CN116740982B - Target parking space determination method and device, storage medium and electronic device - Google Patents

Target parking space determination method and device, storage medium and electronic device Download PDF

Info

Publication number
CN116740982B
CN116740982B CN202311023999.7A CN202311023999A CN116740982B CN 116740982 B CN116740982 B CN 116740982B CN 202311023999 A CN202311023999 A CN 202311023999A CN 116740982 B CN116740982 B CN 116740982B
Authority
CN
China
Prior art keywords
determining
acquisition
error
parking space
acquisition position
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
CN202311023999.7A
Other languages
Chinese (zh)
Other versions
CN116740982A (en
Inventor
朱峰
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.)
HoloMatic Technology Beijing Co Ltd
Original Assignee
HoloMatic Technology Beijing 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 HoloMatic Technology Beijing Co Ltd filed Critical HoloMatic Technology Beijing Co Ltd
Priority to CN202311023999.7A priority Critical patent/CN116740982B/en
Publication of CN116740982A publication Critical patent/CN116740982A/en
Application granted granted Critical
Publication of CN116740982B publication Critical patent/CN116740982B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/14—Traffic control systems for road vehicles indicating individual free spaces in parking areas
    • 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
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/16—Anti-collision systems
    • G08G1/168—Driving aids for parking, e.g. acoustic or visual feedback on parking space
    • 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

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Traffic Control Systems (AREA)
  • Image Analysis (AREA)

Abstract

The application discloses a method and a device for determining a target parking space, a storage medium and an electronic device, and relates to the technical field of intelligent vehicles, wherein the method for determining the target parking space comprises the following steps: acquiring a plurality of acquisition positions when the image acquisition equipment carries out mobile acquisition on an acquisition area; determining parking space error values of a plurality of acquisition positions by using a preset coordinate error model; determining a first error gain value of the first acquisition position according to the parking space error value between the first acquisition position and the second acquisition position, and determining a second error gain value of the second acquisition position according to the parking space error value between the second acquisition position and the third acquisition position; according to the comparison result of the first error gain value and the second error gain value, the target acquisition position is determined, the target parking space state vector acquired by acquiring the acquisition area when the target acquisition position is acquired, and the target parking space is determined based on the target parking space state vector, so that the problem of how to determine more accurate parking spaces in the parking space sensing process is solved.

Description

Target parking space determination method and device, storage medium and electronic device
Technical Field
The application relates to the technical field of intelligent vehicles, in particular to a method and a device for determining a target parking space, a storage medium and an electronic device.
Background
At present, a common automatic parking system can use fish-eye cameras arranged on a vehicle to realize vehicle functions such as visual obstacle sensing, parking space sensing and the like. The ranging method of the fish-eye camera mainly senses key points in the image through deep learning, and calculates the positions of the key points in the actual 3d space based on ground plane assumption and by combining internal and external parameters of the fish-eye camera. However, the image shot by the fisheye camera has the defect of serious edge distortion, the ranging result has the difference of precision, and the determined parking space after the parking space fusion is carried out by using the obtained ranging result is not accurate enough.
The traditional parking space fusion method is generally based on engineering experience, gives different weights to ranging results perceived at different distances and weights for multiple frames, but the method excessively depends on manual experience, does not have explanation in a theoretical level, and cannot obtain accurate parking spaces.
Therefore, in the related art, in the process of parking space sensing, there is a technical problem of how to determine a more accurate parking space.
Aiming at the technical problem of how to determine more accurate parking places in the parking place sensing process in the related technology, no effective solution is proposed yet.
Disclosure of Invention
The embodiment of the application provides a method and a device for determining a target parking space, a storage medium and an electronic device, which at least solve the technical problem of how to determine a more accurate parking space in the process of parking space sensing in the related art.
According to an embodiment of the present application, there is provided a method for determining a target parking space, including: acquiring a plurality of acquisition positions when the image acquisition equipment carries out mobile acquisition on an acquisition area, wherein the image acquisition equipment is installed on a mobile target vehicle; determining parking space error values of the plurality of acquisition positions by using a preset coordinate error model; the plurality of acquisition positions at least comprise a first acquisition position, a second acquisition position and a third acquisition position, the acquisition time of the first acquisition position is later than that of the second acquisition position, and the acquisition time of the second acquisition position is later than that of the third acquisition position; determining a first error gain value of the first acquisition position according to the parking space error value between the first acquisition position and the second acquisition position, and determining a second error gain value of the second acquisition position according to the parking space error value between the second acquisition position and the third acquisition position; and determining a target acquisition position according to a comparison result of the first error gain value and the second error gain value, acquiring a target parking space state vector acquired by acquiring the acquisition area when the target acquisition position is located, and determining the target parking space based on the target parking space state vector.
In an exemplary embodiment, before determining the parking space error values of the plurality of acquisition positions using the preset coordinate error model, the method further includes: determining a vehicle coordinate system taking the first acquisition position as an origin of coordinates; acquiring a first coordinate point acquired in a coordinate value acquisition area of the vehicle coordinate system, and determining a standard deviation value between the first coordinate point and an error coordinate point; constructing an initial fitting surface equation, and determining the surface coefficient of the initial fitting surface equation by using a plurality of standard deviation values to generate the standard deviation value fitting surface equation; and determining the standard deviation fitting surface equation as the preset coordinate error model.
In an exemplary embodiment, determining the standard deviation between the first coordinate point and the error coordinate point includes: back projecting the first coordinate point into an image coordinate system which is already created to obtain a second coordinate point corresponding to the first coordinate point in the image coordinate system; the image coordinate system is a virtual coordinate system with a position projection relation with coordinate points of the vehicle coordinate system; determining error coordinate points which are smaller than the error point distance between the second coordinate points from all coordinate points of the image coordinate system; projecting the error coordinate point and the second coordinate point to the self-vehicle coordinate system to obtain a third coordinate point; and determining the third coordinate point as the error coordinate point, and determining a standard deviation value between the first coordinate point and the third coordinate point as the standard deviation value between the first coordinate point and the error coordinate point.
In one exemplary embodiment, determining the surface coefficients of the initial fitted surface equation using a plurality of standard deviation values to generate a standard deviation fitted surface equation comprises: fitting the initial fit surface equationThe expression is as follows:the method comprises the steps of carrying out a first treatment on the surface of the Wherein said->Said->An argument parameter representing said initial fitting surface equation, said +.>Said->Said->Said->Said->Said->All represent the surface parameters of the initial fitting surface equation; and determining parameter values of the curved surface parameters of the initial fitting curved surface equation based on an iterative algorithm, and respectively replacing the curved surface parameters of the initial fitting curved surface equation with the parameter values of the curved surface parameters to obtain a standard deviation fitting curved surface equation.
In one exemplary embodiment, determining the parameter values of the surface parameters of the initial fitted surface equation based on an iterative algorithm includes: obtaining an initial state variable to be estimated for constructing the standard deviation fitting surface equationAcquiring a parking space state vector which is acquired by acquiring the acquisition area when the parking space state vector is positioned at the ith acquisition position>Wherein, the method comprises the steps of, wherein,，/>i is a positive integer, said ++>And said->Representation ofThe vector value of the parking space state vector, said +. >Representing the standard deviation; determining the error term number of the standard deviation fitting surface equation>Wherein->The method comprises the steps of carrying out a first treatment on the surface of the -adding the initial state variable to be estimated +.>Substituting the number of error terms +.>The iterative algorithm is used for the error term +.>Performing reduced iteration to obtain the error term number +.>Is a difference of iteration; in determining the number of error terms +.>In case the iteration difference of (2) is smaller than a preset value, according to said number of error terms +.>And determining the parameter value of the curved surface parameter of the initial fitting curved surface equation.
In an exemplary embodiment, the iterative algorithm is used to count the number of error termsPerforming reduced iteration to obtain the error term number +.>Comprises: acquiring the initial state to be estimatedVariable->The state variable to be estimated at the time of the kth iteration +.>Wherein->The method comprises the steps of carrying out a first treatment on the surface of the Calculating the state variable to be estimated +.>Error term number->And a jacobian matrix; wherein the jacobian matrix is +.>Relative to the state variable to be estimated +.>Is generated by the derivative of (a); calculating the state variable +.>Is the iterative difference of (a)Wherein the delta equation is based on the number of error terms +. >And obtaining the jacobian matrix and a transpose matrix corresponding to the jacobian matrix.
In an exemplary embodiment, determining the target acquisition location according to the comparison of the first error gain value and the second error gain value includes: determining the first acquisition position as the target acquisition position in the case that the second error gain value of the second acquisition position is smaller than the first error gain value of the first acquisition position; and determining the second acquisition position as the target acquisition position under the condition that the second error gain value of the second acquisition position is larger than the first error gain value of the first acquisition position.
According to another embodiment of the present application, there is further provided a device for determining a target parking space, including: the position acquisition module is used for acquiring a plurality of acquisition positions when the image acquisition equipment carries out mobile acquisition on an acquisition area, wherein the image acquisition equipment is installed on a moving target vehicle; the first determining module is used for determining parking space error values of the plurality of acquisition positions by using a preset coordinate error model; the plurality of acquisition positions at least comprise a first acquisition position, a second acquisition position and a third acquisition position, the acquisition time of the first acquisition position is later than that of the second acquisition position, and the acquisition time of the second acquisition position is later than that of the third acquisition position; the second determining module is used for determining a first error gain value of the first collecting position according to the parking space error value between the first collecting position and the second collecting position and determining a second error gain value of the second collecting position according to the parking space error value between the second collecting position and the third collecting position; and the third determining module is used for determining a target acquisition position according to the comparison result of the first error gain value and the second error gain value, acquiring a target parking space state vector acquired by acquiring the acquisition area when the target acquisition position is located, and determining the target parking space based on the target parking space state vector.
According to still another aspect of the embodiments of the present application, there is also provided a computer-readable storage medium having a computer program stored therein, wherein the computer program is configured to execute the above-described method for determining a target parking space when running.
According to still another aspect of the embodiment of the present application, there is further provided an electronic device including a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes the method for determining a target parking space according to the computer program.
In the embodiment of the application, a plurality of acquisition positions are acquired when the image acquisition equipment carries out mobile acquisition on an acquisition area, wherein the image acquisition equipment is arranged on a mobile target vehicle; determining parking space error values of the plurality of acquisition positions by using a preset coordinate error model; determining a first error gain value of the first acquisition position according to the parking space error value between the first acquisition position and the second acquisition position, and determining a second error gain value of the second acquisition position according to the parking space error value between the second acquisition position and the third acquisition position; determining a target acquisition position according to a comparison result of the first error gain value and the second error gain value, acquiring a target parking space state vector acquired by acquiring the acquisition area when the target acquisition position is located, and determining the target parking space based on the target parking space state vector; by adopting the technical scheme, the technical problem of how to determine more accurate parking spaces in the parking space sensing process is solved, and more accurate parking spaces can be determined.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application.
In order to more clearly illustrate the embodiments of the application or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, and it will be obvious to a person skilled in the art that other drawings can be obtained from these drawings without inventive effort.
FIG. 1 is a schematic diagram of a hardware environment of a method for determining a target parking space according to an embodiment of the present application;
FIG. 2 is a flow chart of a method of determining a target parking space according to an embodiment of the present application;
FIG. 3 is a schematic diagram of a process for generating a preset coordinate error model according to an embodiment of the present application;
FIG. 4 is a schematic diagram of a coordinate value acquisition region of a bicycle coordinate system according to an embodiment of the present application;
FIG. 5 is a schematic diagram of sampling points of an image coordinate system according to an embodiment of the present application;
FIG. 6 is a flow chart of a target parking space determination method according to an embodiment of the application;
FIG. 7 is a schematic illustration of a target vehicle for mobile acquisition according to an embodiment of the application;
FIG. 8 is a block diagram of a target parking space determining apparatus according to an embodiment of the present application;
FIG. 9 is a block diagram of a computer system of an electronic device according to an embodiment of the application;
fig. 10 is a schematic structural view of an alternative electronic device according to an embodiment of the present application.
Detailed Description
In order that those skilled in the art will better understand the present application, a technical solution in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present application without making any inventive effort, shall fall within the scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the application described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
According to one aspect of the embodiment of the application, a method for determining a target parking space is provided. The method for determining the target parking space is widely applied to intelligent digital control application scenes such as intelligent vehicles, intelligent families (Smart Home), intelligent household equipment ecology, intelligent residence (Intelligence House) ecology and the like. Alternatively, in the present embodiment, the above-described method for determining the target parking space may be applied to a hardware environment configured by the terminal device 102 and the server 104 as shown in fig. 1. As shown in fig. 1, the server 104 is connected to the terminal device 102 through a network, and may be used to provide services (such as application services and the like) for a terminal or a client installed on the terminal, a database may be set on the server or independent of the server, for providing data storage services for the server 104, and cloud computing and/or edge computing services may be configured on the server or independent of the server, for providing data computing services for the server 104.
The network may include, but is not limited to, at least one of: wired network, wireless network. The wired network may include, but is not limited to, at least one of: a wide area network, a metropolitan area network, a local area network, and the wireless network may include, but is not limited to, at least one of: WIFI (Wireless Fidelity ), bluetooth. The terminal device 102 may not be limited to being an intelligent vehicle, a PC, a mobile phone, a tablet PC, an intelligent air conditioner, an intelligent smoke machine, an intelligent refrigerator, an intelligent oven, an intelligent stove, an intelligent washing machine, an intelligent water heater, an intelligent washing device, an intelligent dish washer, an intelligent projection device, an intelligent television, an intelligent clothes hanger, an intelligent curtain, an intelligent video, an intelligent socket, an intelligent sound box, an intelligent fresh air device, an intelligent kitchen and toilet device, an intelligent bathroom device, an intelligent floor sweeping robot, an intelligent window cleaning robot, an intelligent mopping robot, an intelligent air purifying device, an intelligent steam box, an intelligent microwave oven, an intelligent kitchen appliance, an intelligent purifier, an intelligent water dispenser, an intelligent door lock, and the like.
In this embodiment, a method for determining a target parking space is provided, which is applied to the terminal device or the intelligent vehicle, and fig. 2 is a flowchart of the method for determining a target parking space according to an embodiment of the present application, where the flowchart includes the following steps:
step S202, acquiring a plurality of acquisition positions when an image acquisition device performs mobile acquisition on an acquisition area, wherein the image acquisition device is installed on a mobile target vehicle;
the image capturing device may be, for example, a fisheye camera, and the installation position of the fisheye camera on the target vehicle may be, for example, under the door handles of the vehicle doors, and the fisheye camera may be installed, for example, for a vehicle with 4 doors, the fisheye camera may be installed under the door handles of the 4 vehicle doors.
In the process of moving the vehicle, the fisheye camera can be used for collecting images of a fixed collecting area, specifically, for example, collecting parking space vertices in the collecting area.
Step S204, determining parking space error values of the plurality of acquisition positions by using a preset coordinate error model; the plurality of acquisition positions at least comprise a first acquisition position, a second acquisition position and a third acquisition position, the acquisition time of the first acquisition position is later than that of the second acquisition position, and the acquisition time of the second acquisition position is later than that of the third acquisition position;
Alternatively, the parking space error value is represented by, for example, variance, standard deviation, etc., which is not limited by the present application.
Optionally, in this step, in the process of moving the vehicle, the third acquisition position, the second acquisition position, and the first acquisition position sequentially pass through, and image acquisition is performed on the acquisition area at each acquisition position.
Alternatively, in this step, in the case where the preset coordinate error model is expressed as the standard deviation fitting surface equation, determining the parking space error values of the plurality of collecting positions using the preset coordinate error model may be understood as inputting the parking space coordinates collected at the first collecting position to the standard deviation fitting surface equation for calculation, obtaining the first parking space error value, and inputting the parking space coordinates collected at the first collecting position to the standard deviation fitting surface equation for calculationAnd calculating to obtain a second vehicle bit error value. Wherein the standard deviation fitting surface equation can be expressed asWherein x and y are independent variables, and can be substituted into the parking space coordinate values, and a, b, c, d, e and f respectively represent the curved surface parameters of the initial fitting curved surface equation, which can be constant.
Step S206, determining a first error gain value of the first acquisition position according to the parking space error value between the first acquisition position and the second acquisition position, and determining a second error gain value of the second acquisition position according to the parking space error value between the second acquisition position and the third acquisition position;
Step S208, determining a target acquisition position according to the comparison result of the first error gain value and the second error gain value, acquiring a target parking space state vector acquired by acquiring the acquisition area when the target acquisition position is located, and determining the target parking space based on the target parking space state vector.
Through the steps, a plurality of acquisition positions are acquired when the image acquisition equipment carries out mobile acquisition on an acquisition area, wherein the image acquisition equipment is installed on a moving target vehicle; determining parking space error values of the plurality of acquisition positions by using a preset coordinate error model; determining a first error gain value of the first acquisition position according to the parking space error value between the first acquisition position and the second acquisition position, and determining a second error gain value of the second acquisition position according to the parking space error value between the second acquisition position and the third acquisition position; determining a target acquisition position according to a comparison result of the first error gain value and the second error gain value, acquiring a target parking space state vector acquired by acquiring the acquisition area when the target acquisition position is located, and determining the target parking space based on the target parking space state vector; by adopting the technical scheme, the technical problem of how to determine a more accurate parking space in the parking space sensing process is solved, and then the more accurate parking space can be determined.
Optionally, in an embodiment, taking the process of determining the gain error value in step S206 as an example to describe the first error gain value for determining the first acquisition position, determining the first error gain value for the first acquisition position according to the parking space error value between the first acquisition position and the second acquisition position may include: determining a first vehicle position error value of the first acquisition position and a second vehicle position error value of the second acquisition position; determining a first error gain value K for the first acquisition location using the formula d ：
，
Wherein the saidFor said first vehicle position error value, said +.>Is the second bit error value.
It should be noted that, the process of determining the second error gain value of the second acquisition position is the same as the process of determining the first error gain value of the first acquisition position, which is not described herein.
In an exemplary embodiment, before executing the technical solution of determining the parking space error values of the plurality of acquisition positions using the preset coordinate error model in the step S204, an implementation process of determining the preset coordinate error model is further provided, which specifically includes: determining a vehicle coordinate system taking the first acquisition position as an origin of coordinates; acquiring a first coordinate point acquired in a coordinate value acquisition area of the vehicle coordinate system, and determining a standard deviation value between the first coordinate point and an error coordinate point; constructing an initial fitting surface equation, and determining the surface coefficient of the initial fitting surface equation by using a plurality of standard deviation values to generate the standard deviation value fitting surface equation; and determining the standard deviation fitting surface equation as the preset coordinate error model.
Alternatively, the vehicle coordinate system may be created from a top view, and then the Z axis is 0, as shown in fig. 4, and may be represented as a 2-dimensional coordinate system.
In an exemplary embodiment, the implementation process of determining the standard deviation value between the first coordinate point and the error coordinate point is further described, and specifically includes the following steps: s11, back-projecting the first coordinate point into an image coordinate system which is already created to obtain a second coordinate point corresponding to the first coordinate point in the image coordinate system; the image coordinate system is a virtual coordinate system with a position projection relation with coordinate points of the vehicle coordinate system; s12, determining error coordinate points which are smaller than the error point distance between the second coordinate points from all coordinate points of the image coordinate system; s13, projecting the error coordinate point and the second coordinate point to the vehicle coordinate system to obtain a third coordinate point; and S14, determining the third coordinate point as the error coordinate point, and determining a standard deviation value between the first coordinate point and the third coordinate point as the standard deviation value between the first coordinate point and the error coordinate point.
In one exemplary embodiment, the process of determining the surface coefficients of the initial fitted surface equation using a plurality of standard deviation values to generate a standard deviation fitted surface equation is illustrated by the following steps: s21, fitting the initial fitting surface equationThe expression is as follows: />The method comprises the steps of carrying out a first treatment on the surface of the Wherein said->Said->An argument parameter representing said initial fitting surface equation, said +.>Said->Said->Said->Said->Said->All represent the surface parameters of the initial fitting surface equation; s22, determining parameter values of the curved surface parameters of the initial fitting curved surface equation based on an iterative algorithm, and respectively replacing the curved surface parameters of the initial fitting curved surface equation with the parameter values of the curved surface parameters to obtain a standard deviation fitting curved surface equation.
The iterative algorithm may be, for example, a gaussian newton iterative method, but is not limited thereto.
In an exemplary embodiment, the step S22 may further include the following implementation steps, including: s221, obtaining an initial state variable to be estimated for constructing the standard deviation fitting surface equationAcquiring a parking space state vector which is acquired by acquiring the acquisition area when the parking space state vector is positioned at the ith acquisition position >Wherein, the method comprises the steps of, wherein,，/>i is a positive integer, said ++>And said->Vector values representing the parking space status vector, said +.>Representing the standard deviation; s222, determining the error term number of the standard deviation fitting surface equation>Wherein->The method comprises the steps of carrying out a first treatment on the surface of the S223, the initial state variable to be estimated is +.>Substituting the number of error terms +.>The iterative algorithm is used for the error term +.>Performing reduced iteration to obtain the error term number +.>Is a difference of iteration; s224, in determining the error term number +.>In case the iteration difference of (2) is smaller than a preset value, according to said number of error terms +.>And determining the parameter value of the curved surface parameter of the initial fitting curved surface equation.
Alternatively, it should be noted that the aboveThe standard deviation is expressed in terms ofThe ith acquisition position is the standard deviation value of the coordinate point acquired in the coordinate value acquisition area of the vehicle coordinate system of the coordinate origin.
In an exemplary embodiment, the iterative algorithm is used for counting the number of error terms in step S223 described abovePerforming reduced iteration to obtain the error term number +.>The technical scheme of the iterative difference value comprises the following specific implementation steps: acquiring the state variable +. >The state variable to be estimated at the time of the kth iteration +.>Wherein, the method comprises the steps of, wherein,the method comprises the steps of carrying out a first treatment on the surface of the Calculating the state variable to be estimated +.>Error term number->And a jacobian matrix; wherein the jacobian matrix is +.>Relative to the state variable to be estimated +.>Is generated by the derivative of (a); calculating the state variable +.>Is>Wherein the increaseThe quantity equation is based on the number of error terms +.>And obtaining the jacobian matrix and a transpose matrix corresponding to the jacobian matrix. Wherein K is a positive integer.
Alternatively, in the present embodiment, the number of error terms is as described aboveRelative to the state variable to be estimated +.>The derivatives of (a) are for example: />，/>，/>，/>，/>，/>。
Optionally, in other embodiments, the number of error terms is determinedIn case the iteration value of (2) is equal to or larger than a preset value, continuing to use the iterative algorithm for the error term number +.>Performing reduced iteration, wherein the state variable to be estimated is +.>The (K+1) th iteration is performed until the number of error terms +.>The iteration value of (2) is smaller than a preset value.
In an exemplary embodiment, the implementation process of determining the target acquisition position in step S208 according to the comparison result of the first error gain value and the second error gain value is described by the following steps: determining the first acquisition position as the target acquisition position in the case that the second error gain value of the second acquisition position is smaller than the first error gain value of the first acquisition position; and determining the second acquisition position as the target acquisition position under the condition that the second error gain value of the second acquisition position is larger than the first error gain value of the first acquisition position.
In order to better understand the process of the method for determining the target parking space, the following describes the flow of the method for implementing the determination of the target parking space in combination with the alternative embodiment, but is not used for limiting the technical scheme of the embodiment of the application.
It should be noted that in the parking space fusion process, multiple frames of fusion needs to be performed on the result of sensing distance measurement, so that by performing error modeling on the result of sensing distance measurement, the accuracy of the result of sensing distance measurement can be improved, and a more stable sensing fusion result can be output. Specifically, for example, modeling analysis can be performed on the error of the ranging of the fisheye camera IPM, and the result of multiple observations is fused and output through a kalman filter.
Optionally, in an embodiment, the process of generating the preset coordinate error model (i.e. the fisheye camera error model in the following embodiment) is described with reference to fig. 3, as shown in fig. 3, fig. 3 is a schematic diagram of the process of generating the preset coordinate error model according to an embodiment of the present application, and the steps of modeling the fisheye camera error are specifically shown as follows:
step S301, acquiring an ROI area of a fisheye camera;
step S302, taking the left looking around camera as an example, a vehicle coordinate system as shown in FIG. 4 is obtained, wherein the vehicle is in the process of vehicle The coordinate system is divided into 8m by 8m regions (corresponding to the coordinate value acquisition regions of the vehicle coordinate system), that is, regions composed of points (6, 9), points (6, 1), points (-2, 9), and points (-2, 1) in fig. 4. A grid can be divided every 0.1m to obtain 80 x 80A point (corresponding to the first coordinate point);
step S303, willBack projecting the point into the image coordinate system to obtain the +.>Dot is theoretical in the image coordinate system +.>Points (i.e., solid circle points in fig. 5, corresponding to the second coordinate points described above);
step S304, taking into account errors of manual labeling and model reasoning of the image, modeling the errors into a series of images which are uniformly distributed along the image space and uniformly sampled according to 3, 5, 7 and 9 pixels, up, down, left and right to obtain a series of images as shown in figure 5Points, i.e., open points (corresponding to the error coordinate points described above) in fig. 5, which are likely to be perceived by the image;
step S305, sampling the image pointsProjecting back into 3d space to get the corresponding +.>(corresponding to the third coordinate point), statistical calculation to obtain +_relative to the reference point>Standard deviation sigma (corresponding to the parking space error value) The corresponding formula is
The method comprises the steps of carrying out a first treatment on the surface of the Wherein N is a positive integer.
Step S306, calculating corresponding standard deviation according to the above steps for each of the 80 x 80 points, fitting the curved surface according to the calculated standard deviation, taking into accountThe z value of (2) is 0, and the error curved surface is modeled as an initial fitting curved surface equation (I) without considering z>Based on the sampling points, namely standard deviation sigma, obtaining corresponding surface coefficients through a Gauss Newton iteration method, and obtaining a fitted fisheye camera error model;
wherein, the state variable to be estimated in the fisheye camera error model is thatEach observed quantity (namely the parking space state vector) is +.>The method comprises the steps of carrying out a first treatment on the surface of the The state variable to be estimated at the time of the K-th iteration +.>Can be expressed as +.>。
Then define the error asThe derivative of each error term with respect to the state variable is determined as follows:
，/>，/>，/>，/>，/>，
thenThe incremental equation for Gauss Newton's method is
(1)
The main steps of the Gauss Newton method are as follows:
1) Initial value of given iteration ；
2) For the kth iterationSubstituting and calculating jacobian matrix corresponding to each error term>Error-> ；
3) According to formula (1), calculating an incremental equation to obtain；
4) If it isSmall enough, stop. Otherwise, let->Returning to the step 2).
In one embodiment, taking a kalman filter fused parking space as an example, a process of determining a target parking space is described with reference to fig. 6, and the specific steps include:
step S601, inputting visual perception parking spaces, and filtering the parking spaces through relevant conditions to remove malformed parking spaces and parking spaces which obviously do not meet the requirements;
step S602, receiving positioning odometer information to obtain corresponding poseCalculating global coordinates of parking space vertexesThe corresponding formula is as follows-> ；
Step S603, correlating the input parking space with the parking space in the global parking space manager through IOU matching, if the matching fails, executing step S604, otherwise executing step S605, and adding the parking space into a history observation list of the parking space;
step S604, a parking space is newly built in the global parking space manager;
step S605, calculating an observation standard deviation sigma corresponding to the peak of the observation parking space according to the fisheye camera error model;
step S606, fusing the parking space vertexes according to the Kalman filter, considering that the parking space vertexes are stationary under the global coordinate system, ignoring the state transition equation and the process noise, the fusion principle of the Kalman filter can be simplified into the following formula:
(2)，
(3)，
(4)。
Wherein the method comprises the steps ofAnd->State value and variance for the last state, +.>And->K is the state value and variance of the current observation d Is Kalman gain (corresponding to error gain value),>(corresponding to the target parking space state vector) and +.>The result after this fusion is obtained.
For formulas (2) to (4) above, the physical meaning is: if the current observation position is located at a position with larger distortion of the fisheye camera, the variance calculated according to the fisheye camera error model, namely the formula (4), is larger theoretically, the Kalman gain Kd calculated by the formula (2) is smaller, and the parking space observed before the current observation can be more trusted at the moment; if the current observation position is positioned in the optimal view angle range of the fisheye camera, theoretically, the variance calculated according to the error model of the fisheye camera is smaller, the calculated Kalman gain Kd is larger, and a parking place which is more trusted to be observed at the time is selected;
step S607, outputting the parking space result after the Kalman filter fusion according to the calculation result of the formula (3).
Further, the process of updating the parking space position by using the kalman filter and the fisheye camera error model can be described with reference to the following example, as shown in fig. 7, for the parking space vertex 1 on the ground, the positions a, b and c are observed respectively, and after the parking space vertex 1 is converted into the global coordinate system, the specific values are respectively corresponding to ，/>，，/>，/>，/>。
When passing through the point a, determining the state value and variance of the point a:
，/>；
while passing through the point b, determining the state value and variance of the point b:
，/>，；
when passing through the point c, determining the state value and variance of the point c:
，/>，/>。
according to the analysis of the example, the variance of the point a is larger, the confidence coefficient is lower, the point b is located at the optimal observation position after passing through the point b, the variance is smaller, the Kalman gain is larger, the observation confidence coefficient is higher, and after updating, the parking space position is mainly observed at the point b, namely, the parking space perceived by the point b is used as a target parking space.
When the vehicle leaves the point b and reaches the point c, the variance of the point c is larger, the Kalman gain is smaller, the confidence is lower, the parking position is still the last state, the Kalman gain observed at this time is the weight is reduced, and the parking position perceived by the point b is taken as the target parking position.
According to the method, modeling is conducted on the IPM ranging error of the fisheye camera, a fisheye camera error model is obtained through surface fitting, so that confidence of the space position of the parking space vertex under different observation angles is estimated, multi-frame fusion is conducted on the space position of the parking space vertex through the Kalman filter, and in a real-vehicle link, the fact that the current method has a more robust parking space fusion effect is verified.
From the description of the above embodiments, it will be clear to a person skilled in the art that the method according to the above embodiments may be implemented by means of software plus the necessary general hardware platform, but of course also by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) comprising several instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method of the various embodiments of the present application.
FIG. 8 is a block diagram of a target parking space determining apparatus according to an embodiment of the present application; as shown in fig. 8, includes:
a position acquisition module 82, configured to acquire a plurality of acquisition positions when an image acquisition device performs mobile acquisition on an acquisition area, where the image acquisition device is mounted on a moving target vehicle;
a first determining module 84, configured to determine parking space error values of the plurality of acquisition positions using a preset coordinate error model; the plurality of acquisition positions at least comprise a first acquisition position, a second acquisition position and a third acquisition position, the acquisition time of the first acquisition position is later than that of the second acquisition position, and the acquisition time of the second acquisition position is later than that of the third acquisition position;
A second determining module 86, configured to determine a first error gain value of the first collecting position according to the parking space error value between the first collecting position and the second collecting position, and determine a second error gain value of the second collecting position according to the parking space error value between the second collecting position and the third collecting position;
and the third determining module 88 is configured to determine a target acquisition position according to a comparison result of the first error gain value and the second error gain value, obtain a target parking space state vector acquired by acquiring the acquisition area when the target acquisition position is located, and determine the target parking space based on the target parking space state vector.
Acquiring a plurality of acquisition positions when the image acquisition equipment carries out mobile acquisition on an acquisition area, wherein the image acquisition equipment is arranged on a mobile target vehicle; determining parking space error values of the plurality of acquisition positions by using a preset coordinate error model; determining a first error gain value of the first acquisition position according to the parking space error value between the first acquisition position and the second acquisition position, and determining a second error gain value of the second acquisition position according to the parking space error value between the second acquisition position and the third acquisition position; determining a target acquisition position according to a comparison result of the first error gain value and the second error gain value, acquiring a target parking space state vector acquired by acquiring the acquisition area when the target acquisition position is located, and determining the target parking space based on the target parking space state vector; by adopting the technical scheme, the technical problem of how to determine more accurate parking spaces in the parking space sensing process is solved, and more accurate parking spaces can be determined.
In one exemplary embodiment, the first determination module 84 further includes: the first determining unit is used for determining a vehicle coordinate system taking the first acquisition position as an origin of coordinates; the second determining unit is used for acquiring a first coordinate point acquired in a coordinate value acquisition area of the vehicle coordinate system and determining a standard deviation value between the first coordinate point and an error coordinate point; the third determining unit is used for constructing an initial fitting surface equation, determining the surface coefficient of the initial fitting surface equation by using a plurality of standard deviation values, and generating the standard deviation value fitting surface equation; and the fourth determining unit is used for determining the standard deviation fitting curved surface equation as the preset coordinate error model.
In an exemplary embodiment, the second determining unit is further configured to perform the following steps: s11, back-projecting the first coordinate point into an image coordinate system which is already created to obtain a second coordinate point corresponding to the first coordinate point in the image coordinate system; the image coordinate system is a virtual coordinate system with a position projection relation with coordinate points of the vehicle coordinate system; s12, determining error coordinate points which are smaller than the error point distance between the second coordinate points from all coordinate points of the image coordinate system; s13, projecting the error coordinate point and the second coordinate point to the vehicle coordinate system to obtain a third coordinate point; and S14, determining the third coordinate point as the error coordinate point, and determining a standard deviation value between the first coordinate point and the third coordinate point as the standard deviation value between the first coordinate point and the error coordinate point.
In an exemplary embodiment, the third determining unit is further configured to performThe method comprises the following steps: s21, fitting the initial fitting surface equationThe expression is as follows: />The method comprises the steps of carrying out a first treatment on the surface of the Wherein said->The saidAn argument parameter representing said initial fitting surface equation, said +.>Said->Said->Said->Said->Said->All represent the surface parameters of the initial fitting surface equation; s22, determining parameter values of the curved surface parameters of the initial fitting curved surface equation based on an iterative algorithm, and respectively replacing the curved surface parameters of the initial fitting curved surface equation with the parameter values of the curved surface parameters to obtain a standard deviation fitting curved surface equation.
In an exemplary embodiment, the third determining unit is further configured to implement the following steps: s221, obtaining an initial state variable to be estimated for constructing the standard deviation fitting surface equationAnd obtain the position of the first partThe parking space state vector +.A parking space state vector obtained by collecting the collecting area when i collecting positions are adopted>Wherein->，/>I is a positive integer, said ++>And said->Vector values representing the parking space status vector, said +.>Representing the standard deviation; s222, determining the error term number of the standard deviation fitting surface equation >Wherein, the method comprises the steps of, wherein,the method comprises the steps of carrying out a first treatment on the surface of the S223, the initial state variable to be estimated is +.>Substituting the number of error terms +.>The iterative algorithm is used for the error term +.>Performing reduced iteration to obtain the error term number +.>Is a difference of iteration; s224, in determining the error term number +.>In case the iteration difference of (2) is smaller than a preset value, according to said number of error terms +.>And determining the parameter value of the curved surface parameter of the initial fitting curved surface equation.
In an exemplary embodiment, the third determining unit is further configured to perform the following implementation steps: acquiring the initial state variable to be estimatedThe state variable to be estimated at the time of the kth iteration +.>Wherein, the method comprises the steps of, wherein,the method comprises the steps of carrying out a first treatment on the surface of the Calculating the state variable to be estimated +.>Error term number->And a jacobian matrix; wherein the jacobian matrix is +.>Relative to the state variable to be estimated +.>Is generated by the derivative of (a); calculating the state variable +.>Is>Wherein the delta equation is based on the number of error terms +.>And obtaining the jacobian matrix and a transpose matrix corresponding to the jacobian matrix. Wherein K is a positive integer.
In one exemplary embodiment, the third determination module 88 is further configured to: determining the first acquisition position as the target acquisition position in the case that the second error gain value of the second acquisition position is smaller than the first error gain value of the first acquisition position; and determining the second acquisition position as the target acquisition position under the condition that the second error gain value of the second acquisition position is larger than the first error gain value of the first acquisition position.
According to one aspect of the present application, there is provided a computer program product comprising a computer program/instruction containing program code for executing the method shown in the flow chart. In such an embodiment, the computer program may be downloaded and installed from the network via the communication portion 909 and/or installed from the removable medium 911. When the computer program is executed by the central processor 901, various functions provided by the embodiments of the present application are performed.
The foregoing embodiment numbers of the present application are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.
It should be noted that, the computer system 900 of the electronic device shown in fig. 9 is only an example, and should not impose any limitation on the functions and the application scope of the embodiments of the present application.
As shown in fig. 9, the computer system 900 includes a central processing unit 901 (Central Processing Unit, CPU) which can execute various appropriate actions and processes according to a program stored in a Read-Only Memory 902 (ROM) or a program loaded from a storage portion 908 into a random access Memory 903 (Random Access Memory, RAM). In the random access memory 903, various programs and data required for system operation are also stored. The cpu 901, the rom 902, and the ram 903 are connected to each other via a bus 904. An Input/Output interface 905 (i.e., an I/O interface) is also connected to bus 904.
The following components are connected to the input/output interface 905: an input section 906 including a keyboard, a mouse, and the like; an output section 907 including a speaker and the like, such as a Cathode Ray Tube (CRT), a liquid crystal display (Liquid Crystal Display, LCD), and the like; a storage portion 908 including a hard disk or the like; and a communication section 909 including a network interface card such as a local area network card, a modem, or the like. The communication section 909 performs communication processing via a network such as the internet. The drive 910 is also connected to the input/output interface 905 as needed. A removable medium 911 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is installed as needed on the drive 910 so that a computer program read out therefrom is installed into the storage section 908 as needed.
In particular, the processes described in the various method flowcharts may be implemented as computer software programs according to embodiments of the application. For example, embodiments of the present application include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method shown in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from the network via the communication portion 909 and/or installed from the removable medium 911. When executed by the central processor 901, performs various functions defined in the system of the present application.
According to still another aspect of the embodiment of the present application, there is further provided an electronic device for implementing the method for determining a target parking space, where the electronic device may be an autonomous vehicle or a server as shown in fig. 1. The present embodiment will be described taking the electronic apparatus as an example of an autonomous vehicle. As shown in fig. 10, the electronic device comprises a memory 1002 and a processor 1004, the memory 1002 having stored therein a computer program, the processor 1004 being arranged to perform the steps of any of the method embodiments described above by means of the computer program.
Alternatively, in this embodiment, the electronic device may be located in at least one network device of a plurality of network devices of the computer network.
Alternatively, in the present embodiment, the above-described processor may be configured to execute the following steps by a computer program:
s1, acquiring a plurality of acquisition positions when an image acquisition device carries out mobile acquisition on an acquisition area, wherein the image acquisition device is installed on a mobile target vehicle;
s2, determining parking space error values of the plurality of acquisition positions by using a preset coordinate error model; the plurality of acquisition positions at least comprise a first acquisition position, a second acquisition position and a third acquisition position, the acquisition time of the first acquisition position is later than that of the second acquisition position, and the acquisition time of the second acquisition position is later than that of the third acquisition position;
s3, determining a first error gain value of the first acquisition position according to the parking space error value between the first acquisition position and the second acquisition position, and determining a second error gain value of the second acquisition position according to the parking space error value between the second acquisition position and the third acquisition position;
s4, determining a target acquisition position according to a comparison result of the first error gain value and the second error gain value, acquiring a target parking space state vector acquired by acquiring the acquisition area when the target acquisition position is located, and determining the target parking space based on the target parking space state vector.
Alternatively, it will be appreciated by those of ordinary skill in the art that the configuration shown in FIG. 10 is merely illustrative and that the electronic device may be an autonomous vehicle. Fig. 10 is not limited to the structure of the electronic device described above. For example, the electronic device may also include more or fewer components (e.g., network interfaces, etc.) than shown in FIG. 10, or have a different configuration than shown in FIG. 10.
The memory 1002 may be configured to store software programs and modules, such as program instructions/modules corresponding to the method and apparatus for determining a target parking space in the embodiment of the present application, and the processor 1004 executes the software programs and modules stored in the memory 1002 to perform various functional applications and data processing, that is, implement the method for determining a target parking space. The memory 1002 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid state memory. In some examples, the memory 1002 may further include memory located remotely from the processor 1004, which may be connected to the terminal via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof. The memory 1002 may specifically, but not limited to, information such as a log for containing sensitive data. As an example, as shown in fig. 10, the memory 1002 may include, but is not limited to, a position obtaining module 82, a first determining module 84, a second determining module 86, and a third determining module 88 in the determining device including the target parking space. In addition, other module units in the determining device of the target parking space may be further included, but are not limited to, and are not described in detail in this example.
Optionally, the transmission device 1006 is configured to receive or transmit data via a network. Specific examples of the network described above may include wired networks and wireless networks. In one example, the transmission means 1006 includes a network adapter (Network Interface Controller, NIC) that can be connected to other network devices and routers via a network cable to communicate with the internet or a local area network. In one example, the transmission device 1006 is a Radio Frequency (RF) module for communicating with the internet wirelessly.
In addition, the electronic device further includes: a display 1008; and a connection bus 1010 for connecting the respective module parts in the above-described electronic apparatus.
In other embodiments, the autonomous vehicle or the server may be a node in a distributed system, where the distributed system may be a blockchain system, and the blockchain system may be a distributed system formed by connecting the plurality of nodes through a network communication. Among them, the nodes may form a Peer-To-Peer (P2P) network, and any type of computing device, such as a server, a terminal, etc., may become a node in the blockchain system by joining the Peer-To-Peer network.
An embodiment of the present application also provides a storage medium including a stored program, wherein the program executes the method of any one of the above.
Alternatively, in the present embodiment, the above-described storage medium may be configured to store program code for performing the steps of:
s1, acquiring a plurality of acquisition positions when an image acquisition device carries out mobile acquisition on an acquisition area, wherein the image acquisition device is installed on a mobile target vehicle;
s2, determining parking space error values of the plurality of acquisition positions by using a preset coordinate error model; the plurality of acquisition positions at least comprise a first acquisition position, a second acquisition position and a third acquisition position, the acquisition time of the first acquisition position is later than that of the second acquisition position, and the acquisition time of the second acquisition position is later than that of the third acquisition position;
s3, determining a first error gain value of the first acquisition position according to the parking space error value between the first acquisition position and the second acquisition position, and determining a second error gain value of the second acquisition position according to the parking space error value between the second acquisition position and the third acquisition position;
S4, determining a target acquisition position according to a comparison result of the first error gain value and the second error gain value, acquiring a target parking space state vector acquired by acquiring the acquisition area when the target acquisition position is located, and determining the target parking space based on the target parking space state vector.
An embodiment of the application also provides an electronic device comprising a memory having stored therein a computer program and a processor arranged to run the computer program to perform the steps of any of the method embodiments described above.
Optionally, the electronic apparatus may further include a transmission device and an input/output device, where the transmission device is connected to the processor, and the input/output device is connected to the processor.
Alternatively, in the present embodiment, the above-described processor may be configured to execute the following steps by a computer program:
s1, acquiring a plurality of acquisition positions when an image acquisition device carries out mobile acquisition on an acquisition area, wherein the image acquisition device is installed on a mobile target vehicle;
s2, determining parking space error values of the plurality of acquisition positions by using a preset coordinate error model; the plurality of acquisition positions at least comprise a first acquisition position, a second acquisition position and a third acquisition position, the acquisition time of the first acquisition position is later than that of the second acquisition position, and the acquisition time of the second acquisition position is later than that of the third acquisition position;
S3, determining a first error gain value of the first acquisition position according to the parking space error value between the first acquisition position and the second acquisition position, and determining a second error gain value of the second acquisition position according to the parking space error value between the second acquisition position and the third acquisition position;
s4, determining a target acquisition position according to a comparison result of the first error gain value and the second error gain value, acquiring a target parking space state vector acquired by acquiring the acquisition area when the target acquisition position is located, and determining the target parking space based on the target parking space state vector.
Alternatively, in the present embodiment, the storage medium may include, but is not limited to: a U-disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a removable hard disk, a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Alternatively, specific examples in this embodiment may refer to examples described in the foregoing embodiments and optional implementations, and this embodiment is not described herein.
It will be appreciated by those skilled in the art that the modules or steps of the application described above may be implemented in a general purpose computing device, they may be concentrated on a single computing device, or distributed across a network of computing devices, they may alternatively be implemented in program code executable by computing devices, so that they may be stored in a memory device for execution by computing devices, and in some cases, the steps shown or described may be performed in a different order than that shown or described, or they may be separately fabricated into individual integrated circuit modules, or multiple modules or steps within them may be fabricated into a single integrated circuit module for implementation. Thus, the present application is not limited to any specific combination of hardware and software.
The foregoing is merely a preferred embodiment of the present application and it should be noted that modifications and adaptations to those skilled in the art may be made without departing from the principles of the present application, which are intended to be comprehended within the scope of the present application.

Claims (8)

1. The method for determining the target parking space is characterized by comprising the following steps of:
acquiring a plurality of acquisition positions when the image acquisition equipment carries out mobile acquisition on an acquisition area, wherein the image acquisition equipment is installed on a mobile target vehicle;
determining parking space error values of the plurality of acquisition positions by using a preset coordinate error model; the plurality of acquisition positions at least comprise a first acquisition position, a second acquisition position and a third acquisition position, the acquisition time of the first acquisition position is later than that of the second acquisition position, and the acquisition time of the second acquisition position is later than that of the third acquisition position;
determining a first error gain value of the first acquisition position according to the parking space error value between the first acquisition position and the second acquisition position, and determining a second error gain value of the second acquisition position according to the parking space error value between the second acquisition position and the third acquisition position;
Determining a target acquisition position according to a comparison result of the first error gain value and the second error gain value, acquiring a target parking space state vector acquired by acquiring the acquisition area when the target acquisition position is located, and determining the target parking space based on the target parking space state vector;
before determining the parking space error values of the plurality of acquisition positions by using a preset coordinate error model, the method further comprises:
determining a vehicle coordinate system taking the first acquisition position as an origin of coordinates;
acquiring a first coordinate point acquired in a coordinate value acquisition area of the vehicle coordinate system, and determining a standard deviation value between the first coordinate point and an error coordinate point;
constructing an initial fitting surface equation, and determining the surface coefficient of the initial fitting surface equation by using a plurality of standard deviation values to generate the standard deviation value fitting surface equation;
determining the standard deviation fitting surface equation as the preset coordinate error model;
wherein determining the standard deviation value between the first coordinate point and the error coordinate point includes:
back projecting the first coordinate point into an image coordinate system which is already created to obtain a second coordinate point corresponding to the first coordinate point in the image coordinate system; the image coordinate system is a virtual coordinate system with a position projection relation with coordinate points of the vehicle coordinate system;
Determining coordinate points which are smaller than the error point distance between the second coordinate points from all coordinate points of the image coordinate system;
projecting a coordinate point which is smaller than the error point distance between the second coordinate point and the second coordinate point to the self-vehicle coordinate system to obtain a third coordinate point;
and determining the third coordinate point as the error coordinate point, and determining a standard deviation value between the first coordinate point and the third coordinate point as the standard deviation value between the first coordinate point and the error coordinate point.
2. The method of claim 1, wherein determining the surface coefficients of the initial fitted surface equation using a plurality of standard deviation values to generate a standard deviation value fitted surface equation comprises:
fitting the initial fit surface equationThe expression is as follows: />；
Wherein the saidSaid->An argument parameter representing said initial fitting surface equation, said +.>Said->The saidSaid->Said->Said->All represent the surface parameters of the initial fitting surface equation;
and determining parameter values of the curved surface parameters of the initial fitting curved surface equation based on an iterative algorithm, and respectively replacing the curved surface parameters of the initial fitting curved surface equation with the parameter values of the curved surface parameters to obtain a standard deviation fitting curved surface equation.
3. The method for determining the target parking space according to claim 2, wherein determining the parameter value of the curved surface parameter of the initial fitting curved surface equation based on an iterative algorithm comprises:
obtaining an initial state variable to be estimated for constructing the standard deviation fitting surface equationAcquiring a parking space state vector which is acquired by acquiring the acquisition area when the parking space state vector is positioned at the ith acquisition position>Wherein, the method comprises the steps of, wherein,，/>i is a positive integer, said ++>And said->Vector values representing the parking space status vector, said +.>Representing the standard deviation;
determining the number of error terms of the standard deviation fitting surface equationWherein, the method comprises the steps of, wherein,；
the initial state variable to be estimatedSubstituting the number of error terms +.>The iterative algorithm is used for the error term +.>Performing reduced iteration to obtain the error term number +.>Is a difference of iteration;
in determining the number of error termsIn case the iteration difference of (2) is smaller than a preset value, according to said number of error terms +.>And determining the parameter value of the curved surface parameter of the initial fitting curved surface equation.
4. The method for determining a target parking space according to claim 3, wherein the iterative algorithm is used for counting the number of error terms Performing reduced iteration to obtain the error term number +.>Comprises:
acquiring the initial state variable to be estimatedThe state variable to be estimated at the time of the kth iteration +.>Wherein, the method comprises the steps of, wherein,；
calculating the state variable to be estimatedError term number->And a jacobian matrix; wherein the jacobian matrix is +.>Relative to the state variable to be estimated +.>Is generated by the derivative of (a);
calculating the state variable to be estimated by using an incremental equationIs>Wherein the delta equation is based on the number of error terms +.>And obtaining the jacobian matrix and a transpose matrix corresponding to the jacobian matrix.
5. The method for determining a target parking space according to claim 1, wherein determining a target acquisition position according to a comparison result of the first error gain value and the second error gain value comprises:
determining the first acquisition position as the target acquisition position in the case that the second error gain value of the second acquisition position is smaller than the first error gain value of the first acquisition position;
and determining the second acquisition position as the target acquisition position under the condition that the second error gain value of the second acquisition position is larger than the first error gain value of the first acquisition position.
6. The utility model provides a target parking stall's determining device which characterized in that includes:
the position acquisition module is used for acquiring a plurality of acquisition positions when the image acquisition equipment carries out mobile acquisition on an acquisition area, wherein the image acquisition equipment is installed on a moving target vehicle;
the first determining module is used for determining parking space error values of the plurality of acquisition positions by using a preset coordinate error model; the plurality of acquisition positions at least comprise a first acquisition position, a second acquisition position and a third acquisition position, the acquisition time of the first acquisition position is later than that of the second acquisition position, and the acquisition time of the second acquisition position is later than that of the third acquisition position;
the second determining module is used for determining a first error gain value of the first collecting position according to the parking space error value between the first collecting position and the second collecting position and determining a second error gain value of the second collecting position according to the parking space error value between the second collecting position and the third collecting position;
the third determining module is used for determining a target acquisition position according to a comparison result of the first error gain value and the second error gain value, acquiring a target parking space state vector acquired from the acquisition area when the target acquisition position is located, and determining the target parking space based on the target parking space state vector;
Wherein, the first determining module further includes: the first determining unit is used for determining a vehicle coordinate system taking the first acquisition position as an origin of coordinates; the second determining unit is used for acquiring a first coordinate point acquired in a coordinate value acquisition area of the vehicle coordinate system and determining a standard deviation value between the first coordinate point and an error coordinate point; the third determining unit is used for constructing an initial fitting surface equation, determining the surface coefficient of the initial fitting surface equation by using a plurality of standard deviation values, and generating the standard deviation value fitting surface equation; a fourth determining unit, configured to determine the standard deviation fitting surface equation as the preset coordinate error model;
the second determining unit is further configured to back-project the first coordinate point into an image coordinate system that has been created, to obtain a second coordinate point corresponding to the first coordinate point in the image coordinate system; the image coordinate system is a virtual coordinate system with a position projection relation with coordinate points of the vehicle coordinate system; determining coordinate points which are smaller than the error point distance between the second coordinate points from all coordinate points of the image coordinate system; projecting a coordinate point which is smaller than the error point distance between the second coordinate point and the second coordinate point to the self-vehicle coordinate system to obtain a third coordinate point; and determining the third coordinate point as the error coordinate point, and determining a standard deviation value between the first coordinate point and the third coordinate point as the standard deviation value between the first coordinate point and the error coordinate point.
7. A computer readable storage medium, characterized in that the computer readable storage medium comprises a stored program, wherein the program when run performs the method of any of the preceding claims 1 to 5.
8. An electronic device comprising a memory and a processor, characterized in that the memory has stored therein a computer program, the processor being arranged to execute the method according to any of the claims 1 to 5 by means of the computer program.
CN202311023999.7A 2023-08-15 2023-08-15 Target parking space determination method and device, storage medium and electronic device Active CN116740982B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311023999.7A CN116740982B (en) 2023-08-15 2023-08-15 Target parking space determination method and device, storage medium and electronic device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311023999.7A CN116740982B (en) 2023-08-15 2023-08-15 Target parking space determination method and device, storage medium and electronic device

Publications (2)

Publication Number Publication Date
CN116740982A CN116740982A (en) 2023-09-12
CN116740982B true CN116740982B (en) 2023-12-01

Family

ID=87911922

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311023999.7A Active CN116740982B (en) 2023-08-15 2023-08-15 Target parking space determination method and device, storage medium and electronic device

Country Status (1)

Country Link
CN (1) CN116740982B (en)

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107784672A (en) * 2016-08-26 2018-03-09 百度在线网络技术（北京）有限公司 For the method and apparatus for the external parameter for obtaining in-vehicle camera
DE102018123393A1 (en) * 2018-09-24 2020-03-26 Denso Corporation Detection of parking areas
CN111007540A (en) * 2018-10-04 2020-04-14 赫尔环球有限公司 Method and apparatus for predicting sensor error
CN113432620A (en) * 2021-06-04 2021-09-24 苏州智加科技有限公司 Error estimation method, error estimation device, vehicle-mounted terminal and storage medium
CN113561963A (en) * 2020-04-29 2021-10-29 华为技术有限公司 Parking method and device and vehicle
CN115086538A (en) * 2021-03-15 2022-09-20 北京字跳网络技术有限公司 Shooting position determining method, device, equipment and medium
WO2023054238A1 (en) * 2021-09-29 2023-04-06 株式会社アイシン Parking assistance device
CN116109698A (en) * 2023-04-11 2023-05-12 禾多科技（北京）有限公司 Method, device and storage medium for determining coordinate value of target virtual parking space
CN116434556A (en) * 2023-04-10 2023-07-14 同方威视科技江苏有限公司 Vehicle information acquisition method, device, equipment and medium thereof

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107784672A (en) * 2016-08-26 2018-03-09 百度在线网络技术（北京）有限公司 For the method and apparatus for the external parameter for obtaining in-vehicle camera
DE102018123393A1 (en) * 2018-09-24 2020-03-26 Denso Corporation Detection of parking areas
CN111007540A (en) * 2018-10-04 2020-04-14 赫尔环球有限公司 Method and apparatus for predicting sensor error
CN113561963A (en) * 2020-04-29 2021-10-29 华为技术有限公司 Parking method and device and vehicle
CN115086538A (en) * 2021-03-15 2022-09-20 北京字跳网络技术有限公司 Shooting position determining method, device, equipment and medium
CN113432620A (en) * 2021-06-04 2021-09-24 苏州智加科技有限公司 Error estimation method, error estimation device, vehicle-mounted terminal and storage medium
WO2023054238A1 (en) * 2021-09-29 2023-04-06 株式会社アイシン Parking assistance device
CN116434556A (en) * 2023-04-10 2023-07-14 同方威视科技江苏有限公司 Vehicle information acquisition method, device, equipment and medium thereof
CN116109698A (en) * 2023-04-11 2023-05-12 禾多科技（北京）有限公司 Method, device and storage medium for determining coordinate value of target virtual parking space

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
车载鱼眼图像的全景图拼接误差分析;曹君 等;测绘科学(第07期);第202-204页 *

Also Published As

Publication number Publication date
CN116740982A (en) 2023-09-12

Similar Documents

Publication Publication Date Title
Miki et al. Elevation mapping for locomotion and navigation using gpu
CN109522803A (en) A kind of room area divides and recognition methods, device and terminal device
Tee et al. Lidar-based 2D SLAM for mobile robot in an indoor environment: A review
CN110422175B (en) Vehicle state estimation method and device, electronic device, storage medium, and vehicle
JP2012529691A (en) 3D image generation
CN112991389B (en) Target tracking method and device and mobile robot
CN110260856A (en) One kind building drawing method and device
CN105869181A (en) Body joint distributed information consistency estimation method based on interacting multiple models
Klančar et al. Mobile-robot pose estimation and environment mapping using an extended Kalman filter
CN112233149A (en) Scene flow determination method and device, storage medium and electronic device
CN116740982B (en) Target parking space determination method and device, storage medium and electronic device
Meyer et al. Geometric BIM verification of indoor construction sites by photogrammetric point clouds and evidence theory
CN103839280A (en) Method for tracking human body posture based on visual information
Liedtke et al. Use of explicit knowledge for the reconstruction of 3-D object geometry
Leung et al. Evaluating set measurement likelihoods in random-finite-set slam
Demim et al. Visual SVSF-SLAM algorithm based on adaptive boundary layer width
Almeida et al. Real-time tracking of moving objects using particle filters
CN114580700B (en) TVDI drought index prediction method based on semantic Bayesian network
Yi et al. Bayesian robot localization using spatial object contexts
CN108776972A (en) A kind of method for tracing object and device
CN114911157A (en) Robot navigation control method and system based on partial observable reinforcement learning
Frey et al. Complexity analysis and efficient measurement selection primitives for high-rate graph SLAM
CN117726908B (en) Training method and device for picture generation model, storage medium and electronic device
CN112445210B (en) Method and device for determining motion trail, storage medium and electronic device
Mahadevaswamy et al. Robotic mapping using autonomous vehicle

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