CN113513985B - Optimization method and device for precision detection, electronic equipment and medium - Google Patents

Optimization method and device for precision detection, electronic equipment and medium Download PDF

Info

Publication number
CN113513985B
CN113513985B CN202110745559.7A CN202110745559A CN113513985B CN 113513985 B CN113513985 B CN 113513985B CN 202110745559 A CN202110745559 A CN 202110745559A CN 113513985 B CN113513985 B CN 113513985B
Authority
CN
China
Prior art keywords
track
coordinate data
coordinate
parking space
determining
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
CN202110745559.7A
Other languages
Chinese (zh)
Other versions
CN113513985A (en
Inventor
黄宇波
杨芷晴
钟辉强
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.)
Guangzhou Xiaopeng Motors Technology Co Ltd
Original Assignee
Guangzhou Xiaopeng Autopilot Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Guangzhou Xiaopeng Autopilot Technology Co Ltd filed Critical Guangzhou Xiaopeng Autopilot Technology Co Ltd
Priority to CN202110745559.7A priority Critical patent/CN113513985B/en
Publication of CN113513985A publication Critical patent/CN113513985A/en
Application granted granted Critical
Publication of CN113513985B publication Critical patent/CN113513985B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
    • G01B11/00—Measuring arrangements characterised by the use of optical techniques
    • G01B11/002—Measuring arrangements characterised by the use of optical techniques for measuring two or more coordinates
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
    • G01B11/00—Measuring arrangements characterised by the use of optical techniques
    • G01B11/14—Measuring arrangements characterised by the use of optical techniques for measuring distance or clearance between spaced objects or spaced apertures
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
    • G01B11/00—Measuring arrangements characterised by the use of optical techniques
    • G01B11/26—Measuring arrangements characterised by the use of optical techniques for measuring angles or tapers; for testing the alignment of axes
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/10—Internal combustion engine [ICE] based vehicles
    • Y02T10/40—Engine management systems

Abstract

The embodiment of the application provides an optimization method, device, electronic equipment and medium for precision detection, wherein the method comprises the following steps: when the vehicle runs, acquiring a first track and first coordinate data matched with a preset first coordinate system, and acquiring a second track and second coordinate data matched with a preset second coordinate system; the first coordinate data is used for identifying the angular point position of a preset physical parking space, and the second coordinate data is used for identifying the angular point position of a visual parking space matched with the physical parking space; determining a first local track in the first track and a second local track in the second track according to the first coordinate data; fitting the first local track and the second local track to convert the second coordinate data into third coordinate data; and comparing the first coordinate data with the third coordinate data to obtain the visual parking space precision. According to the method and the device, when the visual parking space detection precision is determined based on two different coordinate systems, the precision information accuracy can be improved.

Description

Optimization method and device for precision detection, electronic equipment and medium
Technical Field
The application relates to the technical field of automobiles, in particular to an optimization method and device for precision detection, electronic equipment and media.
Background
With the development of electric vehicle technology, more and more electric vehicles are equipped with an automatic parking function, and after the automatic parking function is started, the vehicle may determine a parking space based on different technologies.
In one implementation, a look-around visual detection (Around View Monitor, hereinafter AVM) system is provided in a vehicle, the AVM collecting environmental information of an area near the vehicle and outputting a visual parking spot for the collected environmental information, the vehicle being subsequently capable of automatically parking for the visual parking spot. The four corner points (rectangular end points) are contained in each visual parking space (a rectangle), and the precision of the four corner points actually determines the precision of the final parking position of the vehicle in the visual parking space.
Disclosure of Invention
In view of the foregoing, embodiments of the present application are presented to provide an optimization method, apparatus, electronic device, and medium for precision detection that overcomes or at least partially solves the foregoing problems.
In order to solve the above problems, an embodiment of the present application discloses an optimization method for precision detection, including:
when the vehicle runs, acquiring a first track and first coordinate data matched with a preset first coordinate system, and acquiring a second track and second coordinate data matched with a preset second coordinate system; the first coordinate data is used for identifying the angular point position of a preset physical parking space, and the second coordinate data is used for identifying the angular point position of a visual parking space matched with the physical parking space;
determining a first local track in the first track and a second local track in the second track according to the first coordinate data;
fitting the first local track and the second local track to convert the second coordinate data into third coordinate data;
and comparing the first coordinate data with the third coordinate data to obtain the visual parking space precision.
Optionally, the first coordinate system is an optical positioning coordinate system constructed based on a preset optical positioning system;
the second coordinate system is a vehicle coordinate system constructed based on the vehicle self-positioning.
Optionally, the vehicle is provided with a first positioning assembly; the method further comprises the steps of:
establishing an optical positioning system for the entity parking space;
constructing an optical positioning coordinate system corresponding to the optical positioning system;
the obtaining the first track and the first coordinate data matched with the preset first coordinate system comprises the following steps:
generating a first track according to the positions of the vehicles at the optical positioning coordinate system at all moments determined by the first positioning component;
and determining the position of the angular point of the entity parking space in the optical positioning coordinate system as first coordinate data.
Optionally, the vehicle is provided with a second positioning assembly; the method further comprises the steps of:
determining the position of the vehicle before running as an initial position;
constructing a vehicle coordinate system for the initial position;
the step of obtaining the second track and the second coordinate data matched with the preset second coordinate system comprises the following steps:
generating a second track by adopting the relative positions of the vehicles at all moments and the initial positions determined by the second positioning assembly;
collecting image data matched with the entity parking space;
and determining the position of the corner point of the visual parking space in the vehicle coordinate system as second coordinate data according to the position of the vehicle in the vehicle coordinate system and the image data.
Optionally, for any entity parking space, the first coordinate data includes: a first front-of-the-first back-of-the-first coordinate; the determining a first local track in the first track and a second local track in the second track according to the first coordinate data includes:
determining a target interval on a straight line where the first front-near coordinate and the first rear-near coordinate are located according to a preset length; the midpoint of the target interval is the midpoint of the first front-near coordinate and the first rear-near coordinate;
determining a first track in the target interval as a first local track;
and determining the part of the second track corresponding to the same moment as the first local track as the second local track.
Optionally, before the determining the first local track in the first track and the second local track in the second track according to the first coordinate data, the method further includes:
sequentially determining target entity parking spaces along the first track;
and aiming at the target entity parking space, executing the first local track in the first track and the second local track in the second track according to the first coordinate data.
Optionally, the second positioning assembly is one or more inertial sensors provided for the vehicle.
The application also discloses optimizing device of precision detection, include:
the data acquisition module is used for acquiring a first track and first coordinate data matched with a preset first coordinate system, and a second track and second coordinate data matched with a preset second coordinate system when the vehicle runs; the first coordinate data is used for identifying the angular point position of a preset physical parking space, and the second coordinate data is used for identifying the angular point position of a visual parking space matched with the physical parking space;
the local track determining module is used for determining a first local track in the first track and a second local track in the second track according to the first coordinate data;
the track fitting module is used for fitting the first local track and the second local track so as to convert the second coordinate data into third coordinate data;
and the precision information determining module is used for comparing the first coordinate data with the third coordinate data to obtain the precision of the visual parking space.
The application also discloses an electronic device, comprising: a processor, a memory and a computer program stored on the memory and capable of running on the processor, which when executed by the processor, implements the steps of the optimization method of accuracy detection as described above.
The application also discloses a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the optimization method of accuracy detection as described above.
Embodiments of the present application include the following advantages:
constructing a first coordinate system and a second coordinate system in different modes, and acquiring a first track and first coordinate data matched with the first coordinate system and a second track and second coordinate data matched with a second positioning coordinate in the running process of the vehicle; the first coordinate data is used for identifying the position of the corner point of the preset physical parking space based on the first coordinate system, and the second coordinate data is used for identifying the position of the corner point of the visual parking space corresponding to the physical parking space based on the second coordinate system; and respectively determining a first local track and a second local track in the first track and the second track aiming at the first coordinate data, fitting the first local track and the second local track to map the second coordinate data to the first coordinate system to obtain corresponding third coordinate data, and comparing the first data with the third data to obtain the precision of the visual parking space, wherein the precision of the visual parking space is used for representing the precision of the visual parking space relative to the corresponding entity parking space. Because the first local track and the second local track are determined pertinently based on the first coordinate data, the fitted parts of the first track and the second local track have higher fitting degree, so that the corresponding first coordinate data and third coordinate data have higher accuracy, the accuracy of vision parking space accuracy detection is improved, and the influence of errors of the first track or the second track on vision parking space accuracy determination is avoided.
Drawings
FIG. 1 is a flow chart of steps of an embodiment of an optimization method for accuracy detection of the present application;
FIG. 2 is a schematic diagram of a target interval of the present application;
FIG. 3 is a block diagram of an embodiment of an optimization apparatus for accuracy detection of the present application.
Detailed Description
In order that the above-recited objects, features and advantages of the present application will become more readily apparent, a more particular description of the invention briefly described above will be rendered by reference to specific embodiments that are illustrated in the appended drawings.
One of the core concepts of the embodiments of the present application is that a first local track and a second local track are determined pertinently based on first coordinate data, so that, in the fitted first track and second track, parts of the first local track and the second local track have higher fitting degree, so that corresponding first coordinate data and third coordinate data have higher accuracy, accuracy of visual parking space accuracy detection is improved, and influence of errors of the first track or the second track on visual parking space accuracy determination is avoided.
Referring to fig. 1, a flowchart illustrating steps of an embodiment of an optimization method for precision detection in the present application may specifically include the following steps:
step 101, when a vehicle runs, acquiring a first track and first coordinate data matched with a preset first coordinate system, and acquiring a second track and second coordinate data matched with a preset second coordinate system; the first coordinate data is used for identifying the angular point position of a preset physical parking space, and the second coordinate data is used for identifying the angular point position of a visual parking space matched with the physical parking space;
a plurality of physical parking spaces (for example, an indoor parking lot) can be divided in a region, the parking spaces on the ground are determined to be the physical parking spaces, the physical parking spaces are provided with parking space lines, the enveloping of the parking space lines forms the physical parking spaces, and the intersection points of the parking space lines are the corner points of the physical parking spaces.
The method comprises the steps of establishing a first coordinate system based on the physical parking space, detecting the positions of all angular points of the physical parking space, determining the positions of the angular points in the first coordinate system, obtaining first coordinate data, and taking the first coordinate data as a true value (also called as a standard value) of the angular point positions of the physical parking space. And marking the positions of all the moments in the running process of the vehicle by adopting a first coordinate system to obtain a first track.
And establishing a second coordinate system based on the self-positioning of the vehicle, and marking the positions of all moments in the running process of the vehicle by adopting the second coordinate system to obtain a second track.
The visual parking space is a virtual object corresponding to the physical parking space and is displayed in a digital image mode.
The vehicle is provided with an image acquisition component, and the image acquisition component can be an AVM system in the related art or a camera component positioned at two sides of the vehicle.
When the vehicle runs in the area containing the physical parking space, the image acquisition component can acquire the environment information of the position of the vehicle, the environment information contains the image data of the physical parking space, the image data is correspondingly processed, including but not limited to parking space feature extraction, the visual parking space corresponding to the physical parking space is obtained, and then the position of each corner point of the visual parking space is obtained as second coordinate data.
Step 102, determining a first local track in the first track and a second local track in the second track according to the first coordinate data;
and determining the first partial track which is estimated to be in a specified range of the first coordinate data in the first track and corresponds to any entity parking space, and determining the second partial track which is matched with the moment corresponding to the first partial track in the second track.
The specified range may be a distance section in a certain direction obtained based on the first coordinate data or an area obtained centering on a certain position obtained based on the first coordinate data.
Step 103, fitting the first local track and the second local track to convert the second coordinate data into third coordinate data;
the first local trajectory and the second local trajectory are fitted to map the second coordinate data to the same coordinate system as the first coordinate data. And obtaining third coordinate data matched with the second coordinate data based on the fitted first local track and the second local track, wherein the first coordinate data and the third coordinate data can be marked by adopting the same coordinate system.
And 104, comparing the first coordinate data with the third coordinate data to obtain the visual parking space precision.
The second coordinate data can be understood as a measured value relative to the first coordinate data for representing the true value, and the first coordinate data and the second coordinate data are compared and calculated to determine the matching degree of the visual parking space relative to the physical parking space, namely the accuracy of the visual parking space.
The first track and the second track respectively correspond to different coordinate systems, namely the first track and the second track are determined in different modes, third data matched with the second data are obtained by fitting the first track and the second track, and the visual parking space precision is obtained by comparing the first coordinate data with the third coordinate data.
In the embodiment of the application, a first coordinate system and a second coordinate system are constructed in different modes, and in the process of acquiring the running of the vehicle, a first track and first coordinate data matched with the first coordinate system, and a second track and second coordinate data matched with the second positioning coordinate are acquired; the first coordinate data is used for identifying the position of the corner point of the preset physical parking space based on the first coordinate system, and the second coordinate data is used for identifying the position of the corner point of the visual parking space corresponding to the physical parking space based on the second coordinate system; and respectively determining a first local track and a second local track in the first track and the second track aiming at the first coordinate data, fitting the first local track and the second local track to map the second coordinate data to the first coordinate system to obtain corresponding third coordinate data, and comparing the first data with the third data to obtain the precision of the visual parking space, wherein the precision of the visual parking space is used for representing the precision of the visual parking space relative to the corresponding entity parking space. Because the first local track and the second local track are determined pertinently based on the first coordinate data, the fitted parts of the first track and the second local track have higher fitting degree, so that the corresponding first coordinate data and third coordinate data have higher accuracy, the accuracy of vision parking space accuracy detection is improved, and the influence of errors of the first track or the second track on vision parking space accuracy determination is avoided.
In an optional embodiment of the present application, the first coordinate system is an optical positioning coordinate system constructed based on a preset optical positioning system;
the second coordinate system is a vehicle coordinate system constructed based on the vehicle self-positioning.
The first coordinate system is an optical positioning coordinate system constructed based on an optical positioning mode, and positions corresponding to the optical positioning coordinate system at all times in the running process of the vehicle are determined based on the optical positioning mode.
The second coordinate system is a vehicle coordinate system constructed based on the positioning of the vehicle, and the position corresponding to the vehicle coordinate system in the running process of the vehicle is determined based on the relative positions of the vehicle at all moments.
In an alternative embodiment of the present application, the method further comprises: establishing an optical positioning system for the entity parking space; constructing an optical positioning coordinate system corresponding to the optical positioning system;
the optical positioning system includes: and setting an optical positioner at the corner point of each physical parking space and an optical base station capable of communicating with the optical positioner of each physical parking space. And acquiring the relative positions of the optical positioners and the optical base station through the mutual communication of the optical base station and the optical positioners, and constructing an optical positioning coordinate system based on the relative positions.
The vehicle is provided with a first positioning assembly; the obtaining the first track and the first coordinate data matched with the preset first coordinate system comprises the following steps:
generating a first track according to the positions of the vehicles at the optical positioning coordinate system at all moments determined by the first positioning component; and determining the position of the angular point of the entity parking space in the optical positioning coordinate system as first coordinate data.
The vehicle is also provided with a first positioning component (for example, an optical positioner matched with the optical positioning system), the first positioning component is communicated with the optical base station, so that the position of the vehicle relative to the optical base station in the running process of the vehicle is determined, the position of the vehicle relative to the optical positioning coordinate system is obtained, and a first track is obtained based on the positions of the vehicle relative to the optical base station at all moments of the vehicle.
And determining the position of the entity parking space corner point relative to the optical base station through the relative position of the optical positioner and the optical base station, and marking the position of the entity parking space corner point through an optical positioning coordinate system to obtain first coordinate data.
In an alternative embodiment of the present application, the vehicle is provided with a second positioning assembly; the method further comprises the steps of: determining the position of the vehicle before running as an initial position; constructing a vehicle coordinate system for the initial position;
the second positioning component arranged in the vehicle can detect the running speed information (comprising the running direction and the running unit time distance) of the vehicle, the relative positions of the vehicle at all times can be determined according to the running speed information at all times, a vehicle coordinate system can be built based on the initial position before the vehicle runs, and the positions of the vehicle at all times after the vehicle starts running can be identified based on the vehicle coordinate system.
The second track and the second coordinate data matched with the preset second coordinate system in step 101 may be obtained by the following manner: generating a second track by adopting the relative positions of the vehicles at all moments and the initial positions determined by the second positioning assembly; collecting image data matched with the entity parking space; and determining the position of the corner point of the visual parking space in the vehicle coordinate system as second coordinate data according to the position of the vehicle in the vehicle coordinate system and the image data.
Since the second positioning component can be used for determining the relative position of each moment in the running process of the vehicle, the second track which can be identified by adopting the vehicle coordinate system is obtained through the initial position and the relative position of each moment of the vehicle to the initial position.
The image acquisition component in the vehicle can acquire image data of the entity parking space, image processing is carried out on the image data, the vision parking space can be determined, the relative positions of all angular points of the vision parking space and the vehicle can be further obtained, the positions of the angular points of the vision parking space in a vehicle coordinate system can be determined according to the relative positions of the angular points of the vision parking space and the vehicle, and second coordinate data can be obtained.
As an example, a controller area network (Controller Area Network, CAN) is provided in the vehicle, the CAN is connected to the first positioning component and the second positioning component, and the vehicle CAN receive the content output by the first positioning component and the second positioning component through the CAN and store the content in a customized DBC (CAN Database). The customized DBC correspondingly stores two messages, one coming from a first positioning component is an optical positioning coordinate system constructed according to the relative positioning relation between the signal transmitter and the optical base station, and the other coming from a second positioning component is a vehicle coordinate system constructed according to the vehicle. The customized CAN information is recorded by using the customized DBC, and the positioning based on two independent coordinate systems CAN be obtained at each signal sampling time, so that the track on the two coordinate systems CAN be obtained in the running process of the vehicle, and the method comprises the following steps: a first trajectory relative to the optical positioning coordinate system, and a second trajectory relative to the vehicle coordinate system.
In an optional embodiment of the present application, for any one of the physical parking spaces, the first coordinate data includes: a first front-of-the-first back-of-the-first coordinate; step 102 comprises: determining a target interval on a straight line where the first front-near coordinate and the first rear-near coordinate are located according to a preset length; the midpoint of the target interval is the midpoint of the first front-near coordinate and the first rear-near coordinate; determining a first track in the target interval as a first local track; and determining the part of the second track corresponding to the same moment as the first local track as the second local track.
The parking space (including but not limited to the solid parking space and the visual parking space) comprises four corner points, wherein the four corner points of the same parking space can be defined, two corner points which are close to the vehicle in the direction vertical to the direction of the vehicle are near corner points, two corner points which are far away from the vehicle are far corner points, and front corner points and rear corner points of two front corner points and rear corner points which are far away from the vehicle in the running direction of the vehicle are rear corner points, so that the four corner points are far front corner points, near rear corner points and far rear corner points. Accordingly, the coordinate data may include Near Front (NF) coordinates, far Front (FF) coordinates, near Rear (NR) coordinates, far Rear (FR) coordinates.
The midpoint of the first front-near coordinate and the first rear-near coordinate may be determined, and the midpoint is taken as a center, a preset length on a straight line where the first front-near coordinate and the first rear-near coordinate are located is determined as a target interval, where the target interval is used for defining a range on the straight line where the first front-near coordinate and the first rear-near coordinate are located in the first track and the second track. The part of the first track, which is matched with the target interval, is intercepted to be a first local track, and the positions of the first track and the second track correspond to time, so that the part of the second track, which is the same as the moment corresponding to each position of the first local track, can be intercepted to be a second local track, namely the first local track is determined through the target interval, and the second local track corresponding to the first local track is determined through the time dimension.
Referring to fig. 2, there is shown a schematic diagram of a target section of the present application, the first coordinate data including: first near front coordinate NF LT First near-rear coordinate NR LT 。
Determining a first near-front coordinate NF LT And a first near-rear coordinate NR LT The midpoint a between the two is 6 meters (m, metre) in preset length, and a target section is obtained according to the preset length and the midpoint a, wherein the target section length is 6 meters (namely the length of the line segment BC is 6 meters). In the first near-to-rear coordinate NR LT To the first near front coordinate NF LT The direction is the X-axis direction, the target section is a range 3 meters away from the midpoint a in the X-axis direction, and the portion of the first track within the target section is taken as the first local track 201.
The preset length of 6 meters is only illustrative, and the specific length of the preset length is limited in this application, and may be, for example, 5 meters, 5.5 meters, 6 meters, 6.5 meters, 7 meters, etc.
In an alternative embodiment of the present application, before the determining, according to the first coordinate data, a first local track in the first track and a second local track in the second track, the method further includes: sequentially determining target entity parking spaces along the first track; and aiming at the target entity parking space, executing the first local track in the first track and the second local track in the second track according to the first coordinate data.
In the above-mentioned area that contains entity parking stall, probably a plurality of entity parking stall, corresponding, the vehicle can gather the image data of a plurality of entity parking stall to corresponding a plurality of vision parking stall that obtains.
The accuracy of the visual parking space precision is improved by fitting the first local track and the second local track to each entity parking space one by one.
For example: at least the solid parking space a and the solid parking space b are distributed along the first track in sequence. When the visual parking space precision of the physical parking space a is detected, determining a first local track and a second local track according to the first coordinate data of the physical parking space a, and obtaining the visual parking space precision corresponding to the physical parking space a after fitting the first local track and the second local track; and re-determining the corresponding first partial track and second partial track aiming at the physical parking space b to obtain the visual parking space precision corresponding to the physical parking space b, thereby improving the visual parking space precision accuracy corresponding to each physical parking space.
In an alternative embodiment of the present application, the second positioning assembly is one or more inertial sensors provided for the vehicle.
When the inertial sensor is adopted to determine the second track, because the inertial sensor has measurement errors, if all positions of the first track and the second track are fitted, the influence of the inertial sensor on the detection of the accuracy of the parking space is amplified. For example: when the length of the first track is 1000 meters and the measurement error of the inertial sensor is 3/1000, the length error of the second track and the first track can be 3 meters, and if all the positions of the first track and the second track are adopted for fitting, namely fitting is performed in a globally optimal mode, all the measurement errors generated when the inertial sensor obtains the second track affect the fitting effect. By intercepting and fitting the first local track and the second local track, namely fitting in a locally optimal mode, the influence of the measurement error of the inertial sensor on the precision detection of the vision parking space can be effectively avoided, the target interval is taken as an example, the length error between the first local track and the second local track is 0.018 m when the intercepted first local track and the intercepted second local track are parallel to the entity parking space, and obviously less than the length error of 3 m, and the fitting degree of the first local track and the second local track is higher due to the reduction of the length error, so that the precision detection of the vision parking space is improved.
The measurement error in the second positioning component is characteristic and cannot be eliminated, and by the mode of the embodiment of the application, the first local track and the second local track are fitted, so that the second coordinate data are converted into third coordinate data, and the influence caused by the measurement error of the second positioning component can be effectively avoided when the visual parking space precision is obtained later.
In an embodiment, the distance and the offset angle of the visual parking space relative to the physical parking space may be determined by comparing the first coordinate data and the second coordinate data; and based on the distance and the offset angle, obtaining the visual parking space precision.
Further, the first coordinate data further includes: a first far front coordinate, a first far rear coordinate; the third coordinate data includes: a second near front coordinate, a second far front coordinate, a second near rear coordinate, a second far rear coordinate; the comparing the first coordinate data with the second coordinate data, and determining the distance and the offset angle of the visual parking space relative to the physical parking space comprises:
determining a first distance between the first near-front coordinate and the second near-front coordinate;
determining a second distance between the first near-rear coordinate and the second near-rear coordinate;
determining angles between a straight line where the first near front coordinate and the first far front coordinate are located and a straight line where the second near front coordinate and the second far front coordinate are located as a first offset angle;
and determining the angles between the straight line of the first near-back coordinate and the first far-back coordinate and the straight line of the second near-back coordinate and the second far-back coordinate as second offset angles.
Based on the distance and the offset angle, obtaining the visual parking space precision comprises:
when the first distance difference value and the second distance difference value are not larger than a preset distance threshold value and the first offset angle and the second offset angle are not larger than a preset angle threshold value, determining that the precision of the vision parking space meets the preset precision requirement;
and when at least one of the first distance difference value and the second distance difference value is larger than a preset distance threshold value or at least one of the first offset angle and the second offset angle is larger than a preset angle threshold value, determining that the precision of the vision parking space does not meet the preset precision requirement.
It should be noted that, for simplicity of description, the method embodiments are shown as a series of acts, but it should be understood by those skilled in the art that the embodiments are not limited by the order of acts described, as some steps may occur in other orders or concurrently in accordance with the embodiments. Further, those skilled in the art will appreciate that the embodiments described in the specification are all preferred embodiments and that the acts referred to are not necessarily required by the embodiments of the present application.
Referring to fig. 3, a block diagram of an embodiment of an optimizing apparatus for precision detection according to the present application is shown, which may specifically include the following modules:
the data acquisition module 301 is configured to acquire a first track and first coordinate data that are matched with a preset first coordinate system, and a second track and second coordinate data that are matched with a preset second coordinate system when the vehicle is running; the first coordinate data is used for identifying the angular point position of a preset physical parking space, and the second coordinate data is used for identifying the angular point position of a visual parking space matched with the physical parking space;
the local track determining module 302 is configured to determine a first local track in the first track and a second local track in the second track according to the first coordinate data;
a track fitting module 303, configured to fit the first local track and the second local track, so as to convert the second coordinate data into third coordinate data;
and the precision information determining module 304 is configured to compare the first coordinate data with the third coordinate data to obtain the precision of the visual parking space.
In an optional embodiment of the present application, the first coordinate system is an optical positioning coordinate system constructed based on a preset optical positioning system; the second coordinate system is a vehicle coordinate system constructed based on the vehicle self-positioning.
In an alternative embodiment of the present application, the vehicle is provided with a first positioning assembly; the apparatus further comprises:
the optical positioning system building module is used for building an optical positioning system aiming at the entity parking space;
the optical positioning coordinate system construction module is used for constructing an optical positioning coordinate system corresponding to the optical positioning system;
the data acquisition module 301 includes:
the first track generation sub-module is used for generating a first track according to the positions of the optical positioning coordinate system at all moments of the vehicle, which are determined by the first positioning component;
the first coordinate data determining submodule is used for determining that the position of the angular point of the entity parking space in the optical positioning coordinate system is the first coordinate data.
In an alternative embodiment of the present application, the vehicle is provided with a second positioning assembly; the apparatus further comprises:
an initial position determining module, configured to determine a position of the vehicle before driving as an initial position;
a vehicle coordinate system construction module for constructing a vehicle coordinate system for the initial position;
the data acquisition module 301 includes:
the second track generation sub-module is used for generating a second track by adopting the relative positions of the vehicle at all moments and the initial positions determined by the second positioning assembly;
the image data acquisition sub-module is used for acquiring image data matched with the entity parking space;
and the second coordinate data determining submodule is used for determining the position of the corner point of the vision parking space in the vehicle coordinate system as second coordinate data according to the position of the vehicle in the vehicle coordinate system and the image data.
In an optional embodiment of the present application, for any one of the physical parking spaces, the first coordinate data includes: a first front-of-the-first back-of-the-first coordinate; the local trajectory determination module 302 includes:
the midpoint determining submodule is used for determining a target interval on a straight line where the first front coordinate and the first rear coordinate are located according to a preset length; the midpoint of the target interval is the midpoint of the first front-near coordinate and the first rear-near coordinate;
the first local track determining submodule is used for determining a first track in the target interval as a first local track;
and the second local track determining submodule is used for determining that a part of the second track corresponding to the first local track at the same time is the second local track.
In an alternative embodiment of the present application, the apparatus further comprises:
the target parking space determining module is used for sequentially determining target entity parking spaces along the first track; and calling the local track determining module 302 for the target entity parking space.
In an alternative embodiment of the present application, the second positioning assembly is one or more inertial sensors provided for the vehicle.
For the device embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference is made to the description of the method embodiments for relevant points.
The embodiment of the application also provides electronic equipment, which comprises: the method comprises a processor, a memory and a computer program which is stored in the memory and can run on the processor, wherein the computer program realizes all the processes of the optimization method embodiment of the precision detection when being executed by the processor, can achieve the same technical effect, and is not repeated here.
The embodiment of the application also provides a computer readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the processes of the above-mentioned optimization method embodiment of precision detection are implemented, and the same technical effects can be achieved, so that repetition is avoided, and no further description is given here.
In this specification, each embodiment is described in a progressive manner, and each embodiment is mainly described by differences from other embodiments, and identical and similar parts between the embodiments are all enough to be referred to each other.
It will be apparent to those skilled in the art that embodiments of the present application may be provided as a method, apparatus, or computer program product. Accordingly, the present embodiments may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present application may take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
Embodiments of the present application are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present embodiments have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the embodiments of the present application.
Finally, it is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or terminal device comprising the element.
The foregoing describes in detail a method, apparatus, electronic device, and medium for optimizing precision detection provided in the present application, and specific examples are applied to illustrate principles and embodiments of the present application, where the foregoing examples are only used to help understand the method and core idea of the present application; meanwhile, as those skilled in the art will have modifications in the specific embodiments and application scope in accordance with the ideas of the present application, the present description should not be construed as limiting the present application in view of the above.

Claims (10)

1. An optimization method for precision detection is characterized by comprising the following steps:
when the vehicle runs, acquiring a first track and first coordinate data matched with a preset first coordinate system, and acquiring a second track and second coordinate data matched with a preset second coordinate system; the first coordinate data is used for identifying the angular point position of a preset physical parking space, and the second coordinate data is used for identifying the angular point position of a visual parking space matched with the physical parking space;
determining a track within a specified range from the first coordinate data in the first track as a first local track according to the first coordinate data corresponding to any entity parking space, and determining a second local track matched with the moment corresponding to the first local track in the second track;
fitting the first local track and the second local track to convert the second coordinate data into third coordinate data;
and comparing the first coordinate data with the third coordinate data to obtain the visual parking space precision.
2. The method of claim 1, wherein the step of determining the position of the substrate comprises,
the first coordinate system is an optical positioning coordinate system constructed based on a preset optical positioning system;
the second coordinate system is a vehicle coordinate system constructed based on the vehicle self-positioning.
3. The method of claim 2, wherein the vehicle is provided with a first positioning assembly; the method further comprises the steps of:
establishing an optical positioning system for the entity parking space;
constructing an optical positioning coordinate system corresponding to the optical positioning system;
the obtaining the first track and the first coordinate data matched with the preset first coordinate system comprises the following steps:
generating a first track according to the positions of the vehicles at the optical positioning coordinate system at all moments determined by the first positioning component;
and determining the position of the angular point of the entity parking space in the optical positioning coordinate system as first coordinate data.
4. The method of claim 2, wherein the vehicle is provided with a second positioning assembly; the method further comprises the steps of:
determining the position of the vehicle before running as an initial position;
constructing a vehicle coordinate system for the initial position;
the step of obtaining the second track and the second coordinate data matched with the preset second coordinate system comprises the following steps:
generating a second track by adopting the relative positions of the vehicles at all moments and the initial positions determined by the second positioning assembly;
collecting image data matched with the entity parking space;
and determining the position of the corner point of the visual parking space in the vehicle coordinate system as second coordinate data according to the position of the vehicle in the vehicle coordinate system and the image data.
5. The method of claim 2, wherein for any physical parking space, the first coordinate data comprises: a first front-of-the-first back-of-the-first coordinate; the determining that the track within the specified range from the first coordinate data in the first track is a first local track, and determining that the second local track matched with the moment corresponding to the first local track in the second track includes:
determining a target interval on a straight line where the first front-near coordinate and the first rear-near coordinate are located according to a preset length; the midpoint of the target interval is the midpoint of the first front-near coordinate and the first rear-near coordinate;
determining a first track in the target interval as a first local track;
and determining the part of the second track corresponding to the same moment as the first local track as the second local track.
6. The method of claim 1, wherein prior to said determining that a track within a specified range of the first coordinate data from the first track is a first local track and determining that a second local track of the second track matches a time corresponding to the first local track, the method further comprises:
sequentially determining target entity parking spaces along the first track;
and aiming at the target entity parking space, the steps of determining the track within a specified range from the first coordinate data in the first track as a first local track and determining a second local track matched with the moment corresponding to the first local track in the second track are executed.
7. The method of claim 4, wherein the second positioning assembly is one or more inertial sensors disposed for the vehicle.
8. An optimizing apparatus for precision detection, comprising:
the data acquisition module is used for acquiring a first track and first coordinate data matched with a preset first coordinate system, and a second track and second coordinate data matched with a preset second coordinate system when the vehicle runs; the first coordinate data is used for identifying the angular point position of a preset physical parking space, and the second coordinate data is used for identifying the angular point position of a visual parking space matched with the physical parking space;
the local track determining module is used for determining that a track in a specified range from the first coordinate data in the first track is a first local track according to the first coordinate data corresponding to any entity parking space, and determining a second local track matched with the moment corresponding to the first local track in the second track;
the track fitting module is used for fitting the first local track and the second local track so as to convert the second coordinate data into third coordinate data;
and the precision information determining module is used for comparing the first coordinate data with the third coordinate data to obtain the precision of the visual parking space.
9. An electronic device, comprising: a processor, a memory and a computer program stored on the memory and capable of running on the processor, which when executed by the processor carries out the steps of the optimization method of accuracy detection according to any one of claims 1-7.
10. A computer-readable storage medium, on which a computer program is stored, which computer program, when being executed by a processor, carries out the steps of the optimization method of precision detection according to any one of claims 1 to 7.
CN202110745559.7A 2021-06-30 2021-06-30 Optimization method and device for precision detection, electronic equipment and medium Active CN113513985B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110745559.7A CN113513985B (en) 2021-06-30 2021-06-30 Optimization method and device for precision detection, electronic equipment and medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110745559.7A CN113513985B (en) 2021-06-30 2021-06-30 Optimization method and device for precision detection, electronic equipment and medium

Publications (2)

Publication Number Publication Date
CN113513985A CN113513985A (en) 2021-10-19
CN113513985B true CN113513985B (en) 2023-05-16

Family

ID=78066556

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110745559.7A Active CN113513985B (en) 2021-06-30 2021-06-30 Optimization method and device for precision detection, electronic equipment and medium

Country Status (1)

Country Link
CN (1) CN113513985B (en)

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110940267B (en) * 2018-09-25 2023-04-25 深圳中科飞测科技股份有限公司 Measuring method and measuring system thereof
CN109541571B (en) * 2018-12-29 2021-05-07 北京智行者科技有限公司 EPS zero-offset and multi-line laser radar combined calibration method
CN111376895B (en) * 2018-12-29 2022-03-25 上海汽车集团股份有限公司 Around-looking parking sensing method and device, automatic parking system and vehicle
CN110481551B (en) * 2019-08-16 2020-12-29 中国第一汽车股份有限公司 Automatic lane changing control method and device and vehicle
CN110861639B (en) * 2019-11-28 2021-06-15 安徽江淮汽车集团股份有限公司 Parking information fusion method and device, electronic equipment and storage medium
CN111559372B (en) * 2020-05-20 2021-05-18 湖北亿咖通科技有限公司 Parking space detection performance evaluation method of parking system and electronic equipment
CN112763993A (en) * 2020-12-22 2021-05-07 北京百度网讯科技有限公司 Method and device for calibrating radar parameters, electronic equipment and storage medium
CN112985842B (en) * 2021-05-10 2021-07-20 湖北亿咖通科技有限公司 Parking performance detection method, electronic device and readable storage medium

Also Published As

Publication number Publication date
CN113513985A (en) 2021-10-19

Similar Documents

Publication Publication Date Title
CN110146869B (en) Method and device for determining coordinate system conversion parameters, electronic equipment and storage medium
CN111383279B (en) External parameter calibration method and device and electronic equipment
WO2018142900A1 (en) Information processing device, data management device, data management system, method, and program
CN113418543B (en) Automatic driving sensor detection method and device, electronic equipment and storage medium
CN107845114B (en) Map construction method and device and electronic equipment
CN110146096B (en) Vehicle positioning method and device based on image perception
CN109099920B (en) Sensor target accurate positioning method based on multi-sensor association
CN113147738A (en) Automatic parking positioning method and device
CN110470333B (en) Calibration method and device of sensor parameters, storage medium and electronic device
CN109118537B (en) Picture matching method, device, equipment and storage medium
CN110853366B (en) Method and device for detecting parking position of vehicle
CN110658542B (en) Method, device, equipment and storage medium for positioning and identifying automatic driving automobile
CN114034307A (en) Lane line-based vehicle pose calibration method and device and electronic equipment
CN104748754A (en) Vehicle positioning method and vehicle positioning system thereof
CN111353453A (en) Obstacle detection method and apparatus for vehicle
CN110426714B (en) Obstacle identification method
CN113137973A (en) Image semantic feature point truth value determining method and device
CN114419563A (en) Data processing method, device and system, electronic equipment and storage medium
CN113513983B (en) Precision detection method and device, electronic equipment and medium
CN113702953A (en) Radar calibration method and device, electronic equipment and storage medium
CN113513985B (en) Optimization method and device for precision detection, electronic equipment and medium
CN112689234A (en) Indoor vehicle positioning method and device, computer equipment and storage medium
CN113513984B (en) Parking space recognition precision detection method and device, electronic equipment and storage medium
CN109710594B (en) Map data validity judging method and device and readable storage medium
CN114791282A (en) Road facility coordinate calibration method and device based on vehicle high-precision positioning

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
TR01 Transfer of patent right

Effective date of registration: 20240227

Address after: 510000 No.8 Songgang street, Cencun, Tianhe District, Guangzhou City, Guangdong Province

Patentee after: GUANGZHOU XIAOPENG MOTORS TECHNOLOGY Co.,Ltd.

Country or region after: China

Address before: Room 46, room 406, No. 1, Yichuang street, Zhongxin knowledge city, Huangpu District, Guangzhou, Guangdong 510725

Patentee before: Guangzhou Xiaopeng Automatic Driving Technology Co.,Ltd.

Country or region before: China

TR01 Transfer of patent right