CN109901194A - Onboard system, method, equipment and the storage medium of anticollision - Google Patents
Onboard system, method, equipment and the storage medium of anticollision Download PDFInfo
- Publication number
- CN109901194A CN109901194A CN201910204561.6A CN201910204561A CN109901194A CN 109901194 A CN109901194 A CN 109901194A CN 201910204561 A CN201910204561 A CN 201910204561A CN 109901194 A CN109901194 A CN 109901194A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- barrier
- module
- anticollision
- broadcast
- 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.)
- Pending
Links
Abstract
The present invention provides a kind of onboard system of anticollision, method, equipment and storage mediums, the onboard system of anticollision includes: the first video acquisition module, the roof of the vehicle is set, for acquiring the video data in the vehicle up direction region, the barrier in the vehicle up direction region, and the visual information of the barrier obtained are identified based on the video data；The roof of the vehicle is arranged in first sensor module, senses for the barrier to the vehicle up direction region, and obtain the sensitive information of the barrier；First receiving module, for receiving cartographic information；Prediction module, for predicting the track of the barrier according to visual information, the sensitive information and the cartographic information；And path planning module, for adjusting the driving path of the vehicle according to the track for the barrier predicted.System and method provided by the invention realizes the anticollision of the barrier in vehicle up direction region.
Description
Technical field
The present invention relates to vehicle networked information sharing fields, specifically, being related to the onboard system of anticollision, method, setting
Standby and storage medium.
Background technique
Following car lane road will have more and more automatic driving vehicles, one side of anticollision of automatic driving vehicle
Face derives from provisions of laws and regulations, on the other hand need to consider the actual needs of institute's driving vehicle.Current automatic Pilot anticollision
System only accounts for two-dimentional road traffic scene, and in the complex three-dimensional environment of city, oversize vehicle needs three-dimensional anticollision
It is higher and higher, however, in the prior art not by the technical solution to three-dimensional (vehicle up direction region) anticollision.
Summary of the invention
For the problems of the prior art, the purpose of the present invention is to provide a kind of onboard system of anticollision, method, set
Standby and storage medium realizes anticollision.
The embodiment of the present invention provides a kind of onboard system of anticollision, is set to vehicle, the vehicle-mounted system of the anticollision
System includes:
One first video acquisition module, is arranged in the roof of the vehicle, for acquiring the view in the vehicle up direction region
Frequency evidence identifies the barrier in the vehicle up direction region, and the vision of the barrier obtained based on the video data
Information；
One first sensor module, is arranged in the roof of the vehicle, for the barrier to the vehicle up direction region
It is sensed, and obtains the sensitive information of the barrier；
One first receiving module, for receiving cartographic information；
One prediction module, for predicting the barrier according to visual information, the sensitive information and the cartographic information
Track；And
One path planning module, for adjusting the driving path of the vehicle according to the track for the barrier predicted.
Optionally, further includes:
It broadcasts to surrounding vehicles the track of one broadcast module, the barrier for being predicted this vehicle.
Optionally, further includes:
One second video acquisition module, for acquiring the video counts of front side and posterior region on the vehicle heading
According to；
One identification module, for identifying the vehicle according to the second video acquisition module video data collected
The vehicle location of front side and posterior region in driving direction；
One broadcast object determining module, for according to front side and posterior region on the vehicle heading identified
Vehicle location determines the vehicle on the track of predicted barrier；
The broadcast module is for broadcasting the track for the barrier predicted to identified vehicle.
Optionally, further includes:
One broadcasting reception module, for receiving the broadcast of other vehicles, the broadcast of other vehicles includes at least other vehicles
Feature and other vehicles broadcast channel, the features of other vehicles is for the identification module and second video acquisition module
Video data collected is matched, and to obtain the mapping of vehicle and broadcast channel that the identification module is identified, and is supplied
The broadcast module broadcast.
Optionally, the broadcast of the received other vehicles of the broadcasting reception module further includes the barrier of other vehicle predictions
Track, the track for the barrier that the path planning module is also used to be predicted according to other vehicles adjusts the traveling of the vehicle
Path.
Optionally, further includes:
One trigger module, for the track according to the barrier predicted, when the prediction barrier is located at vehicle driving
On front side of on direction and when posterior region, being somebody's turn to do on front side of on the identification module identification vehicle heading and in posterior region is triggered
Barrier.
Optionally, barrier that the path planning module is identified according to the identification module, adjusts the vehicle in real time
Driving path.
Optionally, first video acquisition module includes at least two cameras.
Optionally, the first sensor module is between at least two cameras.
Optionally, the first sensor module is laser radar sensor.
According to another aspect of the invention, a kind of method of vehicle collision avoidance is also provided, using anticollision as described above
Onboard system, the method for the anticollision includes:
S110: acquiring the video data in the vehicle up direction region, identifies the vehicle up direction based on the video data
The barrier in region, and the visual information of the barrier obtained；
S120: the barrier in the vehicle up direction region is sensed, and obtains the sensitive information of the barrier；
S130: cartographic information is received；
S140: the track of the barrier is predicted according to visual information, the sensitive information and the cartographic information；And
S150: the driving path of the vehicle is adjusted according to the track for the barrier predicted.
Optionally, after the step S140, further includes:
S170: the track for the barrier that this vehicle is predicted is broadcasted to surrounding vehicles.
Optionally, before the step S170, further includes:
S161: the video data of front side and posterior region on the vehicle heading is acquired；
S162: according to the video data of front side and posterior region on the vehicle heading, the vehicle driving is identified
The vehicle location of front side and posterior region on direction；
S163: according to the vehicle location of front side and posterior region on the vehicle heading identified, determine that institute is pre-
Vehicle on the track of the barrier of survey is as vehicle to be broadcast.
Optionally, before the step S170, further includes:
S164: the broadcast of other vehicles, feature and other vehicle of the broadcast of other vehicles including at least other vehicles are received
Broadcast channel, the features of other vehicles is for the identification module and the second video acquisition module video counts collected
According to being matched, to obtain the mapping of vehicle and broadcast channel that the identification module is identified, and for the step S170 into
Row broadcast.
According to another aspect of the invention, a kind of mobile unit of anticollision is also provided, comprising: processor；Memory,
In be stored with the executable instruction of the processor；Wherein, the processor is configured to next via the executable instruction is executed
The step of executing the method for anticollision as described above.
According to another aspect of the invention, a kind of computer readable storage medium is also provided, for storing program, the journey
Sequence is performed the step of method for realizing anticollision as described above.
Onboard system, method, equipment and the storage medium of anticollision of the invention can be realized the barrier in vehicle up direction region
The anticollision for hindering object increases the dimension of anticollision, meets the demand of the three-dimensional collision prevention of automatic Pilot, improves automatic driving vehicle
Safety.
Detailed description of the invention
Upon reading the detailed description of non-limiting embodiments with reference to the following drawings, other feature of the invention,
Objects and advantages will become more apparent upon.
Fig. 1 is the module diagram of the onboard system of anticollision of the invention.
Fig. 2 to Fig. 4 is the schematic diagram of the onboard system of the anticollision of the embodiment of the present invention.
Fig. 5 is the flow chart of the method for the vehicle collision avoidance of the embodiment of the present invention.
Fig. 6 is the structural schematic diagram of vehicle-mounted anti-collision equipment of the invention.And
Fig. 7 is the structural schematic diagram of the computer readable storage medium of one embodiment of the invention.
Specific embodiment
Example embodiment is described more fully with reference to the drawings.However, example embodiment can be with a variety of shapes
Formula is implemented, and is not understood as limited to embodiment set forth herein.On the contrary, thesing embodiments are provided so that the present invention will
Fully and completely, and by the design of example embodiment comprehensively it is communicated to those skilled in the art.It is identical attached in figure
Icon note indicates same or similar structure, thus will omit repetition thereof.
Fig. 1 is the module diagram of the onboard system of anticollision of the invention.Fig. 2 to Fig. 4 is the vehicle of the embodiment of the present invention
The schematic diagram of lane-change.As shown in Figure 1, the embodiment of the present invention provides a kind of onboard system 1 of anticollision, it is set to vehicle,
The onboard system 1 of anticollision includes the first video acquisition module 101, first sensor module 102, the first receiving module 103, pre-
Survey module 104 and path planning module 105.
The roof of the vehicle 20 is arranged in first video acquisition module 101, for acquiring 20 upper area of vehicle
Video data, the barrier for identifying the barrier of 20 upper area of vehicle based on the video data, and obtaining
Visual information.In certain embodiments, first video acquisition module 101 includes at least two cameras 211.Such as
Shown in Fig. 2, the first video acquisition module 101 includes two 180 degree wide-angle fish-eye cameras 211.Two fish-eye cameras 211
Roof is preferably provided in close to vehicle edge, to expand the acquisition range of two fish-eye cameras 211, prevents from being acquired
Video data is blocked by 20 edge of vehicle.Two fish-eye cameras 211 are used to acquire the view of vehicle upper area Z1 (such as Fig. 3)
Frequency evidence, for identification barrier 30 of 20 upper area Z1 of vehicle.Barrier 30 in various embodiments, can be fixed
The fixed obstacles such as building, limit for height roadblock；The aircraft machine being also possible under mobile throwing object in high sky, leaf branch, airport scene
The moving obstacles such as the wing (when aircraft does not move, aircraft wing can also be used as fixed barrier).
The roof of the vehicle 20 is arranged in first sensor module 102, for the barrier to 20 upper area of vehicle
Hinder object to be sensed, and obtains the sensitive information of the barrier.Summarize in some specific embodiments, first sensor module
102 may include at least one laser radar sensor.In the embodiment shown in Figure 2, first sensor module 102 includes one
A laser radar sensor 220.Laser radar sensor 220 is located between two fish-eye cameras 211.
First receiving module 103 is for receiving cartographic information.Cartographic information is for example previously stored where the vehicle 20 in cloud
The three-dimensional map information in region.Specifically, the barrier may be in the three-dimensional if the barrier is fixed obstacle
Cartographic information exists；If the barrier is moving obstacle, which is not present in the three-dimensional map information.If institute
It states barrier and is present in the three-dimensional map information, then can determine that the barrier is fixed obstacle, it can be directly according to three
The parameter (such as length, height, position, shape of the barrier etc.) of the barrier is alerted in dimension cartographic information, is not necessarily to
Trajectory predictions are carried out, the present invention is not limited thereto.
Prediction module 104 is used to predict the barrier according to visual information, the sensitive information and the cartographic information
Track.Prediction module 104 be preferably used Extended Kalman filter come acquired disturbance object track predictive equation and observation
Equation, and the weight of predictive equation and observational equation can be adjusted, thus described in Accurate Prediction according to the different barriers identified
The track of barrier.
Path planning module 105 is used to adjust the driving path of the vehicle according to the track for the barrier predicted.Example
Such as, when the barrier 30 is located on the current driving path of the vehicle, the driving path of the vehicle is adjusted to avoid
The barrier 30.
In one embodiment of the invention, the onboard system 1 of anticollision further includes broadcast module 106.Broadcast module 106
It broadcasts to surrounding vehicles the track of the barrier for being predicted this vehicle.In some embodiments, broadcast module 106 can
The vehicle within the scope of 50 meters of this vehicle is broadcasted with the track for the barrier for being predicted this vehicle, so that surrounding vehicles are according to the barrier
The track of object is hindered to adjust its driving trace.
In a change case of above-described embodiment, the onboard system 1 of anticollision further includes the second video acquisition module
107, identification module 108 and broadcast object determining module 109.Second video acquisition module 107 is for acquiring 20 row of vehicle
Sail the video data of front side and posterior region on direction.As shown in figure 3, the second video acquisition module 107 for example may include taking the photograph
As head 231 and camera 232, for acquiring the video counts of front side and posterior region X1 and X2 in 20 driving direction of vehicle respectively
According to.Further, camera 231 and camera 232 are nearby additionally provided with laser radar sensor to be assisted.
Identification module 108 is used to identify the vehicle according to second video acquisition module 107 video data collected
The vehicle location of front side and posterior region X1 and X2 in driving direction.Such as Fig. 4, identification module 108 can identify 20 row of vehicle
Sail the vehicle location of the vehicle 21 and 22 of front side and posterior region X1 and X2 on direction.
Broadcast object determining module 109 is used for according to front side and posterior region on the vehicle heading identified
Vehicle location determines the vehicle on the track of predicted barrier.As shown in figure 4, the track for the barrier predicted is S,
The vehicle location of the vehicle 21 and 22 of identification module identification is all on S in the track for the barrier predicted, then broadcast object is true
Cover half block 109 determines that vehicle 21 and 22 is vehicle to be broadcast, and by broadcast module 106 that the track S for the barrier predicted is wide
Vehicle 21 and 22 determined by casting to.Vehicle 21 and 22, can also be real if the onboard system of the anticollision of load this case as a result,
Referring now to the anticollision of the barrier in vehicle up direction region.
Further, in a change case of above-described embodiment, the onboard system 1 of anticollision further includes broadcast reception mould
Block 110.Broadcasting reception module 110 is used to receive the broadcast of other vehicles, and the broadcast of other vehicles includes at least other vehicles
The broadcast channel of feature and other vehicles, the feature of other vehicles is for the identification module and the second video acquisition module institute
The video data of acquisition is matched, to obtain the mapping of vehicle and broadcast channel that the identification module is identified, and for institute
State broadcast module broadcast.For example, the broadcast of other vehicles includes at least the license board information of other vehicles and the broadcast of other vehicles
Channel, when identification module identified from the second video acquisition module video data collected on vehicle heading front side and
The license board information of each vehicle of posterior region X1 and X2 can realize vehicle location, license plate in the onboard system 1 of anticollision as a result,
The mapping of information and broadcast channel.When broadcast object determining module 109 determines vehicle to be broadcast, according to vehicle location
The broadcast channel for obtaining vehicle, thus, it is possible to realize the broadcast to the broadcasting van.
In another change case of above-described embodiment, the broadcast of the received other vehicles of broadcasting reception module 110
It further include the track of the barrier of other vehicle predictions.The path planning module 105 is also used to pre- according to other vehicles as a result,
The track of the barrier of survey adjusts the driving path of the vehicle.In this embodiment, the onboard system 1 of anticollision can be sentenced first
Whether the track of disconnected received barrier is consistent with the track for the barrier that this vehicle is predicted；If consistent, no longer need to be gone
The adjustment in path is sailed, if inconsistent, the rail for the barrier that the path planning module 105 is also used to be predicted according to other vehicles
Mark adjusts the driving path of the vehicle.
In yet another embodiment of the present invention, the onboard system 1 of anticollision further includes trigger module 111.Trigger module
111 for the track according to the barrier predicted, when the prediction barrier is located at front side and rear side on vehicle heading
When region, the barrier on front side of on the identification of identification module 108 vehicle heading and in posterior region is triggered.In this reality
It applies in example, the barrier that the path planning module 105 is identified according to the identification module 108 adjusts the vehicle in real time
Driving path.The trajectory predictions error of barrier in order to prevent realizes real-time vehicle heading by trigger module 111
The identification of the barrier of upper front side and posterior region, on the one hand, determine on the other hand the accuracy of prediction is staggered the time when predicting,
The driving path of vehicle can also be changed in time.Compared to the obstacle recognition algorithm carried by identification module 108 itself leads to
It is pre- that 108 pairs of institutes of identification module can be improved in the transmitting for crossing the feature of the triggering of trigger module 111 and the barrier of institute's prediction locus
Survey the identification of the barrier of track.
The present invention is described below, a kind of specific implementation of prediction module is provided.Prediction module uses model foundation, karr
Graceful filtering algorithm and target tracking algorism are realized.
Non-maneuver model and maneuver modeling are established in the present invention.Wherein, non-maneuver model is used to describe linear uniform motion,
Maneuver modeling is for describing remaining movement.
The system model of non-maneuver model can indicate as follows:
X (k+1)=Φ X (k)+GW (k)
Wherein
E [W (k)]=0；E[W(k)WT(j)]=Q δkj。
The measurement model of non-maneuver model can indicate as follows:
Z (k)=HX (k)+V (k)；
Wherein
Wherein, V (k) is zero-mean, and covariance matrix is R white noise, uncorrelated to W (k) (unclear and coherent).X (k) is the k moment
The quantity of state (target is the barrier detected in the present invention) of moving target, wherein x (k) represents x-axis to displacement, and y (k) is represented
Y-axis is to displacement, and Vx, Vy respectively indicate x-axis and y-axis to speed, and Φ is motion model state-transition matrix, and G is system noise
Transfer matrix, W are system noise, and noise is desired for E [W (k)], and H is moving target observational equation transfer matrix, and V is that observation is made an uproar
Sound, Z are moving target observed quantity, and Q is correlation matrix, and T is the unit time, and δ is that (please determine whether the description of T is accurate, and mend
Fill the meaning of δ and the meaning of j)
The system model of maneuver modeling can indicate as follows:
Xm(k+1)=ΦmXm(k)+Gm*Wm(k)；
Wherein
E[Wm=0, (k)]
Observation model is identical as maneuver modeling, and only H-matrix is Hm,
Wherein, the quantity of state of X (k) moving target, wherein x (k) represents x-axis to displacement, and y (k) represents y-axis to displacement, Vx,
Vy respectively indicates x-axis and y-axis to speed, axAnd ayIndicate x-axis and y-axis to acceleration；Φ is motion model state-transition matrix, G
For the transfer matrix of system noise, W is system noise, and noise is desired for E [W (k)], and H is that moving target observational equation shifts square
Battle array, V are observation noise, and Z is moving target observed quantity, and Q is correlation matrix, and T is the unit time, and δ is that (please determine the description of T
It is whether accurate, and supplement the meaning of δ and the meaning of j)
As general Kalman filtering algorithm, its SEQUENTIAL ALGORITHM can be described as follows:
P (k/k-1)=Φ P (k-1)/k-1) ΦT+GQ(k-1)GT
K (k)=P (k/k-1) HT[HP(k/k-1)HT+R]-1
P (k/k)=P (k/k-1)-K (k) HP (k/k-1)
Estimated initial value are as follows:
The evaluated error of estimated initial is；
The evaluated error covariance matrix of estimated initial is；
Pa mCovariance matrix, σ indicates that noise variance, u be control variable (description that please determine u), other with it is aforementioned respectively
The symbol meaning of model is identical.
Target tracking algorism uses two kinds of models, i.e., non-maneuver model and maneuver modeling, and filter works in when no motor-driven
Normal mode (lower-order model), it is motor-driven with a motor-driven detector monitors, once detecting motor-driven, increase a shape in model immediately
State variable is tracked up to adjudicating next time with maneuver modeling and returns to normal non-maneuver model,
Due to using motor-driven target tracking algorism, a key link being related to is exactly motor-driven test problems.
Filter is started to work in normal mode, and the innovation sequence of output is v (k), is enabled
μ (k)=α μ (k-1)+δ (k)；
δ (k)=vT(k)S-1(k)v(k)
Wherein, S (k) is the covariance matrix of v (k).
Take △=(1- α)-1The valid window length motor-driven as detection, the method for motor-driven detection are as follows:
If μ (k) >=Th,
Then think that target begins with a constant acceleration in k- △ -1 and is added, at this moment object module should be turned by lower-order model
To high-order model.
It is whether detection acceleration estimation value has system by the detection method that high-order maneuver modeling retracts the non-maneuver model of low order
Count significant.It enables
WhereinIt is the estimated value of component of acceleration,It is the corresponding blocks of covariance matrix, if
μa(k)<Ta
Then acceleration estimation exits maneuver modeling without significant, filter.
It has been previously noted the initialization of initial state, has been said when detecting motor-driven below, the initialization of filter is asked
Topic.
When kth detects motor-driven, filter assumes to begin with a constant acceleration in k- △ -1, in window
State estimation should be corrected as follows:
First, acceleration is estimated as in k- △
It is the predicted value to measurement,
In the location estimation of k- △ are as follows:
In the velocity estimation of k- △ are as follows:
Covariance matrix amendment are as follows:
Above is only schematically to describe multiple embodiments of the invention, and the present invention is not limited thereto.
It is the flow chart of the method for the vehicle collision avoidance of the embodiment of the present invention referring to Fig. 5, Fig. 5.The present invention provides
Vehicle collision avoidance method, using the onboard system of anticollision as described above.The method of the vehicle collision avoidance includes:
S110: acquiring the video data in the vehicle up direction region, identifies the vehicle up direction based on the video data
The barrier in region, and the visual information of the barrier obtained；
S120: the barrier in the vehicle up direction region is sensed, and obtains the sensitive information of the barrier；
S130: cartographic information is received；
S140: the track of the barrier is predicted according to visual information, the sensitive information and the cartographic information；And
S150: the driving path of the vehicle is adjusted according to the track for the barrier predicted.
In a specific embodiment, further include following steps after the step S140:
S170: the track for the barrier that this vehicle is predicted is broadcasted to surrounding vehicles.
In a specific embodiment, further include following steps before the step S170:
S161: the video data of front side and posterior region on the vehicle heading is acquired；
S162: according to the video data of front side and posterior region on the vehicle heading, the vehicle driving is identified
The vehicle location of front side and posterior region on direction；
S163: according to the vehicle location of front side and posterior region on the vehicle heading identified, determine that institute is pre-
Vehicle on the track of the barrier of survey is as vehicle to be broadcast.
In a specific embodiment, further include following steps before the step S170:
S164: the broadcast of other vehicles, feature and other vehicle of the broadcast of other vehicles including at least other vehicles are received
Broadcast channel, the features of other vehicles is for the identification module and the second video acquisition module video counts collected
According to being matched, to obtain the mapping of vehicle and broadcast channel that the identification module is identified, and for the step S170 into
Row broadcast.
Above is only schematically to describe multiple embodiments of the invention, and the present invention is not limited thereto.
The method of vehicle collision avoidance of the invention can be realized the anticollision of the barrier in vehicle up direction region, increase anti-
The dimension of collision meets the demand of the three-dimensional collision prevention of automatic Pilot, improves the safety of automatic driving vehicle.
The embodiment of the present invention also provides a kind of mobile unit of anticollision, including processor.Memory, wherein being stored with place
Manage the executable instruction of device.Wherein, processor is configured to the step for being performed the method for anticollision via executable instruction is executed
Suddenly.
As above, the onboard system of anticollision of the invention can be realized the anticollision of the barrier in vehicle up direction region, increase
The dimension for having added anticollision meets the demand of the three-dimensional collision prevention of automatic Pilot, improves the safety of automatic driving vehicle.
Person of ordinary skill in the field it is understood that various aspects of the invention can be implemented as system, method or
Program product.Therefore, various aspects of the invention can be embodied in the following forms, it may be assumed that complete hardware embodiment, complete
The embodiment combined in terms of full Software Implementation (including firmware, microcode etc.) or hardware and software, can unite here
Referred to as " circuit ", " module " or " platform ".
Fig. 6 is the structural schematic diagram of the mobile unit of anticollision of the invention.It is described according to the present invention referring to Fig. 6
This embodiment electronic equipment 600.The electronic equipment 600 that Fig. 6 is shown is only an example, should not be to of the invention real
The function and use scope for applying example bring any restrictions.
As shown in fig. 6, electronic equipment 600 is showed in the form of universal computing device.The component of electronic equipment 600 can wrap
Include but be not limited to: at least one processing unit 610, at least one storage unit 620, connection different platform component (including storage
Unit 620 and processing unit 610) bus 630, display unit 640 etc..
Wherein, storage unit is stored with program code, and program code can be executed with unit 610 processed, so that processing is single
Member 610 executes various exemplary implementations according to the present invention described in this specification above-mentioned electronic prescription circulation processing method part
The step of mode.For example, processing unit 610 can execute step as shown in Figure 5 respectively.
Storage unit 620 may include the readable medium of volatile memory cell form, such as Random Access Storage Unit
(RAM) 6201 and/or cache memory unit 6202, it can further include read-only memory unit (ROM) 6203.
Storage unit 620 can also include program/utility with one group of (at least one) program module 6205
6204, such program module 6205 includes but is not limited to: operating system, one or more application program, other program moulds
It may include the realization of network environment in block and program data, each of these examples or certain combination.
Bus 630 can be to indicate one of a few class bus structures or a variety of, including storage unit bus or storage
Cell controller, peripheral bus, graphics acceleration port, processing unit use any bus structures in a variety of bus structures
Local bus.
Electronic equipment 600 can also be with one or more external equipments 700 (such as keyboard, sensing equipment, bluetooth equipment
Deng) communication, can also be enabled a user to one or more equipment interact with the electronic equipment 600 communicate, and/or with make
Any equipment (such as the router, modulation /demodulation that the electronic equipment 600 can be communicated with one or more of the other calculating equipment
Device etc.) communication.This communication can be carried out by input/output (I/O) interface 650.Also, electronic equipment 600 can be with
By network adapter 660 and one or more network (such as local area network (LAN), wide area network (WAN) and/or public network,
Such as internet) communication.Network adapter 660 can be communicated by bus 630 with other modules of electronic equipment 600.It should
Understand, although not shown in the drawings, other hardware and/or software module can be used in conjunction with electronic equipment 600, including but unlimited
In: microcode, device driver, redundant processing unit, external disk drive array, RAID system, tape drive and number
According to backup storage platform etc..
The embodiment of the present invention also provides a kind of computer readable storage medium, and for storing program, program is performed reality
The step of method of existing anticollision.In some possible embodiments, various aspects of the invention are also implemented as one
The form of kind program product comprising program code, when program product is run on the terminal device, program code is for making end
End equipment executes described in this specification above-mentioned electronic prescription circulation processing method part various exemplary realities according to the present invention
The step of applying mode.
As it appears from the above, the program in computer readable storage medium of the invention, which is performed, can be realized vehicle up direction area
The anticollision of the barrier in domain increases the dimension of anticollision, meets the demand of the three-dimensional collision prevention of automatic Pilot, and raising is driven automatically
Sail the safety of vehicle.Fig. 7 is the structural schematic diagram of computer readable storage medium of the invention.Refering to what is shown in Fig. 7, describing
The program product 800 for realizing the above method of embodiment according to the present invention, can be using portable compact disc only
It reads memory (CD-ROM) and including program code, and can be run on terminal device, such as PC.However, this hair
Bright program product is without being limited thereto, and in this document, readable storage medium storing program for executing can be any tangible Jie for including or store program
Matter, the program can be commanded execution system, device or device use or in connection.
Program product can be using any combination of one or more readable mediums.Readable medium can be readable signal Jie
Matter or readable storage medium storing program for executing.Readable storage medium storing program for executing for example can be but be not limited to electricity, magnetic, optical, electromagnetic, infrared ray or partly lead
System, device or the device of body, or any above combination.More specific example (the non exhaustive column of readable storage medium storing program for executing
Table) it include: the electrical connection with one or more conducting wires, portable disc, hard disk, random access memory (RAM), read-only storage
Device (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read only memory (CD-
ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.
Computer readable storage medium may include in a base band or as carrier wave a part propagate data-signal,
In carry readable program code.The data-signal of this propagation can take various forms, including but not limited to electromagnetic signal,
Optical signal or above-mentioned any appropriate combination.Readable storage medium storing program for executing can also be any readable Jie other than readable storage medium storing program for executing
Matter, the readable medium can send, propagate or transmit for by instruction execution system, device or device use or and its
The program of combined use.The program code for including on readable storage medium storing program for executing can transmit with any suitable medium, including but not
It is limited to wireless, wired, optical cable, RF etc. or above-mentioned any appropriate combination.
The program for executing operation of the present invention can be write with any combination of one or more programming languages
Code, programming language include object oriented program language-Java, C++ etc., further include conventional process
Formula programming language-such as " C " language or similar programming language.Program code can be calculated fully in user
It executes in equipment, partly execute on a user device, executing, as an independent software package partially in user calculating equipment
Upper part executes on a remote computing or executes in remote computing device or server completely.It is being related to remotely counting
In the situation for calculating equipment, remote computing device can pass through the network of any kind, including local area network (LAN) or wide area network
(WAN), it is connected to user calculating equipment, or, it may be connected to external computing device (such as utilize ISP
To be connected by internet).
Onboard system, method, equipment and the storage medium of anticollision of the invention can be realized the barrier in vehicle up direction region
The anticollision for hindering object increases the dimension of anticollision, meets the demand of the three-dimensional collision prevention of automatic Pilot, improves automatic driving vehicle
Safety.
The above content is a further detailed description of the present invention in conjunction with specific preferred embodiments, and it cannot be said that
Specific implementation of the invention is only limited to these instructions.For those of ordinary skill in the art to which the present invention belongs, exist
Under the premise of not departing from present inventive concept, a number of simple deductions or replacements can also be made, all shall be regarded as belonging to of the invention
Protection scope.
Claims (16)
1. a kind of onboard system of anticollision, is set to vehicle, which is characterized in that the onboard system of the anticollision includes:
One first video acquisition module, is arranged in the roof of the vehicle, for acquiring the video counts in the vehicle up direction region
According to the visual information for the barrier for identifying the barrier in the vehicle up direction region based on the video data, and obtaining；
One first sensor module, is arranged in the roof of the vehicle, carries out for the barrier to the vehicle up direction region
Sensing, and obtain the sensitive information of the barrier；
One first receiving module, for receiving cartographic information；
One prediction module, for predicting the rail of the barrier according to visual information, the sensitive information and the cartographic information
Mark；And
One path planning module, for adjusting the driving path of the vehicle according to the track for the barrier predicted.
2. the onboard system of anticollision as described in claim 1, which is characterized in that further include:
It broadcasts to surrounding vehicles the track of one broadcast module, the barrier for being predicted this vehicle.
3. the onboard system of anticollision as claimed in claim 2, which is characterized in that further include:
One second video acquisition module, for acquiring the video data of front side and posterior region on the vehicle heading；
One identification module, for identifying the vehicle driving according to the second video acquisition module video data collected
The vehicle location of front side and posterior region on direction；
One broadcast object determining module, for according to the vehicle of front side and posterior region on the vehicle heading identified
Position determines the vehicle on the track of predicted barrier；
The broadcast module is for broadcasting the track for the barrier predicted to identified vehicle.
4. the onboard system of anticollision as claimed in claim 3, which is characterized in that further include:
One broadcasting reception module, for receiving the broadcast of other vehicles, the broadcast of other vehicles includes at least the spy of other vehicles
The feature of the broadcast channel of sign and other vehicles, other vehicles is adopted for the identification module with second video acquisition module
The video data of collection is matched, to obtain the mapping of vehicle and broadcast channel that the identification module is identified, and described in confession
Broadcast module broadcast.
5. the onboard system of anticollision as claimed in claim 4, which is characterized in that the broadcasting reception module is received other
The broadcast of vehicle further includes the track of the barrier of other vehicle predictions, and the path planning module is also used to according to other vehicles
The track of the barrier of prediction adjusts the driving path of the vehicle.
6. the onboard system of anticollision as claimed in claim 3, which is characterized in that further include:
One trigger module, for the track according to the barrier predicted, when the prediction barrier is located at vehicle heading
When upper front side and posterior region, the obstacle on front side of on the identification module identification vehicle heading and in posterior region is triggered
Object.
7. the onboard system of anticollision as claimed in claim 6, which is characterized in that the path planning module is according to the knowledge
The barrier of other module identification, adjusts the driving path of the vehicle in real time.
8. the onboard system of anticollision as described in any one of claim 1 to 7, which is characterized in that first video acquisition
Module includes at least two cameras.
9. the onboard system of anticollision as claimed in claim 8, which is characterized in that the first sensor module is located at least
Between two cameras.
10. the onboard system of anticollision as claimed in claim 9, which is characterized in that the first sensor module is laser
Radar sensor.
11. a kind of method of vehicle collision avoidance, using the vehicle-mounted system of the anticollision as described in any one of claims 1 to 10
System, which is characterized in that the method for the anticollision includes:
S110: acquiring the video data in the vehicle up direction region, identifies the vehicle up direction region based on the video data
Barrier, and obtain the barrier visual information；
S120: the barrier in the vehicle up direction region is sensed, and obtains the sensitive information of the barrier；
S130: cartographic information is received；
S140: the track of the barrier is predicted according to visual information, the sensitive information and the cartographic information；And
S150: the driving path of the vehicle is adjusted according to the track for the barrier predicted.
12. the method for vehicle collision avoidance according to claim 11, which is characterized in that after the step S140, also wrap
It includes:
S170: the track for the barrier that this vehicle is predicted is broadcasted to surrounding vehicles.
13. the method for vehicle collision avoidance according to claim 12, which is characterized in that before the step S170, also wrap
It includes:
S161: the video data of front side and posterior region on the vehicle heading is acquired；
S162: according to the video data of front side and posterior region on the vehicle heading, the vehicle heading is identified
The vehicle location of upper front side and posterior region；
S163: it is predicted according to the vehicle location of front side and posterior region on the vehicle heading identified, determination
Vehicle on the track of barrier is as vehicle to be broadcast.
14. the method for vehicle collision avoidance according to claim 13, which is characterized in that before the step S170, also wrap
It includes:
S164: receiving the broadcast of other vehicles, the broadcast of other vehicles include at least other vehicles feature and other vehicles
Broadcast channel, the features of other vehicles for the identification module and the second video acquisition module video data collected into
Row matching to obtain the mapping of vehicle and broadcast channel that the identification module is identified, and carries out extensively for the step S170
It broadcasts.
15. a kind of mobile unit of anticollision characterized by comprising
Processor；
Memory, wherein being stored with the executable instruction of the processor；
Wherein, the processor is configured to carry out any one of perform claim requirement 11 to 14 via the execution executable instruction
The step of method of the vehicle collision avoidance.
16. a kind of computer readable storage medium, for storing program, which is characterized in that described program is performed realization power
Benefit require any one of 11 to 14 described in vehicle collision avoidance method the step of.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910204561.6A CN109901194A (en) | 2019-03-18 | 2019-03-18 | Onboard system, method, equipment and the storage medium of anticollision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910204561.6A CN109901194A (en) | 2019-03-18 | 2019-03-18 | Onboard system, method, equipment and the storage medium of anticollision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109901194A true CN109901194A (en) | 2019-06-18 |
Family
ID=66953706
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910204561.6A Pending CN109901194A (en) | 2019-03-18 | 2019-03-18 | Onboard system, method, equipment and the storage medium of anticollision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109901194A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111442777A (en) * | 2020-04-02 | 2020-07-24 | 东软睿驰汽车技术（沈阳）有限公司 | Path planning method and device, electronic equipment and storage medium |
| CN112649011A (en) * | 2020-12-01 | 2021-04-13 | 禾多科技（北京）有限公司 | Vehicle obstacle avoidance method, device, equipment and computer readable medium |
| WO2021134354A1 (en) * | 2019-12-30 | 2021-07-08 | 深圳元戎启行科技有限公司 | Path prediction method and apparatus, computer device, and storage medium |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020155415A1 (en) * | 2001-04-24 | 2002-10-24 | Carr Douglas M. | Amusement area devoted and structured for skilled maneuvering of a vehicle |
| CN101241188A (en) * | 2007-02-06 | 2008-08-13 | 通用汽车环球科技运作公司 | Collision avoidance system and method of detecting overpass locations using data fusion |
| WO2013051081A1 (en) * | 2011-10-03 | 2013-04-11 | トヨタ自動車株式会社 | Vehicle driving support system |
| CN203157847U (en) * | 2013-04-23 | 2013-08-28 | 马勇 | Vehicle height anti-collision visible radar device |
| CN106627574A (en) * | 2016-12-22 | 2017-05-10 | 深圳市元征科技股份有限公司 | Early warning method for vehicle collision, device and system |
| CN108177651A (en) * | 2017-11-29 | 2018-06-19 | 张好明 | A kind of quick unmanned vehicle detection obstacle avoidance system of Multi-sensor Fusion |
| CN108281040A (en) * | 2017-12-28 | 2018-07-13 | 东南大学 | A kind of more vehicle collaborative obstacle avoidance system and methods |
| CN108333589A (en) * | 2018-03-13 | 2018-07-27 | 苏州青飞智能科技有限公司 | A kind of automatic driving vehicle obstacle detector |
| CN108536149A (en) * | 2018-04-25 | 2018-09-14 | 吉林大学 | A kind of automatic driving vehicle avoidance obstacle device and control method based on the paths Dubins |
| CN108896994A (en) * | 2018-05-11 | 2018-11-27 | 武汉环宇智行科技有限公司 | A kind of automatic driving vehicle localization method and equipment |
| CN109062209A (en) * | 2018-08-07 | 2018-12-21 | 安徽工程大学 | A kind of intelligently auxiliary Ride Control System and its control method |
| CN109213134A (en) * | 2017-07-03 | 2019-01-15 | 百度在线网络技术（北京）有限公司 | The method and apparatus for generating automatic Pilot strategy |
| CN109409311A (en) * | 2018-11-07 | 2019-03-01 | 上海为森车载传感技术有限公司 | A kind of limit for height method for early warning based on binocular stereo vision |
| CN109435852A (en) * | 2018-11-08 | 2019-03-08 | 湖北工业大学 | A kind of panorama type DAS (Driver Assistant System) and method for large truck |
-
2019
- 2019-03-18 CN CN201910204561.6A patent/CN109901194A/en active Pending
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020155415A1 (en) * | 2001-04-24 | 2002-10-24 | Carr Douglas M. | Amusement area devoted and structured for skilled maneuvering of a vehicle |
| CN101241188A (en) * | 2007-02-06 | 2008-08-13 | 通用汽车环球科技运作公司 | Collision avoidance system and method of detecting overpass locations using data fusion |
| WO2013051081A1 (en) * | 2011-10-03 | 2013-04-11 | トヨタ自動車株式会社 | Vehicle driving support system |
| CN203157847U (en) * | 2013-04-23 | 2013-08-28 | 马勇 | Vehicle height anti-collision visible radar device |
| CN106627574A (en) * | 2016-12-22 | 2017-05-10 | 深圳市元征科技股份有限公司 | Early warning method for vehicle collision, device and system |
| CN109213134A (en) * | 2017-07-03 | 2019-01-15 | 百度在线网络技术（北京）有限公司 | The method and apparatus for generating automatic Pilot strategy |
| CN108177651A (en) * | 2017-11-29 | 2018-06-19 | 张好明 | A kind of quick unmanned vehicle detection obstacle avoidance system of Multi-sensor Fusion |
| CN108281040A (en) * | 2017-12-28 | 2018-07-13 | 东南大学 | A kind of more vehicle collaborative obstacle avoidance system and methods |
| CN108333589A (en) * | 2018-03-13 | 2018-07-27 | 苏州青飞智能科技有限公司 | A kind of automatic driving vehicle obstacle detector |
| CN108536149A (en) * | 2018-04-25 | 2018-09-14 | 吉林大学 | A kind of automatic driving vehicle avoidance obstacle device and control method based on the paths Dubins |
| CN108896994A (en) * | 2018-05-11 | 2018-11-27 | 武汉环宇智行科技有限公司 | A kind of automatic driving vehicle localization method and equipment |
| CN109062209A (en) * | 2018-08-07 | 2018-12-21 | 安徽工程大学 | A kind of intelligently auxiliary Ride Control System and its control method |
| CN109409311A (en) * | 2018-11-07 | 2019-03-01 | 上海为森车载传感技术有限公司 | A kind of limit for height method for early warning based on binocular stereo vision |
| CN109435852A (en) * | 2018-11-08 | 2019-03-08 | 湖北工业大学 | A kind of panorama type DAS (Driver Assistant System) and method for large truck |
Non-Patent Citations (2)
| Title |
|---|
| G.VIJAYA PADMA REDDY ET AL.: "Image Based Obstacle Detection and Path Planning for Solar Powered Autonomous Vehicle", 《2016 INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION FOR HUMANITARIAN APPLICATIONS (RAHA》 * |
| 张金旺 等: "基于概率统计的车辆运动轨迹预测方法", 《军事交通学院学报》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021134354A1 (en) * | 2019-12-30 | 2021-07-08 | 深圳元戎启行科技有限公司 | Path prediction method and apparatus, computer device, and storage medium |
| CN111442777A (en) * | 2020-04-02 | 2020-07-24 | 东软睿驰汽车技术（沈阳）有限公司 | Path planning method and device, electronic equipment and storage medium |
| CN112649011A (en) * | 2020-12-01 | 2021-04-13 | 禾多科技（北京）有限公司 | Vehicle obstacle avoidance method, device, equipment and computer readable medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109927719B (en) | Auxiliary driving method and system based on obstacle trajectory prediction | |
| Barth et al. | Estimating the driving state of oncoming vehicles from a moving platform using stereo vision | |
| EP3663882B1 (en) | Information processing device, information processing method, program and mobile unit | |
| RU2735340C1 (en) | Parking control method and parking control device | |
| CN100552742C (en) | Safe movement support device | |
| CN111923927B (en) | Method and apparatus for interactive perception of traffic scene prediction | |
| US10369993B2 (en) | Method and device for monitoring a setpoint trajectory to be traveled by a vehicle for being collision free | |
| EP3403216B1 (en) | Systems and methods for augmenting upright object detection | |
| EP3106836A1 (en) | A unit and method for adjusting a road boundary | |
| CN111522350B (en) | Sensing method, intelligent control equipment and automatic driving vehicle | |
| CN206493897U (en) | Vehicle environmental sensory perceptual system and autonomous driving vehicle | |
| EP3666599A1 (en) | Parking control method and parking control device | |
| CN109901194A (en) | Onboard system, method, equipment and the storage medium of anticollision | |
| WO2019073920A1 (en) | Information processing device, moving device and method, and program | |
| CN107728646B (en) | Method and system for automatically controlling camera of automatic driving vehicle | |
| US20200278208A1 (en) | Information processing apparatus, movable apparatus, information processing method, movable-apparatus control method, and programs | |
| CN110879598A (en) | Information fusion method and device of multiple sensors for vehicle | |
| US20220253065A1 (en) | Information processing apparatus, information processing method, and information processing program | |
| CN112987002A (en) | Obstacle danger identification method, system and device | |
| WO2021153176A1 (en) | Autonomous movement device, autonomous movement control method, and program | |
| Chen et al. | Multi-sensor information fusion algorithm with central level architecture for intelligent vehicle environmental perception system | |
| CN110371025A (en) | Method, system, equipment and the storage medium of the preposition collision detection for operating condition of overtaking other vehicles | |
| US20200125111A1 (en) | Moving body control apparatus | |
| CN111144415A (en) | Method for detecting micro pedestrian target | |
| CN109871020B (en) | Vehicle-mounted automatic driving system, method, equipment and storage medium |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190618 |
|
| WD01 | Invention patent application deemed withdrawn after publication |