of road traffic danger scene
Vehicle movement precarious position evaluation factor is added in model, and the method for being then based on model carries out the screening of traffic hazard scene,
Traffic hazard is judged with respect to information such as the position, forms of motion, precarious positions of this vehicle by comprehensive descision target lead object
State, if highway traffic data is judged as danger in the dangerous traffic scene screening model of foundation, the at this moment traffic field
Scape is traffic hazard scene.
Fig. 5 is the flow chart of the screening technique embodiment three of road traffic danger scene of the present invention, as shown in figure 5, this reality
The method for applying example may include:
Step 301: the object in vehicle driving regional scope is confirmed as potential danger object；
Step 302: to potential danger object by distance sort, using apart from nearest potential danger object as
Risk object object；
Step 303: calculating vehicle and slow down under current vehicle speed with the collision time of risk object object and/or safety arrestment
Degree；
Step 304: when collision time less than the first preset threshold and/or safety arrestment retarded velocity less than the second preset threshold
When, confirm that the scene is traffic hazard scene；
Step 305: traffic hazard scene being deconstructed, with the building for traffic hazard scene library.
It can confirm that current scene is traffic hazard scene after completing the confirmation of risk object object and precarious position assessment, when
The preceding moment is dangerous scene state point, but traffic hazard scene is a dynamic process, it is necessary to have complete dangerous shape
At could be effective for the development and research and development of Driving Scene with development process.Dangerous scene destructing is exactly by dangerous scene state point
Destructing is to have the traffic hazard scene of formation and development process, is mainly sorted out by object, scene element extracts, scene state
Point extension is constituted.
As shown in fig. 6-7, specifically classification and field can be carried out to risk object object with the information that operation environment sensor acquires
Scape elements recognition, it is dangerous with the dangerous form that conflicts of this vehicle for the straight trip of this vehicle crossroad if targets of type is city SUV
Object robs capable left-hand rotation；Record the two vehicle kinematics letter of for example preceding 3s and rear 2s in the preset time period of dangerous scene state point front and back
Breath, such as speed, acceleration, relative distance, relative velocity, corner, track.The speed of this vehicle and risk object object in this 5s
Degree, track, relative position information just constitute complete traffic hazard scene, complete to the destructing of this traffic hazard scene.
The present embodiment three on the basis of example 2, increases the step of deconstructing to traffic hazard scene, so as to
More easily it is used for the building of traffic hazard scene library.
Substantially, the screening of traffic hazard scene can use the scene screening technique based on model-driven, wherein dangerous mesh
Marking object confirmation model, precarious position assessment models and traffic hazard scene destructing model can be all in Matlab-Simulink
Modeling is completed, and concrete model framework can refer to Fig. 8.
To sum up, the screening technique for the road traffic danger scene that the embodiment of the present invention proposes, has fully considered road traffic
In a possibility that crashing, can be found in magnanimity road data those most worthies, it is most dangerous, most test
The traffic hazard of meaning.
In addition, this method has fully considered the complexity of big data scene screening, it is artificial carry out the time-consuming of scene screening and
Arduously, can automatically in road data quickly, efficiently, high texture filter out traffic hazard scene, for building scene library beat
Lower basis.
Driving Scene library is the basic resource of ADAS and automated driving system research and development and test, and traffic hazard scene is
The most scene base resource of safe value in Driving Scene library.The method that the embodiment of the present invention proposes is as dangerous driving scene library
An important ring for construction, can be significantly reduced the workload of scene researcher, high-quality, efficient, rapidly filter out needs
Scene.
Fig. 9 is the structural schematic diagram of the screening plant embodiment one of road traffic danger scene of the present invention, as shown in figure 9,
The device of the present embodiment may include:
First confirmation module 11, for confirming risk object according to vehicle driving regional scope in highway traffic data
Object；
Second confirmation module 12, for when vehicle has risk of collision with risk object object under current vehicle speed, confirmation should
Scene is traffic hazard scene.
The device of the present embodiment can be used for executing the technical solution of embodiment of the method shown in Fig. 1, realization principle and skill
Art effect is similar, and details are not described herein again.
Figure 10 is the structural schematic diagram of the screening plant embodiment two of road traffic danger scene of the present invention, such as Figure 10 institute
Show, the device of the present embodiment may include:
First confirmation submodule 21, for the object in vehicle driving regional scope to be confirmed as potential danger object；
Sorting sub-module 22 will be apart from nearest potential danger for sorting to potential danger object by distance
Object is as risk object object；
Computational submodule 23, for calculate vehicle under current vehicle speed with the collision time and/or safety of risk object object
Braking deceleration；
Second confirmation submodule 24 is small less than the first preset threshold and/or safety arrestment retarded velocity for working as collision time
When the second preset threshold, confirm that the scene is traffic hazard scene.
Preferably, vehicle driving regional scope is to be no more than preset distance at left and right sides of wheelpath, when vehicle is in straight way
When driving, wheelpath is considered as straight line, and when vehicle is in negotiation of bends, wheelpath is considered as curve.
The device of the present embodiment can be used for executing the technical solution of embodiment of the method shown in Fig. 2, realization principle and skill
Art effect is similar, and details are not described herein again.
It is different in view of there is the degree of risk of collision under different vehicle speed conditions, in order to more accurately assess traffic hazard shape
State, it is preferred that the first preset threshold and the second preset threshold change, this vehicle with the relative velocity of Ben Che and risk object object
Smaller with the relative velocity of risk object object, the first preset threshold is bigger, and the second preset threshold is smaller.
Specifically, the first preset threshold TTC0Calculation formula are 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, vrelFor the relative velocity of Ben Che and risk object object.
Second preset threshold asafe0Calculation formula are 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, vrelFor the relative velocity of Ben Che and risk object object.
Figure 11 is the structural schematic diagram of the screening plant embodiment three of road traffic danger scene of the present invention, such as Figure 11 institute
Show, the device of the present embodiment may include:
First confirmation submodule 21, for the object in vehicle driving regional scope to be confirmed as potential danger object；
Sorting sub-module 22 will be apart from nearest potential danger for sorting to potential danger object by distance
Object is as risk object object；
Computational submodule 23, for calculate vehicle under current vehicle speed with the collision time and/or safety of risk object object
Braking deceleration；
Second confirmation submodule 24 is small less than the first preset threshold and/or safety arrestment retarded velocity for working as collision time
When the second preset threshold, confirm that the scene is traffic hazard scene；
Module 25 is deconstructed, for deconstructing to traffic hazard scene, with the building for traffic hazard scene library.
Preferably, module is deconstructed, is further used for deconstructing dangerous scene state point to have formation and development process
Traffic hazard scene, the traffic hazard scene include risk object species type, Ben Che and risk object object in dangerous scene state
Speed, track, relative position information in the preset time period of point front and back.
The device of the present embodiment can be used for executing the technical solution of embodiment of the method shown in Fig. 5, realization principle and skill
Art effect is similar, and details are not described herein again.
The embodiment of the present invention also provides a kind of electronic equipment, as shown in figure 12, may be implemented shown in Fig. 1,2 and 5 of the present invention
The process of embodiment of the method, the electronic equipment may include: shell 41, processor 42, memory 43, circuit board 44 and power supply electricity
Road 45, wherein circuit board 44 is placed in the space interior that shell 41 surrounds, and processor 42 and memory 43 are arranged in circuit board 44
On；Power circuit 45, for each circuit or the device power supply for above-mentioned electronic equipment；Memory 43 is for storing executable journey
Sequence code；Processor 42 is run and executable program code pair by reading the executable program code stored in memory 43
The program answered, for executing aforementioned either method embodiment method.
Processor 42 to the specific implementation procedures of above-mentioned steps and processor 42 by operation executable program code come
The step of further executing may refer to the description of embodiment of the method shown in Fig. 1,2 and 5 of the present invention, and details are not described herein.
The electronic equipment exists in a variety of forms, including but not limited to:
(1) mobile communication equipment: the characteristics of this kind of equipment is that have mobile communication function, and to provide speech, data
Communication is main target.This Terminal Type includes: smart phone (such as iPhone), multimedia handset, functional mobile phone and low
Hold mobile phone etc..
(2) super mobile personal computer equipment: this kind of equipment belongs to the scope of personal computer, there is calculating and processing function
Can, generally also have mobile Internet access characteristic.This Terminal Type includes: PDA, MID and UMPC equipment etc., such as iPad.
(3) portable entertainment device: this kind of equipment can show and play multimedia content.Such equipment include: audio,
Video player (such as iPod), handheld device, e-book and intelligent toy and portable car-mounted navigation equipment.
(4) server: providing the equipment of the service of calculating, and the composition of server includes that processor, hard disk, memory, system are total
Line etc., server is similar with general computer architecture, but due to needing to provide highly reliable service, in processing energy
Power, stability, reliability, safety, scalability, manageability etc. are more demanding.
(5) other electronic equipments with data interaction function.
The embodiment of the present invention also provides a kind of computer readable storage medium, and meter is stored in computer readable storage medium
Calculation machine program realizes any of the above-described embodiment of the method method and step when computer program is executed by processor.
The embodiment of the present invention also provides a kind of application program, and application program is performed to realize that either method of the present invention is real
The method that example offer is provided.
The above is merely preferred embodiments of the present invention, be not intended to limit the invention, it is all in spirit of the invention and
Within principle, any modification, equivalent replacement, improvement and so on be should all be included in the protection scope of the present invention.
Claims (10)
1. a kind of screening technique of road traffic danger scene, it is characterised in that: according to vehicle driving in highway traffic data
Regional scope confirms risk object object；
When vehicle has risk of collision with the risk object object under current vehicle speed, confirm that the scene is traffic hazard scene；
It is described to confirm that risk object object includes: according to vehicle driving regional scope in highway traffic data
Object in vehicle driving regional scope is confirmed as potential danger object；
To potential danger object by distance sort, using apart from nearest potential danger object as the risk object
Object.
2. a kind of screening technique of road traffic danger scene according to claim 1, it is characterised in that: the vehicle row
Sail regional scope be wheelpath at left and right sides of be no more than preset distance, when vehicle straight way when driving, wheelpath is considered
It is straight line, when vehicle is in negotiation of bends, wheelpath is considered as curve.
3. a kind of screening technique of road traffic danger scene according to claim 1, it is characterised in that: described to work as vehicle
When having risk of collision with the risk object object under current vehicle speed, confirm that the scene is that traffic hazard scene includes:
Calculate collision time and/or safety arrestment retarded velocity of the vehicle under current vehicle speed with the risk object object；
When the collision time less than the first preset threshold and/or the safety arrestment retarded velocity less than the second preset threshold when,
Confirm that the scene is traffic hazard scene.
4. a kind of screening technique of road traffic danger scene according to claim 3, it is characterised in that: described first is pre-
If threshold value changes with the relative velocity of Ben Che and the risk object object, the relative velocity of Ben Che and the risk object object are got over
Small, first preset threshold is bigger；
The first preset threshold TTC0Calculation formula are 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, vrelFor the relative velocity of Ben Che and the risk object object.
5. a kind of screening technique of road traffic danger scene according to claim 3, it is characterised in that: described second is pre-
If threshold value changes with the relative velocity of Ben Che and the risk object object, the relative velocity of Ben Che and the risk object object are got over
Small, second preset threshold is smaller；
The second preset threshold asafe0Calculation formula are 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, vrelFor the relative velocity of Ben Che and the risk object object.
6. the screening technique of -5 any a kind of road traffic danger scenes according to claim 1, it is characterised in that: described
When vehicle has risk of collision with the risk object object under current vehicle speed, confirm that the scene is that traffic hazard scene is gone back later
It include: to be deconstructed to the traffic hazard scene, with the building for traffic hazard scene library；It is described to the traffic hazard
It includes: to deconstruct dangerous scene state point to have the traffic hazard scene of formation and development process, the friendship that scene, which carries out destructing,
Logical danger scene includes risk object species type, Ben Che and risk object object before and after the dangerous scene state point in preset time period
Speed, track, relative position information.
7. a kind of screening plant of road traffic danger scene, it is characterised in that: the first confirmation module, in road traffic number
Risk object object is confirmed according to vehicle driving regional scope according to middle；Second confirmation module, for when vehicle is under current vehicle speed
When having risk of collision with the risk object object, confirm that the scene is traffic hazard scene；
First confirmation module includes: the first confirmation submodule, for the object in vehicle driving regional scope to be confirmed as
Potential danger object；Sorting sub-module will be apart from recently potential for sorting to potential danger object by distance
Risk object object is as the risk object object；
The vehicle driving regional scope be wheelpath at left and right sides of be no more than preset distance, when vehicle straight way when driving,
Wheelpath is considered as straight line, and when vehicle is in negotiation of bends, wheelpath is considered as curve；
Second confirmation module includes:
Computational submodule is made under current vehicle speed with the collision time of the risk object object and/or safety for calculating vehicle
Dynamic deceleration；Second confirmation submodule, for subtracting when the collision time less than the first preset threshold and/or the safety arrestment
When speed is less than the second preset threshold, confirm that the scene is traffic hazard scene；
First preset threshold changes with the relative velocity of Ben Che and the risk object object, Ben Che and the risk object
The relative velocity of object is smaller, and first preset threshold is bigger；
Screening plant further includes destructing module, for deconstructing to the traffic hazard scene, to be used for traffic hazard scene
The building in library；The destructing module, being further used for deconstructing dangerous scene state point is the friendship for having formation and development process
Logical danger scene, which includes risk object species type, Ben Che and risk object object in dangerous scene state point
Speed, track in the preset time period of front and back, relative position information.
8. a kind of screening plant of road traffic danger scene according to claim 7, it is characterised in that: described first is pre-
If threshold value TTC0Calculation formula are 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, vrelFor the relative velocity of Ben Che and the risk object object；
Second preset threshold changes with the relative velocity of Ben Che and the risk object object, Ben Che and the risk object
The relative velocity of object is smaller, and second preset threshold is smaller；
The second preset threshold asafe0Calculation formula are 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, vrelFor the relative velocity of Ben Che and the risk object object.
9. a kind of electronic equipment, which is characterized in that the electronic equipment includes: shell, processor, memory, circuit board and electricity
Source circuit, wherein circuit board is placed in the space interior that shell surrounds, and processor and memory setting are on circuit boards；Power supply
Circuit, for each circuit or the device power supply for above-mentioned electronic equipment；Memory is for storing executable program code；Processing
Device runs program corresponding with executable program code by reading the executable program code stored in memory, for holding
Any method in row preceding claims 1 to 5.
10. a kind of computer readable storage medium, which is characterized in that the computer-readable recording medium storage have one or
Multiple programs, one or more of programs can be executed by one or more processor, with realize preceding claims 1 to
Any method in 5.
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 true CN109835348A (en) | 2019-06-04 |
| CN109835348B 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) |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110775034A (en) * | 2019-11-07 | 2020-02-11 | 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 |
| CN111559388A (en) * | 2020-03-26 | 2020-08-21 | 吉利汽车研究院（宁波）有限公司 | Target vehicle screening method, device, equipment and storage medium |
| CN111803065A (en) * | 2020-06-23 | 2020-10-23 | 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 |
| 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 |
| CN113778108A (en) * | 2021-10-09 | 2021-12-10 | 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 |
| CN113815620A (en) * | 2021-10-26 | 2021-12-21 | 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 |
| CN113868875A (en) * | 2021-09-30 | 2021-12-31 | 天津大学 | Method, device and equipment for automatically generating test scene and storage medium |
| CN114104000A (en) * | 2021-12-16 | 2022-03-01 | 智己汽车科技有限公司 | Dangerous scene evaluation and processing system, method and storage medium |
| CN114132311A (en) * | 2021-12-28 | 2022-03-04 | 联创汽车电子有限公司 | Method and module for screening dangerous targets for automatic emergency braking of vehicle |
| CN114435356A (en) * | 2020-10-30 | 2022-05-06 | 华为技术有限公司 | Dangerous scene processing method and device |
| 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 |
| CN114550475A (en) * | 2020-11-24 | 2022-05-27 | 通用汽车环球科技运作有限责任公司 | Method and system for interactive hypothesis estimation for multi-vehicle traffic for autonomous driving |
| CN115273539A (en) * | 2022-06-16 | 2022-11-01 | 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 |
| CN115524996A (en) * | 2022-09-13 | 2022-12-27 | 工业和信息化部装备工业发展中心 | Edge scene supplement method and device of analog simulation scene library |
| CN115563020A (en) * | 2022-12-05 | 2023-01-03 | 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
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110775034A (en) * | 2019-11-07 | 2020-02-11 | 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 |
| 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 |
| CN111559388A (en) * | 2020-03-26 | 2020-08-21 | 吉利汽车研究院（宁波）有限公司 | Target vehicle screening method, device, equipment and storage medium |
| CN111803065A (en) * | 2020-06-23 | 2020-10-23 | 北方工业大学 | Dangerous traffic scene identification method and system based on electroencephalogram data |
| 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 |
| CN114550475A (en) * | 2020-11-24 | 2022-05-27 | 通用汽车环球科技运作有限责任公司 | Method and system for interactive hypothesis estimation for multi-vehicle traffic for autonomous driving |
| CN113868875A (en) * | 2021-09-30 | 2021-12-31 | 天津大学 | Method, device and equipment for automatically generating test scene and storage medium |
| CN113868875B (en) * | 2021-09-30 | 2022-06-17 | 天津大学 | Method, device and equipment for automatically generating test scene and storage medium |
| CN113778108A (en) * | 2021-10-09 | 2021-12-10 | 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 |
| CN113815620A (en) * | 2021-10-26 | 2021-12-21 | 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 |
| 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 |
| CN114104000A (en) * | 2021-12-16 | 2022-03-01 | 智己汽车科技有限公司 | Dangerous scene evaluation and processing system, method 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 |
| CN114132311A (en) * | 2021-12-28 | 2022-03-04 | 联创汽车电子有限公司 | Method and module for screening dangerous targets 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 |
| CN115273539A (en) * | 2022-06-16 | 2022-11-01 | 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 |
| CN115524996A (en) * | 2022-09-13 | 2022-12-27 | 工业和信息化部装备工业发展中心 | Edge scene supplement method and device of analog simulation scene library |
| CN115563020A (en) * | 2022-12-05 | 2023-01-03 | 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109835348B (en) | 2021-04-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109835348A (en) | A kind of screening technique and device of road traffic danger scene | |
| EP3627471B1 (en) | Method and device for assisting in controlling automatic driving of vehicle, and system | |
| US10814884B2 (en) | Autonomous vehicle site test method and apparatus, device and readable medium | |
| CN111123735B (en) | Automatic driving simulation operation method and device | |
| CN110462543A (en) | The method based on emulation that perception for assessing automatic driving vehicle requires | |
| CN109211575B (en) | Unmanned vehicle and site testing method, device and readable medium thereof | |
| CN114364591A (en) | Navigation system and method for vehicle | |
| US20230350399A1 (en) | Operational testing of autonomous vehicles | |
| CN109901156A (en) | A kind of subject fusion method and apparatus of vehicle millimetre-wave radar and camera | |
| CN110910673B (en) | Method and system for reminding pedestrian to collide with vehicle, camera and mobile terminal | |
| CN111477030B (en) | Vehicle collaborative risk avoiding method, vehicle end platform, cloud end platform and storage medium | |
| CN110047276A (en) | The congestion status of barrier vehicle determines method, apparatus and Related product | |
| CN108089573A (en) | Vehicle vision | |
| CN110491127A (en) | A kind of current bootstrap technique, device and readable storage medium storing program for executing | |
| Cerri et al. | Computer vision at the hyundai autonomous challenge | |
| CN101612925A (en) | Determine the method for driving demand value | |
| CN109781129A (en) | A kind of road surface safety detection system and method based on inter-vehicular communication | |
| CN112257542B (en) | Obstacle sensing method, storage medium and electronic device | |
| CN111160132B (en) | Method and device for determining lane where obstacle is located, electronic equipment and storage medium | |
| US20220289253A1 (en) | Method for evaluating autonomous driving system, apparatus and storage medium | |
| KR102057453B1 (en) | Acceleration and deceleration device and method of vehicle based on driving habits | |
| WO2021112889A1 (en) | Assertive vehicle detection model generation and implementation | |
| CN111258312B (en) | Movable model, control method, device, system, equipment and storage medium thereof | |
| Caruntu et al. | Cyber-physical systems-based architecture for signalized traffic corridors: Monitoring and synchronized coordination | |
| Tian et al. | Experimental design of integrated platform for demonstration of cooperative vehicle infrastructure systems in china |
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 |