CN109435942A - A kind of parking stall line parking stall recognition methods and device based on information fusion - Google Patents
A kind of parking stall line parking stall recognition methods and device based on information fusion Download PDFInfo
- Publication number
- CN109435942A CN109435942A CN201811283453.4A CN201811283453A CN109435942A CN 109435942 A CN109435942 A CN 109435942A CN 201811283453 A CN201811283453 A CN 201811283453A CN 109435942 A CN109435942 A CN 109435942A
- Authority
- CN
- China
- Prior art keywords
- parking stall
- line
- angle point
- inter
- vehicle
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 230000004927 fusion Effects 0.000 title claims abstract description 34
- 238000001514 detection method Methods 0.000 claims abstract description 39
- 230000004888 barrier function Effects 0.000 claims abstract description 11
- 238000000605 extraction Methods 0.000 claims description 8
- 238000007689 inspection Methods 0.000 claims description 8
- 238000002594 fluoroscopy Methods 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 6
- 238000013519 translation Methods 0.000 claims description 6
- 235000004522 Pentaglottis sempervirens Nutrition 0.000 claims description 5
- 230000009466 transformation Effects 0.000 claims description 5
- 235000021152 breakfast Nutrition 0.000 claims description 2
- 239000000284 extract Substances 0.000 claims description 2
- 238000007670 refining Methods 0.000 claims description 2
- 230000000717 retained effect Effects 0.000 claims 1
- 230000000007 visual effect Effects 0.000 abstract description 13
- 238000005516 engineering process Methods 0.000 description 5
- 238000013507 mapping Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 238000011160 research Methods 0.000 description 4
- 241000208340 Araliaceae Species 0.000 description 2
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 2
- 235000003140 Panax quinquefolius Nutrition 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- JEIPFZHSYJVQDO-UHFFFAOYSA-N ferric oxide Chemical compound O=[Fe]O[Fe]=O JEIPFZHSYJVQDO-UHFFFAOYSA-N 0.000 description 2
- 235000008434 ginseng Nutrition 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 230000008447 perception Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 241001300198 Caperonia palustris Species 0.000 description 1
- 241000196324 Embryophyta Species 0.000 description 1
- 235000000384 Veronica chamaedrys Nutrition 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000013011 mating Effects 0.000 description 1
- 238000007500 overflow downdraw method Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000006641 stabilisation Effects 0.000 description 1
- 238000011105 stabilization Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units, or advanced driver assistance systems for ensuring comfort, stability and safety or drive control systems for propelling or retarding the vehicle
- B60W30/06—Automatic manoeuvring for parking
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R1/00—Optical viewing arrangements; Real-time viewing arrangements for drivers or passengers using optical image capturing systems, e.g. cameras or video systems specially adapted for use in or on vehicles
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S15/00—Systems using the reflection or reradiation of acoustic waves, e.g. sonar systems
- G01S15/88—Sonar systems specially adapted for specific applications
- G01S15/93—Sonar systems specially adapted for specific applications for anti-collision purposes
- G01S15/931—Sonar systems specially adapted for specific applications for anti-collision purposes of land vehicles
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R2300/00—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle
- B60R2300/10—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the type of camera system used
- B60R2300/105—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the type of camera system used using multiple cameras
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R2300/00—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle
- B60R2300/30—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the type of image processing
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R2300/00—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle
- B60R2300/60—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by monitoring and displaying vehicle exterior scenes from a transformed perspective
- B60R2300/607—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by monitoring and displaying vehicle exterior scenes from a transformed perspective from a bird's eye viewpoint
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R2300/00—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle
- B60R2300/80—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the intended use of the viewing arrangement
- B60R2300/806—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the intended use of the viewing arrangement for aiding parking
Abstract
The present invention disclose it is a kind of based on information fusion parking stall line parking stall recognition methods and device.Parking stall line parking stall recognition methods records parking stall angular coordinate at this time, and enabling it is the first parking stall angle point comprising steps of identify parking stall angle point from vehicle body side birds-eye view, and when parking stall angle point and camera be in parallel position;The ultrasonic radar of vehicle start detect vehicle towards the first parking stall angle point it is lateral on whether have barrier, if so, then returning to previous step, otherwise carry out next step;Similarly obtain the second parking stall angle point;The parking stall general width of parking stall line parking stall and the lateral distance of vehicle and parking stall line parking stall are calculated according to two parking stall angle points.The present invention can be achieved to identify the detection for having standard vehicle bit flag line parking stall, utilize the detection for having clear in ultrasonic radar identification parking stall, the operating range value obtained using wheel speed sensors is merged with visual information obtains parking stall angular coordinate, the final identification for realizing parking stall line parking stall.
Description
Technical field
The present invention relates to automatic parking technical fields, and in particular to a kind of parking stall line parking stall identification side based on information fusion
Method and device.
Background technique
Automated parking system (Automatic Parking System, APS) is collection environment sensing, decision and a rule
It draws, the functions such as intelligent control and execution are the important components of intelligent driving auxiliary system in the integrated system of one.As
The environment perception technology of one of the big key technology of automated parking system three is mainly with ultrasonic radar or monocular cam at present
Main perception identifying system has been achieved for part successful application, and part commercialization is applied on real vehicle.In recent years
Come, multi-sensor information fusion technology becomes the hot spot of major colleges and universities and research institution, and in mobile robot field to obtain
Certain research achievement, but it is in research of the automatic parking field to information fusion technology also fewer and fewer.
At present common automatic parking technical field about the research that parking stall line parking stall identify be based primarily upon monocular vision with
360 viewing systems carry out parking stall measure.Parking stall line parking stall identifying system based on monocular vision is narrow due to single camera view
Small reason is difficult to include entire parallel space, such as to include entire parallel space, then need from vehicle apart from parking stall it is lateral away from
It is even farther from 4m is greater than, but usually parallel space space beside is narrow, leads to not identify parking stall.Based on 360 viewing systems
Parking stall line parking stall identifying system although solve the narrow disadvantage in the visual field, but with the expansion in the visual field, noise in image,
Illumination, the influences such as ground texture can reduce the accuracy of identification of parking stall line, such as to improve accuracy of identification, then need more complicated algorithm
Design, calculation amount can increase, and real-time reduces.
Summary of the invention
To solve to be difficult to the technical issues of including entire parallel space because single camera view is narrow, the present invention is proposed
A kind of parking stall line parking stall recognition methods and device based on information fusion.
To achieve the above object, the invention adopts the following technical scheme:
A kind of parking stall line parking stall recognition methods based on information fusion, using the camera of vehicle as coordinate origin, vehicle
Driving direction is that positive direction of the x-axis establishes O1Xy coordinate system;Using the rear shaft center of vehicle point as origin, the driving direction of vehicle is x
Axis positive direction establishes Oxy coordinate system;Parking stall line parking stall passes through the first parking stall angle point on the same side
Second parking stall angle pointAnd vehicle is from the first parking stall angle pointDrive towards the second parking stall angle pointDuring obtained parking stall general width LpIt determines;The vehicle is in the process of moving to two parking stall angle points
Carry out camera shooting and respectively thus to obtain corresponding vehicle body side birds-eye view;
Parking stall line parking stall recognition methods comprising steps of
Step 1: identifying parking stall angle point (x from vehicle body side birds-eye view oneinter, yinter), and parking stall angle point
(xinter, yinter) with camera be in parallel position when, record parking stall angular coordinate at this time, and enable its be the first parking stall
Angle point
Wherein, road surface region foundation is higher than based on parking stall line partial pixel in vehicle body side birds-eye view, from the body side
Parking stall angle point (x is extracted in the birds-eye view of faceinter, yinter);
Parking stall angle point and camera are in the Rule of judgment of parallel position are as follows: X/2- δ3≤xinter≤X/2+δ3, wherein X
For birds-eye view abscissa maximum value, value 540, δ3It is 10;
Step 2: the ultrasonic radar of vehicle starts to detect vehicle towards the first parking stall angle pointIt is lateral on
Whether barrier is had, if so, then return step one, otherwise carries out step 3;
Step 3: similarly obtaining the second parking stall angle point according to step 1
Step 4: according to the first parking stall angle pointWith the second parking stall angle pointCalculate parking stall line vehicle
The parking stall general width L of positionpAnd the lateral distance y of vehicle and parking stall line parking stallp;
Wherein, parking stall general width LpAre as follows:
Lateral distance ypAre as follows: yP=K+ (Y-yinter) k, wherein K is blind area distance, installs pitch angle by camera
And height determines;Y is birds-eye view ordinate maximum value, value 430;K is exactly real world plane and inverse fluoroscopy images plane
Than column coefficient.
As a further improvement of the foregoing solution, parking stall angle point (xinter, yinter) extracting method comprising steps of
A) feature extraction and binaryzation are carried out to vehicle body side birds-eye view;
B) noise removal in edge is done to the vehicle body side birds-eye view after feature extraction and binaryzation;
C) image thinning is carried out to the vehicle body side birds-eye view of removal edge breakfast;
D) inspection side straight line is done to the vehicle body side birds-eye view after refinement and seeks the intersection point of inspection side straight line, inspection side straight line
Intersection point, that is, parking stall angle point (xinter, yinter)。
Further, feature extraction and the step of binaryzation are as follows:
In the vehicle body side birds-eye view, the gray value of parking stall line is higher than the pixel value positioned at parking stall line two sides, if depositing
Its left and right of pixel ratio meet a predetermined parking stall line width pixel value it is high or there are a pixel ratio its up and down apart
The grey scale pixel value of one predetermined parking stall line width is high, that is, thinks that the pixel is a possible parking stall line pixel, to the pixel
Point sets 255, otherwise sets 0, i.e. g to the pixel1(x, y) are as follows:
Wherein,dV+e(x, y) is that line feature templates in parking stall are asked when moving to right
The feature taken, dV-e(x, y) is the feature sought when line feature templates in parking stall move to left, dP+e(x, y) is on parking stall line feature templates
The feature sought when shifting, dP-e(x, y) is the feature sought when line feature templates in parking stall move down, and p (x, y) is the grayscale image of input,
The i.e. described vehicle body side birds-eye view, p (x, y ± e) they are that the grayscale image is carried out the figure after the translation of left and right by e pixel, p (x ±
E, y) it is that the grayscale image is carried out to the figure after upper and lower translation, δ by e pixel0It is 40.
Further, the step of edge noise removes are as follows: continue to handle as follows with vehicle body side birds-eye view:
Wherein
FL(xn), FR(xn) it is respectively left and right curvilinear equation, g1(x, y) is the binaryzation characteristic pattern of input, g2(x, y) is defeated
Binaryzation characteristic pattern out.
Further, the step of image thinning are as follows: image framework is obtained using Zhang-Suen thinning algorithm refined image,
Vehicle body side birds-eye view after refining.
Further, the detection of probability Hough transformation is carried out to the top edge of the vehicle body side birds-eye view after obtained refinement,
Retain radially and tangentially longest line segment respectively according to length, wherein a longest line segment is inspection side straight line, then seeks parking stall
Angle point (xinter, yinter)。
Still further, parking stall angle point (xinter, yinter) finding process it is as follows:
Straight line where tangential line segment is defined as straight line one, and straight line where radial line segments is defined as straight line two, it is known that two are not
Two point (x of parallel straight line one1, y1)、(x2, y2) and straight line two two point (x3, y3)、(x4, y4), a point following situation is asked
It takes:
It 3) is exactly slope k when two straight lines are all perpendicular to x-axis1、k2It is not present;
4) only has straight line perpendicular to x-axis, i.e. k1Or k2It is not present, is had according to slope definition and its slope-intercept form of an equation
Then the equation of straight line one is y=k1x+b1;
Then two straight-line intersection coordinates are
3) two straight lines are all not perpendicular to x-axis, i.e. k1、k2All exist, is had according to slope definition and its slope-intercept form of an equation
Then the equation of straight line one is y=k1x+b1, two equation of straight line is y=k2x+b2
Then two straight-line intersection coordinates are
Preferably, parking stall angle point (xinter, yinter) extracting method further comprise the steps of: e) Type division.
More preferably, according to parking stall angle point (xinter,yinter) and straight line one two point (x1, y1)、(x2, y2) by parking stall
Markings are divided into three classes: T-shape, left " L " type, right " L " type, and judgment criteria is as follows:
Wherein, δ1It is 30, δ2It is 5.
The present invention also provides a kind of parking stall line stall recognition devices based on information fusion, use above-mentioned any based on letter
The parking stall line parking stall recognition methods of fusion is ceased, the parking stall line stall recognition device includes:
Parking stall Corner Detection module is used to obtain the first parking stall angle pointWith the second parking stall angle point
Detection of obstacles module is used for the ultrasonic radar detection vehicle using vehicle towards the first parking stall angle pointIt is lateral on whether have barrier;
Computing module is used for when the detection of obstacles module does not detect barrier, according to the first parking stall angle
PointWith the second parking stall angle pointCalculate the parking stall general width L of parking stall line parking stallpAnd vehicle and vehicle
The lateral distance y of bit line parking stallp。
The present invention is based on the parking stall line parking stall recognition methods of information fusion can realize to there is standard vehicle bit flag line parking stall
Detection identification, using having the detection of clear in ultrasonic radar identification parking stall, the traveling that is obtained using wheel speed sensors away from
It is merged from value with visual information and obtains parking stall angular coordinate, the final identification for realizing parking stall line parking stall.
Detailed description of the invention
Fig. 1 is the software system framework using the parking stall line parking stall identifying system of parking stall line parking stall recognition methods of the invention
Figure.
Fig. 2 is that the parking stall line in parking stall line of the present invention parking stall recognition methods detects intermediate result figure.
Fig. 3 is the parking stall markings type definition figure in parking stall line of the present invention parking stall recognition methods.
Fig. 4 is that the information of parking stall line of the present invention parking stall recognition methods merges flow chart.
Fig. 5 is the plane visual ranging illustraton of model based on inverse perspective mapping in parking stall line of the present invention parking stall recognition methods.
Fig. 6 is the explanatory diagram of the parking stall establishment of coordinate system in parking stall line of the present invention parking stall recognition methods.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.
Parking stall line parking stall recognition methods based on information fusion of the invention, applied to the parking stall line vehicle merged based on information
In the identification device of position, the parking stall line stall recognition device based on information fusion can be loaded in the identifying system of parking stall line parking stall.Vehicle
Bit line parking stall identifying system is made of following a few class systems:
1. power-supply system;By that can provide the battery of 12V DC electricity, ultrasonic sensor is complete using additional power supply module
At transformation, computer completes transformation using inverter, and other equipment all have mating independent potential device.
2. sensor-based system;The high definition USB camera of monocular cam model HD DOGITAL CAMERA;Ultrasonic wave passes
Sensor is the ultrasonic radar of the model KS103 of certain producer production;Wheel speed sensors are revolved using the increment type of certain company production
Turn encoder, model BS80T20-5-24F-360BM, umber of pulse 360.
3. communication system: the communication data of current system includes:
(1) processing result image is sent to controller of parking by CAN;
(2) ultrasonic radar data are sent to controller of parking by IIC communication mode;
(3) wheel speed sensors data are sent to controller of parking by CAN.
Parking stall line parking stall identifying system can integral installation on Yangze river and Huai river IEV4 pure electric automobile.Wherein, line parking stall in parking stall is known
The monocular camera HD DOGITAL CAMERA of other system is mounted at rearview mirror, is located at vehicle body side;Parking stall line parking stall identification system
The ultrasonic radar of system is mounted on front-wheel fender, terrain clearance 80cm;The wheel speed of parking stall line parking stall identifying system senses
Device is separately mounted on two hind axles of automobile.
The system mainly includes off-line calibration and Inverse projection module, parking stall Corner Detection and visual token module, letter
Fusion Module is ceased, parking stall establishment of coordinate system module, it can be achieved that know the parking stall for having standard vehicle bit flag line precisely in real time
Not.The system includes following part: ultrasonic radar of the ultrasonic radar using the model KS103 of certain producer production, maximum
Detection range is 5m;The high definition USB camera for the HD DOGITAL CAMERA that camera is produced using certain producer, with liftoff height
Spend 80cm, 30 degree of setting parameter calibrations of pitch angle;Wheel speed sensors use the incremental rotary encoder of certain company production, model
For BS80T20-5-24F-360BM, umber of pulse 360;Parking stall establishment of coordinate system module be Independent Development Design with
The controller of parking developed based on the minimum system of FreescaleMC9S128 single-chip microcontroller.Camera and wheel speed sensors pass through
The channel CAN is by information collection to controller of parking, and ultrasonic radar is with IIC communication mode by signal acquisition to controller of parking.
System can provide the parking stall markings testing result before vehicle body side within the scope of 5.5m with the frequency stabilization of 100HZ, and can area
Divide T-shape parking stall markings and left and right " L " type parking stall markings.System cost is cheap, low in energy consumption, whole shifting with higher
Plant property is suitble to commercialization.
The working principle of the parking stall line parking stall identifying system: off-line calibration and Inverse projection module utilize Zhang Zhengyou phase
Machine standardization writes internal reference and the calibration of outer ginseng that program completes camera, passes through the high definition USB camera of HDDOGITAL CAMERA
Current parking stall image is acquired, and carries out Inverse projection according to inside and outside parameter, image is got a bird's eye view in acquisition;Parking stall Corner Detection and vision
Corner Detection module in parking stall in range finder module locally highlights characteristic and angle caused by the constraint of parallel up rightness based on parking stall markings
It spends constraint condition and obtains the parking stall Corner Detection of present frame as a result, visual token module is obtained based on the birds-eye view of Inverse projection
The lateral distance value of present frame parking stall angle point.
Parking stall line parking stall recognition methods based on information fusion of the invention, using the camera of vehicle as coordinate origin,
The driving direction of vehicle is that positive direction of the x-axis establishes O1Xy coordinate system;Using the first parking stall angular coordinate as origin, the traveling side of vehicle
Ox ' y ' coordinate system is established to for positive direction of the x-axis.Parking stall line parking stall passes through the first parking stall angle point on the same sideSecond parking stall angle pointAnd vehicle is from the first parking stall angle pointDrive towards the second parking stall angle
PointDuring obtained parking stall general width LpIt determines.The vehicle is in the process of moving to two parking stalls angle
Point carries out camera shooting and respectively thus to obtain corresponding vehicle body side birds-eye view.
Parking stall line parking stall recognition methods comprising steps of
Step 1: identifying parking stall angle point (x from vehicle body side birds-eye view oneinter, yinter), and parking stall angle point
(xinter, yinter) with camera be in parallel position when, record parking stall angular coordinate at this time, and enable its be the first parking stall
Angle point
Wherein, road surface region foundation is higher than based on parking stall line partial pixel in vehicle body side birds-eye view, from the body side
Parking stall angle point (x is extracted in the birds-eye view of faceinter, yinter);
Parking stall angle point and camera are in the Rule of judgment of parallel position are as follows:
X/2-δ3≤xinter≤X/2+δ3, wherein X is birds-eye view abscissa maximum value, value 540, δ3It is 10;
Step 2: the ultrasonic radar of vehicle starts to detect vehicle towards the first parking stall angle pointIt is lateral on
Whether barrier is had, if so, then return step one, otherwise carries out step 3;
Step 3: similarly obtaining the second parking stall angle point according to step 1
Step 4: according to the first parking stall angle pointWith the second parking stall angle pointCalculate parking stall line vehicle
The parking stall general width L of positionpAnd the lateral distance y of vehicle and parking stall line parking stallp;
Wherein, parking stall general width LpAre as follows:
Lateral distance ypAre as follows: yP=K+ (Y-yinter) k, wherein K is blind area distance, installs pitch angle by camera
It determines;Y is birds-eye view ordinate maximum value, value 430;K is exactly the ratio column of real world plane and inverse fluoroscopy images plane
Coefficient.
The parking stall line parking stall recognition methods based on information fusion is being programmed to, and may be designed to a kind of based on information
The parking stall line stall recognition device of fusion, this parking stall line stall recognition device includes: parking stall Corner Detection module, is used to obtain
Take the first parking stall angle pointWith the second parking stall angle pointDetection of obstacles module is used for using vehicle
Ultrasonic radar detection vehicle towards the first parking stall angle pointIt is lateral on whether have barrier;Computing module,
For when the detection of obstacles module does not detect barrier, according to the first parking stall angle pointWith the second vehicle
Parallactic angle pointCalculate the parking stall general width L of parking stall line parking stallpAnd the lateral distance y of vehicle and parking stall line parking stallp。
The present invention is based on the parking stall line parking stall identifying systems of information fusion can realize to there is standard vehicle bit flag line parking stall
Detection identification, using having the detection of clear in ultrasonic radar identification parking stall, the traveling that is obtained using wheel speed sensors away from
It is merged from value with visual information and obtains parking stall angular coordinate, the final identification for realizing parking stall line parking stall.
Embodiment 1
Referring to Fig. 1, the parking stall line parking stall identifying system based on information fusion specifically includes that off-line calibration on software frame
And Inverse projection module M1, parking stall Corner Detection and visual token module M2, information Fusion Module M3, parking stall establishment of coordinate system
Module M4.
The off-line calibration and Inverse projection module M1 are completed flat relative to vehicle body side for acquiring image information
The Inverse projection in face, obtains vehicle body side birds-eye view, and off-line calibration and Inverse projection module M1 include carrying out camera internal reference
With the off-line calibration module M11 and Inverse projection module M12 of outer ginseng.Off-line calibration module M11 is sought using signature point
The external parameter of camera internal parameter and camera relative to car body coordinate.Inverse projection module M12 acquires BGR image in real time,
And calculated camera internal parameter and external parameter, it converts image to birds-eye view (Bird-eye View), and will
It is converted into gray level image, i.e., the subsequent vehicle body side birds-eye view for needing to carry out data processing.
Parking stall Corner Detection and visual token module M2 are for carrying out parking stall Corner Detection and vehicle body side away from parking stall angle point
Distance detection, parking stall Corner Detection and visual token module M2 include parking stall Corner Detection module M21 and based on inverse perspective mapping
Planar Ranging module M22.Parking stall Corner Detection module M21 is based on parking stall line partial pixel in vehicle body side birds-eye view and is higher than road
Face region foundation extracts parking stall angle point (x from the vehicle body side birds-eye viewinter, yinter).Planar Ranging module M22 is obtained
Pick-up parallactic angle point (xinter, yinter) distance value y apart from vehicle body sidep, in the present embodiment, obtained using a planar Ranging model
Distance value of the pick-up parallactic angle point apart from vehicle body side.
Parking stall Corner Detection module M21 exports parking stall angle point (xinter, yinter) data processing method comprising steps of
A) feature extraction and binaryzation.
Referring to fig. 2 (a), parking stall line feature extraction based on an assumption that i.e. parking stall line gray value be higher than its two sides pixel
Value, if it exists its left and right of pixel ratio meet a parking stall line width pixel value it is high or there are its phases up and down of a pixel ratio
Grey scale pixel value away from a parking stall line width is high, that is, thinks that the pixel is a possible parking stall line pixel, which sets
255;If a certain pixel pixel adjacent thereto does not meet above-mentioned condition, which sets 0.
Wherein,
g1(x, y) is the preliminary parking stall line characteristic pattern sought, dV+e(x, y) is that line feature templates in parking stall are sought when moving to right
Feature, dV-e(x, y) is the feature sought when line feature templates in parking stall move to left, dP+eWhen (x, y) is that line feature templates in parking stall move up
The feature sought, dP-e(x, y) is the feature that line feature templates in parking stall are sought when moving down, and p (x, y) be the grayscale image inputted, p (x,
Y ± e) it is that the grayscale image being originally inputted is subjected to the figure after the translation of left and right by e pixel, p (x ± e, y) will be originally inputted
Grayscale image is carried out the figure after upper and lower translation by e pixel.
B) birds-eye view edge removes earlier.
Referring to fig. 2 (b), to the parking stall line feature extracted, due to being obtained in off-line calibration and Inverse projection module
Birds-eye view inward flange also comply with compared with outer edge and meet the high condition of pixel value of a parking stall line width than its left and right, and
After calibration, this edge line is fixed curve.Several pixel coordinates on two curves are taken using off-line method, are utilized
The tool box cftool in Matlab carries out curve fitting, and obtaining fit curve equation is FL(xn) and FR(xn), to above-mentioned (a)
Figure continues to handle as follows:
Wherein
FL(xn), FR(xn) it is respectively left and right curvilinear equation.
g1(x, y) is the binaryzation characteristic pattern of input, g2(x, y) is the binaryzation characteristic pattern of output.
C) image thinning.
Referring to fig. 2 (c), the binary picture with parking stall line feature is obtained using Zhang-Suen thinning algorithm refined image
To image framework.
D) it examines side straight line and seeks vertical parallel straight-line intersection.
Referring to fig. 2 (d), the detection of probability Hough transformation is carried out to obtained image framework lower edge, is protected respectively according to length
Radially and tangentially longest line segment is stayed, the linear equation of line segment is sought and seeks its intersection point, process is as follows:
Two point (x of known two not parallel straight lines 1 (straight line where tangential line segment)1, y1)、(x2, y2) and straight line 2
Two point (x of (straight line where radial line segments)3, y3)、(x4, y4), a point following situation is sought:
It 5) is exactly slope k when two straight lines are all perpendicular to x-axis1、k2It is not present.Range is not discussed in the present invention.
6) only has straight line perpendicular to x-axis, i.e. k1Or k2It is not present, there are such cases for straight line 2 of the present invention.According to
Slope definition and its slope-intercept form of an equation have
Then the equation of straight line 1 is y=k1x+b1;
Then two straight-line intersection coordinates are
3) two straight lines are all not perpendicular to x-axis, i.e. k1、k2All exist.Had according to slope definition and its slope-intercept form of an equation
Then the equation of straight line 1 is y=k1x+b1, 2 equation of straight line is y=k2x+b2
Then two straight-line intersection coordinates are
E) Type division.
(e) and Fig. 3 referring to fig. 2, according to above-mentioned gained intersection point (xinter,yinter) and straight line 1 (straight line where tangential line segment)
Two point (x1, y1)、(x2, y2) parking stall markings are divided into three classes: T-shape, left " L " type, right " L " type, judgment criteria is such as
Under:
Information Fusion Module M3 is used to obtain range information and camera that ultrasonic radar and wheel speed sensors obtain
Visual information merged, acquisition establish parking stall coordinate system characteristic point coordinate.
Referring to Fig. 4, the information Fusion Module M3 is mainly comprised the steps that
Step 1, the parking stall angle point of camera detection mark vehicle bit line parking stall, if identifying parking stall angle point and parking stall angle point
When being in parallel position with camera, parking stall angular coordinate at this time is recorded, and enables it for the first parking stall angle point
Step 2, ultrasonic radar start whether detection laterally has barrier, if so, return to step 1, if nothing, continue into
Row step M3S3;
Step 3, the parking stall angle point of camera detection mark vehicle bit line parking stall, if identifying parking stall angle point and parking stall angle point
When being in parallel position with camera, parking stall angular coordinate at this time is recorded, and enables it for the second parking stall angle point
Step 4 calculates the target according to the coordinate of the first parking stall angle point and the second parking stall angle point
The width of parking stall and lateral distance from vehicle and target parking stall.
Wherein, the first parking stall angular coordinateWith the second parking stall angular coordinateHorizontal seat
Mark is obtained by what wheel speed sensors obtained from vehicle operating range, and ordinate is by the parking stall Corner Detection and visual token module
The planar Ranging module M22 based on inverse perspective mapping in M2 is obtained.
Parking stall establishment of coordinate system module M4 is determined for judging that the parking stall detected meets vertical parking stall or parallel space
From vehicle and parking stall relative position, and then carry out respective paths planning.Parking stall establishment of coordinate system module M4 utilizes information Fusion Module
The first obtained parking stall angular coordinateWith the second parking stall angular coordinateParking stall is calculated substantially
Width LP, according to the judgement of parking stall width given threshold it is parallel space or vertical parking stall, according to being calculated from vehicle rear axle
Centre coordinate carries out path planning, general width L in parking stall thereinPIt is calculated by following formula:
In the present embodiment, referring to figure, 5, video camera is mounted at vehicle body side rearview mirror, flat based on inverse perspective mapping
Face range finder module principle: inverse fluoroscopy images theoretically have stringent line style relationship with true planar, that is, get a bird's eye view each in image
The corresponding real area of a block of pixels (1pix*1pix) be all it is equal, get a bird's eye view the distance of certain point-to-point transmission in image in other words
With there are following relationships at a distance from two o'clock corresponding in real world plane, i.e.,
DAB=kdab
Wherein, DABWhat is indicated is the Euclidean distance between real world Plane-point A and point B, and unit takes mm, dabIt indicates
Be the Euclidean distance of real world planar point A and point B in getting a bird's eye view image between corresponding point a and point b, unit is pixel
(pix), k is then the coefficient of relationship of birds-eye view Yu real world plane, and unit is mm/pix.
On practical vehicle, since the limited view of camera generally can all have blind area, bowing when this and camera are installed
The elevation angle is related, as shown in Figure 3:
Then D=K+kd
Wherein, D is parking stall markings (tangential straight line) at a distance from vehicle body side;K is the blind area of video camera, can be passed through
Experiment measures to obtain;And k is exactly real world plane and inverse fluoroscopy images plane than column coefficient;D is parking stall markings
Place is against the position of fluoroscopy images and the pixel distance of image least significant end.
Then distance of the parking stall angle point obtained by the planar Ranging module based on inverse perspective mapping to vehicle body side are as follows:
yP=K+ (Y-yinter)·k
Wherein, yPFor the ordinate of parking stall angle point, the i.e. distance of parking stall markings (tangential straight line) away from vehicle body side;K is
Blind area distance is determined by camera installation pitch angle;Y is birds-eye view ordinate maximum value, value 430;yinterFor parking stall
Two straight-line intersection ordinate value of markings;K is exactly real world plane and inverse fluoroscopy images plane than column coefficient.
It is that positive direction of the x-axis establishes O from vehicle driving direction using camera as coordinate origin referring to Fig. 61Xy coordinate system;With
One parking stall angle point is origin, is that positive direction of the x-axis establishes Ox ' y ' coordinate system from vehicle driving direction.Parking stall angle in information Fusion Module
Axial coordinate is determining as shown, identifying parking stall angle point and parking stall angle point from after vehicle in point coordinate and parking stall establishment of coordinate system module
When being in parallel position with camera (I position in figure), parking stall angular coordinate at this time is recorded, and enables it for the first parking stall angle
PointSecond parking stall angular coordinate is similarly;Wherein parking stall angle point and camera are in the Rule of judgment of parallel position
Are as follows:
X/2-δ3≤xinter≤X/2+δ3
Wherein, X is birds-eye view abscissa maximum value, value 540.
When sailing to II position in figure from garage, the coordinate points of camera become at this time
Wherein, xcBy being obtained from vehicle traveling distance value;
Wherein, W is parking stall developed width, is learnt by ultrasonic radar detection or is learnt by national standard.
Then when sailing to II position in figure from garage, from the coordinate points of vehicle rear shaft center are as follows:
Wherein, L is distance of the camera away from rear axle, and w is from vehicle vehicle width.
Those of ordinary skill in the art will appreciate that: realize that all or part of the steps of above-mentioned each method embodiment can lead to
The relevant hardware of program instruction is crossed to complete.Program above-mentioned can be stored in a computer readable storage medium.The journey
When being executed, execution includes the steps that above-mentioned each method embodiment to sequence;And storage medium above-mentioned include: ROM, RAM, magnetic disk or
The various media that can store program code such as person's CD.
Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention., rather than its limitations;To the greatest extent
Pipe present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: its according to
So be possible to modify the technical solutions described in the foregoing embodiments, or to some or all of the technical features into
Row equivalent replacement;And these are modified or replaceed, various embodiments of the present invention technology that it does not separate the essence of the corresponding technical solution
The range of scheme.
Claims (10)
1. a kind of parking stall line parking stall recognition methods based on information fusion, which is characterized in that
Using the camera of vehicle as coordinate origin, the driving direction of vehicle is that positive direction of the x-axis establishes O1Xy coordinate system;With the first vehicle
Position angular coordinate is origin, and the driving direction of vehicle is that positive direction of the x-axis establishes Ox ' y ' coordinate system;Parking stall line parking stall passes through
The first parking stall angle point on the same sideSecond parking stall angle pointAnd vehicle is from the first parking stall
Angle pointDrive towards the second parking stall angle pointDuring obtained parking stall general width LpIt determines;The vehicle
In the process of moving two parking stall angle points are carried out with camera shooting respectively and thus to obtain corresponding vehicle body side birds-eye view;
Parking stall line parking stall recognition methods comprising steps of
Step 1: identifying parking stall angle point (x from vehicle body side birds-eye view oneinter, yinter), and parking stall angle point (xinter,
yinter) with camera be in parallel position when, record parking stall angular coordinate at this time, and enable its be the first parking stall angle point
Wherein, road surface region foundation is higher than based on parking stall line partial pixel in vehicle body side birds-eye view, from the vehicle body side bird
It looks down from a height and extracts parking stall angle point (x in figureinter, yinter);
Parking stall angle point and camera are in the Rule of judgment of parallel position are as follows: X/2- δ3≤xinter≤X/2+δ3, wherein X is to get a bird's eye view
Figure abscissa maximum value, value 540, δ3It is 10;
Step 2: the ultrasonic radar of vehicle starts to detect vehicle towards the first parking stall angle pointIt is lateral on whether have
Barrier, if so, then return step one, otherwise carries out step 3;
Step 3: similarly obtaining the second parking stall angle point according to step 1
Step 4: according to the first parking stall angle pointWith the second parking stall angle pointCalculate parking stall line parking stall
Parking stall general width LpAnd the lateral distance y of vehicle and parking stall line parking stallp;
Wherein, parking stall general width LpAre as follows:
Lateral distance ypAre as follows: yP=K+ (Y-yinter) k, wherein K is blind area distance, installs pitch angle by camera and height is determined
It is fixed;Y is birds-eye view ordinate maximum value, value 430;K is exactly the ratio column system of real world plane and inverse fluoroscopy images plane
Number.
2. the parking stall line parking stall recognition methods as described in claim 1 based on information fusion, which is characterized in that parking stall angle point
(xinter, yinter) extracting method comprising steps of
A) feature extraction and binaryzation are carried out to vehicle body side birds-eye view;
B) noise removal in edge is done to the vehicle body side birds-eye view after feature extraction and binaryzation;
C) image thinning is carried out to the vehicle body side birds-eye view of removal edge breakfast;
D) inspection side straight line is done to the vehicle body side birds-eye view after refinement and seeks the intersection point of inspection side straight line, the friendship of the inspection side straight line
Point is parking stall angle point (xinter, yinter)。
3. as claimed in claim 2 based on information fusion parking stall line parking stall recognition methods, which is characterized in that feature extraction and
The step of binaryzation are as follows:
In the vehicle body side birds-eye view, the pixel value of parking stall line is higher than the pixel value positioned at parking stall line two sides, and if it exists one
Its left and right of a pixel ratio meet predetermined parking stall line width pixel value it is high or there is a pixel ratio its apart one up and down
The grey scale pixel value of predetermined parking stall line width is high, that is, thinks that the pixel is a possible parking stall line pixel, set to the pixel
255,0, i.e. g otherwise are set to the pixel1(x, y) are as follows:
Wherein,dV+e(x, y) is that line feature templates in parking stall are sought when moving to right
Feature, dV-e(x, y) is the feature sought when line feature templates in parking stall move to left, dP+eWhen (x, y) is that line feature templates in parking stall move up
The feature sought, dP-e(x, y) is the feature sought when line feature templates in parking stall move down, and p (x, y) is the grayscale image of input, i.e. institute
Vehicle body side birds-eye view is stated, p (x, y ± e) is that the grayscale image is carried out the figure after the translation of left and right, p (x ± e, y) by e pixel
For the grayscale image to be carried out to the figure after upper and lower translation, δ by e pixel0It is 40.
4. the parking stall line parking stall recognition methods as claimed in claim 2 based on information fusion, which is characterized in that edge noise is gone
Except the step of are as follows: continue to handle as follows with vehicle body side birds-eye view:
Wherein
FL(xn), FR(xn) it is respectively left and right curvilinear equation, g1(x, y) is the binaryzation characteristic pattern of input, g2(x, y) is output
Binaryzation characteristic pattern.
5. the parking stall line parking stall recognition methods as claimed in claim 2 based on information fusion, which is characterized in that image thinning
Step are as follows: image framework is obtained using Zhang-Suen thinning algorithm refined image, that is, the vehicle body side birds-eye view after refining.
6. the parking stall line parking stall recognition methods as claimed in claim 2 based on information fusion, which is characterized in that thin to what is obtained
The lower edge of vehicle body side birds-eye view after change carries out the detection of probability Hough transformation, is retained respectively radially and tangentially most according to length
Long line segment wherein a longest line segment is inspection side straight line, then seeks parking stall angle point (xinter, yinter)。
7. the parking stall line parking stall recognition methods as claimed in claim 6 based on information fusion, which is characterized in that parking stall angle point
(xinter, yinter) finding process it is as follows:
Straight line where tangential line segment is defined as straight line one, and straight line where radial line segments is defined as straight line two, it is known that two not parallel
Straight line one two point (x1, y1)、(x2, y2) and straight line two two point (x3, y3)、(x4, y4), a point following situation is sought:
It 1) is exactly slope k when two straight lines are all perpendicular to x-axis1、k2It is not present;
2) only has straight line perpendicular to x-axis, i.e. k1Or k2It is not present, is had according to slope definition and its slope-intercept form of an equation
Then the equation of straight line one is y=k1x+b1;
Then two straight-line intersection coordinates are
3) two straight lines are all not perpendicular to x-axis, i.e. k1、k2All exist, is had according to slope definition and its slope-intercept form of an equation
Then the equation of straight line one is y=k1x+b1, two equation of straight line is y=k2x+b2
Then two straight-line intersection coordinates are
8. the parking stall line parking stall recognition methods as claimed in claim 7 based on information fusion, which is characterized in that parking stall angle point
(xinter, yinter) extracting method further comprise the steps of: e) Type division.
9. the parking stall line parking stall recognition methods as claimed in claim 8 based on information fusion, which is characterized in that according to parking stall angle
Point (xinter,yinter) and straight line one two point (x1, y1)、(x2, y2) parking stall markings are divided into three classes: T-shape, left " L "
Type, right " L " type, judgment criteria are as follows:
Wherein, δ1It is 30, δ2It is 5.
10. a kind of parking stall line stall recognition device based on information fusion, which is characterized in that it is used as in claim 1 to 9
Parking stall line parking stall recognition methods based on information fusion described in any one, the parking stall line stall recognition device include:
Parking stall Corner Detection module is used to obtain the first parking stall angle pointWith the second parking stall angle point
Detection of obstacles module is used for the ultrasonic radar detection vehicle using vehicle towards the first parking stall angle point
It is lateral on whether have barrier;
Computing module is used for when the detection of obstacles module does not detect barrier, according to the first parking stall angle pointWith the second parking stall angle pointCalculate the parking stall general width L of parking stall line parking stallpAnd vehicle and parking stall
The lateral distance y of line parking stallp。
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811283453.4A CN109435942B (en) | 2018-10-31 | 2018-10-31 | Information fusion-based parking space line and parking space recognition method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811283453.4A CN109435942B (en) | 2018-10-31 | 2018-10-31 | Information fusion-based parking space line and parking space recognition method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109435942A true CN109435942A (en) | 2019-03-08 |
CN109435942B CN109435942B (en) | 2024-04-09 |
Family
ID=65548957
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811283453.4A Active CN109435942B (en) | 2018-10-31 | 2018-10-31 | Information fusion-based parking space line and parking space recognition method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109435942B (en) |
Cited By (31)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109740584A (en) * | 2019-04-02 | 2019-05-10 | 纽劢科技(上海)有限公司 | Automatic parking parking space detection method based on deep learning |
CN110070752A (en) * | 2019-05-29 | 2019-07-30 | 北京百度网讯科技有限公司 | One kind is parked appraisal procedure, device, electronic equipment and storage medium |
CN110097087A (en) * | 2019-04-04 | 2019-08-06 | 浙江科技学院 | A kind of automatic binding reinforcing bars location recognition method |
CN110293964A (en) * | 2019-06-25 | 2019-10-01 | 重庆长安汽车股份有限公司 | Automatic parking merges parking stall judgment method, system, computer readable storage medium and vehicle |
CN110390306A (en) * | 2019-07-25 | 2019-10-29 | 湖州宏威新能源汽车有限公司 | Detection method, vehicle and the computer readable storage medium of right angle parking stall |
CN110414355A (en) * | 2019-06-27 | 2019-11-05 | 沈阳工业大学 | The right bit sky parking stall of view-based access control model and parking stall line detecting method during parking |
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 |
CN111311925A (en) * | 2020-01-21 | 2020-06-19 | 北京百度网讯科技有限公司 | Parking space detection method and device, electronic equipment, vehicle and storage medium |
CN111754468A (en) * | 2020-06-10 | 2020-10-09 | 深圳南方德尔汽车电子有限公司 | Parking space detection method and device based on projection, computer equipment and storage medium |
CN112036385A (en) * | 2020-11-04 | 2020-12-04 | 天津天瞳威势电子科技有限公司 | Library position correction method and device, electronic equipment and readable storage medium |
CN112052782A (en) * | 2020-08-31 | 2020-12-08 | 安徽江淮汽车集团股份有限公司 | Around-looking-based parking space identification method, device, equipment and storage medium |
CN112172797A (en) * | 2020-09-27 | 2021-01-05 | 华人运通(上海)自动驾驶科技有限公司 | Parking control method, device, equipment and storage medium |
CN112201078A (en) * | 2020-09-30 | 2021-01-08 | 中国人民解放军军事科学院国防科技创新研究院 | Automatic parking space detection method based on graph neural network |
CN112455430A (en) * | 2020-12-02 | 2021-03-09 | 苏州优达斯汽车科技有限公司 | Method for detecting inclined parking spaces without parking space lines, parking method and parking system |
CN112598922A (en) * | 2020-12-07 | 2021-04-02 | 安徽江淮汽车集团股份有限公司 | Parking space detection method, device, equipment and storage medium |
CN112633152A (en) * | 2020-12-22 | 2021-04-09 | 深圳佑驾创新科技有限公司 | Parking space detection method and device, computer equipment and storage medium |
CN112622885A (en) * | 2020-12-30 | 2021-04-09 | 惠州市德赛西威汽车电子股份有限公司 | Method and system for constructing inclined parking spaces based on ultrasonic radar |
CN112767425A (en) * | 2020-12-30 | 2021-05-07 | 智车优行科技(北京)有限公司 | Parking space detection method and device based on vision |
CN112776797A (en) * | 2021-02-27 | 2021-05-11 | 重庆长安汽车股份有限公司 | Original parking space parking establishment method and system, vehicle and storage medium |
CN112863242A (en) * | 2021-02-08 | 2021-05-28 | 广州小鹏自动驾驶科技有限公司 | Parking space detection method and device |
CN112983085A (en) * | 2021-04-30 | 2021-06-18 | 的卢技术有限公司 | Parking space line identification method based on vision |
CN113053164A (en) * | 2021-05-11 | 2021-06-29 | 吉林大学 | Parking space identification method using look-around image |
CN113255405A (en) * | 2020-02-12 | 2021-08-13 | 广州汽车集团股份有限公司 | Parking space line identification method and system, parking space line identification device and storage medium |
CN113311437A (en) * | 2021-06-08 | 2021-08-27 | 安徽域驰智能科技有限公司 | Method for improving angular point position accuracy of vehicle-mounted radar positioning side parking space |
CN113799769A (en) * | 2021-09-28 | 2021-12-17 | 北京经纬恒润科技股份有限公司 | Detection method and device for parking space identification precision and automatic driving vehicle |
CN113822156A (en) * | 2021-08-13 | 2021-12-21 | 北京易航远智科技有限公司 | Parking space detection processing method and device, electronic equipment and storage medium |
CN113885532A (en) * | 2021-11-11 | 2022-01-04 | 江苏昱博自动化设备有限公司 | Unmanned floor truck control system of barrier is kept away to intelligence |
CN114475434A (en) * | 2020-11-11 | 2022-05-13 | 广州汽车集团股份有限公司 | Control and adjustment method and system for reversing exterior rearview mirror and storage medium |
EP4033457A1 (en) * | 2021-01-20 | 2022-07-27 | Guangzhou Xiaopeng Autopilot Technology Co., Ltd. | Parking space detection method and apparatus |
CN115148047A (en) * | 2022-07-25 | 2022-10-04 | 中汽创智科技有限公司 | Parking space detection method and device |
CN115206130A (en) * | 2022-07-12 | 2022-10-18 | 合众新能源汽车有限公司 | Parking space detection method, system, terminal and storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP2436577A2 (en) * | 2010-09-30 | 2012-04-04 | Valeo Schalter und Sensoren GmbH | Device and method for detecting free parking spots |
CN104933409A (en) * | 2015-06-12 | 2015-09-23 | 北京理工大学 | Parking space identification method based on point and line features of panoramic image |
CN105946853A (en) * | 2016-04-28 | 2016-09-21 | 中山大学 | Long-distance automatic parking system and method based on multi-sensor fusion |
CN108281041A (en) * | 2018-03-05 | 2018-07-13 | 东南大学 | A kind of parking space's detection method blended based on ultrasonic wave and visual sensor |
-
2018
- 2018-10-31 CN CN201811283453.4A patent/CN109435942B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP2436577A2 (en) * | 2010-09-30 | 2012-04-04 | Valeo Schalter und Sensoren GmbH | Device and method for detecting free parking spots |
CN104933409A (en) * | 2015-06-12 | 2015-09-23 | 北京理工大学 | Parking space identification method based on point and line features of panoramic image |
CN105946853A (en) * | 2016-04-28 | 2016-09-21 | 中山大学 | Long-distance automatic parking system and method based on multi-sensor fusion |
CN108281041A (en) * | 2018-03-05 | 2018-07-13 | 东南大学 | A kind of parking space's detection method blended based on ultrasonic wave and visual sensor |
Cited By (43)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109740584A (en) * | 2019-04-02 | 2019-05-10 | 纽劢科技(上海)有限公司 | Automatic parking parking space detection method based on deep learning |
CN109740584B (en) * | 2019-04-02 | 2019-06-25 | 纽劢科技(上海)有限公司 | Automatic parking parking space detection method based on deep learning |
CN110097087A (en) * | 2019-04-04 | 2019-08-06 | 浙江科技学院 | A kind of automatic binding reinforcing bars location recognition method |
CN110097087B (en) * | 2019-04-04 | 2021-06-11 | 浙江科技学院 | Automatic reinforcing steel bar binding position identification method |
CN110070752A (en) * | 2019-05-29 | 2019-07-30 | 北京百度网讯科技有限公司 | One kind is parked appraisal procedure, device, electronic equipment and storage medium |
CN110293964A (en) * | 2019-06-25 | 2019-10-01 | 重庆长安汽车股份有限公司 | Automatic parking merges parking stall judgment method, system, computer readable storage medium and vehicle |
CN110414355A (en) * | 2019-06-27 | 2019-11-05 | 沈阳工业大学 | The right bit sky parking stall of view-based access control model and parking stall line detecting method during parking |
CN110390306A (en) * | 2019-07-25 | 2019-10-29 | 湖州宏威新能源汽车有限公司 | Detection method, vehicle and the computer readable storage medium of right angle parking stall |
CN110390306B (en) * | 2019-07-25 | 2021-08-10 | 湖州宏威新能源汽车有限公司 | Method for detecting right-angle parking space, vehicle and computer readable storage medium |
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 |
CN111311925A (en) * | 2020-01-21 | 2020-06-19 | 北京百度网讯科技有限公司 | Parking space detection method and device, electronic equipment, vehicle and storage medium |
US11594134B2 (en) | 2020-01-21 | 2023-02-28 | Apollo Intelligent Driving Technology (Beijing) Co., Ltd. | Parking space detection method and apparatus, electronic device, vehicle and storage medium |
CN113255405A (en) * | 2020-02-12 | 2021-08-13 | 广州汽车集团股份有限公司 | Parking space line identification method and system, parking space line identification device and storage medium |
CN111754468A (en) * | 2020-06-10 | 2020-10-09 | 深圳南方德尔汽车电子有限公司 | Parking space detection method and device based on projection, computer equipment and storage medium |
CN112052782B (en) * | 2020-08-31 | 2023-09-05 | 安徽江淮汽车集团股份有限公司 | Method, device, equipment and storage medium for recognizing parking space based on looking around |
CN112052782A (en) * | 2020-08-31 | 2020-12-08 | 安徽江淮汽车集团股份有限公司 | Around-looking-based parking space identification method, device, equipment and storage medium |
CN112172797B (en) * | 2020-09-27 | 2021-12-17 | 华人运通(上海)自动驾驶科技有限公司 | Parking control method, device, equipment and storage medium |
CN112172797A (en) * | 2020-09-27 | 2021-01-05 | 华人运通(上海)自动驾驶科技有限公司 | Parking control method, device, equipment and storage medium |
CN112201078A (en) * | 2020-09-30 | 2021-01-08 | 中国人民解放军军事科学院国防科技创新研究院 | Automatic parking space detection method based on graph neural network |
CN112201078B (en) * | 2020-09-30 | 2021-08-10 | 中国人民解放军军事科学院国防科技创新研究院 | Automatic parking space detection method based on graph neural network |
CN112036385B (en) * | 2020-11-04 | 2021-02-02 | 天津天瞳威势电子科技有限公司 | Library position correction method and device, electronic equipment and readable storage medium |
CN112036385A (en) * | 2020-11-04 | 2020-12-04 | 天津天瞳威势电子科技有限公司 | Library position correction method and device, electronic equipment and readable storage medium |
CN114475434B (en) * | 2020-11-11 | 2023-08-04 | 广州汽车集团股份有限公司 | Control and adjustment method for reversing outside rearview mirror, system and storage medium thereof |
CN114475434A (en) * | 2020-11-11 | 2022-05-13 | 广州汽车集团股份有限公司 | Control and adjustment method and system for reversing exterior rearview mirror and storage medium |
CN112455430A (en) * | 2020-12-02 | 2021-03-09 | 苏州优达斯汽车科技有限公司 | Method for detecting inclined parking spaces without parking space lines, parking method and parking system |
CN112598922A (en) * | 2020-12-07 | 2021-04-02 | 安徽江淮汽车集团股份有限公司 | Parking space detection method, device, equipment and storage medium |
CN112633152A (en) * | 2020-12-22 | 2021-04-09 | 深圳佑驾创新科技有限公司 | Parking space detection method and device, computer equipment and storage medium |
CN112633152B (en) * | 2020-12-22 | 2021-11-26 | 深圳佑驾创新科技有限公司 | Parking space detection method and device, computer equipment and storage medium |
CN112622885B (en) * | 2020-12-30 | 2022-03-22 | 惠州市德赛西威汽车电子股份有限公司 | Method and system for constructing inclined parking spaces based on ultrasonic radar |
CN112767425A (en) * | 2020-12-30 | 2021-05-07 | 智车优行科技(北京)有限公司 | Parking space detection method and device based on vision |
CN112622885A (en) * | 2020-12-30 | 2021-04-09 | 惠州市德赛西威汽车电子股份有限公司 | Method and system for constructing inclined parking spaces based on ultrasonic radar |
EP4033457A1 (en) * | 2021-01-20 | 2022-07-27 | Guangzhou Xiaopeng Autopilot Technology Co., Ltd. | Parking space detection method and apparatus |
CN112863242A (en) * | 2021-02-08 | 2021-05-28 | 广州小鹏自动驾驶科技有限公司 | Parking space detection method and device |
CN112863242B (en) * | 2021-02-08 | 2022-07-01 | 广州小鹏自动驾驶科技有限公司 | Parking space detection method and device |
CN112776797A (en) * | 2021-02-27 | 2021-05-11 | 重庆长安汽车股份有限公司 | Original parking space parking establishment method and system, vehicle and storage medium |
CN112983085A (en) * | 2021-04-30 | 2021-06-18 | 的卢技术有限公司 | Parking space line identification method based on vision |
CN113053164A (en) * | 2021-05-11 | 2021-06-29 | 吉林大学 | Parking space identification method using look-around image |
CN113311437A (en) * | 2021-06-08 | 2021-08-27 | 安徽域驰智能科技有限公司 | Method for improving angular point position accuracy of vehicle-mounted radar positioning side parking space |
CN113822156A (en) * | 2021-08-13 | 2021-12-21 | 北京易航远智科技有限公司 | Parking space detection processing method and device, electronic equipment and storage medium |
CN113799769A (en) * | 2021-09-28 | 2021-12-17 | 北京经纬恒润科技股份有限公司 | Detection method and device for parking space identification precision and automatic driving vehicle |
CN113885532A (en) * | 2021-11-11 | 2022-01-04 | 江苏昱博自动化设备有限公司 | Unmanned floor truck control system of barrier is kept away to intelligence |
CN115206130A (en) * | 2022-07-12 | 2022-10-18 | 合众新能源汽车有限公司 | Parking space detection method, system, terminal and storage medium |
CN115148047A (en) * | 2022-07-25 | 2022-10-04 | 中汽创智科技有限公司 | Parking space detection method and device |
Also Published As
Publication number | Publication date |
---|---|
CN109435942B (en) | 2024-04-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109435942A (en) | A kind of parking stall line parking stall recognition methods and device based on information fusion | |
CN107738612B (en) | Automatic parking space detection and identification system based on panoramic vision auxiliary system | |
CN106952308B (en) | Method and system for determining position of moving object | |
CN106295560B (en) | Lane keeping method based on vehicle-mounted binocular camera and segmented PID control | |
CN104657735B (en) | Method for detecting lane lines, system, lane departure warning method and system | |
JP6670071B2 (en) | Vehicle image recognition system and corresponding method | |
CN111563412B (en) | Rapid lane line detection method based on parameter space voting and Bessel fitting | |
JP4714104B2 (en) | Object tilt detection device | |
EP2757527B1 (en) | System and method for distorted camera image correction | |
CN107392103A (en) | The detection method and device of road surface lane line, electronic equipment | |
CN101281022A (en) | Method for measuring vehicle distance based on single eye machine vision | |
EP3594902B1 (en) | Method for estimating a relative position of an object in the surroundings of a vehicle and electronic control unit for a vehicle and vehicle | |
CN106250816A (en) | A kind of Lane detection method and system based on dual camera | |
Huang et al. | Tightly-coupled LIDAR and computer vision integration for vehicle detection | |
CN103593671A (en) | Wide-range lane line vision inspection method based on collaboration of three cameras | |
JP5188429B2 (en) | Environment recognition device | |
CN105059190A (en) | Vision-based automobile door-opening bump early-warning device and method | |
CN110992424B (en) | Positioning method and system based on binocular vision | |
JP4956099B2 (en) | Wall detector | |
CN114495066A (en) | Method for assisting backing | |
Wang et al. | Lane detection based on two-stage noise features filtering and clustering | |
Jung et al. | Stereo vision-based forward obstacle detection | |
Saleem et al. | Effects of ground manifold modeling on the accuracy of stixel calculations | |
Tian et al. | Vision based lane detection for active security in intelligent vehicle | |
JP4847303B2 (en) | Obstacle detection method, obstacle detection program, and obstacle detection apparatus |
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 |