CN109703467A - It is a kind of for Vehicular intelligent driving bootstrap technique, system - Google Patents
It is a kind of for Vehicular intelligent driving bootstrap technique, system Download PDFInfo
- Publication number
- CN109703467A CN109703467A CN201910007023.8A CN201910007023A CN109703467A CN 109703467 A CN109703467 A CN 109703467A CN 201910007023 A CN201910007023 A CN 201910007023A CN 109703467 A CN109703467 A CN 109703467A
- Authority
- CN
- China
- Prior art keywords
- driver
- advance
- source vehicle
- turning
- hump
- 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
Landscapes
- Traffic Control Systems (AREA)
- Navigation (AREA)
Abstract
The present invention relates to a kind of bootstrap techniques for Vehicular intelligent driving, system, the hump of pre- travel inside edge line described in the foreground image is captured according to foreground image, or the imaginary line vertex by the point along the source vehicle y direction apart from the source vehicle pre-determined distance as the pre- travel, the hump or imaginary line vertex are with current vehicle speed, the accurate dynamic changes such as pre- traveling road alignment, accurately indicate the hump or imaginary line vertex, pass through the hump or imaginary line vertex and driver's pupil position line, the virtual location of hump or imaginary line vertex on transparent windshield head-up display described in accurate dynamic validation, the vision guide region generated by the accurate dynamic virtual position is necessarily accurate, vision guide region is accurately indicated to driver, from Fundamentally prevent traffic accident.
Description
Technical field
The present invention relates to motor vehicles driving safety technical field more particularly to a kind of guidance for Vehicular intelligent driving
Method, system.
Background technique
Highway bend section accident amount is big.Because of bend section, driver will not only control the travel speed of vehicle, also want
In due course according to road alignment, suitable steering wheel rotation corner.If the manipulation of steering wheel angle is not in time, it is easy for endangering
Dangerous accident.
Applicant experimental research find that, driver grasps steering wheel angle by observing the variation of road alignment
Vertical, vision has the function of guiding in advance for trailer reversing.If therefore can actively guide driver's region-of-interest, it will be expert at
Play the role of good in vehicle safety, and it is prevent traffic accident basic that driver's region-of-interest, which accurately guides,.
Summary of the invention
In order to solve the above-mentioned technical problem, the purpose of the present invention is to provide a kind of guidance sides for Vehicular intelligent driving
Method, system.
According to an aspect of the invention, there is provided a kind of bootstrap technique for Vehicular intelligent driving, including following step
It is rapid:
According to the electronic map of source vehicle region, judge that the source vehicle travels road alignment in advance, if turning road
Section then acquires the running environment data information of source vehicle, acquires driver's facial information, wherein the running environment data letter
Breath includes foreground image;
According to the source vehicle travel in advance road alignment, driver take aim in advance the time, source vehicle current vehicle speed, it is default judge away from
From preset relation determine with a distance from default judgement;
Judge that whether there is or not interfering bodies in the default judgement distance according to the running environment data information, if nothing, basis
The foreground image captures the hump of pre- travel inside edge line described in the foreground image, if can not capture
Function, then on the ground, using the point along the source vehicle y direction apart from the source vehicle pre-determined distance as the pre- traveling
The imaginary line vertex of road;
By the hump or the imaginary line vertex and the driver determining according to driver's facial information
Pupil position line, using the intersection point of the line and transparent windshield head-up display as datum mark, according to datum mark and
Preset condition is generated in the head-up vision guide region of transparent windshield.
Further, time, source vehicle current vehicle speed are taken aim at according to the pre- traveling road alignment, driver in advance, presets and sentences
Turn-off from preset relation determine with a distance from default judgement, comprising:
According to turning section turning radius, in advance take aim at the time with road radius variation coefficient, turning radius with length change
Rate, turning driver take aim at the preset relation of time in advance and show that the turning driver takes aim at the time in advance;
Time, source vehicle current vehicle speed, default judgement are taken aim in advance according to the pre- traveling road alignment, the turning driver
The preset relation of distance, which determines to preset, judges distance.
The bootstrap technique for Vehicular intelligent driving, further includes:
According to pre- traveling road alignment, the driver take aim in advance the time, source vehicle current vehicle speed, pre-determined distance default pass
It is to determine pre-determined distance.
According to pre- traveling road alignment, the driver take aim in advance the time, source vehicle current vehicle speed, pre-determined distance default pass
It is to determine that pre-determined distance includes:
According to turning section turning radius, in advance take aim at the time with road radius variation coefficient, turning radius with length change
Rate, turning driver take aim at the preset relation of time in advance and show that the turning driver takes aim at the time in advance;
Time, source vehicle current vehicle speed, pre-determined distance are taken aim in advance according to the pre- traveling road alignment, the turning driver
Preset relation determine pre-determined distance.
It is described turning section turning radius, it is described it is pre- take aim at the time with road radius variation coefficient, the turning radius with
The change rate of length, the turning driver take aim at the preset relation of time in advance are as follows:
Wherein,
T is that turning driver takes aim at the time in advance, unit: s;
R is the turning radius in turning section, unit: m;
K is to take aim at the time in advance with road radius variation coefficient, recommends value range [2,5] * 10-3;
DR/dl is change rate of the turning radius with length, dimensionless.
Turning radius, the turning radius in the turning section are obtained with the change rate of length by electronic map.
Driver's facial information is acquired by the first camera, and the running environment data information passes through the second camera shooting
Head acquisition, first camera and second camera are respectively arranged on front side of interior driver on corresponding windshield.
The driver's pupil position determined according to driver's facial information, comprising:
Driver's pupil is obtained in the first three-dimensional seat established based on the first camera according to driver's facial information
The first coordinate position under mark system;
By first coordinate position of driver's pupil according to the first camera on the source vehicle windshield
Installation site and angular transition are at the second coordinate position under the second three-dimensional system of coordinate established based on the source vehicle.
The curve of pre- travel inside edge line described in the foreground image is successfully captured according to the foreground image
Vertex, comprising:
Obtain third coordinate position of the hump under the third three-dimensional system of coordinate established based on second camera;
By the third coordinate position of the hump according to second camera on the source vehicle windshield
Installation site and angular transition at the 4-coordinate position under the second three-dimensional system of coordinate established based on the source vehicle.
The vision guide region is centered on the intersection point, with the number of d*sin (3/57.34) to (6/57.34) d*sin
Value is the multiple concentric circles or class concentric circles that radius generates color gradient, the color gradient of the multiple concentric circles or class concentric circles
The variation configuration of degree of concern need to be put into according to driver, wherein d is distance of driver's pupil to the intersection point.
According to another aspect of the present invention, a kind of guidance system for Vehicular intelligent driving is provided, comprising:
Information acquisition unit is configured to the electronic map according to source vehicle region, judges that the source vehicle is carried out ahead of schedule
Road alignment is sailed, if turning section, then the running environment data information of source vehicle is acquired, acquires driver's facial information,
In, the running environment data information includes foreground image;
It is default to judge apart from generation unit, it is configured to travel road alignment, driver in advance according to the source vehicle and take aim in advance
Time, source vehicle current vehicle speed, the default preset relation for judging distance, which determine to preset, judges distance;
Hump capture unit is configured to judge the default judgement distance according to the running environment data information
Interior whether there is or not interfering bodies, if nothing, capture pre- travel inside edge described in the foreground image according to the foreground image
The hump of line on the ground, will be preset along the source vehicle y direction apart from the source vehicle if capture is unsuccessful
Imaginary line vertex of the point of distance as the pre- travel;
Vision guide Area generation unit is configured to by the hump or the imaginary line vertex and according to institute
Driver's pupil position line that driver's facial information determines is stated, with the line and transparent windshield head-up display
Intersection point is generated according to datum mark and preset condition in the head-up view of transparent windshield as datum mark
Feel guidance field.
According to another aspect of the present invention, a kind of equipment is provided, the equipment includes:
One or more processors;
Memory, for storing one or more programs,
When one or more of programs are executed by one or more of processors, so that one or more of places
It manages device and executes as above described in any item methods.
According to another aspect of the present invention, provide it is a kind of be stored with the computer-readable of computer program and deposit medium,
As above described in any item methods are realized when the program is executed by processor.
Compared with prior art, the invention has the following advantages:
1, the exemplary bootstrap technique for Vehicular intelligent driving of the present invention captures the foreground image according to foreground image
Described in pre- travel inside edge line hump, or will be pre- apart from the source vehicle along the source vehicle y direction
If imaginary line vertex of the point of distance as the pre- travel, the hump or imaginary line vertex are with current
The accurate dynamic changes such as speed, pre- traveling road alignment, accurately indicate the hump or imaginary line vertex, by described
Hump or imaginary line vertex and driver's pupil position line, hump or imaginary line described in accurate dynamic validation
Virtual location of the vertex on transparent windshield head-up display, the vision guide area generated by the accurate dynamic virtual position
Domain is necessarily accurate, and vision guide region is accurately indicated to driver, fundamentally prevents traffic accident.
2, the exemplary guidance system for Vehicular intelligent driving of the present invention, composition is simple, by each composition system and
It cooperates between unit, from the hump of the pre- travel inside edge line of prospect picture catching, or apart from institute
State the imaginary line vertex of the pre- travel of source vehicle pre-determined distance, with current vehicle speed, travel road alignment in advance
Etc. accurate dynamic change, pass through the hump or imaginary line vertex and driver's pupil position line and the transparent glass that keeps out the wind
The hump or imaginary line vertex of glass head-up display intersection point confirmation are on transparent windshield head-up display
Virtual location is accurate, and the vision guide region generated by the accurate dynamic virtual position is necessarily accurate, fundamentally prevents traffic
The generation of accident.
3, it the exemplary equipment of the present invention and is stored with the computer-readable of computer program and deposits medium, realize with current
The quantization vision guide region of the accurate dynamic changes such as speed, pre- traveling road alignment, accurately indicates vision guide to driver
Region, and then prevent traffic accident, which is worthy to be popularized.
Detailed description of the invention
Fig. 1 is the bootstrap technique flow chart that embodiment one is used for Vehicular intelligent driving;
Fig. 2 is the first camera and second camera schematic view of the mounting position in embodiment one;
Fig. 3 is that driver's blinkpunkt falls in using hump as origin, is in the region of radius with D*sin (x/57.34)
Probability density distribution figure;
Fig. 4 is that driver's blinkpunkt falls in using hump as origin, is in the region of radius with D*sin (x/57.34)
Cumulative probability distribution map;
Fig. 5 is the turning section bootstrap technique schematic diagram of embodiment one;
Fig. 6 is third coordinate of one hump of embodiment under the third three-dimensional system of coordinate established based on second camera
Position view;
Fig. 7 is the intersection point schematic diagram of one hump of embodiment and driver's interpupillary line and front windshield of vehicle;
When Fig. 8 is that one vehicle of embodiment turns left, the vision guide area schematic that is shown on the windshield using HUD;
When Fig. 9 is that one vehicle of embodiment is turned right, the vision guide area schematic that is shown on the windshield using HUD.
Specific embodiment
In order to be better understood by technical solution of the present invention, combined with specific embodiments below, Figure of description is to the present invention
It is described further.
Embodiment one:
A kind of bootstrap technique for Vehicular intelligent driving is present embodiments provided, as shown in Figure 1, comprising the following steps:
S1, according to the electronic map of source vehicle region, judge that the source vehicle travels road alignment in advance, if turning
Section then acquires the running environment data information of source vehicle, acquires driver's facial information, and driver's facial information passes through
The acquisition of first camera, the running environment data information are acquired by second camera, and first camera and second is taken the photograph
As head is respectively arranged on front side of interior driver on corresponding windshield, as shown in Figure 2, wherein the running environment data letter
Breath includes foreground image.
S2, it road alignment, driver are travelled in advance according to the source vehicle takes aim at the time in advance, source vehicle current vehicle speed, default sentence
Turn-off from preset relation determine with a distance from default judgement, specifically include:
According to turning section turning radius, in advance take aim at the time with road radius variation coefficient, turning radius with length change
Rate, turning driver take aim at the preset relation of time in advance and show that the turning driver takes aim at the time in advance, wherein the turning section
Turning radius, turning radius with length change rate pass through electronic map obtain;
Time, source vehicle current vehicle speed, default judgement are taken aim in advance according to the pre- traveling road alignment, the turning driver
The preset relation of distance, which determines to preset, judges distance,
It is described turning section turning radius, it is described it is pre- take aim at the time with road radius variation coefficient, the turning radius with
The change rate of length, the turning driver take aim at the preset relation of time in advance are as follows:
Wherein,
T is that turning driver takes aim at the time in advance, unit: s;
R is the turning radius in turning section, unit: m;
K is to take aim at the time in advance with road radius variation coefficient, recommends value range [2,5] * 10-3;
DR/dl is change rate of the turning radius with length, dimensionless.
S3, judge that whether there is or not interfering bodies in the default judgement distance according to the running environment data information, if nothing, root
The hump of pre- travel inside edge line described in the foreground image is captured according to the foreground image,
Wherein, pre- travel inside edge line described in the foreground image is successfully captured according to the foreground image
Hump, comprising:
Obtain third coordinate position of the hump under the third three-dimensional system of coordinate established based on second camera;
By the third coordinate position of the hump according to second camera on the source vehicle windshield
Installation site and angular transition at the 4-coordinate position under the second three-dimensional system of coordinate established based on the source vehicle.
It, on the ground, will be along the source vehicle y direction apart from the source vehicle pre-determined distance if capture is unsuccessful
Imaginary line vertex of the point as the pre- travel, wherein pre-determined distance is according to the pre- traveling road alignment, driving
People takes aim at time, source vehicle current vehicle speed, the determination of the preset relation of pre-determined distance in advance.
Wherein, time, source vehicle current vehicle speed, pre-determined distance are taken aim at according to pre- traveling road alignment, the driver in advance
Preset relation determines pre-determined distance, comprising:
According to turning section turning radius, in advance take aim at the time with road radius variation coefficient, turning radius with length change
Rate, turning driver take aim at the preset relation of time in advance and show that the turning driver takes aim at the time in advance;
Time, source vehicle current vehicle speed, pre-determined distance are taken aim in advance according to the pre- traveling road alignment, the turning driver
Preset relation determine pre-determined distance.
S4, by the hump or the imaginary line vertex and the driving that is determined according to driver's facial information
People's pupil position line, using the intersection point of the line and transparent windshield head-up display as datum mark, according to datum mark
And preset condition is generated in the head-up vision guide region of transparent windshield, the vision guide area
Domain generates color gradient centered on the intersection point, by radius of the numerical value of d*sin (3/57.34) to d*sin (6/57.34)
The color gradient root of multiple concentric circles or class concentric circles, the multiple concentric circles or class concentric circles (i.e. close to circular concentric circles)
The variation configuration of degree of concern need to be put into according to driver, convenient for driver turning Emergency time, to focus according to needing to throw
The variation for entering degree of concern carries out careful distribution again, so that limited concern power is put into the area that should most pay close attention to by driver
Domain further increases the vision guide regional guidance accuracy, wherein d is distance of driver's pupil to the intersection point.It should
Generally color is gradually shallow from small to large for the color gradient rule of the multiple concentric circles in vision guide region or class concentric circles.
Fig. 3 is that driver's blinkpunkt falls in using hump as origin, is in the region of radius with D*sin (x/57.34)
Probability density distribution figure.Wherein, D is to drive head part to the distance of hump, and x is driver's sight angle on curve top
Variation range around point.
Fig. 4 is that driver's blinkpunkt falls in using hump as origin, is in the region of radius with D*sin (x/57.34)
Cumulative probability distribution map.Wherein, D is to drive head part to the distance of hump, and x is driver's sight angle on curve top
Variation range around point.
From two figures above it is found that driver's blinkpunkt falls in using hump as origin, is partly with D*sin (3/57.34)
Cumulative probability in the region of diameter reaches 50% or more, falls in using hump as origin, with D*sin (6/57.34) as radius
Region in cumulative probability reach 85% or more.Therefore, the guidance field radius value on windshield should be in d*sin (3/
57.34) to d*sin (6/57.34) range.
Wherein, the driver's pupil position determined according to driver's facial information, comprising:
Driver's pupil is obtained in the first three-dimensional seat established based on the first camera according to driver's facial information
The first coordinate position under mark system;
By first coordinate position of driver's pupil according to the first camera on the source vehicle windshield
Installation site and angular transition are at the second coordinate position under the second three-dimensional system of coordinate established based on the source vehicle.
Turning section bootstrap technique is as shown in figure 5,1 is the road ahead environment in the turning section driver visual field;2 be curved
Road inside edge line;3 be lane line;4 be bend outer ledge line.
The above-mentioned bootstrap technique specific implementation step for Vehicular intelligent driving is as follows:
S1: vehicle centre console is opened;
S2: unlocking vehicle GPS positions this vehicle, imports the local electronic map in this vehicular seat area, judges front road
Route shape, if straight trip, this system does not work, if bend section;
S3: using electronic map estimate this vehicle driving road ahead radius and its change rate (the i.e. described turning section
Turning radius, turning radius with length change rate), while open it is (infrared to take the photograph towards the second camera in front of vehicle driving
As head B), when installation, the roll angle roll_b and yaw angle yaw_b of second camera are both needed to be 0, record second camera in vehicle
Installation site and angle (Xb, Yb, Zb, pitch_b, roll_b, yaw_b) on acquire running environment data information, institute
Stating running environment data information includes foreground image foreground image and obstacle information, judge vehicle front T*V distance it is interior whether
There are interfering bodies i.e. other traffic participants (vehicle, pedestrian etc.),
Wherein,
V: vehicle driving speed, unit m/s,
T: turning driver takes aim at the time in advance, solution formula:
Wherein,
T is that turning driver takes aim at the time in advance, unit: s;
R is the turning radius in turning section, unit: m;
K is to take aim at the time in advance with road radius variation coefficient, recommends value range [2,5] * 10-3;
DR/dl is change rate of the turning radius with length, dimensionless.
System does not work if having other traffic participants, if nothing, obtains foreground image captured by second camera
In, can point most outstanding, as hump, judgment curves vertex obtain lane inside edge line in the horizontal direction, if
Can, then third coordinate position of the hump under the third three-dimensional system of coordinate established based on second camera is obtained, i.e.,
As shown in Figure 6 by shooting road traffic environment, hump is obtained in the third three-dimensional coordinate established based on second camera
Third coordinate position under system;By the third coordinate position of the hump according to second camera in the source vehicle
Installation site and angular transition on windshield are sat at the 4th under the second three-dimensional system of coordinate established based on the source vehicle
Cursor position.If cannot obtain, on the ground, the point of T*V distance is got over as virtual song apart from vehicle along vehicle y direction
Line vertex.
It opens towards the first camera (infrared camera A) for driving human face and acquires driver's facial information, driven
Sail first coordinate position of people's pupil under the first three-dimensional system of coordinate established based on the first camera;By the institute of driver's pupil
The first coordinate position is stated according to installation site of first camera on the source vehicle windshield and angular transition at being based on
The second coordinate position under the second three-dimensional system of coordinate that the source vehicle is established, the first camera need to record its peace on vehicle
Holding position and angle (Xa, Ya, Za, pitch_b, roll_a, yaw_a), the first camera should be mounted on as far as possible drives head part
Center, so as to capture driver's pupil in maximum magnitude;
S4: the hump or the terrestrial virtual hump and driver's interpupillary line and vehicle front windshield are solved
The intersection point of glass, the hump as shown in Figure 7 and driver's interpupillary line and the intersection point of front windshield of vehicle are illustrated;
S5: centered on the intersection point, drawing multiple concentric rings or class concentric ring (such as close to circular ellipse), multiple
The value range of concentric ring or the concentric circle radius of class is the numerical value of d*sin (3/57.34) to (6/57.34) d*sin, and partly
The small circle of diameter or class circle should be identified with dark colour, and the big circle of radius or class circle are identified with light colour, the institute of color
To change, be intended to embody the variation of degree of concern, far from center, degree of concern more it is low wherein, d is to drive
For people's pupil to the distance of the intersection point, multiple concentric ring or class concentric ring are that turning moment HUD is shown on the windshield
The vision guide region shown, when being illustrated in figure 8 vehicle left-hand rotation, the vision guide region shown on the windshield using HUD,
It guides driver to pay close attention at the hump, when being illustrated in figure 9 vehicle right-hand rotation, is shown on the windshield using HUD
Vision guide region, guidance driver pay close attention at the hump.
It is proved through a large number of experiments, when negotiation of bends, driver's blinkpunkt concentrates on the hump of lane inside edge line
Place is come so that position of the hump in the driver visual field is held essentially constant by keeping steering wheel rotation corner, can
So that vehicle passes through bend section.
The present embodiment additionally provides a kind of guidance system for Vehicular intelligent driving, comprising:
Information acquisition unit is configured to the electronic map according to source vehicle region, judges that the source vehicle is carried out ahead of schedule
Road alignment is sailed, if turning section, then the running environment data information of source vehicle is acquired, acquires driver's facial information,
In, the running environment data information includes foreground image;
It is default to judge apart from generation unit, it is configured to travel road alignment, driver in advance according to the source vehicle and take aim in advance
Time, source vehicle current vehicle speed, the default preset relation for judging distance, which determine to preset, judges distance, is also configured to:
According to turning section turning radius, in advance take aim at the time with road radius variation coefficient, turning radius with length change
Rate, turning driver take aim at the preset relation of time in advance and show that the turning driver takes aim at the time in advance;
Time, source vehicle current vehicle speed, default judgement are taken aim in advance according to the pre- traveling road alignment, the turning driver
The preset relation of distance, which determines to preset, judges distance,
Wherein, the turning radius in the turning section, described pre- take aim at the time with road radius variation coefficient, the bend half
Diameter takes aim at the preset relation of time with the change rate of length, the turning driver in advance are as follows:
Wherein,
T is that turning driver takes aim at the time in advance, unit: s;
R is the turning radius in turning section, unit: m;
K is to take aim at the time in advance with road radius variation coefficient, recommends value range [2,5] * 10-3;
DR/dl is change rate of the turning radius with length, dimensionless;
Hump capture unit is configured to judge the default judgement distance according to the running environment data information
Interior whether there is or not interfering bodies, if nothing, capture pre- travel inside edge described in the foreground image according to the foreground image
The hump of line on the ground, will be preset along the source vehicle y direction apart from the source vehicle if capture is unsuccessful
Imaginary line vertex of the point of distance as the pre- travel, it is pre- with specific reference to the pre- traveling road alignment, driver
Take aim at the time, source vehicle current vehicle speed, the preset relation of pre-determined distance determine pre-determined distance, more specifically include:
According to turning section turning radius, in advance take aim at the time with road radius variation coefficient, turning radius with length change
Rate, turning driver take aim at the preset relation of time in advance and show that the turning driver takes aim at the time in advance;
Time, source vehicle current vehicle speed, pre-determined distance are taken aim in advance according to the pre- traveling road alignment, the turning driver
Preset relation determine pre-determined distance;
Vision guide Area generation unit is configured to by the hump or the imaginary line vertex and according to institute
Driver's pupil position line that driver's facial information determines is stated, with the line and transparent windshield head-up display
Intersection point is generated according to datum mark and preset condition in the head-up view of transparent windshield as datum mark
Feel guidance field.
It should be appreciated that systems or unit that the above-mentioned guidance system for Vehicular intelligent driving is recorded are used for above-mentioned
Each step of the bootstrap technique description of Vehicular intelligent driving is corresponding.As a result, above with respect to the operation and feature of method description
The systems and unit wherein included of the above-mentioned guidance system for Vehicular intelligent driving are equally applicable to, it is no longer superfluous herein
It states.
As on the other hand, the present embodiment additionally provides the equipment for being suitable for being used to realize the embodiment of the present application, and equipment includes
Computer system, the computer system include central processing unit (CPU), can be according to being stored in read-only memory
(ROM) corresponding program of each step of the above-mentioned bootstrap technique description for Vehicular intelligent driving of execution in or from storage
It is partially loaded into random access storage device (RAM) and is used to execute what the above-mentioned bootstrap technique for Vehicular intelligent driving described
Each corresponding program of step and execute various movements appropriate and processing.In RAM, also it is stored with each needed for system operatio
Kind program and data.CPU, ROM and RAM are connected with each other by bus.Input/output (I/O) interface is also connected to bus.
I/O interface is connected to lower component: the importation including keyboard, mouse etc.;Including such as cathode-ray tube
(CRT), the output par, c of liquid crystal display (LCD) etc. and loudspeaker etc.;Storage section including hard disk etc.;And including all
Such as communications portion of the network interface card of LAN card, modem.Communications portion executes logical via the network of such as internet
Letter processing.Driver is also connected to I/O interface as needed.Detachable media, such as disk, CD, magneto-optic disk, semiconductor are deposited
Reservoir etc. is installed as needed on a drive, in order to be mounted into as needed from the computer program read thereon
Storage section.
Particularly, in accordance with an embodiment of the present disclosure, each step of the above-mentioned bootstrap technique description for Vehicular intelligent driving
Suddenly the process described may be implemented as computer software programs.For example, embodiment of the disclosure includes a kind of computer program
Product comprising the computer program being tangibly embodied on machine readable media, the computer program include for executing
The program code of the above-mentioned bootstrap technique for Vehicular intelligent driving.In such embodiments, which can lead to
It crosses communications portion to be downloaded and installed from network, and/or is mounted from detachable media.
Flow chart in attached drawing illustrates the system according to various embodiments of the invention, method and computer program product
Architecture, function and operation in the cards.In this regard, each box in flow chart can represent a module,
A part of program segment or code, a part of the module, program segment or code include one or more for realizing rule
The executable instruction of fixed logic function.It should also be noted that in some implementations as replacements, function marked in the box
It can also occur in a different order than that indicated in the drawings.For example, two boxes succeedingly indicated can actually be basic
It is performed in parallel, they can also be executed in the opposite order sometimes, and this depends on the function involved.It is also noted that
The combination of each box in flow chart and the box in flow chart can use the dedicated of functions or operations as defined in executing
Hardware based system realize, or can realize using a combination of dedicated hardware and computer instructions.
Being described in the embodiment of the present application involved unit or module can be realized by way of software, can also be with
It is realized by way of hardware.Described unit or module also can be set in the processor.These units or module
Title does not constitute the restriction to the unit or module itself under certain conditions.
As on the other hand, the present embodiment additionally provides a kind of computer readable storage medium, the computer-readable storage
Medium can be computer readable storage medium included in system described in above-described embodiment;It is also possible to individualism,
Without the computer readable storage medium in supplying equipment.Computer-readable recording medium storage has one or more than one journey
Sequence, described program be used to execute by one or more than one processor be described in the application for Vehicular intelligent driving
Bootstrap technique.
Above description is only the preferred embodiment of the application and the explanation to institute's application technology principle.Those skilled in the art
Member is it should be appreciated that invention scope involved in the application, however it is not limited to technology made of the specific combination of above-mentioned technical characteristic
Scheme, while should also cover in the case where not departing from the inventive concept, it is carried out by above-mentioned technical characteristic or its equivalent feature
Any combination and the other technical solutions formed.Such as features described above has similar function with (but being not limited to) disclosed herein
Energy.
Claims (10)
1. a kind of bootstrap technique for Vehicular intelligent driving, characterized in that the following steps are included:
According to the electronic map of source vehicle region, judge that the source vehicle travels road alignment in advance, if turning section, then
The running environment data information of source vehicle is acquired, acquires driver's facial information, wherein the running environment data information includes
Foreground image;
Road alignment, driver is travelled in advance according to the source vehicle to take aim at the time in advance, source vehicle current vehicle speed, default judge distance
Preset relation, which determines to preset, judges distance;
Judge that whether there is or not interfering bodies in the default judgement distance according to the running environment data information, if nothing, according to
Foreground image captures the hump of pre- travel inside edge line described in the foreground image, if capture is unsuccessful,
On the ground, by the point along the source vehicle y direction apart from the source vehicle pre-determined distance as the pre- travel
Imaginary line vertex;
By the hump or the imaginary line vertex and the driver pupil determining according to driver's facial information
Position line according to datum mark and is preset using the intersection point of the line and transparent windshield head-up display as datum mark
Condition is generated in the head-up vision guide region of transparent windshield.
2. the bootstrap technique according to claim 1 for Vehicular intelligent driving, characterized in that according to the pre- travel road
Route shape, driver take aim at the time in advance, source vehicle current vehicle speed, the default preset relation for judge distance determine to preset and judge distance,
Include:
According to turning section turning radius, in advance take aim at the time with road radius variation coefficient, turning radius with length change rate,
Turning driver takes aim at the preset relation of time in advance and show that the turning driver takes aim at the time in advance;
The time is taken aim in advance according to the pre- traveling road alignment, the turning driver, source vehicle current vehicle speed, default judges distance
Preset relation determine and default judge distance.
3. the bootstrap technique according to claim 1 for Vehicular intelligent driving, characterized in that further include:
It is true that time, source vehicle current vehicle speed, the preset relation of pre-determined distance are taken aim in advance according to the pre- traveling road alignment, driver
Determine pre-determined distance.
4. the bootstrap technique according to claim 3 for Vehicular intelligent driving, characterized in that according to the pre- travel road
Route shape, driver take aim at the time in advance, source vehicle current vehicle speed, the preset relation of pre-determined distance determine that pre-determined distance includes:
According to turning section turning radius, in advance take aim at the time with road radius variation coefficient, turning radius with length change rate,
Turning driver takes aim at the preset relation of time in advance and show that the turning driver takes aim at the time in advance;
According to it is described it is pre- traveling road alignment, it is described turning driver take aim in advance the time, source vehicle current vehicle speed, pre-determined distance it is pre-
If relationship determines pre-determined distance.
5. the bootstrap technique according to claim 2 or 4 for Vehicular intelligent driving, characterized in that the turning section
Turning radius, the pre- change rate for taking aim at the time with road radius variation coefficient, the turning radius with length, the turning
Driver takes aim at the preset relation of time in advance are as follows:
Wherein,
T is that turning driver takes aim at the time in advance, unit: s;
R is the turning radius in turning section, unit: m;
K is to take aim at the time in advance with road radius variation coefficient, recommends value range [2,5] * 10-3;
DR/dl is change rate of the turning radius with length, dimensionless.
6. the bootstrap technique according to claim 1 for Vehicular intelligent driving, characterized in that the driving human face letter
Breath by the first camera acquire, the running environment data information by second camera acquire, first camera with
Second camera is respectively arranged on front side of interior driver on corresponding windshield.
7. the bootstrap technique according to claim 6 for Vehicular intelligent driving, characterized in that according to the driver face
Driver's pupil position that portion's information determines, comprising:
Driver's pupil is obtained in the first three-dimensional system of coordinate established based on the first camera according to driver's facial information
Under the first coordinate position;
Installation by first coordinate position of driver's pupil according to the first camera on the source vehicle windshield
Position and angular transition are at the second coordinate position under the second three-dimensional system of coordinate established based on the source vehicle.
8. the bootstrap technique according to claim 6 for Vehicular intelligent driving, characterized in that according to the foreground image
Success captures the hump of pre- travel inside edge line described in the foreground image, comprising:
Obtain third coordinate position of the hump under the third three-dimensional system of coordinate established based on second camera;
Peace by the third coordinate position of the hump according to second camera on the source vehicle windshield
Holding position and angular transition are at the 4-coordinate position under the second three-dimensional system of coordinate established based on the source vehicle.
9. the bootstrap technique according to claim 1 for Vehicular intelligent driving, characterized in that the vision guide region
Centered on the intersection point, the more of color gradient are generated by radius of the numerical value of d*sin (3/57.34) to d*sin (6/57.34)
The color gradient of a concentric circles or class concentric circles, the multiple concentric circles or class concentric circles need to put into degree of concern according to driver
Variation configuration, wherein d be driver's pupil to the intersection point distance.
10. a kind of guidance system for Vehicular intelligent driving, characterized in that include:
Information acquisition unit is configured to the electronic map according to source vehicle region, judges the pre- travel road of the source vehicle
Route shape then acquires the running environment data information of source vehicle if turning section, acquires driver's facial information, wherein institute
Stating running environment data information includes foreground image;
It is default to judge apart from generation unit, be configured to be travelled in advance according to the source vehicle road alignment, driver take aim in advance the time,
Source vehicle current vehicle speed, the default preset relation for judging distance, which determine to preset, judges distance;
Hump capture unit is configured to judge have in the default judgement distance according to the running environment data information
Noiseless body captures pre- travel inside edge line described in the foreground image according to the foreground image if nothing
It hump on the ground, will be along the source vehicle y direction apart from the source vehicle pre-determined distance if capture is unsuccessful
Imaginary line vertex of the point as the pre- travel;
Vision guide Area generation unit is configured to drive the hump or the imaginary line vertex with according to described
Driver's pupil position line that human face's information determines is sailed, with the intersection point of the line and transparent windshield head-up display
As datum mark, generated according to datum mark and preset condition for drawing in the head-up vision of transparent windshield
Lead region.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910007023.8A CN109703467B (en) | 2019-01-04 | 2019-01-04 | It is a kind of for Vehicular intelligent driving bootstrap technique, system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910007023.8A CN109703467B (en) | 2019-01-04 | 2019-01-04 | It is a kind of for Vehicular intelligent driving bootstrap technique, system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109703467A true CN109703467A (en) | 2019-05-03 |
CN109703467B CN109703467B (en) | 2019-09-06 |
Family
ID=66260728
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910007023.8A Active CN109703467B (en) | 2019-01-04 | 2019-01-04 | It is a kind of for Vehicular intelligent driving bootstrap technique, system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109703467B (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112799387A (en) * | 2019-10-25 | 2021-05-14 | 杭州海康汽车技术有限公司 | Robot control method and device and robot |
CN112896181A (en) * | 2021-01-14 | 2021-06-04 | 重庆长安汽车股份有限公司 | Electronic fence control method, system, vehicle and storage medium |
CN113138594A (en) * | 2020-01-20 | 2021-07-20 | 北京四维图新科技股份有限公司 | Automatic driving method and device |
CN112799387B (en) * | 2019-10-25 | 2024-06-07 | 杭州海康汽车技术有限公司 | Robot control method and device and robot |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130050655A1 (en) * | 2011-08-29 | 2013-02-28 | Denso Corporation | Head-up display apparatus, screen member, manufacturing method thereof and image projecting method |
CN103895572A (en) * | 2014-04-22 | 2014-07-02 | 北京汽车研究总院有限公司 | Method and device for displaying driving information of vehicle in front visual field |
CN105313774A (en) * | 2014-07-09 | 2016-02-10 | 现代摩比斯株式会社 | Driving assistant apparatus of vehicle and operating method thereof |
CN205601703U (en) * | 2016-03-22 | 2016-09-28 | 华晨汽车集团控股有限公司 | Car is preceding, side blind area indicating system |
CN108725323A (en) * | 2017-04-21 | 2018-11-02 | 梅克朗有限两合公司 | For the visor alternative system of the camera system of vehicle including the camera system and including the driver assistance system of the system |
-
2019
- 2019-01-04 CN CN201910007023.8A patent/CN109703467B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130050655A1 (en) * | 2011-08-29 | 2013-02-28 | Denso Corporation | Head-up display apparatus, screen member, manufacturing method thereof and image projecting method |
CN103895572A (en) * | 2014-04-22 | 2014-07-02 | 北京汽车研究总院有限公司 | Method and device for displaying driving information of vehicle in front visual field |
CN105313774A (en) * | 2014-07-09 | 2016-02-10 | 现代摩比斯株式会社 | Driving assistant apparatus of vehicle and operating method thereof |
CN205601703U (en) * | 2016-03-22 | 2016-09-28 | 华晨汽车集团控股有限公司 | Car is preceding, side blind area indicating system |
CN108725323A (en) * | 2017-04-21 | 2018-11-02 | 梅克朗有限两合公司 | For the visor alternative system of the camera system of vehicle including the camera system and including the driver assistance system of the system |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112799387A (en) * | 2019-10-25 | 2021-05-14 | 杭州海康汽车技术有限公司 | Robot control method and device and robot |
CN112799387B (en) * | 2019-10-25 | 2024-06-07 | 杭州海康汽车技术有限公司 | Robot control method and device and robot |
CN113138594A (en) * | 2020-01-20 | 2021-07-20 | 北京四维图新科技股份有限公司 | Automatic driving method and device |
CN113138594B (en) * | 2020-01-20 | 2024-04-19 | 北京四维图新科技股份有限公司 | Automatic driving method and device |
CN112896181A (en) * | 2021-01-14 | 2021-06-04 | 重庆长安汽车股份有限公司 | Electronic fence control method, system, vehicle and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN109703467B (en) | 2019-09-06 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109334670B (en) | A kind of vehicle drive people monitoring and early warning method, system, equipment and storage medium | |
CN106314152B (en) | Vehicle parking assistance device and vehicle with it | |
US8514101B2 (en) | Driving maneuver assist on full windshield head-up display | |
CN101644932B (en) | Apparatus for travel support | |
US8994558B2 (en) | Automotive augmented reality head-up display apparatus and method | |
WO2020125178A1 (en) | Vehicle driving prompting method and apparatus | |
CN108765490A (en) | The visual field method of adjustment and device of panorama sketch, storage medium, electronic equipment | |
CN109484299A (en) | Control method, apparatus, the storage medium of the display of augmented reality display device | |
CN106503636B (en) | A kind of road sighting distance detection method and device of view-based access control model image | |
CN110203210A (en) | A kind of lane departure warning method, terminal device and storage medium | |
CN109703467B (en) | It is a kind of for Vehicular intelligent driving bootstrap technique, system | |
CN103732480A (en) | Method and device for assisting a driver in performing lateral guidance of a vehicle on a carriageway | |
CN107284379A (en) | AR optical projection systems and projecting method for vehicle safe driving | |
CN108437896A (en) | Vehicle drive assisting method, device, equipment and storage medium | |
CN104118357B (en) | A kind of backing track line generation method, device and reversing guiding device | |
CN110962746B (en) | Driving assisting method, system and medium based on sight line detection | |
CN106064587A (en) | Multi-lane vehicle distance recognition method and device based on license plate recognition | |
JP2017167758A (en) | Control device for vehicle | |
CN108248504A (en) | For controlling the device and method of the virtual engine sound of vehicle | |
CN110239424A (en) | Method, system, equipment and the storage medium of the distance-light switching of automatic Pilot | |
CN110293903A (en) | A kind of Vehicular turn lamp control method, device, equipment and storage medium | |
US20220388543A1 (en) | Systems and methods for displaying trajectories for autonomous vehicles | |
CN105934368A (en) | Perspective representation of a vehicle environment with a vehicle model on a vehicle display | |
JP2005148973A (en) | Information presenting device | |
CN109492835A (en) | Determination method, model training method and the relevant apparatus of vehicle control information |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |