CN106601076A - Automobile self-help training device based on strapdown inertial navigation and area-array cameras and method - Google Patents
Automobile self-help training device based on strapdown inertial navigation and area-array cameras and method Download PDFInfo
- Publication number
- CN106601076A CN106601076A CN201611040667.XA CN201611040667A CN106601076A CN 106601076 A CN106601076 A CN 106601076A CN 201611040667 A CN201611040667 A CN 201611040667A CN 106601076 A CN106601076 A CN 106601076A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- formula
- yaw angle
- image
- storehouse
- 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
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B19/00—Teaching not covered by other main groups of this subclass
- G09B19/16—Control of vehicles or other craft
- G09B19/167—Control of land vehicles
Abstract
The invention discloses an automobile self-help training device based on strapdown inertial navigation and area-array cameras and a method. The automobile self-help training device comprises two area-array cameras, an interior client, a liquid crystal screen and a loudspeaker, wherein the area-array cameras are used for collecting image information of an automobile in a starting position; a system can acquire an initial position and an initial attitude angle of the automobile through the image information collected by the area-array cameras; a 2.4G radio frequency module, an MCU module and a digital strapdown navigation device are integrated in the interior client, and the interior client is used for acquiring a practical position and a practical attitude angle of the automobile in an advancing process and calculating a deviation of a current position and an ideal position of the automobile; the liquid crystal screen is used for displaying an offset of the automobile; and the loudspeaker is used for reminding a leaner. Through the automobile self-help training device, the leaner can learn in a self-help mode, the learning interest can be promoted, the learning efficiency can be increased, and the learning time can be shortened.
Description
Technical field
The present invention relates to technical field of vehicle detection, and in particular to a kind of automobile based on inertial navigation and area array cameras is certainly
Help training devicess and method.
Background technology
While with China's market for automobiles region saturation, the competition between driving school is also growing more intense.How reduces cost, carry
The training effectiveness of high student, annoyings the operators of each driving school.If the partial automation that driving school trains can be realized, will
Substantial amounts of manpower can be saved, and is conducive to the further operation and development of driving school.
The content of the invention
For the problems referred to above, the invention provides a kind of based on strap-down navigation and the automobile self training side of area array cameras
Method, storehouse or side are stopped to drive the study of Self-help vehicle formula for student, are comprised the following steps:
2 area array cameras are separately mounted to the both sides of vehicle headstock by step 1, when student starts exercise storehouse or side
During parking, by 2 area array cameras detect vehicles and the relative position relation between storehouse or side parking start line to obtain
The initial position of vehicle and initial yaw angle;
Step 2, determines that vehicle needs the coordinate at each turning point of steering, root during storehouse or lateral parking
According to the vehicle initial position and initial yaw angle that obtain, preferable planning driving path is carried out curve fitting using interpolation method;
Step 3, obtains real time position and yaw angle of the vehicle during storehouse or lateral parking;
Step 4, the vehicle centroid position coordinateses (X (w), Y (w)) and vehicle body fallen according to vehicle during storehouse or side coil are horizontal
Pivot angle θ, tries to achieve ideal path to the online normal of vehicle body yaw angle theta, and the length of normal degree is vehicle location side-play amount d;
Step 5, carries out showing vehicle location side-play amount d by the display screen before driver's cabin, if student's adjustment car
It is in the right direction, then show screen display vehicle location side-play amount d reduce;If student adjusts the anisotropy of vehicle,
Showing vehicle location side-play amount d of screen display increases, and is stopped with reaching student and driving Self-help vehicle formula and fall storehouse or side;
Vehicle cab is also equipped with speaker:
If the driving path of vehicle offsets ideal path to the left, speaker sends voice " vehicle offsets to the left ";
If the driving path of vehicle offsets ideal path to the right, speaker sends voice " vehicle offsets to the right ".
Further, the initial position and initial yaw angle of the acquisition vehicle described in step 1 includes:
Step 11, by 2 area array cameras garage ground reticle image is shot, using the ground reticle image as original image,
And noise reduction pretreatment is carried out to original image, obtain pretreatment image;
Step 12, HSV is converted to by the color space of pretreatment image by BGR, and carries out binaryzation to pretreatment image
Process, obtain binary image;
Step 13, is carried out after edge extracting to binary image, detects the straight line in bianry image after edge extracting, and is carried
The pixel at straight line is taken out, the coordinate of the pixel is fitted, graticule is in image coordinate system with obtaining garage
Slope k1,k2With intercept d1,d2;
Step 14, calculates the initial position and initial yaw angle of vehicle, i.e. vehicle horizontal by (formula 1), (formula 2) and (formula 3)
Pivot angle θ0With vehicle center point and horizontal range D in sideline1,D2:
In formula, aij、bij、cij, m, n, q be calibration coefficient.
Further, the interpolation method described in step 2 is specially cubic spline interpolation.
Further, real time position and horizontal stroke of the vehicle during storehouse or lateral parking is obtained described in step 3
Pivot angle includes:
Step 31, obtains the real-time angular velocity signal ω of vehicle, and process is filtered to ω;
Step 32, by (formula 4) the real-time yaw angle theta of vehicle is calculated:
θt=θt-1+∫ωdt+θ0(formula 4)
Wherein, t falls the moment value during storehouse or lateral parking for vehicle, and t=1,2 ..., ω are the real-time angle of vehicle
Rate signal;
Step 33, the real-time acceleration signal a of collection vehicle(B), and to a(B)It is filtered process;
Step 34, by (formula 5) and (formula 6) coordinate X of the vehicle centroid under earth coordinates is calculated(w)And Y(w):
X(w)=∫ ∫ (a(B)cosθdt)+X0(formula 5)
Y(w)=∫ ∫ (a(B)sinθdt)+Y0(formula 6)
Wherein, X(w)And Y(w)Respectively coordinate of the vehicle centroid under earth coordinates, θ for vehicle real-time yaw angle,
X0、Y0The respectively initial coordinate of vehicle centroid.
Further, process is filtered to the ω described in step 31 by (formula 7):
Wherein, t falls the moment value during storehouse or lateral parking for vehicle, and t=1,2 ..., K are filter factor,
For t angular velocity signal estimated value.
Present invention also offers it is a kind of based on strap-down navigation and the automobile self training devicess of area array cameras, drive for student
Sail the study of Self-help vehicle formula and fall storehouse or side and stop, including image capture module, default ideal path module, obtain mould in real time
Block, acquisition side-play amount module, self-service driving module;
Described image acquisition module includes 2 area array cameras, and 2 area array cameras are separately mounted to vehicle near headstock
Both sides, for when student start exercise fall storehouse or side stop when, detect vehicles by 2 area array cameras and pass through 2 faces
Array camera detect vehicle and the relative position relation between storehouse or side parking start line with obtain vehicle initial position and
Initial yaw angle;
The default ideal path module is used to determine that vehicle needs the every of steering during storehouse or lateral parking
Coordinate at individual turning point, according to the vehicle initial position and initial yaw angle that obtain, using interpolation method to preferable planning driving path
Carry out curve fitting;
The real-time acquisition module is used to obtain real time position and yaw of the vehicle during storehouse or lateral parking
Angle;
It is described to obtain the vehicle centroid position coordinateses (X that side-play amount module is used to being fallen according to vehicle during storehouse or side coil
(w), Y (w)) and vehicle body yaw angle theta, ideal path is tried to achieve to the online normal of vehicle body yaw angle theta, the length of normal degree is
Vehicle location side-play amount d;
The self-service driving module includes display screen and speaker, is shown by the display screen before driver's cabin
Vehicle location side-play amount d, if student's adjustment vehicle is in the right direction, vehicle location side-play amount d for showing screen display reduces;
If student adjusts the anisotropy of vehicle, showing vehicle location side-play amount d of screen display increases, and to reach student car is driven
It is self-service fall storehouse or side stop;
Vehicle cab is also equipped with speaker:
If the driving path of vehicle offsets ideal path to the left, speaker sends voice " vehicle offsets to the left ";
If the driving path of vehicle offsets ideal path to the right, speaker sends voice " vehicle offsets to the right ".
Further, the initial position and initial yaw angle of the acquisition vehicle described in image capture module includes:
Step 11, by 2 area array cameras garage ground reticle image is shot, using the ground reticle image as original image,
And noise reduction pretreatment is carried out to original image, obtain pretreatment image;
Step 12, HSV is converted to by the color space of pretreatment image by BGR, and carries out binaryzation to pretreatment image
Process, obtain binary image;
Step 13, after edge extracting (Caany operators) is carried out to binary image, detects straight in image after edge extracting
Line, and the pixel at straight line is extracted, it is fitted according to the coordinate of the pixel, obtain garage ground graticule and sit in image
Slope k in mark system1,k2With intercept d1,d2;
Step 14, calculates the initial position and initial yaw angle of vehicle, i.e. vehicle horizontal by (formula 1), (formula 2) and (formula 3)
Pivot angle θ0With vehicle center point and horizontal range D in sideline1,D2:
In formula, aij、bij、cij, m, n, q be calibration coefficient.
Further, preset the interpolation method described in ideal path module and be specially cubic spline interpolation.
Further, real-time position of the vehicle during storehouse or lateral parking is obtained described in real-time acquisition module
Put includes with yaw angle:
Step 31, obtains the real-time angular velocity signal ω of vehicle, and process is filtered to ω;
Step 32, by (formula 4) the real-time yaw angle theta of vehicle is calculated:
θt=θt-1+∫ωdt+θ0(formula 4)
Wherein, t falls the moment value during storehouse or lateral parking for vehicle, and t=1,2 ..., ω are the real-time angle of vehicle
Rate signal;
Step 33, the real-time acceleration signal a of collection vehicle(B), and to a(B)It is filtered process;
Step 34, by (formula 5) and (formula 6) coordinate X of the vehicle centroid under earth coordinates is calculated(w)And Y(w):
X(w)=∫ ∫ (a(B)cosθdt)+X0(formula 5)
Y(w)=∫ ∫ (a(B)sinθdt)+Y0(formula 6)
Wherein, X(w)And Y(w)Respectively coordinate of the vehicle centroid under earth coordinates, θ for vehicle real-time yaw angle,
X0、Y0The respectively initial coordinate of vehicle centroid.
Further, process is filtered to the ω described in step 31 by (formula 7):
Wherein, the moment value that t falls in storehouse or side docking process for vehicle, t=1,2 ..., K are filter factor,For t
Moment angular velocity signal estimated value.
Compared with prior art, the present invention has following technique effect:
The present invention detects vehicle with storehouse or side parking by being installed on 2 area array cameras of the vehicle near headstock both sides
The initial relative position relation of starting point, and preferable vehicle travel path is generated, strapdown is then utilized in vehicular motion
Guider obtains in real time the attitude and positional information of vehicle, and is contrasted with ideal path, calculates Current vehicle position
The deviation with ideal position is put, the departure is fed back to into student finally by human-computer interaction interface, and guide it to carry out vehicle body
Attitude and the amendment of position.By training devicess proposed by the invention and its algorithm, student can carry out self-service study,
Learning interest is improved, increases the learning efficiency, shorten learning time.In view of the huge automobile textual criticism market of China, energy of the present invention
Enough produce huge economic and social benefit.
Description of the drawings
Fig. 1 is the hardware connection diagram of the present invention;
Fig. 2 is the automobile self training devicess and its algorithm area array cameras based on strap-down navigation and area array cameras of the present invention
Schematic view of the mounting position;
Fig. 3 is vehicle initial position and initial yaw angle algorithm flow chart;
Fig. 4 is image binaryzation design sketch;
Fig. 5 is that fitting a straight line shows figure;;
Signal before Fig. 6 vehicle route node regulations;
Signal after Fig. 7 vehicle route node regulations;
Fig. 8 body modeling schematic diagrams;
Fig. 9 vehicle shifts amount calculates schematic diagram;
Figure 10 is the comparison diagram for testing path and ideal path.
Specific embodiment
Embodiment 1
Present embodiments provide a kind of based on strap-down navigation and automobile self training devicess' control algolithm of area array cameras, tool
Body step is:
1st, 2 area array cameras are separately mounted to into vehicle near the both sides of headstock, when student starts exercise storehouse or side
During parking, by 2 area array cameras detect vehicles and the relative position relation between storehouse or side parking start line to obtain
The initial position of vehicle and initial yaw angle;;
The present invention obtains initial position and initial yaw angle of the vehicle centroid in earth coordinates using machine vision, its
The flow chart of algorithm is as shown in figure 3, the algorithm involved by the part includes following several big steps:
(1) picture signal is obtained, and carries out Image semantic classification
The present invention shoots the field ground of falling storehouse graticule using the photographic head for being installed on vehicular sideview.MCU obtains the original graph in place
As after, first pretreatment is carried out to image, to reduce the noise of image, and improve the resolution of image.
(2) line translation and binaryzation are entered to the color space of image
Method of the present invention using carrying out changing then binaryzation by the color space of picture.In this example, MCU will scheme
The color space of picture is converted to HSV by BGR, then carries out binaryzation according to given threshold value to the saturation passage of image.Two
Design sketch after value is as shown in Figure 4.
(3) place of the falling storehouse graticule in image is fitted, obtains parameter of the garage graticule in image coordinate system
In order to obtain attitude and position of the vehicle in earth coordinates, need to obtain garage graticule first in image coordinate system
In parameter, including slope, intercept.The method that adopts of the present invention for:Edge extracting, Ran Houjian are carried out to binary image
Straight line in altimetric image, extracts afterwards the neighbouring pixel that goes beyond the scope, and then carries out place mark according to the coordinate of these pixels
The centrage fitting of line, obtains the straight line parameter of correlation.
In this example, rim detection adopts Canny operators, straight-line detection then mainly to utilize Hough transformation, the ginseng of straight line
Number fitting employs method of least square.In this example, the display in the picture of the straight line after fitting is as shown in Figure 5.By adjusting
The setting angle of whole video camera and position, can make camera that the right angle electrical at site boundary right angle is photographed in same piece image,
And two mutually perpendicular sidelines of right angle, and it is calculated the slope k of this two lines1,k2With intercept d1,d2。
(4) conversion of coordinate system and the calculating of the initial yaw angle of vehicle and locus
In previous step, the calculated straight line parameters of MCU are the parameters in image coordinate system, need to carry out it
Conversion can just obtain yaw angle theta of the vehicle in earth coordinates0With vehicle center point and horizontal range D in sideline1,D2.This
The bright yaw angle theta that vehicle is calculated by below equation0
In formula, aij、bij、cij, m, n, q be calibration coefficient.By gathering experimental data, it may be determined that go out these coefficients
Numerical value.
After obtaining the distance in vehicle body yaw angle and the vertical sideline of centroid distance two, you can determine the barycenter of vehicle in the earth
The initial yaw angle of coordinate and vehicle in coordinate system, the integral and calculating of generation and path for next step ideal path is provided just
Beginning condition.
2nd, determine that vehicle needs the coordinate at each turning point of steering during storehouse or lateral parking, according to
The vehicle initial position for arriving and initial yaw angle, are carried out curve fitting using interpolation method to preferable planning driving path;
In the present embodiment using vehicle fall storehouse or lateral parking section start coordinate as origin, vehicle is estimated with the origin
Need to carry out 7 steerings in storehouse or when changing trains or buses vehicle could to be parked in garage, in GB storehouse or lateral parking field are fallen
Ground gathers this 7 turning points, that is, obtain the coordinate at each turning point.
The centroid position of vehicle during by considering to start to move backward, the present invention utilizes a kind of algorithm based on cubic spline interpolation
Generate the reversing path of vehicle.Its specific algorithm is as follows:
The present embodiment, by coach coordinate position of the vehicle at each steering node, Ran Houyi are artificially marked
According to the initial yaw angle and the initial coordinate position of vehicle centroid of vehicle, these coordinate points are rotated and offset, be next
The Cubic Spline Fitting of step diametal curve provides node.Signal before and after vehicle route node regulation is as shown in Figures 6 and 7.
Following (the unit of steering node coordinate demarcated by coach in the present embodiment:m):
(0,-0.2)(0.6,0.8)(1.6,2.8)(3,3.8)(3.4,3.9)(3.8,3,98)(4.2,4)
Graphics proportion 1cm=2m is taken, then experimental result is as shown in Figure 10.
3rd, real time position and yaw angle of the vehicle during storehouse or lateral parking is obtained;
During the practice of subject two, the travel speed of vehicle is typically relatively low, and the physical features of selected exercise floor compared with
For flat.Therefore, the motion of vehicle during the practice of subject two can be considered as uniform motion.Therefore using two axle inertial navigations, build
Vertical Car body model is as shown in Figure 8.Wherein, G points be vehicle centroid position, x(B), y(B)Respectively the transverse axis of vehicle body coordinate system and
The longitudinal axis, x(w), y(w)Respectively earth coordinates are horizontally and vertically.Here obtain vehicle using following algorithm to fall during storehouse
Position and yaw angle:
1) the angular velocity signal ω that digital gyroscope is measured is obtained, because gyroscope has zero partially, certainty of measurement is affected,
Temperature correction is carried out firstly the need of to it.Here adopt and temperature correction is realized based on the temperature compensation of BP neural network.
Because this class algorithm is not the content that the present invention is stressed, repeat no more here.Then the digital signal value of acquisition is converted to
Circular measure;
2) original angular velocity signal ω includes noise, needs to be filtered it process.Because vehicle is in the even of low speed
Fast transport condition, therefore it is believed that useful signal is concentrated mainly on low-frequency range.Here believed using the method angular velocity of differential filtering
Number ω is filtered process, and specific formula is as follows:
Wherein, K is filter factor,For t angular velocity signal estimated value.The big of filter factor K is chosen by appropriate
It is little, you can to complete the Real-Time Filtering of angular velocity signal.
3) by being integrated to the angular velocity signal for obtaining, the yaw angle theta of vehicle is solved, computing formula is as follows:
θt=θt-1+∫ωdt+θ0, t=1,2 ... (7)
Wherein, θtFor vehicle t yaw angle.
The value of the yaw angle theta of vehicle can be drawn according to above-mentioned formula, the yaw angle of vehicle has been thereby determined that.
4) the acceleration signal a that accelerometer is measured is obtained(B), while process is filtered to it using differential filtering method,
To remove impact of the noise jamming to certainty of measurement.Concrete formula is as follows:
Wherein, K is filter factor,For t acceleration signal estimated value.Choose filter factor K's by appropriate
Size, you can complete the Real-Time Filtering to acceleration signal.
5) the acceleration signal a of above-mentioned acquisition(B)For the acceleration signal under vehicle body coordinate system, in order to ask the position of vehicle
Information, it is necessary first to which the acceleration signal under vehicle body coordinate system is converted to the acceleration signal under earth coordinates, that is, ask and add
Rate signal a(B)Projection in earth coordinates, concrete formula is as follows:
Wherein,Acceleration respectively in earth coordinates lower edge horizontally and vertically.
By carrying out quadratic integral to above-mentioned tried to achieve acceleration, you can draw vehicle centroid under earth coordinates
Coordinate X(w)And Y(w)。X(w)And Y(w)Solution formula it is as follows:
X(w)=∫ ∫ (a(B)cosθdt)+X0 (11)
Y(w)=∫ ∫ (a(B)sinθdt)+Y0 (12)
Wherein, X(w)And Y(w)The vertical coordinate for being vehicle centroid under earth coordinates and abscissa, X0And Y0For vehicle centroid
Initial vertical coordinate and abscissa under earth coordinates.
Position (X of the vehicle centroid during storehouse can be drawn using above step and algorithm(w),Y(w)) and vehicle horizontal stroke
Pivot angle θ, the amount subsequently to calculate vehicle shift ideal path provides condition.
4th, vehicle falls the calculating of side-play amount during storehouse
Side-play amount of the vehicle during storehouse refers to down the actual travel path of vehicle and ideal path during storehouse
Deviation.The centroid position coordinate i.e. (X that vehicle falls during storehouse can be obtained by digital strap-down navigation(w),Y(w)) and vehicle body
Yaw angle theta, by ideal path line the online normal of yaw angle is made, then the length of normal degree is vehicle location side-play amount d,
Its schematic diagram is as shown in Figure 9.Algorithm steps and computing formula are as follows:
(1) straight line expression formula L of normal is obtained;
The present invention seeks straight line expression formula using a known point coordinates and slope, and the expression formula of straight line L is as follows:
(2) the intersection point Q of straight line L and ideal path line S (x) is sought;
Simultaneous straight line S (x) and L, solution draws intersection point Q coordinates (x, y)
(3) ask Q points to G points apart from d;
5th, side-play amount will be included on liquid crystal display screen by the form of progress bar, while progress bar can enter according to the adjustment of student
Degree is changed (elongation and shortening), and when the adjustment direction of student is correct, with the increase of adjustment amount, progress bar can shorten;
When the adjustment direction mistake of student, with the increase of adjustment amount, progress bar can extend.Join when correcting side-play amount for student
Examine.Speaker plays a part of to remind student in vehicle shift ideal path.When the driving path of vehicle offsets to the left ideal
During path, speaker sends voice message student " vehicle offsets to the left ";When vehicle offsets to the right during ideal path, speaker
Send voice message student " vehicle offsets to the right ".
Further, for convenience of operator, can to side-play amount given threshold, when side-play amount exceedes the threshold value,
Speaker is just functioned to, and points out driver.
The step of being related in above-described embodiment and algorithm are equally applicable to the sundry item training of subject two.
Embodiment 2
Referring to Fig. 1, the present embodiment be given a kind of automobile self training devicess based on strap-down navigation and area array cameras and its
Algorithm, its device includes 2 area array cameras, in-car client, liquid crystal display screen and speaker.Wherein:
Referring to Fig. 2,2 area array cameras are respectively arranged in vehicle near the both sides of headstock, fall for starting exercise in student
When storehouse or side are stopped, detect the relative tertiary location relation between vehicle and starting point to obtain the initial position and initially of vehicle
Yaw angle.Integrated A/D modular converters, 2.4G radio-frequency modules and MCU module in area array cameras.
Integrated 2.4G radio-frequency modules, MCU module and digital strap-down navigation device in in-car client, for falling in student
Storehouse or side are stopped when practising, and the positional information of vehicle is obtained in real time and vehicle is calculated and is closed with the relative position of ideal path
System, and error signal is passed through into display screen or loudspeaker feedback to student.
Liquid crystal display screen is used for showing the side-play amount of vehicle, while the progress bar on liquid crystal display screen shows the adjustment progress of student.
Speaker plays suggesting effect, and when vehicle offsets ideal path to the left or to the right, speaker can be given accordingly
Prompting.
In-car client includes 2.4G radio-frequency modules, MCU module and digital strap-down navigation device in the present embodiment, its knot
Composition is as shown in Figure 1.
Claims (10)
1. a kind of based on strap-down navigation and the automobile self training method of area array cameras, drive the study of Self-help vehicle formula for student
Storehouse or side are stopped, it is characterised in that comprised the following steps:
2 area array cameras are separately mounted to the both sides of vehicle headstock by step 1, and when student starts exercise, storehouse or side are stopped
When, by 2 area array cameras detect vehicles and the relative position relation between storehouse or side parking start line to obtain vehicle
Initial position and initial yaw angle;
Step 2, determines that vehicle needs the coordinate at each turning point of steering during storehouse or lateral parking, according to
The vehicle initial position for arriving and initial yaw angle, are carried out curve fitting using interpolation method to preferable planning driving path;
Step 3, obtains real time position and yaw angle of the vehicle during storehouse or lateral parking;
Step 4, the vehicle centroid position coordinateses (X (w), Y (w)) and vehicle body yaw angle fallen according to vehicle during storehouse or side coil
θ, tries to achieve ideal path to the online normal of vehicle body yaw angle theta, and the length of normal degree is vehicle location side-play amount d;
Step 5, carries out showing vehicle location side-play amount d by the display screen before driver's cabin, if student's adjustment vehicle
In the right direction, then vehicle location side-play amount d for showing screen display reduces;If student adjusts the anisotropy of vehicle, show
Vehicle location side-play amount d of screen display increases, and drives that Self-help vehicle formula falls storehouse or side is stopped to reach student;
Vehicle cab is also equipped with speaker:
If the driving path of vehicle offsets ideal path to the left, speaker sends voice " vehicle offsets to the left ";
If the driving path of vehicle offsets ideal path to the right, speaker sends voice " vehicle offsets to the right ".
2. automobile self training method as claimed in claim 1, it is characterised in that the acquisition vehicle described in step 1 just
Beginning position and initial yaw angle include:
Step 11, by 2 area array cameras garage ground reticle image is shot, as original image and right using the ground reticle image
Original image carries out noise reduction pretreatment, obtains pretreatment image;
Step 12, HSV is converted to by the color space of pretreatment image by BGR, and carries out binary conversion treatment to pretreatment image,
Obtain binary image;
Step 13, is carried out after edge extracting to binary image, detects the straight line in bianry image after edge extracting, and is extracted
Pixel at straight line, the coordinate of the pixel is fitted, and obtains slope of the ground graticule in garage in image coordinate system
k1,k2With intercept d1,d2;
Step 14, by (formula 1), (formula 2) and (formula 3) initial position and initial yaw angle, i.e. Vehicular yaw angle θ of vehicle are calculated0
With vehicle center point and horizontal range D in sideline1,D2:
In formula, aij、bij、cij, m, n, q be calibration coefficient.
3. automobile self training method as claimed in claim 1, it is characterised in that the interpolation method described in step 2 is specially
Cubic spline interpolation.
4. automobile self training method as claimed in claim 1, it is characterised in that the acquisition vehicle described in step 3 is falling
Real time position and yaw angle during storehouse or lateral parking includes:
Step 31, obtains the real-time angular velocity signal ω of vehicle, and process is filtered to ω;
Step 32, by (formula 4) the real-time yaw angle theta of vehicle is calculated:
θt=θt-1+∫ωdt+θ0(formula 4)
Wherein, t falls the moment value during storehouse or lateral parking for vehicle, and t=1,2 ..., ω are the real-time angular velocity of vehicle
Signal;
Step 33, the real-time acceleration signal a of collection vehicle(B), and to a(B)It is filtered process;
Step 34, by (formula 5) and (formula 6) coordinate X of the vehicle centroid under earth coordinates is calculated(w)And Y(w):
X(w)=∫ ∫ (a(B)cosθdt)+X0(formula 5)
Y(w)=∫ ∫ (a(B)sinθdt)+Y0(formula 6)
Wherein, X(w)And Y(w)Respectively coordinate of the vehicle centroid under earth coordinates, θ for vehicle real-time yaw angle, X0、Y0
The respectively initial coordinate of vehicle centroid.
5. automobile self training method as claimed in claim 4, it is characterised in that by (formula 7) to the ω described in step 31
It is filtered process:
Wherein, t falls the moment value during storehouse or lateral parking for vehicle, and t=1,2 ..., K are filter factor,For t when
Carve angular velocity signal estimated value.
6. a kind of based on strap-down navigation and the automobile self training devicess of area array cameras, drive the study of Self-help vehicle formula for student
Storehouse or side are stopped, it is characterised in that including image capture module, default ideal path module, real-time acquisition module, acquisition
Side-play amount module, self-service driving module;
Described image acquisition module includes 2 area array cameras, and 2 area array cameras are separately mounted to vehicle near the two of headstock
Side, for when student starts to practise falling storehouse or side parking, vehicles being detected and by 2 face battle array phases by 2 area array cameras
Machine detect vehicle and the relative position relation between storehouse or side parking start line to obtain the initial position and initially of vehicle
Yaw angle;
The default ideal path module is used to determine that vehicle needs each for turning to turn during storehouse or lateral parking
To at coordinate, according to the vehicle initial position and initial yaw angle that obtain, preferable planning driving path is carried out using interpolation method
Curve matching;
The real-time acquisition module is used to obtain real time position and yaw angle of the vehicle during storehouse or lateral parking;
It is described to obtain vehicle centroid position coordinateses (X (w), Y that side-play amount module is used to being fallen according to vehicle during storehouse or side coil
(w)) and vehicle body yaw angle theta, ideal path is tried to achieve to the online normal of vehicle body yaw angle theta, the length of normal degree is vehicle
Position offset d;
The self-service driving module includes display screen and speaker, and by the display screen before driver's cabin display vehicle is carried out
Position offset d, if student's adjustment vehicle is in the right direction, vehicle location side-play amount d for showing screen display reduces;If learning
The anisotropy of member's adjustment vehicle, then showing vehicle location side-play amount d of screen display increases, and vehicle is driven certainly to reach student
Help formula to fall storehouse or side to stop;
Vehicle cab is also equipped with speaker:
If the driving path of vehicle offsets ideal path to the left, speaker sends voice " vehicle offsets to the left ";
If the driving path of vehicle offsets ideal path to the right, speaker sends voice " vehicle offsets to the right ".
7. automobile self training devicess as claimed in claim 6, it is characterised in that the acquisition car described in image capture module
Initial position and initial yaw angle include:
Step 11, by 2 area array cameras garage ground reticle image is shot, as original image and right using the ground reticle image
Original image carries out noise reduction pretreatment, obtains pretreatment image;
Step 12, HSV is converted to by the color space of pretreatment image by BGR, and carries out binary conversion treatment to pretreatment image,
Obtain binary image;
Step 13, after edge extracting (Caany operators) is carried out to binary image, detects the straight line in image after edge extracting,
And the pixel at straight line is extracted, and it is fitted according to the coordinate of the pixel, garage ground graticule is obtained in image coordinate
Slope k in system1,k2With intercept d1,d2;
Step 14, by (formula 1), (formula 2) and (formula 3) initial position and initial yaw angle, i.e. Vehicular yaw angle θ of vehicle are calculated0
With vehicle center point and horizontal range D in sideline1,D2:
In formula, aij、bij、cij, m, n, q be calibration coefficient.
8. automobile self training devicess as claimed in claim 6, it is characterised in that inserting described in default ideal path module
Value method is specially cubic spline interpolation.
9. automobile self training devicess as claimed in claim 1, it is characterised in that the acquisition car described in acquisition module in real time
Real time position and yaw angle during storehouse or lateral parking includes:
Step 31, obtains the real-time angular velocity signal ω of vehicle, and process is filtered to ω;
Step 32, by (formula 4) the real-time yaw angle theta of vehicle is calculated:
θt=θt-1+∫ωdt+θ0(formula 4)
Wherein, t falls the moment value during storehouse or lateral parking for vehicle, and t=1,2 ..., ω are the real-time angular velocity of vehicle
Signal;
Step 33, the real-time acceleration signal a of collection vehicle(B), and to a(B)It is filtered process;
Step 34, by (formula 5) and (formula 6) coordinate X of the vehicle centroid under earth coordinates is calculated(w)And Y(w):
X(w)=∫ ∫ (a(B)cosθdt)+X0(formula 5)
Y(w)=∫ ∫ (a(B)sinθdt)+Y0(formula 6)
Wherein, X(w)And Y(w)Respectively coordinate of the vehicle centroid under earth coordinates, θ for vehicle real-time yaw angle, X0、Y0
The respectively initial coordinate of vehicle centroid.
10. automobile self training devicess as claimed in claim 8, it is characterised in that by (formula 7) to the ω described in step 31
It is filtered process:
Wherein, the moment value that t falls in storehouse or side docking process for vehicle, t=1,2 ..., K are filter factor,For t
Angular velocity signal estimated value.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611040667.XA CN106601076B (en) | 2016-11-11 | 2016-11-11 | A kind of automobile self training device and method based on inertial navigation and area array cameras |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611040667.XA CN106601076B (en) | 2016-11-11 | 2016-11-11 | A kind of automobile self training device and method based on inertial navigation and area array cameras |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106601076A true CN106601076A (en) | 2017-04-26 |
CN106601076B CN106601076B (en) | 2019-06-18 |
Family
ID=58592767
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611040667.XA Expired - Fee Related CN106601076B (en) | 2016-11-11 | 2016-11-11 | A kind of automobile self training device and method based on inertial navigation and area array cameras |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106601076B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111645688A (en) * | 2019-09-19 | 2020-09-11 | 摩登汽车有限公司 | Method and device for calculating vehicle weight and gravity center in real time, electronic equipment and vehicle |
CN112486156A (en) * | 2019-09-10 | 2021-03-12 | 中车株洲电力机车研究所有限公司 | Automatic tracking control system and control method for vehicle |
CN113561897A (en) * | 2021-07-15 | 2021-10-29 | 河北三国新能源科技有限公司 | Method and system for judging ramp parking position of driving test vehicle based on panoramic all-round view |
Citations (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1522892A (en) * | 2003-01-29 | 2004-08-25 | ��ʽ��������Զ�֯�������� | Parking assisting device |
CN1591256A (en) * | 2003-08-28 | 2005-03-09 | 丰田自动车株式会社 | Vehicle backward movement assist device and vehicle parking assist device |
CN1737501A (en) * | 2004-08-20 | 2006-02-22 | 爱信精机株式会社 | Parking auxiliary device for vehicle and parking auxiliary method |
CN1987357A (en) * | 2006-12-26 | 2007-06-27 | 浙江工业大学 | Intelligent parking auxiliary device based on omnibearing computer sight |
CN101300157A (en) * | 2005-10-31 | 2008-11-05 | 丰田自动车株式会社 | Parking assisting system |
CN101635839A (en) * | 2008-07-25 | 2010-01-27 | 日产自动车株式会社 | Parking assistance apparatus and parking assistance method |
US20100060486A1 (en) * | 2008-09-09 | 2010-03-11 | Kabushiki Kaisha Toyota Jidoshokki | Parking assist apparatus |
JP2010195265A (en) * | 2009-02-26 | 2010-09-09 | Toyota Motor Corp | Parking facility |
CN101945256A (en) * | 2009-07-01 | 2011-01-12 | 福特全球技术公司 | The auxiliary back of reversing camera system with touch-screen display |
JP2011255812A (en) * | 2010-06-10 | 2011-12-22 | Aisin Seiki Co Ltd | Parking support device |
CN103235327A (en) * | 2013-04-07 | 2013-08-07 | 清华大学 | GNSS/MINS (global navigation satellite system/micro-electro-mechanical systems inertial navigation system) super-deep combination navigation method, system and device |
CN103499350A (en) * | 2013-09-28 | 2014-01-08 | 长安大学 | High-precision vehicle positioning method for fusing multi-source information under GPS (global positioning system) blind area and device |
CN103591955A (en) * | 2013-11-21 | 2014-02-19 | 西安中科光电精密工程有限公司 | Combined navigation system |
CN103847733A (en) * | 2012-11-28 | 2014-06-11 | 伊莱比特汽车公司 | Technique and apparatus for assisting driving a vehicle |
CN103900611A (en) * | 2014-03-28 | 2014-07-02 | 北京航空航天大学 | Method for aligning two composite positions with high accuracy and calibrating error of inertial navigation astronomy |
CN104197944A (en) * | 2014-03-03 | 2014-12-10 | 明日交通公司 | Position sensing system of intelligent vehicle navigation |
CN104608692A (en) * | 2013-11-05 | 2015-05-13 | 现代摩比斯株式会社 | Parking auxiliary system and the method |
-
2016
- 2016-11-11 CN CN201611040667.XA patent/CN106601076B/en not_active Expired - Fee Related
Patent Citations (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1522892A (en) * | 2003-01-29 | 2004-08-25 | ��ʽ��������Զ�֯�������� | Parking assisting device |
CN1591256A (en) * | 2003-08-28 | 2005-03-09 | 丰田自动车株式会社 | Vehicle backward movement assist device and vehicle parking assist device |
CN1737501A (en) * | 2004-08-20 | 2006-02-22 | 爱信精机株式会社 | Parking auxiliary device for vehicle and parking auxiliary method |
CN101300157A (en) * | 2005-10-31 | 2008-11-05 | 丰田自动车株式会社 | Parking assisting system |
CN1987357A (en) * | 2006-12-26 | 2007-06-27 | 浙江工业大学 | Intelligent parking auxiliary device based on omnibearing computer sight |
CN101635839A (en) * | 2008-07-25 | 2010-01-27 | 日产自动车株式会社 | Parking assistance apparatus and parking assistance method |
US20100060486A1 (en) * | 2008-09-09 | 2010-03-11 | Kabushiki Kaisha Toyota Jidoshokki | Parking assist apparatus |
JP2010195265A (en) * | 2009-02-26 | 2010-09-09 | Toyota Motor Corp | Parking facility |
CN101945256A (en) * | 2009-07-01 | 2011-01-12 | 福特全球技术公司 | The auxiliary back of reversing camera system with touch-screen display |
JP2011255812A (en) * | 2010-06-10 | 2011-12-22 | Aisin Seiki Co Ltd | Parking support device |
CN103847733A (en) * | 2012-11-28 | 2014-06-11 | 伊莱比特汽车公司 | Technique and apparatus for assisting driving a vehicle |
CN103235327A (en) * | 2013-04-07 | 2013-08-07 | 清华大学 | GNSS/MINS (global navigation satellite system/micro-electro-mechanical systems inertial navigation system) super-deep combination navigation method, system and device |
CN103499350A (en) * | 2013-09-28 | 2014-01-08 | 长安大学 | High-precision vehicle positioning method for fusing multi-source information under GPS (global positioning system) blind area and device |
CN104608692A (en) * | 2013-11-05 | 2015-05-13 | 现代摩比斯株式会社 | Parking auxiliary system and the method |
CN103591955A (en) * | 2013-11-21 | 2014-02-19 | 西安中科光电精密工程有限公司 | Combined navigation system |
CN104197944A (en) * | 2014-03-03 | 2014-12-10 | 明日交通公司 | Position sensing system of intelligent vehicle navigation |
CN103900611A (en) * | 2014-03-28 | 2014-07-02 | 北京航空航天大学 | Method for aligning two composite positions with high accuracy and calibrating error of inertial navigation astronomy |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112486156A (en) * | 2019-09-10 | 2021-03-12 | 中车株洲电力机车研究所有限公司 | Automatic tracking control system and control method for vehicle |
CN111645688A (en) * | 2019-09-19 | 2020-09-11 | 摩登汽车有限公司 | Method and device for calculating vehicle weight and gravity center in real time, electronic equipment and vehicle |
CN111645688B (en) * | 2019-09-19 | 2022-05-17 | 摩登汽车有限公司 | Method and device for calculating vehicle weight and gravity center in real time, electronic equipment and vehicle |
CN113561897A (en) * | 2021-07-15 | 2021-10-29 | 河北三国新能源科技有限公司 | Method and system for judging ramp parking position of driving test vehicle based on panoramic all-round view |
Also Published As
Publication number | Publication date |
---|---|
CN106601076B (en) | 2019-06-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106092121B (en) | Automobile navigation method and device | |
CN106379237B (en) | Vehicle lane-changing overall process DAS (Driver Assistant System) based on augmented reality | |
CN106256606B (en) | A kind of lane departure warning method based on vehicle-mounted binocular camera | |
CN103535029B (en) | Driving assistance device | |
CN105329238B (en) | A kind of autonomous driving vehicle lane-change control method based on monocular vision | |
CN105180933B (en) | Mobile robot reckoning update the system and method based on the detection of straight trip crossing | |
CN104118430B (en) | A kind of Parallel parking system based on sliding formwork Active Disturbance Rejection Control and method of parking | |
CN107554430A (en) | Vehicle blind zone view method, apparatus, terminal, system and vehicle | |
CN107963077A (en) | A kind of control method of vehicle by crossing, apparatus and system | |
CN107203738A (en) | Vehicle lane boundary alignment | |
CN107577996A (en) | A kind of recognition methods of vehicle drive path offset and system | |
CN107229908A (en) | A kind of method for detecting lane lines | |
CN106503636A (en) | A kind of road sighting distance detection method of view-based access control model image and device | |
CN104374391B (en) | A kind of vehicle driving trace computing system and calculation method | |
CN107462223A (en) | Driving sight distance self-operated measuring unit and measuring method before a kind of highway is turned | |
CN105719483B (en) | The vehicle driving trace bulk sample notebook data acquisition methods that a kind of video is combined with GPS | |
CN106601076A (en) | Automobile self-help training device based on strapdown inertial navigation and area-array cameras and method | |
CN105976402A (en) | Real scale obtaining method of monocular vision odometer | |
CN108765490A (en) | The visual field method of adjustment and device of panorama sketch, storage medium, electronic equipment | |
CN107284455A (en) | A kind of ADAS systems based on image procossing | |
CN104390644A (en) | Method for detecting field obstacle based on field navigation image collection equipment | |
CN106864458A (en) | It is a kind of automatic around barrier system and method, intelligent automobile | |
CN111967360A (en) | Target vehicle attitude detection method based on wheels | |
CN107878561A (en) | A kind of dynamic reverse trajectory discharge drawing method and its device | |
CN110562140A (en) | Multi-camera implementation method and system of transparent A column |
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 | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20190618 Termination date: 20191111 |
|
CF01 | Termination of patent right due to non-payment of annual fee |