CN109284731B - Parking space type identification method for inclined parking space of automatic parking system - Google Patents

Parking space type identification method for inclined parking space of automatic parking system Download PDF

Info

Publication number
CN109284731B
CN109284731B CN201811189462.7A CN201811189462A CN109284731B CN 109284731 B CN109284731 B CN 109284731B CN 201811189462 A CN201811189462 A CN 201811189462A CN 109284731 B CN109284731 B CN 109284731B
Authority
CN
China
Prior art keywords
parking space
vehicle
parking
space
type
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.)
Active
Application number
CN201811189462.7A
Other languages
Chinese (zh)
Other versions
CN109284731A (en
Inventor
姜武华
辛鑫
谢有浩
田博
陈无畏
赵林峰
徐礼伟
高凯旋
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.)
Hefei University of Technology
Original Assignee
Hefei University of Technology
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 Hefei University of Technology filed Critical Hefei University of Technology
Priority to CN201811189462.7A priority Critical patent/CN109284731B/en
Publication of CN109284731A publication Critical patent/CN109284731A/en
Application granted granted Critical
Publication of CN109284731B publication Critical patent/CN109284731B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
    • G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
    • G06V20/586—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of parking space
    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/60—Type of objects
    • G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
    • G06V20/63—Scene text, e.g. street names
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/60—Type of objects
    • G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
    • G06V20/625—License plates
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V2201/00—Indexing scheme relating to image or video recognition or understanding
    • G06V2201/08—Detecting or categorising vehicles

Abstract

The invention discloses a parking space type identification method for an inclined parking space of an automatic parking system. The parking space type identification method is used for automatically identifying the parking space type of an inclined parking space between a first parking space vehicle and a second parking space vehicle when the vehicle to be parked runs along the direction from the first parking space vehicle to the second parking space vehicle. The parking space type identification method comprises the following steps: determining a reference object; collecting data; analyzing the data; and identifying the type of the parking space. The method can effectively identify the parking space type of the inclined parking space in the initial garage searching stage of automatic parking, solve the problem of parking loss of the existing automatic parking system in the inclined parking space, and improve the intellectualization of parking space identification of the automatic parking system. The invention also discloses a parking method of the inclined parking space of the automatic parking system by adopting the parking space type identification method and a parking space type identification device of the inclined parking space for the automatic parking system by adopting the parking space type identification method.

Description

Parking space type identification method for inclined parking space of automatic parking system
Technical Field
The invention relates to the technical field of automatic parking, in particular to a parking space type identification method for an inclined parking space of an automatic parking system, a parking method for the inclined parking space of the automatic parking system adopting the parking space type identification method, and a parking space type identification device for the inclined parking space of the automatic parking system adopting the parking space type identification method.
Background
In recent years, the contradiction between the continuous increase of the automobile keeping quantity and the insufficient parking space in China is increasingly prominent. The parking difficulty becomes a problem to be solved urgently. Under the large background of the rapid development of the unmanned technology, an intelligent automatic parking system is indispensable.
The automatic parking technology is a key component of the unmanned automobile technology, and the parking space identification is the key and difficult point of the automatic parking system. Along with the industrialization process of the automatic parking technology, the requirement for parking space identification intellectualization is higher and higher.
The existing automatic parking system carries parallel parking and vertical parking, but automatic parking of inclined parking spaces is not seen. In order to solve the problem of recognition of the oblique parking spaces and the defect of oblique parking in the automatic parking system, it is necessary to provide a parking space type recognition method for the oblique parking spaces in the initial garage searching stage of automatic parking.
Disclosure of Invention
In order to solve the technical problem that the traditional automatic parking system cannot realize automatic parking of the inclined parking spaces, the invention provides a parking space type identification method for the inclined parking spaces of the automatic parking system, a parking method for the inclined parking spaces of the automatic parking system by adopting the parking space type identification method, and a parking space type identification device for the inclined parking spaces of the automatic parking system by adopting the parking space type identification method.
In order to achieve the purpose, the invention adopts the following technical scheme:
a space type identifying method for a diagonal space of an automatic parking system for automatically identifying a space type of the diagonal space between a first space vehicle and a second space vehicle when a vehicle to be parked travels in a direction from the first space vehicle to the second space vehicle, the space type identifying method comprising the steps of:
firstly, determining a reference object
Determining an initial position of the vehicle to be parked, the initial position being defined as: when the parking place type identification method is started, the position of the vehicle to be parked is located;
secondly, data acquisition
Acquiring the running distance of the vehicle to be parked in real time in the running process of the vehicle to be parked;
the said is to be treatedWhen a parking vehicle drives to the first parking space vehicle, acquiring the lateral distance Y from one side of the vehicle body of the vehicle to be parked to the first parking space vehicle in real time11；
When the vehicle to be parked drives to the second parking space vehicle, the lateral distance Y from one side of the vehicle body of the vehicle to be parked to the second parking space vehicle is collected in real time21；
Analyzing data
And (3) judging: the method comprises the steps that firstly, a license plate of the first parking space vehicle appears, then a front wheel of the first parking space vehicle appears, or firstly, the front wheel of the first parking space vehicle appears, then the license plate of the first parking space vehicle appears;
judging the lateral distance Y11Whether the distance is within a preset first lateral distance range or not is judged, if yes, the current running distance X of the vehicle to be parked is recorded11Thereby forming a plurality of sets of data (X)11，Y11) In said plurality of sets of data (X)11，Y11) To find out the lateral distance Y11The data set with the minimum value is used as the coordinate point A of the first vehicle position vehicle1；
When the front wheel of the first parking space vehicle appears, recording the current running distance X of the vehicle to be parked12And the current lateral distance Y12Definition of (X)12，Y12) Is a coordinate point B of the first parking space vehicle1；
The license plate of the second vehicle position appears first, then the front wheel of the second vehicle position appears, or the front wheel of the license plate of the second vehicle position appears first, then the license plate of the second vehicle position appears;
judging the lateral distance Y21Whether the distance is within a preset second lateral distance range or not is judged, if yes, the current running distance X of the vehicle to be parked is recorded21Thereby forming a plurality of sets of data (X)21，Y21) In said plurality of sets of data (X)21，Y21) To find out the lateral distance Y21The data set with the minimum value is used as the coordinate point A of the first vehicle position vehicle2；
When the front wheel of the vehicle at the second parking space appears, recording the current running distance X of the vehicle to be parked22And the current lateral distance Y22Definition of (X)22，Y22) As a coordinate point B of the second space vehicle2；
Calculating a lateral distance W of the first and second space vehiclesP，WP＝X21-X11When the license plate of the first parking space vehicle appears first and then the front wheel of the first parking space vehicle appears, the parking space angle α of the first parking space vehicle is calculated1，
Figure GDA0002407958140000031
When the license plate of the second vehicle position appears first and then the front wheel of the second vehicle position appears later, the parking space angle α of the second vehicle position is calculated2，
Figure GDA0002407958140000032
Fourthly, identifying the type of the parking space
According to α1、α2、WPAnd judging the parking space type of the inclined parking space.
As a further improvement of the above solution, the parking space types include:
if 25 < α1＜35，25＜α2< 35, and WPIf the parking space is more than 5.5m, the parking space type is 30-degree inclined parking space, and if the parking space is more than 25 and less than α1＜35，25＜α2< 35, and WPIf the parking space is less than 5.5m, the parking space is invalid, and the parking space is prompted to be continuously searched;
if 40 < α1＜50，40＜α2< 50, and WPIf the parking space is more than 5.5m, the parking space type is a 45-degree inclined parking space, and if the parking space type is more than 40 and less than α1＜50，40＜α2< 50, and WPIf the parking space is less than 5.5m, the parking space is invalid, and the parking space is prompted to be continuously searched;
if 55 < α1＜65，55＜α2< 65, and WPIf the parking space is more than 5.5m, the parking space type is 60-degree inclined parking space, and if the parking space is more than 55 and less than α1＜65，55＜α2< 65, and WPIf the parking space is less than 5.5m, the parking space is invalid, and the parking space is prompted to be continuously searched;
if 115 < α1＜125，115＜α2< 125 and WPIf the parking space is more than 5.5m, the parking space type is 120-degree inclined parking space, and if the parking space is more than 115 and less than α1＜125，115＜α2< 125, and WPIf the parking space is less than 5.5m, the parking space is invalid, and the parking space is prompted to be continuously searched;
if 130 < α1＜140，130＜α2< 140, and WPIf the parking space is more than 5.5m, the parking space type is 135-degree inclined parking space, for example, 130 is less than α1＜140，130＜α2< 140, and WPIf the parking space is less than 5.5m, the parking space is invalid, and the parking space is prompted to be continuously searched;
if 145 < α1＜155，145＜α2< 155, and WPIf the parking space is more than 5.5m, the parking space type is 150-degree inclined parking space, and if 145 is more than α1＜155，145＜α2< 155, and WPIf the parking space is less than 5.5m, the parking space is invalid, and the parking space is prompted to be continuously searched.
As a further improvement of the above solution, when the vehicle to be parked drives towards the first parking space vehicle, the image of the first parking space vehicle is acquired in real time to form a continuous first image set; judging the continuity of the first image set: the method comprises the steps of firstly displaying a license plate of the first vehicle position, then displaying front wheels of the first vehicle position, or firstly displaying the front wheels of the first vehicle position, and then displaying the license plate of the first vehicle position.
As a further improvement of the above scheme, when the vehicle to be parked drives towards the second vehicle location, the image of the second vehicle location is acquired in real time to form a continuous second image set; and judging the continuity of the second image set: the license plate of the second vehicle position appears first, the front wheel of the second vehicle position appears later, or the front wheel of the second vehicle position appears first and the license plate of the second vehicle position appears later.
And further, the information of the front wheels and the license plate of the vehicle in the parking space is collected in real time through a camera arranged on the vehicle to be parked.
As a further improvement of the above solution, when the front wheel of the first space vehicle appears first and then the license plate of the first space vehicle appears, the space angle α of the first space vehicle is calculated2，
Figure GDA0002407958140000041
As a further improvement of the above solution, when the front wheel of the second space vehicle appears first and the license plate of the second space vehicle appears later, the space angle α of the second space vehicle is calculated2，
Figure GDA0002407958140000051
As a further improvement of the scheme, the driving distance of the vehicle to be parked is acquired in real time through a wheel speed sensor, and the lateral distance from one side of the vehicle body of the vehicle to be parked to the vehicle in the parking space is acquired through an ultrasonic sensor.
As a further improvement of the scheme, the lateral distance of the vehicle corresponding to the corresponding parking space is collected once every other preset interval of the driving distance.
As a further improvement of the above solution, the distance X is traveled11As abscissa, by said lateral distance Y11Is ordinate, and is based on sets of data (X)11，Y11) Establishing a first horizontal and vertical coordinate lookup table, and finding out the multiple data sets (X) according to the first horizontal and vertical coordinate lookup table11，Y11) Finding out corresponding running distance according to the lateral distance of the minimum value, thereby obtaining a coordinate point A1；
By a distance X of travel12As abscissa, by said lateral distance Y12Is ordinate, and is based on sets of data (X)21，Y21) Establishing a second horizontal and vertical coordinate lookup table, and finding out the multiple groups of data according to the second horizontal and vertical coordinate lookup tableGroup (X)21，Y21) Finding out corresponding running distance according to the lateral distance of the minimum value, thereby obtaining a coordinate point A2。
The invention also provides a parking method of the inclined parking space of the automatic parking system, which comprises the following steps:
starting an automatic parking system, and identifying the parking space type of an inclined parking space by adopting the arbitrary parking space type identification method for the inclined parking space of the automatic parking system, wherein different parking space types correspond to different parking programs;
and calling a corresponding parking program according to the recognized parking space type.
The present invention also provides a parking space type recognition apparatus for an inclined parking space of an automatic parking system, the parking space type recognition apparatus comprising:
a determine reference module for determining a reference;
the data acquisition module is used for acquiring data;
an analysis data module for analyzing data;
the parking place type identification module is used for identifying the type of a parking place;
the method for identifying the parking space type of the inclined parking space of the automatic parking system comprises the steps of determining a reference object, collecting data, analyzing data and identifying the parking space type.
Compared with the prior art, the method can effectively identify the parking space type of the inclined parking space in the initial garage searching stage of automatic parking, solve the problem of parking loss of the existing automatic parking system in the inclined parking space, and improve the intellectualization of the parking space identification of the automatic parking system.
Drawings
Fig. 1 is a parking schematic diagram of a method for parking a slant parking space in an automatic parking system according to the present invention.
Fig. 2 is a flowchart of a parking method for a diagonal parking space of the automatic parking system according to the present invention, which employs a parking space type recognition method for a diagonal parking space of the automatic parking system.
Fig. 3 is a schematic diagram of the detectable effective region of the ultrasonic sensor in the method for identifying the type of the inclined parking space of the automatic parking system according to the present invention.
Fig. 4 shows two typical tilted parking space plane models.
FIG. 5 is a flowchart of a parking space type recognition method of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention.
The invention discloses a parking space type identification method for an inclined parking space of an automatic parking system, which is used for automatically identifying the parking space type of the inclined parking space between a first parking space vehicle and a second parking space vehicle when a vehicle to be parked runs along the direction from the first parking space vehicle to the second parking space vehicle. The parking space type identification method can be applied to an automatic parking system, and when the automatic parking system realizes parking in an inclined parking space, the adopted inclined parking space parking method comprises the following steps: starting an automatic parking system, and identifying the parking space types of the inclined parking spaces, wherein different parking space types correspond to different parking programs; and calling a corresponding parking program according to the recognized parking space type. When the parking space type is identified, the parking space type identification method can be adopted. As shown in fig. 1, when a vehicle to be parked travels along a direction from a first space vehicle I to a second space vehicle II, it is desired to automatically identify a space type of an inclined space between the first space vehicle and the second space vehicle and automatically park in a target space.
Referring to fig. 2, the parking space type identification method of the present invention includes the following steps.
Firstly, determining a reference object
Determining an initial position of the vehicle to be parked.
The initial position may be defined as: and when the parking space type identification method is started, the position of the vehicle to be parked is located.
Secondly, data acquisition
Data acquisition in this embodiment, there are three main aspects.
On the first hand, in the running process of the vehicle to be parked, the running distance of the vehicle to be parked is collected in real time. The driving distance of the vehicle to be parked can be acquired in real time through a wheel speed sensor, and the wheel speed sensor can be installed on two rear wheels of the vehicle to be parked.
In a second aspect, when the vehicle to be parked drives towards the first parking space vehicle, the lateral distance Y from one side of the vehicle body of the vehicle to be parked to the first parking space vehicle is collected in real time11。
In a third aspect, when the vehicle to be parked drives towards the vehicle at the second parking space, the lateral distance Y from one side of the vehicle body of the vehicle to be parked to the vehicle at the second parking space is acquired in real time21。
The device comprises a front wheel, a rear wheel, an ultrasonic sensor, a front wheel cover, a parking space and a parking space, wherein the ultrasonic sensor is used for acquiring the lateral distance from one side of the vehicle body of the vehicle to be parked to the parking space, and the ultrasonic sensor can be arranged on the wheel cover of the front wheel. And meanwhile, the lateral distance of the vehicle corresponding to the corresponding parking space is collected once every other preset interval of the driving distance. The preset interval can be set according to the requirements of actual conditions, for example, the running distance of 80mm, the lateral distance of the corresponding parking space vehicle can be collected once.
Analyzing data
(1) And (3) judging: the license plate of the first parking space vehicle appears first, then the front wheel of the first parking space vehicle appears (the front wheel is close to the self vehicle, and the same is true below), or the front wheel of the first parking space vehicle appears first, then the license plate of the first parking space vehicle appears.
The judging method can adopt the following steps:
when the vehicle to be parked drives to the first parking space vehicle, acquiring images of the first parking space vehicle in real time to form a continuous first image set;
judging the continuity of the first image set: the method comprises the steps of firstly displaying a license plate of the first vehicle position, then displaying front wheels of the first vehicle position, or firstly displaying the front wheels of the first vehicle position, and then displaying the license plate of the first vehicle position.
The first image set can be acquired through a camera arranged on the vehicle to be parked, and information about front wheels and license plates of the vehicle in the parking space can be acquired in real time.
(2) Judging the lateral distance Y11Whether the distance is within a preset first lateral distance range or not is judged, if yes, the current running distance X of the vehicle to be parked is recorded11Thereby forming a plurality of sets of data (X)11，Y11) In said plurality of sets of data (X)11，Y11) To find out the lateral distance Y11The data set with the minimum value is used as the coordinate point A of the first vehicle position vehicle1。
The first lateral distance range may be set according to actual conditions, and is, in this embodiment, between 200mm and 2500 mm.
(3) When the front wheel of the first parking space vehicle appears, recording the current running distance X of the vehicle to be parked12And the current lateral distance Y12Definition of (X)12，Y12) For a first position vehicle, i.e. coordinate point B1。
(4) And (3) judging: the license plate of the second vehicle position appears first, the front wheel of the second vehicle position appears later, or the front wheel of the second vehicle position appears first and the license plate of the second vehicle position appears later.
The judging method can adopt the following steps:
when the vehicle to be parked drives to the second parking space vehicle, acquiring images of the second parking space vehicle in real time to form a continuous second image set;
and judging the continuity of the second image set: the license plate of the second vehicle position appears first, the front wheel of the second vehicle position appears later, or the front wheel of the second vehicle position appears first and the license plate of the second vehicle position appears later.
The acquisition of the second image set can also acquire information about the front wheels and license plates of the vehicle in the parking space in real time through a camera mounted on the vehicle to be parked.
(5) Judging the lateral distance Y21Whether the distance is within a preset second lateral distance range or not is judged, if yes, the current running distance X of the vehicle to be parked is recorded21Thereby forming a plurality of sets of data (X)21，Y21) In said plurality of sets of data (X)21，Y21) To find out the lateral distance Y21The data set with the minimum value is used as the coordinate point A of the first vehicle position vehicle2。
(6) When the front wheel of the vehicle at the second parking space appears, recording the current running distance X of the vehicle to be parked22And the current lateral distance Y22Definition of (X)22，Y22) Coordinate point B of second-place vehicle2。
(7) Calculating a lateral distance W of the first and second space vehiclesP，WP＝X21-X11When the license plate of the first parking space vehicle appears first and then the front wheel of the first parking space vehicle appears, the parking space angle α of the first parking space vehicle is calculated1，
Figure GDA0002407958140000091
It should be noted that, when the front wheel of the first parking space vehicle appears first and then the license plate of the first parking space vehicle appears, the parking space angle α of the first parking space vehicle is calculated1，
Figure GDA0002407958140000092
(8) When the license plate of the second vehicle position appears first and then the front wheel of the second vehicle position appears later, the parking space angle α of the second vehicle position is calculated2，
Figure GDA0002407958140000093
It should be noted that, when the front wheel of the second space vehicle appears first and then the license plate of the second space vehicle appears, the space angle α of the second space vehicle is calculated2，
Figure GDA0002407958140000101
Fourthly, identifying the type of the parking space
According to α1、α2、WPAnd judging the parking space types of the inclined parking spaces, wherein the inclined parking space types can be divided into six types, namely 30-degree inclined parking spaces, 45-degree inclined parking spaces, 60-degree inclined parking spaces, 120-degree inclined parking spaces, 135-degree inclined parking spaces and 150-degree inclined parking spaces, and can be divided into more types according to actual conditions.
(1) If 25 < α1＜35，25＜α2< 35, and WPIf the parking space is more than 5.5m, the parking space type is 30-degree inclined parking space, and if the parking space is more than 25 and less than α1＜35，25＜α2< 35, and WPIf the parking space is less than 5.5m, the parking space is invalid, and the parking space is prompted to be continuously searched;
(2) if 40 < α1＜50，40＜α2< 50, and WPIf the parking space is more than 5.5m, the parking space type is a 45-degree inclined parking space, and if the parking space type is more than 40 and less than α1＜50，40＜α2< 50, and WPIf the parking space is less than 5.5m, the parking space is invalid, and the parking space is prompted to be continuously searched;
(3) if 55 < α1＜65，55＜α2< 65, and WPIf the parking space is more than 5.5m, the parking space type is 60-degree inclined parking space, and if the parking space is more than 55 and less than α1＜65，55＜α2< 65, and WPIf the parking space is less than 5.5m, the parking space is invalid, and the parking space is prompted to be continuously searched;
(4) if 115 < α1＜125，115＜α2< 125 and WPIf the parking space is more than 5.5m, the parking space type is 120-degree inclined parking space, and if the parking space is more than 115 and less than α1＜125，115＜α2< 125, and WPIf the parking space is less than 5.5m, the parking space is invalid, and the parking space is prompted to be continuously searched;
(5) if it is not130＜α1＜140，130＜α2< 140, and WPIf the parking space is more than 5.5m, the parking space type is 135-degree inclined parking space, for example, 130 is less than α1＜140，130＜α2< 140, and WPIf the parking space is less than 5.5m, the parking space is invalid, and the parking space is prompted to be continuously searched;
(6) if 145 < α1＜155，145＜α2< 155, and WPIf the parking space is more than 5.5m, the parking space type is 150-degree inclined parking space, and if 145 is more than α1＜155，145＜α2< 155, and WPIf the parking space is less than 5.5m, the parking space is invalid, and the parking space is prompted to be continuously searched.
The parking space type identification method for the inclined parking space of the automatic parking system can be set into a software APP form, or a program installation package form and the like, and is displayed, and corresponding functional modules can be correspondingly set to form a corresponding parking space type identification device for the inclined parking space of the automatic parking system. In this embodiment, the parking space type recognition device includes:
a determine reference module for determining a reference;
the data acquisition module is used for acquiring data;
an analysis data module for analyzing data;
and the parking place type identification module is used for identifying the type of the parking place.
The reference object determination, the data collection, the data analysis and the parking space identification type are respectively the reference object determination, the data collection, the data analysis and the parking space identification type, and are not described in detail herein.
The present invention will be described in detail below.
Referring to fig. 3, according to the principle of detecting the distance by the ultrasonic sensor, when encountering a slope, the detectable effective range is limited, the effective area detected by the ultrasonic sensor is a shadow area, the angle of the ultrasonic sensor relative to the side of the vehicle body is slightly different according to the angle of the vehicle body
Figure GDA0002407958140000111
In the case of the increase in the number of,the detectable effective range will become smaller and smaller.
Referring to fig. 4, in order to simplify the problem, it is assumed that the vehicle advances along the positive direction of the x axis, the ultrasonic sensor and the camera detect the distance information and the information of the front wheels and the license plate in real time along the direction of the y axis, the parking space angle calculation formula 1 corresponds to the graph (a), and the parking space angle calculation formula 2 corresponds to the graph (b).
Referring to fig. 5, a flowchart of a parking space type identification method for an inclined parking space in an initial parking space searching stage of automatic parking is shown, wherein the method comprises the following steps:
1) starting an automatic parking system and entering an initial garage searching stage;
2) real-time collection of running distance information X of bicycle by wheel speed sensordistanceThe ultrasonic sensor collects the lateral distance Y once every 40msdistanceThe camera collects information of whether a vehicle at a parking space has front wheels and a license plate in real time;
3) when the front wheel is identified by the camera, the driving distance X at the moment is recordedB1Lateral distance YB1Plane model I car B as inclined parking space1Point coordinates; when the camera identifies the front wheel again, the driving distance X at the moment is recordedB2Lateral distance YB2Vehicle B as inclined parking space plane model II2Point coordinates;
4) when the detection distance value of the ultrasonic sensor reaches the effective area, namely Y is more than 200mmdistanceIf < 2500mm, the driving distance X at this time is recorded0Lateral distance Y0And storing them in predefined arrays X1 and Y1 respectively, i.e. making X1[0]＝X0，Y1[0]＝Y0(ii) a Accordingly, a horizontal and vertical coordinate lookup table is established, i.e. X1[ k [ ]]＝X1[k-1]+ deltaX when the distance X is traveleddistance＝X1[k]When it is, let Y1[ k]＝YdistanceWhere deltaX is a predefined fixed value, k is 1,2, …, 15; find the minimum value in the array Y1 and let YA1＝Y1[k]And corresponding to XA1＝X1[k]A car as an inclined parking space plane model I1Point coordinates; obtaining the inclined parking space plane model II vehicle A by the same method2Point coordinates;
5) if the license plate is recognized first and then recognizedIf the front wheels are distinguished, the angle α of the inclined parking space is calculated according to a formula 1, otherwise, the angle α of the inclined parking space is calculated according to a formula 2, wherein the formula 1 for calculating the angle of the inclined parking space is as follows:
Figure GDA0002407958140000121
formula 2 for calculating the angle of the inclined parking space is as follows:
Figure GDA0002407958140000122
6) calculation of A1And A2Transverse distance W of pointsP＝XA2-XA1；
7) According to the angle α of the inclined parking space I1II vehicle angle α2And WPJudging the parking space type of the inclined parking space;
8) calling a corresponding parking subprogram according to the parking space type of the inclined parking space; the inclined parking spaces are divided into six types including 30-degree inclined parking spaces, 45-degree inclined parking spaces, 60-degree inclined parking spaces, 120-degree inclined parking spaces, 135-degree inclined parking spaces and 150-degree inclined parking spaces:
if 25 < α1(α2) < 35 and WPIf the parking space is more than 5.5m, the parking space type is 30-degree inclined parking space, and if the parking space is more than 25 and less than α1(α2) < 35 and WPIf the parking space is less than 5.5m, the parking space is invalid, and the parking space is prompted to be continuously searched;
if 40 < α1(α2) < 50 and WPIf the parking space is more than 5.5m, the parking space type is a 45-degree inclined parking space, and if the parking space type is more than 40 and less than α1(α2) < 50 and WPIf the parking space is less than 5.5m, the parking space is invalid, and the parking space is prompted to be continuously searched;
if 55 < α1(α2) < 65 and WPIf the parking space is more than 5.5m, the parking space type is 60-degree inclined parking space, and if the parking space is more than 55 and less than α1(α2) < 65 and WPIf the parking space is less than 5.5m, the parking space is invalid, and the parking space is prompted to be continuously searched;
if 115 < α1(α2) < 125 and WPIf the parking space is more than 5.5m, the parking space type is 120-degree inclined parking space, for example, 25 is less than α1(α2) < 35 and WPIf the distance is less than 5.5m, then the vehicle is parkedIf the parking space is invalid, prompting to continue searching the parking space;
if 130 < α1(α2) < 140 and WPIf the parking space is more than 5.5m, the parking space type is 135-degree inclined parking space, for example, 130 is less than α1(α2) < 140 and WPIf the parking space is less than 5.5m, the parking space is invalid, and the parking space is prompted to be continuously searched;
if 145 < α1(α2) < 155 and WPIf the parking space is more than 5.5m, the parking space type is 150-degree inclined parking space, and if 145 is more than α1(α2) < 155 and WPIf the parking space is less than 5.5m, the parking space is invalid, and the parking space is prompted to be continuously searched;
9) and calling a corresponding parking subprogram according to the output parking space type.
Therefore, the parking space type of the inclined parking space in the initial garage searching stage of automatic parking can be effectively identified, the problem that the existing automatic parking system is lack of inclined parking space in parking is solved, and the intellectualization of parking space identification of the automatic parking system is improved.
Those of ordinary skill in the art will understand that: all or a portion of the steps of implementing the above-described method embodiments may be performed by hardware associated with program instructions. The program may be stored in a computer-readable storage medium. When executed, the program performs steps comprising the method embodiments described above; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.

Claims (10)

1. A space type identifying method for an oblique space of an automatic parking system, for automatically identifying a space type of the oblique space between a first space vehicle and a second space vehicle when a vehicle to be parked travels along a direction from the first space vehicle to the second space vehicle, characterized in that: the parking space type identification method comprises the following steps:
firstly, determining a reference object
Determining an initial position of the vehicle to be parked, the initial position being defined as: when the parking place type identification method is started, the position of the vehicle to be parked is located;
secondly, data acquisition
Acquiring the running distance of the vehicle to be parked in real time in the running process of the vehicle to be parked;
when the vehicle to be parked drives to the first parking space vehicle, acquiring the lateral distance Y from one side of the vehicle body of the vehicle to be parked to the first parking space vehicle in real time11；
When the vehicle to be parked drives to the second parking space vehicle, the lateral distance Y from one side of the vehicle body of the vehicle to be parked to the second parking space vehicle is collected in real time21；
Analyzing data
And (3) judging: the method comprises the steps that firstly, a license plate of the first parking space vehicle appears, then a front wheel of the first parking space vehicle appears, or firstly, the front wheel of the first parking space vehicle appears, then the license plate of the first parking space vehicle appears;
judging the lateral distance Y11Whether the distance is within a preset first lateral distance range or not is judged, if yes, the current running distance X of the vehicle to be parked is recorded11Thereby forming a plurality of sets of data (X)11，Y11) In said plurality of sets of data (X)11，Y11) To find out the lateral distance Y11The data set with the minimum value is used as the coordinate point A of the first vehicle position vehicle1；
When the front wheel of the first parking space vehicle appears, recording the current running distance X of the vehicle to be parked12And the current lateral distance Y12Definition of (X)12，Y12) Is a stand forCoordinate point B of the first vehicle position vehicle1；
And (3) judging: the license plate of the second vehicle position appears first, then the front wheel of the second vehicle position appears, or the front wheel of the second vehicle position appears first, then the license plate of the second vehicle position appears;
judging the lateral distance Y21Whether the distance is within a preset second lateral distance range or not is judged, if yes, the current running distance X of the vehicle to be parked is recorded21Thereby forming a plurality of sets of data (X)21，Y21) In said plurality of sets of data (X)21，Y21) To find out the lateral distance Y21The data set with the minimum value is used as the coordinate point A of the first vehicle position vehicle2；
When the front wheel of the vehicle at the second parking space appears, recording the current running distance X of the vehicle to be parked22And the current lateral distance Y22Definition of (X)22，Y22) As a coordinate point B of the second space vehicle2；
Calculating a lateral distance W of the first and second space vehiclesP，WP＝X21-X11When the license plate of the first parking space vehicle appears first and then the front wheel of the first parking space vehicle appears, the parking space angle α of the first parking space vehicle is calculated1，
Figure FDA0002407958130000021
When the license plate of the second vehicle position appears first and then the front wheel of the second vehicle position appears later, the parking space angle α of the second vehicle position is calculated2，
Figure FDA0002407958130000022
Fourthly, identifying the type of the parking space
According to α1、α2、WPAnd judging the parking space type of the inclined parking space.
2. The slot type recognition method for a diagonal slot of an automated parking system according to claim 1, wherein the slot type includes:
if 25 < α1＜35，25＜α2< 35, and WPIf the parking space is more than 5.5m, the parking space type is 30-degree inclined parking space, and if the parking space is more than 25 and less than α1＜35，25＜α2< 35, and WPIf the parking space is less than 5.5m, the parking space is invalid, and the parking space is prompted to be continuously searched;
if 40 < α1＜50，40＜α2< 50, and WPIf the parking space is more than 5.5m, the parking space type is a 45-degree inclined parking space, and if the parking space type is more than 40 and less than α1＜50，40＜α2< 50, and WPIf the parking space is less than 5.5m, the parking space is invalid, and the parking space is prompted to be continuously searched;
if 55 < α1＜65，55＜α2< 65, and WPIf the parking space is more than 5.5m, the parking space type is 60-degree inclined parking space, and if the parking space is more than 55 and less than α1＜65，55＜α2< 65, and WPIf the parking space is less than 5.5m, the parking space is invalid, and the parking space is prompted to be continuously searched;
if 115 < α1＜125，115＜α2< 125 and WPIf the parking space is more than 5.5m, the parking space type is 120-degree inclined parking space, and if the parking space is more than 115 and less than α1＜125，115＜α2< 125, and WPIf the parking space is less than 5.5m, the parking space is invalid, and the parking space is prompted to be continuously searched;
if 130 < α1＜140，130＜α2< 140, and WPIf the parking space is more than 5.5m, the parking space type is 135-degree inclined parking space, for example, 130 is less than α1＜140，130＜α2< 140, and WPIf the parking space is less than 5.5m, the parking space is invalid, and the parking space is prompted to be continuously searched;
if 145 < α1＜155，145＜α2< 155, and WPIf the parking space is more than 5.5m, the parking space type is 150-degree inclined parking space, and if 145 is more than α1＜155，145＜α2< 155, and WPIf the parking space is less than 5.5m, the parking space is invalid, and the parking space is prompted to be continuously searched.
3. The slot type recognition method for a diagonal slot of an automated parking system according to claim 1,
when the vehicle to be parked drives to the first parking space vehicle, acquiring images of the first parking space vehicle in real time to form a continuous first image set; judging the continuity of the first image set: the method comprises the steps that firstly, a license plate of the first parking space vehicle appears, then a front wheel of the first parking space vehicle appears, or firstly, the front wheel of the first parking space vehicle appears, then the license plate of the first parking space vehicle appears;
when the vehicle to be parked drives to the second parking space vehicle, acquiring images of the second parking space vehicle in real time to form a continuous second image set; and judging the continuity of the second image set: the license plate of the second vehicle position appears first, the front wheel of the second vehicle position appears later, or the front wheel of the second vehicle position appears first and the license plate of the second vehicle position appears later.
4. The method of claim 1, wherein the parking space angle α of the first parking space vehicle is calculated when the front wheels of the first parking space vehicle appear first and the license plate of the first parking space vehicle appears later1，
Figure FDA0002407958130000031
5. The method for identifying the type of a parking space in an inclined parking space of an automatic parking system as claimed in claim 1 or 4, wherein the parking space angle α of the second space vehicle is calculated when the front wheels of the second space vehicle appear first and the license plate of the second space vehicle appears later2，
Figure FDA0002407958130000032
6. The method for identifying the type of a parking space of an inclined parking space of an automatic parking system as claimed in claim 1, wherein the driving distance of the vehicle to be parked is collected in real time by a wheel speed sensor, and the lateral distance from the side of the vehicle body of the vehicle to be parked to the vehicle in the parking space is collected by an ultrasonic sensor.
7. The slot type recognition method for a diagonal slot of an automated parking system as claimed in claim 1, wherein the lateral distance corresponding to the vehicle of the corresponding slot is collected once every predetermined interval of the driving distance.
8. The slot type recognition method for a skewed slot in an automated parking system of claim 1, wherein the distance X is traveled11As abscissa, by said lateral distance Y11Is ordinate, and is based on sets of data (X)11，Y11) Establishing a first horizontal and vertical coordinate lookup table, and finding out the multiple data sets (X) according to the first horizontal and vertical coordinate lookup table11，Y11) Finding out corresponding running distance according to the lateral distance of the minimum value, thereby obtaining a coordinate point A1；
By a distance X of travel12As abscissa, by said lateral distance Y12Is ordinate, and is based on sets of data (X)21，Y21) Establishing a second horizontal and vertical coordinate lookup table, and finding out the multiple data sets (X) according to the second horizontal and vertical coordinate lookup table21，Y21) Finding out corresponding running distance according to the lateral distance of the minimum value, thereby obtaining a coordinate point A2。
9. A method for parking an inclined parking space of an automatic parking system comprises the following steps:
starting an automatic parking system, and identifying the parking space types of the inclined parking spaces, wherein different parking space types correspond to different parking programs;
calling a corresponding parking program according to the recognized parking space type;
it is characterized in that the preparation method is characterized in that,
when identifying the parking space type, the parking space type identification method for the skewed parking space of the automatic parking system according to any one of claims 1 to 8 is used.
10. A parking space type recognition device for a skewed parking space of an automatic parking system, the parking space type recognition device comprising:
a determine reference module for determining a reference;
the data acquisition module is used for acquiring data;
an analysis data module for analyzing data;
the parking place type identification module is used for identifying the type of a parking place;
the method for identifying the type of the inclined parking space of the automatic parking system according to any one of claims 1 to 8 comprises the steps of determining a reference object, collecting data, analyzing data and identifying the type of the inclined parking space.
CN201811189462.7A 2018-10-12 2018-10-12 Parking space type identification method for inclined parking space of automatic parking system Active CN109284731B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811189462.7A CN109284731B (en) 2018-10-12 2018-10-12 Parking space type identification method for inclined parking space of automatic parking system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811189462.7A CN109284731B (en) 2018-10-12 2018-10-12 Parking space type identification method for inclined parking space of automatic parking system

Publications (2)

Publication Number Publication Date
CN109284731A CN109284731A (en) 2019-01-29
CN109284731B true CN109284731B (en) 2020-04-24

Family

ID=65177101

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811189462.7A Active CN109284731B (en) 2018-10-12 2018-10-12 Parking space type identification method for inclined parking space of automatic parking system

Country Status (1)

Country Link
CN (1) CN109284731B (en)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP7398196B2 (en) 2019-03-11 2023-12-14 フォルシアクラリオン・エレクトロニクス株式会社 Parking support device and parking support method
CN111114538B (en) * 2020-02-18 2021-11-05 威马智慧出行科技（上海）有限公司 Automatic parking, backing and warehousing parking space judgment method, electronic equipment and automobile
CN111361550B (en) * 2020-03-19 2021-11-30 奇瑞汽车股份有限公司 Parking space identification method and device and storage medium
CN111731275B (en) * 2020-06-30 2021-12-07 中国第一汽车股份有限公司 Automatic parking method and device for spatial oblique parking spaces, vehicle and storage medium

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107364442A (en) * 2017-06-23 2017-11-21 深圳市盛路物联通讯技术有限公司 A kind of automatic stop process and system

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105774655B (en) * 2016-03-11 2018-04-17 江苏大学 One kind tilts parking stall detection device and method
JP6644425B2 (en) * 2016-07-07 2020-02-12 アルパイン株式会社 Travel route generation device and travel route generation method
CN108254752B (en) * 2017-12-20 2020-03-27 广州汽车集团股份有限公司 Method and device for detecting inclined parking spaces and automatic parking method and system

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107364442A (en) * 2017-06-23 2017-11-21 深圳市盛路物联通讯技术有限公司 A kind of automatic stop process and system

Also Published As

Publication number Publication date
CN109284731A (en) 2019-01-29

Similar Documents

Publication Publication Date Title
CN109284731B (en) Parking space type identification method for inclined parking space of automatic parking system
CN109435942B (en) Information fusion-based parking space line and parking space recognition method and device
US8922394B2 (en) Apparatus and method for parking position display of vehicle
US9076047B2 (en) System and method for recognizing parking space line markings for vehicle
US9467645B2 (en) System and method for recognizing parking space line markings for vehicle
WO2015043510A1 (en) Lane line detection method and system, and method and system for lane deviation prewarning
US20140104422A1 (en) Apparatus and method for determining parking area
CN112349144B (en) Monocular vision-based vehicle collision early warning method and system
CN109871732B (en) Parking grid identification system and method thereof
US9104920B2 (en) Apparatus and method for detecting obstacle for around view monitoring system
CN110658539B (en) Vehicle positioning method, device, vehicle and computer readable storage medium
CN110889974B (en) Intelligent parking space identification method and device and automobile
CN112836633A (en) Parking space detection method and parking space detection system
CN109472251B (en) Object collision prediction method and device
CN112885108B (en) Vehicle change detection method and system on parking space based on deep learning algorithm
CN104902261A (en) Device and method for road surface identification in low-definition video streaming
CN108189626B (en) Tire pressure detection method and device, storage medium and automobile
CN110210324B (en) Road target rapid detection early warning method and system
EP3725626B1 (en) Automatic parking method and device, intelligent vehicle and computer storage medium
CN106874837B (en) Vehicle detection method based on video image processing
CN114067598B (en) Method and device for determining idle parking spaces
JP2018169924A (en) Learning data collection apparatus, learning data collection system, and learning data collection method
EP3726498B1 (en) Automatic parking method and device, intelligent vehicle and computer storage medium
JP2924063B2 (en) Image processing type traffic flow measurement device
CN112037536A (en) Vehicle speed measuring method and device based on video feature recognition

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant