CN106183981A - Obstacle detection method based on automobile, device and automobile - Google Patents
Obstacle detection method based on automobile, device and automobile Download PDFInfo
- Publication number
- CN106183981A CN106183981A CN201610574011.XA CN201610574011A CN106183981A CN 106183981 A CN106183981 A CN 106183981A CN 201610574011 A CN201610574011 A CN 201610574011A CN 106183981 A CN106183981 A CN 106183981A
- Authority
- CN
- China
- Prior art keywords
- automobile
- model
- roadblock
- image
- vehicle
- 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
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60Q—ARRANGEMENT OF SIGNALLING OR LIGHTING DEVICES, THE MOUNTING OR SUPPORTING THEREOF OR CIRCUITS THEREFOR, FOR VEHICLES IN GENERAL
- B60Q9/00—Arrangement or adaptation of signal devices not provided for in one of main groups B60Q1/00 - B60Q7/00, e.g. haptic signalling
- B60Q9/008—Arrangement or adaptation of signal devices not provided for in one of main groups B60Q1/00 - B60Q7/00, e.g. haptic signalling for anti-collision purposes
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R1/00—Optical viewing arrangements; Real-time viewing arrangements for drivers or passengers using optical image capturing systems, e.g. cameras or video systems specially adapted for use in or on vehicles
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R2300/00—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle
- B60R2300/10—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the type of camera system used
- B60R2300/105—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the type of camera system used using multiple cameras
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R2300/00—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle
- B60R2300/80—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the intended use of the viewing arrangement
- B60R2300/8093—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the intended use of the viewing arrangement for obstacle warning
Abstract
The embodiment of the invention discloses a kind of Obstacle detection method based on automobile, device and automobile, it belongs to vehicular field, at least can solve the problem that automobile of the prior art cannot detect whether front exists the roadblock information such as alarming sign automatically, thus easily cause the technical problem of vehicle accident.It is somebody's turn to do Obstacle detection method based on automobile, including: obtain the image of motor vehicle environment；The roadblock model library that inquiry is preset, it is judged that described image whether with at least one roadblock Model Matching of comprising in described roadblock model library；When judged result is for being, generate road-block prompting information.
Description
Technical field
The present embodiments relate to vehicular field, be specifically related to a kind of Obstacle detection method based on automobile, device and vapour
Car.
Background technology
At present, along with becoming increasingly popular of private car, traffic is the most complicated, during the phenomenon such as scratching between vehicle, collision
There is generation.Once there is above-mentioned vehicle accident, on the one hand, the massive losses in terms of lives and properties can be brought；On the other hand, for
Saving scene, relates to thing vehicle and is the most temporarily trapped on traffic major trunk roads, although relate to thing vehicle during being detained generally
Alarming sign can be sent to rear car, such as, light for vehicle is set to double sudden strain of a muscle pattern or erects indicating fault board etc..
But, during realizing the present invention, inventor finds to there is following problem in prior art: driving of rear car
The person of sailing, due to fatigue driving or the impact of the factors such as absent minded, is very easy to ignore the warning-sign that front truck sends
Know, thus cause car to car impact, and then cause second accident.
Summary of the invention
In view of the above problems, it is proposed that the embodiment of the present invention is to provide a kind of road based on automobile solving the problems referred to above
Barrier detection method, device and automobile.
An aspect according to the embodiment of the present invention, it is provided that a kind of Obstacle detection method based on automobile, including: obtain
The image of motor vehicle environment；Roadblock model library that inquiry is preset, it is judged that whether described image comprises with described roadblock model library
At least one roadblock Model Matching；When judged result is for being, generate road-block prompting information.
Alternatively, the step of the image of described acquisition motor vehicle environment farther includes: determine the current running state of automobile,
When the current running state determining described automobile is forward traveling, obtain the image of vehicle front；When determining described automobile
When current running state is state of rolling backward, obtain the image at automobile rear；When determining that the current running state of described automobile is for turning
During curved state, obtain the image of automobile turning side.
Alternatively, described default roadblock model library includes: light for vehicle scintillation model and/or indicating fault board mould
Type.
Alternatively, described light for vehicle scintillation model is dynamic model, and described dynamic model farther includes: described car
The flicker frequency of taillight, flash color, between scintillation intensity and the quantity of described light for vehicle and adjacent taillight between
Away from；Described indicating fault board model is static models, and described static models farther include: the shape of described indicating fault board
Shape, design and color.
Alternatively, described judge described image whether with at least one roadblock model of comprising in described roadblock model library
The step joined specifically includes: calculate the similarity between described image and described roadblock model, when result of calculation is more than presetting threshold
Described image and described roadblock Model Matching is determined during value；Further, described method farther includes: obtain the current of described automobile
Speed, and described predetermined threshold value is dynamically determined according to described current vehicle speed.
Alternatively, described road-block prompting information is that auditory tone cues information, picture cues information and/or steering wheel vibration carry
Show information.
Another aspect according to the embodiment of the present invention, it is provided that a kind of Obstacle detection device based on automobile, including: obtain
Delivery block, for obtaining the image of motor vehicle environment；Judge module, for inquiring about default roadblock model library, it is judged that described image
Whether with at least one roadblock Model Matching of comprising in described roadblock model library；Reminding module, is used for when judged result is yes
Time, generate road-block prompting information.
Alternatively, described acquisition module farther includes: determine submodule, the first photographic head, second camera and the 3rd
Photographic head, wherein, described determine submodule for determining the current running state of automobile, when the current line determining described automobile
When the state of sailing is forward traveling, obtained the image of vehicle front by described first photographic head；When determining working as of described automobile
When front transport condition is state of rolling backward, obtained the image at automobile rear by described second camera；When determining described automobile
Current running state when being turn condition, obtained the image of automobile turning side by described 3rd photographic head.
Alternatively, described default roadblock model library includes: light for vehicle scintillation model and/or indicating fault board mould
Type.
Alternatively, described light for vehicle scintillation model is dynamic model, and described dynamic model farther includes: described car
The flicker frequency of taillight, flash color, between scintillation intensity and the quantity of described light for vehicle and adjacent taillight between
Away from；
Described indicating fault board model is static models, and described static models farther include: described indicating fault board
Shape, design and color.
Alternatively, described judge module specifically for: calculate the similarity between described image and described roadblock model, when
Described image and described roadblock Model Matching is determined when result of calculation is more than predetermined threshold value；Further, described predetermined threshold value is according to working as
Front truck speed is dynamically determined.
Alternatively, described road-block prompting information is that auditory tone cues information, picture cues information and/or steering wheel vibration carry
Show information.
Another aspect according to the embodiment of the present invention, it is provided that a kind of automobile, including above-mentioned Obstacle detection device.
In Obstacle detection method based on automobile, device and the automobile that the embodiment of the present invention provides, it is possible to according to automobile
Image around and default roadblock model library detect whether motor vehicle environment exists roadblock automatically, and when testing result is for being
Automatically driver is pointed out.As can be seen here, the mode in the embodiment of the present invention effectively can be pointed out driver thus avoid causing
Vehicle accident, is greatly improved safety on the run.
Described above is only the general introduction of technical solution of the present invention, in order to better understand the technological means of the present invention,
And can be practiced according to the content of description, and in order to allow above and other objects of the present invention, the feature and advantage can
Become apparent, below especially exemplified by the detailed description of the invention of the present invention.
Accompanying drawing explanation
By reading the detailed description of hereafter preferred implementation, various other advantage and benefit common for this area
Technical staff will be clear from understanding.Accompanying drawing is only used for illustrating the purpose of preferred implementation, and is not considered as the present invention
Restriction.And in whole accompanying drawing, it is denoted by the same reference numerals identical parts.In the accompanying drawings:
Fig. 1 shows the flow chart of the Obstacle detection method based on automobile that the embodiment of the present invention provides；
Fig. 2 shows the flow chart of the Obstacle detection method based on automobile that another specific embodiment of the present invention provides；
Fig. 3 shows the structure chart of the Obstacle detection device based on automobile that another embodiment of the present invention provides；
Fig. 4 shows the structure chart of the Obstacle detection device based on automobile that another embodiment of the present invention provides；
Fig. 5 shows the structure chart of the automobile that another embodiment of the present invention provides；
Fig. 6 shows the structure chart of the automobile that another embodiment of the present invention provides.
Detailed description of the invention
It is more fully described the exemplary embodiment of the disclosure below with reference to accompanying drawings.Although accompanying drawing shows the disclosure
Exemplary embodiment, it being understood, however, that may be realized in various forms the disclosure and should be by embodiments set forth here
Limited.On the contrary, it is provided that these embodiments are able to be best understood from the disclosure, and can be by the scope of the present disclosure
Complete conveys to those skilled in the art.
Embodiments provide a kind of Obstacle detection method based on automobile, device and automobile, at least can solve the problem that
Automobile of the prior art is because cannot automatically detect whether front exists the roadblock information such as alarming sign and easily cause traffic
The technical problem of accident.
Fig. 1 shows the flow chart of the Obstacle detection method based on automobile that the embodiment of the present invention provides.As it is shown in figure 1,
The method comprises the following steps:
Step S110: obtain the image of motor vehicle environment.
Wherein, the image of motor vehicle environment can obtain in real time by being arranged on one or more photographic head of automobile external.
For example, it is possible to arrange a photographic head at automotive front end, for obtaining the image of vehicle front when automobile front driving；Can be at vapour
Car rear end arranges another photographic head, for obtaining the image at automobile rear when reversing automobile；Can also be each in automobile both sides
Two photographic head are set, for obtaining the image of automobile turning side when automobile turning.
Step S120: the roadblock model library that inquiry is preset, it is judged that whether described image comprises in described roadblock model library
At least one roadblock Model Matching.
Wherein, roadblock model library stores the model corresponding to various types of roadblock, for example, it is possible to include vehicle
Taillight scintillation model and/or indicating fault board model etc..Wherein, light for vehicle scintillation model is usually dynamic model, this model
Include: the flicker frequency of described light for vehicle, flash color, scintillation intensity and the quantity of described light for vehicle and adjacent
Spacing etc. between taillight；Indicating fault board model is usually static models, and this model includes: the shape of described indicating fault board
Shape, design and color etc..And for example, roadblock model library can also include pedestrian dummy, animal model etc., to prevent because going out suddenly
Existing people, thing and accidents caused.
Specifically, judge image whether with roadblock model library in comprise at least one roadblock Model Matching time, permissible
First image is carried out the pretreatment operation such as denoising, filtering, then, judges figure by modes such as default similarity-rough set algorithms
It seem no and roadblock Model Matching.
Step S130: when judged result is for being, generates road-block prompting information.
Wherein, road-block prompting information can be accomplished in several ways flexibly, for example, it may be auditory tone cues information, figure
As information and/or steering wheel vibration information etc..
As can be seen here, the mode in the embodiment of the present invention effectively can be pointed out driver thus avoid causing traffic thing
Therefore, safety on the run is greatly improved.
Fig. 2 shows the flow chart of the Obstacle detection method based on automobile that another specific embodiment of the present invention provides.
As in figure 2 it is shown, the method comprises the following steps:
Step S210: determine the current running state of automobile, obtains the image of motor vehicle environment according to current running state.
Wherein, step S210 can perform in vehicle traveling process in real time.Specifically, when the current driving determining automobile
When state is forward traveling, obtain the image of vehicle front, to guarantee automobile safety during moving ahead；When determining automobile
Current running state when being state of rolling backward, obtain the image at automobile rear, to guarantee safety during reversing automobile；When determining
When the current running state of automobile is turn condition, obtain the image of automobile turning side.Such as, when the current driving determining automobile
When state is for turning to the left, obtain the image of automobile left side；When determining that the current running state of automobile is for bending to right, obtain
The image of car right side.
When implementing, respectively photographic head can be set for various location at automobile, such as, arrange at automotive front end
One photographic head, for shooting the image of vehicle front；Second camera is set in automobile rear end, for shooting the figure at automobile rear
Picture；Arranging the 3rd photographic head in automobile both sides, for shooting the image of automobile both sides, wherein, the 3rd photographic head specifically includes point
It is not arranged on two photographic head of vehicle right and left both sides.Correspondingly, work by controlling different photographic head, vapour can be got
The image of the different angles of car, it is of course also possible to obtain the image of all angles of automobile simultaneously, and by the image of all angles
It is spliced into a width panoramic picture, to reach to fully understand the purpose of peripheral vehicle road conditions, so, can when automobile takes a sudden turn suddenly
Preferably to avoid traffic accident.
Step S220: the image got is carried out pretreatment.
Wherein, pretreatment is mainly used in denoising.Due to vehicle jolt, the impact of the extraneous factor such as light change, cause car
The image that load photographic head obtains in real time may obscure because of Vehicular vibration, to this, can be filtered by modes such as Filtering Processing
Noise in image, to improve the accuracy of subsequent treatment.Concrete filtering algorithm can select the most flexibly, the present invention
This is not construed as limiting.
Step S230: be analyzed pretreated image calculating, to extract the region to be identified comprised in image.
Wherein it is possible to realize the analytical calculation to image, the purpose of analytical calculation by various image analysis algorithm flexibly
It is: remove the extraneous areas in image, and then extract the region to be identified in image.Such as, it is in, when automobile, the shape that moves ahead
During state, may comprise background area in the image of photographic head shooting, such as sky, the greenery patches etc. of both sides of highway, these regions are equal
It is not belonging to the predetermined running region of automobile, therefore, belongs to extraneous areas；Correspondingly, image comprises front truck and front truck with
The region in the section before this car belongs to the predetermined running region of automobile, therefore, belongs to region to be identified.
By extracting region to be identified, it is possible to the amount of calculation during reduction subsequent match, improve follow-up processing speed.
It addition, those skilled in the art can also divide extraneous areas and region to be identified by other means, in a word, as long as can be by
The picture position that may comprise roadblock is included in region to be identified.
It addition, above-mentioned step S220 and step S230 are optional step, in other embodiment of the present invention, it is possible to
To omit step S220 and step S230, or, it is also possible to step S220 and step S230 are merged into a step.
Step S240: the roadblock model library that inquiry is preset, it is judged that image whether with roadblock model library in comprise at least one
Individual roadblock Model Matching.
Wherein, mainly judge whether the region to be identified obtained in step S230 comprises at least in roadblock model library
One roadblock Model Matching.When specifically judging, the region to be identified in image and roadblock mould can be calculated by similarity algorithm
Similarity between type, determines image and roadblock Model Matching, and then determines bag in image when similarity is higher than predetermined threshold value
Containing roadblock, it should driver is pointed out.Those skilled in the art can select various types of similarity algorithm to enter flexibly
Row calculates, and the present invention does not limit concrete algorithm types.
Preferably due to whether automobile can bump against the current driving speed being heavily dependent on automobile with the roadblock in front
Degree and automobile and roadblock between distance: automobile driving speed is the fastest, the easiest because have little time brake and bump against；With roadblock it
Between distance the nearest, the most easily bump against.Therefore, in the present invention can be with between the current vehicle speed of composite vehicle and automobile and roadblock
Distance comprehensively determine when driver is pointed out.Distance between automobile and roadblock can by region to be identified with
Similarity estimation between roadblock model: under normal circumstances, the distance between automobile and roadblock is the most remote, due to image blurring, leads
Cause the similarity between region to be identified and roadblock model the lowest；Distance between automobile and roadblock is the nearest, owing to image is clear,
Cause the similarity between region to be identified and roadblock model the highest.Therefore, predetermined threshold value mentioned above can be dynamically determined:
The current vehicle speed of automobile is the highest, and the numerical value of this predetermined threshold value is the lowest, breaks down to prevent from having little time brake because speed is too fast；
The current vehicle speed of automobile is the lowest, and the numerical value of this predetermined threshold value is the highest, to prevent from erroneous judgement occur because identifying inaccurate.It is embodied as
Time, automobile speed scope can be divided into multiple interval, correspondingly, predetermined threshold value is set as multiple different number of threshold values
Value, each threshold value corresponds respectively to a vehicle speed intervals.Such as, by vehicle speed range (0,50km/h] be divided into the firstth district
Between, the threshold value of this interval correspondence is N1；Vehicle speed range (50km/h, 80km/h) is divided into the second interval, and this interval is right
The threshold value answered is N2；Vehicle speed range (80km/h, 120km/h) is divided into the 3rd interval, the number of threshold values that this interval is corresponding
Value is N3.Wherein, N1 is more than N2, and N2 is more than N3.Can be dynamically determined default by the way according to current vehicle speed scope
The numerical value of threshold value, thus compromise between security and accuracy.
It addition, in above-mentioned implementation, due to automobile whether can with the roadblock in front bump against also with the brake of automobile
Can be relevant, the automobile that braking quality is the best is less susceptible to accident occur, and the automobile obviously easier appearance that braking quality is the poorest
Accident, therefore, in the present embodiment, it is also possible to obtain the vehicle information of automobile and the braking quality that this vehicle is corresponding in advance,
When arranging predetermined threshold value, it is respectively directed to different money vehicle and different threshold value, such as, the vehicle that braking quality is the best are set
The numerical value of corresponding predetermined threshold value is the highest, to reach clearly to identify, prevent the effect of erroneous judgement；The vehicle correspondence that braking quality is the poorest
The numerical value of predetermined threshold value the lowest, to reach to point out as early as possible, avoid the effect of accident.
It addition, in addition to the rationally selection of predetermined threshold value, the kind of roadblock model and degree of accuracy also can affect differentiation knot
Really.In the present embodiment, roadblock model library kind can include multiple, for example, it is possible to include light for vehicle scintillation model, fault
Each class models such as direction board model, pedestrian dummy, small animal model, other barrier models, as long as can be to running car
The object model that route impacts can be stored in above-mentioned roadblock model library.
Wherein, light for vehicle scintillation model can be dynamic model, and this dynamic model farther includes: light for vehicle
Spacing between quantity and the adjacent taillight of flicker frequency, flash color, scintillation intensity and light for vehicle.Such as, usual car
Because of fault rest on highway time, bilateral taillight can replace flash red and yellow with predeterminated frequency, red by collecting in advance
The information such as lamp and the scintillation time of amber light, flicker frequency, flash color and scintillation intensity can accurately judge whether front deposits
In fault car.Wherein, flicker frequency, changes colour etc. can be represented, for example, it is possible to arrange parameter by the dynamic parameter preset
One is used for representing that flicker frequency, parameter two are used for representing changes colour etc..It addition, the quantity of the light for vehicle set in model can
To be two, the spacing before two taillights is determined by the actual range between two lamps on automobile.
Indicating fault board model can be static models, and static models farther include: the shape of indicating fault board, face
Normal complexion pattern.Wherein, indicating fault board is typically triangle, warning sign with yellow flag, therefore, it can according to this warning
The model that the color of board, shape are corresponding with setting with pattern.
Step S250: when judged result is for being, generates road-block prompting information.
Wherein, if the judged result of step S240 is no, do not process, continue the follow-up image got is entered in real time
Row is analyzed and is judged.If the judged result of step S240 is yes, illustrate that vehicle front exists roadblock, need to generate road-block prompting letter
Breath, to remind driver's careful driving.
Specifically, road-block prompting information can be accomplished in several ways.In the present embodiment, following three kind reality is given
Existing mode:
In the first implementation, road-block prompting information is auditory tone cues information.At this point it is possible to arrange at automotive interior
Audible alarm module, this alarm module can send the voice of " front exists roadblock, and Please drive carefully " etc and carry according to setting
Show；Or, this alarm module can also send the buzz of " too beep-" etc according to setting.By audible alarm module energy
Enough give driver prompting from audition angle.
In the second implementation, road-block prompting information is picture cues information.At this point it is possible to arrange on instrumental panel
Image alarm module, this image alarm module can be according to arranging the alarm pattern that display is preset, for example, it is possible to show eye-catching
Red warning mark lamp.Driver can be given from visual angle by image alarm module to point out.
In the third implementation, road-block prompting information is steering wheel vibration information.At this point it is possible at steering wheel
Inside installs vibrating motor additional, and by the raw vibration of this vibrating motor control direction hair updo, and then prompting driver exists abnormal conditions.
Driver can be given from sense of touch angle by steering wheel vibration mode to point out.
Three kinds of above-mentioned modes both can be used alone, it is also possible to is used in combination.Such as, by above-mentioned three kinds of implementations knot
Driver can be given from the multiple angle of audition, vision and sense of touch altogether to point out in all directions simultaneously, thus farthest
Avoid traffic accident.
Fig. 3 shows the structure chart of the Obstacle detection device based on automobile that another embodiment of the present invention provides.Such as Fig. 3 institute
Showing, this device includes: acquisition module 31, judge module 32 and reminding module 33.Wherein, acquisition module 31 is used for obtaining automobile week
The image enclosed.Judge module 32 is for inquiring about default roadblock model library, it is judged that described image whether with described roadblock model library
In at least one roadblock Model Matching of comprising.Reminding module 33, for when judged result is for being, generates road-block prompting information.
The concrete structure of above-mentioned modules and operation principle can refer to the description of appropriate section in embodiment of the method, herein
Repeat no more.
Fig. 4 shows the structure chart of the Obstacle detection device based on automobile that another embodiment of the present invention provides.Such as Fig. 4 institute
Showing, this device includes: acquisition module 41, judge module 42 and reminding module 43.Wherein, acquisition module 41 farther includes: really
Stator modules the 411, first photographic head 412, second camera 413 and the 3rd photographic head 414.
Wherein, acquisition module 41 is for obtaining the image of motor vehicle environment.Described determine that submodule 411 is for determining automobile
Current running state, when the current running state determining described automobile is forward traveling, by described first photographic head 412
Obtain the image of vehicle front；When the current running state determining described automobile is state of rolling backward, take the photograph by described second
As an image at 413 acquisition automobile rears；When the current running state determining described automobile is turn condition, by described
3rd photographic head 414 obtains the image of automobile turning side.
Wherein, described default roadblock model library includes: light for vehicle scintillation model and/or indicating fault board model.
Described light for vehicle scintillation model is dynamic model, and described dynamic model farther includes: the flicker frequency of described light for vehicle
Spacing between rate, flash color, scintillation intensity and the quantity of described light for vehicle and adjacent taillight；Described indicating fault
Board model is static models, and described static models farther include: the shape of described indicating fault board, design and color.
Alternatively, described judge module specifically for: calculate the similarity between described image and described roadblock model, when
Described image and described roadblock Model Matching is determined when result of calculation is more than predetermined threshold value；Further, described predetermined threshold value is according to working as
Front truck speed is dynamically determined.
Wherein, described road-block prompting information is auditory tone cues information, picture cues information and/or steering wheel vibration prompting
Information.
The concrete structure of above-mentioned modules and operation principle can refer to the description of appropriate section in embodiment of the method, herein
Repeat no more.
Fig. 5 shows the structure chart of the automobile 500 that another embodiment of the present invention provides, and this automobile 500 includes above-mentioned Fig. 3 institute
The Obstacle detection device shown, specifically includes: acquisition module 31, judge module 32 and reminding module 33.
Fig. 6 shows the structure chart of the automobile 600 that another embodiment of the present invention provides, and this automobile 600 includes above-mentioned Fig. 4 institute
The Obstacle detection device shown, specifically includes: acquisition module 41, judge module 42 and reminding module 43.Wherein, acquisition module 41 enters
One step comprises determining that submodule the 411, first photographic head 412, second camera 413 and the 3rd photographic head 414.
In Obstacle detection method based on automobile, device and the automobile that the embodiment of the present invention provides, it is possible to according to automobile
Image around and default roadblock model library detect whether motor vehicle environment exists roadblock automatically, and when testing result is for being
Automatically driver is pointed out.As can be seen here, the mode in the embodiment of the present invention effectively can be pointed out driver thus avoid causing
Vehicle accident, is greatly improved safety on the run.
Although additionally, it will be appreciated by those of skill in the art that embodiments more in this include institute in other embodiments
Including some feature rather than further feature, but the combination of the feature of different embodiment means to be in the scope of the present invention
Within and form different embodiments.Such as, in the following claims, embodiment required for protection any it
One can mode use in any combination.
The all parts embodiment of the present invention can realize with hardware, or to run on one or more processor
Software module realize, or with combinations thereof realize.It will be understood by those of skill in the art that and can use in practice
Microprocessor or digital signal processor (DSP) realize the some or all portions in device according to embodiments of the present invention
The some or all functions of part.The present invention is also implemented as the part for performing method as described herein or complete
The equipment in portion or device program (such as, computer program and computer program).Such program realizing the present invention
Can store on a computer-readable medium, or can be to have the form of one or more signal.Such signal is permissible
Download from internet website and obtain, or provide on carrier signal, or provide with any other form.
The present invention will be described rather than limits the invention to it should be noted above-described embodiment, and ability
Field technique personnel can design alternative embodiment without departing from the scope of the appended claims.In the claims,
Any reference marks that should not will be located between bracket is configured to limitations on claims.Word " comprises " and does not excludes the presence of not
Arrange element in the claims or step.Word "a" or "an" before being positioned at element does not excludes the presence of multiple such
Element.The present invention and can come real by means of including the hardware of some different elements by means of properly programmed computer
Existing.If in the unit claim listing equipment for drying, several in these devices can be by same hardware branch
Specifically embody.Word first, second and third use do not indicate that any order.These word explanations can be run after fame
Claim.
Claims (13)
1. an Obstacle detection method based on automobile, it is characterised in that including:
Obtain the image of motor vehicle environment；
The roadblock model library that inquiry is preset, it is judged that described image whether with at least one roadblock of comprising in described roadblock model library
Model Matching；
When judged result is for being, generate road-block prompting information.
Method the most according to claim 1, it is characterised in that the step of the image of described acquisition motor vehicle environment is wrapped further
Include:
Determine the current running state of automobile, when the current running state determining described automobile is forward traveling, obtain automobile
The image in front；When the current running state determining described automobile is state of rolling backward, obtain the image at automobile rear；When determining
When the current running state of described automobile is turn condition, obtain the image of automobile turning side.
Method the most according to claim 1, it is characterised in that described default roadblock model library includes: light for vehicle
Scintillation model and/or indicating fault board model.
Method the most according to claim 3, it is characterised in that described light for vehicle scintillation model is dynamic model, and institute
State dynamic model to farther include: the flicker frequency of described light for vehicle, flash color, scintillation intensity and described vehicle tail
Spacing between quantity and the adjacent taillight of lamp；
Described indicating fault board model is static models, and described static models farther include: the shape of described indicating fault board
Shape, design and color.
Method the most according to claim 1, it is characterised in that described judge described image whether with described roadblock model library
In the step of at least one roadblock Model Matching that comprises specifically include:
Calculate the similarity between described image and described roadblock model, determine described figure when result of calculation is more than predetermined threshold value
Picture and described roadblock Model Matching；
Further, described method farther includes: obtain the current vehicle speed of described automobile, and described predetermined threshold value according to described currently
Speed is dynamically determined.
Method the most according to claim 1, it is characterised in that described road-block prompting information is auditory tone cues information, image
Information and/or steering wheel vibration information.
7. an Obstacle detection device based on automobile, it is characterised in that including:
Acquisition module, for obtaining the image of motor vehicle environment；
Judge module, for inquiring about default roadblock model library, it is judged that whether described image comprises in described roadblock model library
At least one roadblock Model Matching；
Reminding module, for when judged result is for being, generates road-block prompting information.
Device the most according to claim 7, it is characterised in that described acquisition module farther includes: determine submodule,
One photographic head, second camera and the 3rd photographic head, wherein,
Described determine submodule for determining the current running state of automobile, when the current running state determining described automobile is
During forward traveling, obtained the image of vehicle front by described first photographic head；When the current driving shape determining described automobile
When state is state of rolling backward, obtained the image at automobile rear by described second camera；When the current line determining described automobile
When the state of sailing is turn condition, obtained the image of automobile turning side by described 3rd photographic head.
Device the most according to claim 7, it is characterised in that described default roadblock model library includes: light for vehicle
Scintillation model and/or indicating fault board model.
Device the most according to claim 9, it is characterised in that described light for vehicle scintillation model is dynamic model, and institute
State dynamic model to farther include: the flicker frequency of described light for vehicle, flash color, scintillation intensity and described vehicle tail
Spacing between quantity and the adjacent taillight of lamp；
Described indicating fault board model is static models, and described static models farther include: the shape of described indicating fault board
Shape, design and color.
11. devices according to claim 7, it is characterised in that described judge module specifically for:
Calculate the similarity between described image and described roadblock model, determine described figure when result of calculation is more than predetermined threshold value
Picture and described roadblock Model Matching；Further, described predetermined threshold value is dynamically determined according to current vehicle speed.
12. devices according to claim 7, it is characterised in that described road-block prompting information is auditory tone cues information, image
Information and/or steering wheel vibration information.
13. 1 kinds of automobiles, it is characterised in that include the arbitrary described Obstacle detection device of claim 7-12.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610574011.XA CN106183981B (en) | 2016-07-19 | 2016-07-19 | Obstacle detection method, apparatus based on automobile and automobile |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610574011.XA CN106183981B (en) | 2016-07-19 | 2016-07-19 | Obstacle detection method, apparatus based on automobile and automobile |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106183981A true CN106183981A (en) | 2016-12-07 |
| CN106183981B CN106183981B (en) | 2018-08-07 |
Family
ID=57493597
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610574011.XA Active CN106183981B (en) | 2016-07-19 | 2016-07-19 | Obstacle detection method, apparatus based on automobile and automobile |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106183981B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107240299A (en) * | 2017-07-20 | 2017-10-10 | 北京纵目安驰智能科技有限公司 | Autonomous land vehicle is to mobile object identification and the method for vehicle obstacle-avoidance |
| CN107463886A (en) * | 2017-07-20 | 2017-12-12 | 北京纵目安驰智能科技有限公司 | A kind of double method and systems for dodging identification and vehicle obstacle-avoidance |
| WO2018120470A1 (en) * | 2016-12-30 | 2018-07-05 | 华为技术有限公司 | Image processing method for use when reversing vehicles and relevant equipment therefor |
| CN110673609A (en) * | 2019-10-10 | 2020-01-10 | 北京小马慧行科技有限公司 | Vehicle running control method, device and system |
| CN110991320A (en) * | 2019-11-29 | 2020-04-10 | 北京百度网讯科技有限公司 | Road condition detection method and device, electronic equipment and storage medium |
| CN112925301A (en) * | 2019-12-05 | 2021-06-08 | 杭州海康机器人技术有限公司 | Control method for AGV danger avoidance and AGV |
| CN113052190A (en) * | 2021-04-01 | 2021-06-29 | 威海职业学院(威海市技术学院) | Visual auxiliary system and method based on image processing |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080266168A1 (en) * | 2006-03-01 | 2008-10-30 | Toyota Jidosha Kabushiki Kaisha | Obstacle Detecting Method, Obstacle Detecting Apparatus, and Standard Moving-Body Model |
| US20090268948A1 (en) * | 2008-04-24 | 2009-10-29 | Gm Global Technology Operations, Inc. | Pixel-based texture-rich clear path detection |
| CN102117546A (en) * | 2011-03-10 | 2011-07-06 | 上海交通大学 | On-vehicle traffic light assisting device |
| CN202454078U (en) * | 2012-02-27 | 2012-09-26 | 上海理工大学 | Road vehicle detecting device |
| CN103287372A (en) * | 2013-06-19 | 2013-09-11 | 贺亮才 | Automobile anti-collision safe protecting method based on image processing |
| JP5551236B2 (en) * | 2010-03-03 | 2014-07-16 | パナソニック株式会社 | Road condition management system and road condition management method |
| CN105438184A (en) * | 2015-12-22 | 2016-03-30 | 上海卓易科技股份有限公司 | Vehicle and method and system for recognizing traffic signs to assist in driving |
-
2016
- 2016-07-19 CN CN201610574011.XA patent/CN106183981B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080266168A1 (en) * | 2006-03-01 | 2008-10-30 | Toyota Jidosha Kabushiki Kaisha | Obstacle Detecting Method, Obstacle Detecting Apparatus, and Standard Moving-Body Model |
| US20090268948A1 (en) * | 2008-04-24 | 2009-10-29 | Gm Global Technology Operations, Inc. | Pixel-based texture-rich clear path detection |
| JP5551236B2 (en) * | 2010-03-03 | 2014-07-16 | パナソニック株式会社 | Road condition management system and road condition management method |
| CN102117546A (en) * | 2011-03-10 | 2011-07-06 | 上海交通大学 | On-vehicle traffic light assisting device |
| CN202454078U (en) * | 2012-02-27 | 2012-09-26 | 上海理工大学 | Road vehicle detecting device |
| CN103287372A (en) * | 2013-06-19 | 2013-09-11 | 贺亮才 | Automobile anti-collision safe protecting method based on image processing |
| CN105438184A (en) * | 2015-12-22 | 2016-03-30 | 上海卓易科技股份有限公司 | Vehicle and method and system for recognizing traffic signs to assist in driving |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018120470A1 (en) * | 2016-12-30 | 2018-07-05 | 华为技术有限公司 | Image processing method for use when reversing vehicles and relevant equipment therefor |
| CN108430831A (en) * | 2016-12-30 | 2018-08-21 | 华为技术有限公司 | A kind of method and its relevant device of reversing image procossing |
| CN107240299A (en) * | 2017-07-20 | 2017-10-10 | 北京纵目安驰智能科技有限公司 | Autonomous land vehicle is to mobile object identification and the method for vehicle obstacle-avoidance |
| CN107463886A (en) * | 2017-07-20 | 2017-12-12 | 北京纵目安驰智能科技有限公司 | A kind of double method and systems for dodging identification and vehicle obstacle-avoidance |
| CN107463886B (en) * | 2017-07-20 | 2023-07-25 | 北京纵目安驰智能科技有限公司 | Double-flash identification and vehicle obstacle avoidance method and system |
| CN110673609A (en) * | 2019-10-10 | 2020-01-10 | 北京小马慧行科技有限公司 | Vehicle running control method, device and system |
| CN110991320A (en) * | 2019-11-29 | 2020-04-10 | 北京百度网讯科技有限公司 | Road condition detection method and device, electronic equipment and storage medium |
| CN110991320B (en) * | 2019-11-29 | 2023-09-26 | 阿波罗智能技术(北京)有限公司 | Road condition detection method and device, electronic equipment and storage medium |
| CN112925301A (en) * | 2019-12-05 | 2021-06-08 | 杭州海康机器人技术有限公司 | Control method for AGV danger avoidance and AGV |
| CN113052190A (en) * | 2021-04-01 | 2021-06-29 | 威海职业学院(威海市技术学院) | Visual auxiliary system and method based on image processing |
| CN113052190B (en) * | 2021-04-01 | 2022-05-31 | 威海职业学院(威海市技术学院) | Visual auxiliary system and method based on image processing |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106183981B (en) | 2018-08-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106183981B (en) | Obstacle detection method, apparatus based on automobile and automobile | |
| RU2597066C2 (en) | Method and device for identification of road signs | |
| JP3912416B2 (en) | Vehicle departure prevention control device | |
| JP6868122B2 (en) | Vehicle control device, vehicle with it, and control method | |
| DE112016006199B4 (en) | INFORMATION DISPLAY DEVICE AND INFORMATION DISPLAY METHOD | |
| EP2523173B1 (en) | Driver assisting system and method for a motor vehicle | |
| US20130010114A1 (en) | Apparatus for detecting object approaching vehicle | |
| CN110758234A (en) | Vehicle lamp projection method and related product | |
| CN108482367A (en) | A kind of method, apparatus and system driven based on intelligent back vision mirror auxiliary | |
| CN106218644A (en) | Doubling auxiliary device based on automobile, method and automobile | |
| CN107452217A (en) | Fast traffic lane drives warning unit and method | |
| CN112109703A (en) | Vehicle control method, vehicle control system, vehicle, and storage medium | |
| CN106314424A (en) | Overtaking assisting method and device based on automobile and automobile | |
| CN102941851B (en) | Lane Mark identification fiduciary level improves system and method thereof | |
| JP2017151963A (en) | Method and device for supporting driver | |
| US20180249093A1 (en) | On-vehicle display control device, on-vehicle display system, on-vehicle display control method, and non-transitory storage medium | |
| JP2008052320A (en) | Surround monitoring system | |
| CN109987025B (en) | Vehicle driving assistance system and method for night environment | |
| JP2014229101A (en) | Vehicular display device | |
| KR101839978B1 (en) | Apparatus and method for determining traveling status of vehicle | |
| US9988059B2 (en) | Vehicle behavior detection device | |
| JP2016517103A (en) | Method for activating the driver assistant function when detecting the light of the brake light using the camera | |
| CN108216024A (en) | A kind of Lane Departure Warning System and its method | |
| US10864919B2 (en) | Alarm apparatus for a vehicle with driving control | |
| JP6354356B2 (en) | Forward situation judgment device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20180330 Address after: 100025 Beijing city Chaoyang District Yaojieyuan Road No. 105, No. 3 Building 8 layer 909 Applicant after: Music Automotive (Beijing) Co., Ltd. Address before: 100025 Beijing city Chaoyang District Yaojieyuan Road No. 105, No. 3 Building 10 layer 1102 Applicant before: Music Holdings (Beijing) Limited Applicant before: Smart car technology (Beijing) Co., Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20180929 Address after: 511458 9, Nansha District Beach Road, Guangzhou, Guangdong, 9 Patentee after: Hengda Faraday future intelligent vehicle (Guangdong) Co., Ltd. Address before: 100025 8 floor 909, 105 building 3, Yao Yuan Road, Chaoyang District, Beijing. Patentee before: Music Automotive (Beijing) Co., Ltd. |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20190312 Address after: 100015 Building No. 7, 74, Jiuxianqiao North Road, Chaoyang District, Beijing, 001 Patentee after: FAFA Automobile (China) Co., Ltd. Address before: 511458 9, Nansha District Beach Road, Guangzhou, Guangdong, 9 Patentee before: Hengda Faraday future intelligent vehicle (Guangdong) Co., Ltd. |
|
| TR01 | Transfer of patent right |