CN109784292A - A method of the intelligent automobile for parking garage independently finds parking stall - Google Patents

A method of the intelligent automobile for parking garage independently finds parking stall Download PDF

Info

Publication number
CN109784292A
CN109784292A CN201910069541.2A CN201910069541A CN109784292A CN 109784292 A CN109784292 A CN 109784292A CN 201910069541 A CN201910069541 A CN 201910069541A CN 109784292 A CN109784292 A CN 109784292A
Authority
CN
China
Prior art keywords
vehicle
parking stall
point
parking
line
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201910069541.2A
Other languages
Chinese (zh)
Inventor
华一丁
龚进峰
戎辉
唐风敏
王文扬
郭蓬
何佳
齐麟
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China Automotive Technology and Research Center Co Ltd
AERI Tianjin Automotive Engineering Research Institute Co Ltd
Original Assignee
China Automotive Technology and Research Center Co Ltd
AERI Tianjin Automotive Engineering Research Institute Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by China Automotive Technology and Research Center Co Ltd, AERI Tianjin Automotive Engineering Research Institute Co Ltd filed Critical China Automotive Technology and Research Center Co Ltd
Priority to CN201910069541.2A priority Critical patent/CN109784292A/en
Publication of CN109784292A publication Critical patent/CN109784292A/en
Pending legal-status Critical Current

Links

Abstract

The present invention provides a kind of methods that the intelligent automobile for parking garage independently finds parking stall, comprising: S1, demarcates to vehicle-mounted vision system;S2, using vehicle side camera acquisition lane two sides parking stall image information, and identify judge whether there is vehicle;S3, the lane line that parking lot is identified using the front camera of vehicle, are set the definite value of a vehicle distances lane line length, keep vehicle in this definite value at a distance from lane line;S4, there is no lane line position in corner, supplement vehicle driving trace by three rank Beziers, multiple discrete points are obtained on the driving trace of supplement, the corner of steering wheel is calculated by discrete point.The method that intelligent automobile of the present invention for parking garage independently finds parking stall can accurately be identified parking stall by vision-based detection and the method for positioning, go on smoothly automatic parking.

Description

A method of the intelligent automobile for parking garage independently finds parking stall
Technical field
The invention belongs to automatic Pilot technical fields, autonomous more particularly, to a kind of intelligent automobile for parking garage The method for finding parking stall.
Background technique
With the continuous development of automatic driving technology, application of the automatic Pilot indoors in parking lot also starts to obtain Extensive concern.In parking garage traditional at present, the problem for perplexing driver is to find empty parking stall.And it solves at present The method on Automatic-searching to parking stall is required to very high cost and workload in parking lot indoors, it is difficult to solve indoors In parking lot the problem of Automatic-searching parking stall.
Summary of the invention
In view of this, the present invention is directed to propose a kind of intelligent automobile for parking garage independently finds the side on parking stall Method, to solve the problems, such as that existing automatic Pilot technology indoors is difficult to find parking stall in parking lot.
In order to achieve the above objectives, the technical scheme of the present invention is realized as follows:
A method of the intelligent automobile for parking garage independently finds parking stall, comprising:
S1, vehicle-mounted vision system is demarcated;
S2, using vehicle side camera acquisition lane two sides parking stall image information, and identify judge whether There is vehicle;
S3, the lane line that parking lot is identified using the front camera of vehicle, set a vehicle distances lane line length Definite value, keep vehicle in this definite value at a distance from lane line;
S4, there is no lane line position in corner, vehicle driving trace is supplemented by three rank Beziers, in supplement Multiple discrete points are obtained on driving trace, and the corner of steering wheel is calculated by discrete point.
Further, in the step S1, using scaling board in side camera and the front camera progress of vehicle The calibration of ginseng, line distortion of going forward side by side calibration.
Further, in the step S2, by identifying that the tag line on parking stall judges whether there is vehicle.
Further, in the step S2, the specific method is as follows for identification marking line:
After S201, video camera collect the image comprising parking stall tag line, image is pre-processed, set it is white, yellow, The value range in the hsv color space of Lan Sanse only identified the parking stall tag line of different colours by color-match, Filter out most of interference information in image background;
S202, the parking stall tag line extracted is plotted in the picture of a blank background, edge inspection is carried out to it It surveys and Probabilistic Hough Transform extracts straightway;
S203, the straightway extracted is classified, is clustered, simultaneously close in alignment section conllinear of Straight-line segments mergence Retain, in view of parking stall tag line have certain width, according to this feature of brightness every straightway vertical direction into Row scanning, brightness value variation show as the rule of first increases and then decreases in a certain range judge its for parking stall tag line, Retained, it is on the contrary then give up;
S204, the frame for finally drawing out parking stall find out four angle points on parking stall.
Further, in the step S3, the image of front camera acquisition is subjected to binaryzation, and pass through Hough transformation Bianry image is handled.
Further, to Lane detection calculating, the specific method is as follows:
S301, regard parameter space as discrete, establish a two-dimensional array and initialize, this two-dimensional array is referred to as Accumulator, for recording accumulation result and statistics peak value, the dimension of accumulator should be equal with the number of unknown parameter, here straight line (ρ, θ) two parameters are contained only in polar equation, therefore need to only establish two-dimentional accumulator, the first dimension representative image in accumulator The range of straight slope in coordinate space, second ties up the range of Linear intercept in representative image coordinate space;
When S302, detection straight line, each point (i, j) in image is traversed, calculates all pixels point in the corresponding ρ in each angle θ Value counts the number of ρ value appearance;
S303, setting threshold value are considered as detecting straight line when the number that ρ value occurs is higher than the threshold value.And in decision Setting a definite value d is vehicle at a distance from lane line, and keeps function to make vehicle at straight line according to lane line by lane It is travelled.
Further, the specific method is as follows by the step S4:
S401, when automatic running is to intersection, i.e., when road is without lane line, be with vehicle point C at this time Initial point, and transverse and longitudinal coordinate of the A point in the lane that will be driven to by camera measurement relative to vehicle front camera, in turn The transverse and longitudinal coordinate of B point is calculated by the definite value d in implementation steps S3, B point is the terminal that vehicle travels at turning;
S402, turning starting point and end point location information are obtained according to step S401, then chooses two control point compositions Four control points of three rank Beziers pass through the available three ranks Bezier of the transverse and longitudinal coordinate information at four control points Expression formula, three rank Bezier formula are as follows:
In formula, XAIndicate the abscissa of the starting point A under plane right-angle coordinate;YAIt indicates under plane right-angle coordinate The ordinate of starting point A;XBIndicate the abscissa of the control point B under plane right-angle coordinate;YBIt indicates in plane right-angle coordinate The ordinate of lower control point B;XCIndicate the abscissa of the control point C under plane right-angle coordinate;YCIt indicates in plane rectangular coordinates It is the ordinate of lower control point C;XDIndicate the abscissa of the terminating point D under plane right-angle coordinate;YDIt indicates to sit in flat square Mark is the ordinate of lower terminating point D;
S403, due to three rank Beziers it is the expression formula about time t, three rank shellfishes is obtained by given time parameter Discrete point on Sai Er curve, and wheel steering angle is calculated by discrete point, steering wheel angle is calculated further according to vehicle parameter.
Compared with the existing technology, the intelligent automobile of the present invention for parking garage independently finds the side on parking stall Method has the advantage that
(1) intelligent automobile of the present invention for parking garage independently finds the method on parking stall when target is stopped When the adjacent one or both sides of position do not have parked vehicle, the automated parking system based on sensors such as ultrasonic radars can not be positioned The position on parking stall, the present invention can accurately be identified parking stall by vision-based detection and the method for positioning, be made automatic It parks and goes on smoothly.
(2) intelligent automobile of the present invention for parking garage independently finds the method on parking stall when target is stopped When the stand of the parked vehicle of the position left and right sides is irregular, the present invention can be accurate by vision-based detection and the method for positioning Identify parking stall, the stand for excluding left and right parked vehicle adversely affects automatic parking bring.
(3) intelligent automobile of the present invention for parking garage independently finds the method on parking stall in automatic parking Before, the starting stand of different types of parking stall (vertical parking stall, horizontal parking stall, oblique line parking stall) vehicle is faced Difference, the present invention identify different parking stall types by the method for visual identity, make vehicle can be by before automatic parking It is parked according to defined requirement, and then smoothly realizes automatic parking.
Detailed description of the invention
The attached drawing for constituting a part of the invention is used to provide further understanding of the present invention, schematic reality of the invention It applies example and its explanation is used to explain the present invention, do not constitute improper limitations of the present invention.In the accompanying drawings:
Fig. 1 is the flow chart on autonomous searching parking stall described in the embodiment of the present invention;
Fig. 2 is the front and back comparison diagram of vision calibration described in the embodiment of the present invention;
Fig. 3 is the flow chart that parking stall tag line and four angle points are identified described in the embodiment of the present invention;
Fig. 4 is negotiation of bends schematic diagram described in the embodiment of the present invention.
Specific embodiment
It should be noted that in the absence of conflict, the feature in embodiment and embodiment in the present invention can phase Mutually combination.
In the description of the present invention, it is to be understood that, term " center ", " longitudinal direction ", " transverse direction ", "upper", "lower", The orientation or positional relationship of the instructions such as "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outside" is It is based on the orientation or positional relationship shown in the drawings, is merely for convenience of description of the present invention and simplification of the description, rather than instruction or dark Show that signified device or element must have a particular orientation, be constructed and operated in a specific orientation, therefore should not be understood as pair Limitation of the invention.In addition, term " first ", " second " etc. are used for description purposes only, it is not understood to indicate or imply phase To importance or implicitly indicate the quantity of indicated technical characteristic.The feature for defining " first ", " second " etc. as a result, can To explicitly or implicitly include one or more of the features.In the description of the present invention, unless otherwise indicated, " multiple " It is meant that two or more.
In the description of the present invention, it should be noted that unless otherwise clearly defined and limited, term " installation ", " phase Even ", " connection " shall be understood in a broad sense, for example, it may be being fixedly connected, may be a detachable connection, or be integrally connected;It can To be mechanical connection, it is also possible to be electrically connected;It can be directly connected, can also can be indirectly connected through an intermediary Connection inside two elements.For the ordinary skill in the art, above-mentioned term can be understood by concrete condition Concrete meaning in the present invention.
The present invention will be described in detail below with reference to the accompanying drawings and embodiments.
As shown in Figure 1, a kind of method that the intelligent automobile for parking garage independently finds parking stall, comprising:
S1, vehicle-mounted vision system is demarcated;
S2, using vehicle side camera acquisition lane two sides parking stall image information, and identify judge whether There is vehicle;
S3, the lane line that parking lot is identified using the front camera of vehicle, set a vehicle distances lane line length Definite value, keep vehicle in this definite value at a distance from lane line;
S4, there is no lane line position in corner, vehicle driving trace is supplemented by three rank Beziers, in supplement Multiple discrete points are obtained on driving trace, and the corner of steering wheel is calculated by discrete point.
As shown in Fig. 2, in the step S1, using scaling board in side camera and the front camera progress of vehicle The calibration of ginseng, line distortion of going forward side by side calibration.
In the step S2, vehicle is judged whether there is by the tag line and four angle points that identify parking stall.
As shown in figure 3, in the step S2, identification judges whether there is vehicle in parking stall that the specific method is as follows:
After S201, video camera collect the image comprising parking stall tag line, image is pre-processed, set it is white, yellow, The value range in the hsv color space of Lan Sanse only identified the parking stall tag line of different colours by color-match, Filter out most of interference information in image background;
S202, the parking stall tag line extracted is plotted in the picture of a blank background, edge inspection is carried out to it It surveys and Probabilistic Hough Transform extracts straightway;
S203, the straightway extracted is classified, is clustered, simultaneously close in alignment section conllinear of Straight-line segments mergence Retain, in view of parking stall tag line have certain width, according to this feature of brightness every straightway vertical direction into Row scanning, brightness value variation show as the rule of first increases and then decreases in a certain range judge its for parking stall tag line, Retained, it is on the contrary then give up;
S204, the frame for finally drawing out parking stall find out four angle points on parking stall.
In the step S3, the image of front camera acquisition is subjected to binaryzation, and by Hough transformation to binary map As being handled.
To Lane detection calculating, the specific method is as follows:
S301, regard parameter space as discrete, establish a two-dimensional array and initialize, this two-dimensional array is referred to as Accumulator, for recording accumulation result and statistics peak value, the dimension of accumulator should be equal with the number of unknown parameter, here straight line (ρ, θ) two parameters are contained only in polar equation, therefore need to only establish two-dimentional accumulator, the first dimension representative image in accumulator The range of straight slope in coordinate space, second ties up the range of Linear intercept in representative image coordinate space;
When S302, detection straight line, each point (i, j) in image is traversed, calculates all pixels point in the corresponding ρ in each angle θ Value counts the number of ρ value appearance;
S303, setting threshold value are considered as detecting straight line when the number that ρ value occurs is higher than the threshold value.And in decision Setting a definite value d is vehicle at a distance from lane line, and keeps function to make vehicle at straight line according to lane line by lane It is travelled.
As shown in figure 4, the specific method is as follows by the step S4:
S401, when automatic running is to intersection, i.e., when road is without lane line, be with vehicle point C at this time Initial point, and transverse and longitudinal coordinate of the A point in the lane that will be driven to by camera measurement relative to vehicle front camera, in turn The transverse and longitudinal coordinate of B point is calculated by the definite value d in implementation steps S3, B point is the terminal that vehicle travels at turning;
S402, turning starting point and end point location information are obtained according to step S401, then chooses two control point compositions Four control points of three rank Beziers pass through the available three ranks Bezier of the transverse and longitudinal coordinate information at four control points Expression formula, three rank Bezier formula are as follows:
In formula, XAIndicate the abscissa of the starting point A under plane right-angle coordinate;YAIt indicates under plane right-angle coordinate The ordinate of starting point A;XBIndicate the abscissa of the control point B under plane right-angle coordinate;YBIt indicates in plane right-angle coordinate The ordinate of lower control point B;XCIndicate the abscissa of the control point C under plane right-angle coordinate;YCIt indicates in plane rectangular coordinates It is the ordinate of lower control point C;XDIndicate the abscissa of the terminating point D under plane right-angle coordinate;YDIt indicates to sit in flat square Mark is the ordinate of lower terminating point D;
S403, due to three rank Beziers it is the expression formula about time t, three rank shellfishes is obtained by given time parameter Discrete point on Sai Er curve, and wheel steering angle is calculated by discrete point, steering wheel angle is calculated further according to vehicle parameter.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all in essence of the invention Within mind and principle, any modification, equivalent replacement, improvement and so on be should all be included in the protection scope of the present invention.

Claims (7)

1. a kind of method that the intelligent automobile for parking garage independently finds parking stall characterized by comprising
S1, vehicle-mounted vision system is demarcated;
S2, using vehicle side camera acquisition lane two sides parking stall image information, and identify judge whether there is vehicle;
S3, the lane line that parking lot is identified using the front camera of vehicle, set determining for a vehicle distances lane line length Value, keeps vehicle in this definite value at a distance from lane line;
S4, there is no lane line position in corner, vehicle driving trace is supplemented by three rank Beziers, in the traveling of supplement Multiple discrete points are obtained on track, and the corner of steering wheel is calculated by discrete point.
2. the method that the intelligent automobile according to claim 1 for parking garage independently finds parking stall, feature It is: in the step S1, carries out the calibration of internal reference to the side camera and front camera of vehicle using scaling board, go forward side by side Line distortion calibration.
3. the method that the intelligent automobile according to claim 1 for parking garage independently finds parking stall, feature It is: in the step S2, by identifying that the tag line on parking stall judges whether there is vehicle.
4. the method that the intelligent automobile according to claim 1 to 3 for parking garage independently finds parking stall, It is characterized in that, the specific method is as follows for identification marking line in the step S2:
After S201, video camera collect the image comprising parking stall tag line, image is pre-processed, setting white, yellow, blue three The parking stall tag line of different colours is only identified by color-match, is filtered by the value range in the hsv color space of color Fall most of interference information in image background;
S202, the parking stall tag line extracted is plotted in the picture of a blank background, it is carried out edge detection and Probabilistic Hough Transform extracts straightway;
S203, the straightway extracted is classified, is clustered, close to conllinear Straight-line segments mergence Duan Bingbao in alignment It stays, there is certain width in view of parking stall tag line, the vertical direction according to this feature of brightness in every straightway carries out Scanning, brightness value variation show as the rule of first increases and then decreases in a certain range judge its for parking stall tag line, general It retains, on the contrary then give up;
S204, the frame for finally drawing out parking stall find out four angle points on parking stall.
5. the method that the intelligent automobile according to claim 1 for parking garage independently finds parking stall, feature Be: in the step S3, by front camera acquisition image carry out binaryzation, and by Hough transformation to bianry image into Row processing.
6. the method that the intelligent automobile according to claim 5 for parking garage independently finds parking stall, feature It is, to Lane detection calculating, the specific method is as follows:
S301, regard parameter space as discrete, establish a two-dimensional array and initialize, this two-dimensional array is referred to as cumulative Device, for recording accumulation result and statistics peak value, the dimension of accumulator should be equal with the number of unknown parameter, and straight line pole is sat here (ρ, θ) two parameters are contained only in mark equation, therefore need to only establish two-dimentional accumulator, the first dimension representative image coordinate in accumulator The range of straight slope in space, second ties up the range of Linear intercept in representative image coordinate space;
When S302, detection straight line, each point (i, j) in image is traversed, calculates all pixels point in the corresponding ρ value in each angle θ, system Count out the number of ρ value appearance;
S303, setting threshold value are considered as detecting straight line when the number that ρ value occurs is higher than the threshold value.And it is set in decision One definite value d is vehicle keeps function to carry out vehicle at straight line according to lane line at a distance from lane line, and through lane Traveling.
7. the method that the intelligent automobile according to claim 1 for parking garage independently finds parking stall, feature It is, the specific method is as follows by the step S4:
S401, when automatic running is to intersection, i.e., when road is without lane line, using vehicle point C at this time as starting point, And transverse and longitudinal coordinate of the A point in the lane that will be driven to by camera measurement relative to vehicle front camera, and then pass through Definite value d in implementation steps S3 calculates the transverse and longitudinal coordinate of B point, and B point is the terminal that vehicle travels at turning;
S402, turning starting point and end point location information are obtained according to step S401, then chooses two control points and forms three ranks Four control points of Bezier, pass through the table of the available three ranks Bezier of the transverse and longitudinal coordinate information at four control points Up to formula, three rank Bezier formula are as follows:
In formula, XAIndicate the abscissa of the starting point A under plane right-angle coordinate;YAExpression originates under plane right-angle coordinate The ordinate of point A;XBIndicate the abscissa of the control point B under plane right-angle coordinate;YBExpression is controlled under plane right-angle coordinate Make the ordinate of point B;XCIndicate the abscissa of the control point C under plane right-angle coordinate;YCIt indicates under plane right-angle coordinate The ordinate of control point C;XDIndicate the abscissa of the terminating point D under plane right-angle coordinate;YDIt indicates in plane right-angle coordinate The ordinate of lower terminating point D;
S403, due to three rank Beziers it is the expression formula about time t, three rank Bezier is obtained by given time parameter Discrete point on curve, and wheel steering angle is calculated by discrete point, steering wheel angle is calculated further according to vehicle parameter.
CN201910069541.2A 2019-01-24 2019-01-24 A method of the intelligent automobile for parking garage independently finds parking stall Pending CN109784292A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910069541.2A CN109784292A (en) 2019-01-24 2019-01-24 A method of the intelligent automobile for parking garage independently finds parking stall

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910069541.2A CN109784292A (en) 2019-01-24 2019-01-24 A method of the intelligent automobile for parking garage independently finds parking stall

Publications (1)

Publication Number Publication Date
CN109784292A true CN109784292A (en) 2019-05-21

Family

ID=66502248

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910069541.2A Pending CN109784292A (en) 2019-01-24 2019-01-24 A method of the intelligent automobile for parking garage independently finds parking stall

Country Status (1)

Country Link
CN (1) CN109784292A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110544386A (en) * 2019-09-18 2019-12-06 奇瑞汽车股份有限公司 parking space identification method and device and storage medium

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110544386A (en) * 2019-09-18 2019-12-06 奇瑞汽车股份有限公司 parking space identification method and device and storage medium

Similar Documents

Publication Publication Date Title
CN106205170B (en) Intersection accurate parking device and method for automatic driving
Kong et al. Vanishing point detection for road detection
Kluge Extracting road curvature and orientation from image edge points without perceptual grouping into features
CN104834889A (en) Marking line detection system and marking line detection method
CN101727671B (en) Single camera calibration method based on road surface collinear three points and parallel line thereof
US20050169501A1 (en) Method and apparatus for determining driving lane of vehicle, and computer product
US20180033148A1 (en) Method, apparatus and device for detecting lane boundary
CN104700414A (en) Rapid distance-measuring method for pedestrian on road ahead on the basis of on-board binocular camera
CN103630122B (en) Monocular vision lane line detection method and distance measurement method thereof
US10977504B2 (en) Vehicle-mounted image target objection recognition device
CN103487034A (en) Method for measuring distance and height by vehicle-mounted monocular camera based on vertical type target
CN102446355B (en) Method for detecting target protruding from plane based on double viewing fields without calibration
CN104217427A (en) Method for positioning lane lines in traffic surveillance videos
CN108394416B (en) parking space display auxiliary method and system
CN103020613A (en) Method and device for identifying signal lamps on basis of videos
CN106651953A (en) Vehicle position and gesture estimation method based on traffic sign
CN109849922B (en) Visual information and GIS information fusion-based method for intelligent vehicle
CN109784292A (en) A method of the intelligent automobile for parking garage independently finds parking stall
Wu et al. Adjacent lane detection and lateral vehicle distance measurement using vision-based neuro-fuzzy approaches
CN109635737B (en) Auxiliary vehicle navigation positioning method based on road marking line visual identification
WO2019071212A1 (en) System and method of determining a curve
Chang et al. Real-time vision-based preceding vehicle tracking and recognition
CN108470142A (en) Lane location method based on inverse perspective projection and track distance restraint
CN102483881B (en) Pedestrian-crossing marking detecting method and pedestrian-crossing marking detecting device
CN109791598A (en) The image processing method of land mark and land mark detection system for identification

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