CN113253278A - Parking space identification method and device and computer storage medium - Google Patents
Parking space identification method and device and computer storage medium Download PDFInfo
- Publication number
- CN113253278A CN113253278A CN202110470409.XA CN202110470409A CN113253278A CN 113253278 A CN113253278 A CN 113253278A CN 202110470409 A CN202110470409 A CN 202110470409A CN 113253278 A CN113253278 A CN 113253278A
- Authority
- CN
- China
- Prior art keywords
- distance
- sample
- automobile
- point
- parking space
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 32
- 230000009191 jumping Effects 0.000 claims abstract description 39
- 238000001914 filtration Methods 0.000 claims description 13
- 238000001514 detection method Methods 0.000 claims description 12
- 238000010276 construction Methods 0.000 claims description 5
- 238000004422 calculation algorithm Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 5
- 230000004927 fusion Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 206010063385 Intellectualisation Diseases 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S15/00—Systems using the reflection or reradiation of acoustic waves, e.g. sonar systems
- G01S15/02—Systems using the reflection or reradiation of acoustic waves, e.g. sonar systems using reflection of acoustic waves
- G01S15/06—Systems determining the position data of a target
- G01S15/08—Systems for measuring distance only
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S15/00—Systems using the reflection or reradiation of acoustic waves, e.g. sonar systems
- G01S15/88—Sonar systems specially adapted for specific applications
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Computer Networks & Wireless Communication (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
- Measurement Of Velocity Or Position Using Acoustic Or Ultrasonic Waves (AREA)
Abstract
The embodiment of the application discloses a parking space identification method and device and a computer storage medium, and belongs to the technical field of automatic driving. The method comprises the following steps: obtaining distance sample information through an ultrasonic radar installed on an automobile, wherein the distance sample information is used for describing the distance between an obstacle detected by the ultrasonic radar and the automobile; determining a distance sample jumping point from the distance sample information, wherein the distance sample jumping point is used for describing the starting position and the ending position of an obstacle located in the current environment; and matching the parking space types according to the distance sample trip points and the stored automobile model samples so as to identify the parking spaces in the current environment of the automobile. According to the embodiment of the application, the distance sample jumping points are determined through the distance sample information of the ultrasonic radar, and the parking space type matching is carried out according to the distance sample jumping points and the automobile model samples, so that the parking space is identified, the parking space identification cost is reduced, and the parking space identification accuracy is improved.
Description
Technical Field
The embodiment of the application relates to the technical field of automatic driving, in particular to a parking space identification method and device and a computer storage medium.
Background
Along with the development of society, automobiles are more and more intelligent in development, wherein automatic parking is one of the intelligentized expressions of automobiles. One of the key technologies for automatic parking of automobiles is parking space identification.
At present, when the parking space is identified, the parking space is generally identified through an image vision sensor, or the parking space is identified through a mode of combining the image vision sensor and an ultrasonic radar sensor. When the parking space is identified through the image vision sensor, the image can be collected through the image vision sensor, and the collected image is processed through an image algorithm, so that the parking space is identified. When carrying out parking stall discernment through image vision sensor and ultrasonic radar sensor, image vision sensor gathers the image, and ultrasonic radar sensor can acquire ultrasonic radar data, later fuses the image of gathering with ultrasonic radar data, through the data identification parking stall after fusing.
However, when the parking space is identified by the image vision sensor, an image algorithm is needed, the image algorithm is complex, and in rainy and snowy weather, the acquired image may not be clear enough, so that the parking space identification may not be accurate enough. And when carrying out parking stall discernment through the mode that image vision sensor and ultrasonic radar sensor combined together, involve the data fusion algorithm, the fusion algorithm is equally complicated, and the mode that two sensors combined together leads to the parking stall to discern the cost higher.
Disclosure of Invention
The embodiment of the application provides a parking space identification method and device and a computer storage medium, which can be used for solving the problems of low parking space identification accuracy or high parking space identification cost in the related technology. The technical scheme is as follows:
on the one hand, a parking space identification method is provided, and the method comprises the following steps:
obtaining distance sample information through an ultrasonic radar installed on an automobile, wherein the distance sample information is used for describing the distance between an obstacle detected by the ultrasonic radar and the automobile;
determining a distance sample jumping point from the distance sample information, wherein the distance sample jumping point is used for describing the starting position and the ending position of an obstacle located in the current environment;
and matching the parking space types according to the distance sample trip points and the stored automobile model samples so as to identify the parking spaces in the current environment of the automobile.
In some embodiments, said determining a distance sample trip point from said distance sample information comprises:
acquiring body state information of the automobile;
according to the automobile body state information, taking any point in the space where the automobile is located as an origin, taking the detection direction of the ultrasonic radar as a longitudinal axis, and taking the driving direction of the automobile as a transverse axis to construct a two-dimensional space coordinate system;
filtering the distance sample information to filter out sample information which does not meet the distance requirement in the distance sample information;
constructing a distance curve in the two-dimensional space coordinate system through the filtered distance sample information;
determining the distance sample trip point from the distance curve.
In some embodiments, said determining said distance sample trip point from said distance curve comprises:
dividing the distance curve into two sub-sample curves by taking a reference division point in the distance curve as a division basis, wherein the reference division point is any reference point which is not selected as the division basis, and the any reference point is a point corresponding to any distance sample information;
for each reference point in each sub-sample curve, determining a mean square error for the each reference point;
adding the mean square error of each reference point in each sub-sample curve to obtain a residual value, and dividing the distance curve into two sub-sample curves by taking a reference dividing point in the distance curve as a dividing basis until a minimum residual value is obtained, or until N residual values larger than or equal to a residual threshold value are obtained, wherein N is a positive integer larger than or equal to 2;
when the minimum residual value is obtained, determining a reference point corresponding to the minimum residual value as the distance sample trip point; or when N residual values which are larger than or equal to the residual threshold value are acquired, determining the reference points corresponding to the N residual values as the distance sample jumping points.
In some embodiments, the performing parking space type matching according to the distance sample trip point and a stored car model sample to identify a parking space in the current environment where the car is located includes:
determining an obstacle profile corresponding to the distance sample jumping point according to the distance sample jumping point;
determining a correlation between the obstacle profile and a stored car model sample;
when the correlation between the obstacle contour and the automobile model sample is smaller than or equal to a correlation threshold value, determining that the obstacle contour and the automobile model sample are successfully matched;
determining the parking space type corresponding to the automobile model sample as the parking space type of the parking space in the current environment of the automobile;
and identifying the parking space in the current environment of the automobile according to the parking space type and the distance sample trip point.
In some embodiments, the identifying parking spaces in the current environment of the automobile according to the space types and the distance sample trip points includes:
determining a space to be identified according to the distance sample jumping points, wherein the space to be identified is a space without obstacles;
and when the space distance of the space to be identified is greater than or equal to the parking distance corresponding to the parking space type, determining that the space to be identified is the parking space in the current environment of the automobile.
In another aspect, a parking space recognition apparatus is provided, the apparatus including:
the system comprises an acquisition module, a detection module and a display module, wherein the acquisition module is used for acquiring distance sample information through an ultrasonic radar installed on an automobile, and the distance sample information is used for describing the distance between an obstacle detected by the ultrasonic radar and the automobile;
the determining module is used for determining a distance sample jumping point from the distance sample information, and the distance sample jumping point is used for describing the starting position and the ending position of an obstacle located in the current environment;
and the identification module is used for identifying the parking space in the current environment of the automobile according to the distance sample trip point.
In some embodiments, the determining module comprises:
the acquisition submodule is used for acquiring the body state information of the automobile;
the first construction submodule is used for constructing a two-dimensional space coordinate system by taking any point in the space where the automobile is located as an origin, the detection direction of the ultrasonic radar as a longitudinal axis and the driving direction of the automobile as a transverse axis according to the automobile body state information;
the filtering submodule is used for filtering the distance sample information to filter out sample information which does not meet the distance requirement in the distance sample information;
the second construction submodule is used for constructing a distance curve in the two-dimensional space coordinate system through the filtered distance sample information;
a first determining submodule for determining the distance sample trip point from the distance curve.
In some embodiments, the first determination submodule is to:
dividing the distance curve into two sub-sample curves by taking a reference division point in the distance curve as a division basis, wherein the reference division point is any reference point which is not selected as the division basis, and the any reference point is a point corresponding to any distance sample information;
for each reference point in each sub-sample curve, determining a mean square error for the each reference point;
adding the mean square error of each reference point in each sub-sample curve to obtain a residual value, and dividing the distance curve into two sub-sample curves by taking a reference dividing point in the distance curve as a dividing basis until a minimum residual value is obtained, or until N residual values larger than or equal to a residual threshold value are obtained, wherein N is a positive integer larger than or equal to 2;
when the minimum residual value is obtained, determining a reference point corresponding to the minimum residual value as the distance sample trip point; or when N residual values which are larger than or equal to the residual threshold value are acquired, determining the reference points corresponding to the N residual values as the distance sample jumping points.
In some embodiments, the identification module comprises:
the second determining submodule is used for determining an obstacle outline corresponding to the distance sample jumping point according to the distance sample jumping point;
a third determining submodule for determining a correlation between the obstacle profile and a stored car model sample;
a fourth determining submodule, configured to determine that the obstacle contour and the automobile model sample are successfully matched when a correlation between the obstacle contour and the automobile model sample is smaller than or equal to a correlation threshold;
a fifth determining submodule, configured to determine a parking space type corresponding to the automobile model sample as a parking space type of a parking space in an environment where the automobile is currently located;
and the identification submodule is used for identifying the parking stall in the current environment of the automobile according to the stall type and the distance sample trip point.
In some embodiments, the identifier module is to:
determining a space to be identified according to the distance sample jumping points, wherein the space to be identified is a space without obstacles;
and when the space distance of the space to be identified is greater than or equal to the parking distance corresponding to the parking space type, determining that the space to be identified is the parking space in the current environment of the automobile.
In another aspect, a computer storage medium is provided, where instructions are stored on the computer storage medium, and when executed by a processor, the instructions implement any one of the steps of the above parking space identification method.
The beneficial effects brought by the technical scheme provided by the embodiment of the application at least comprise:
in the embodiment of the application, the distance sample trip point can be determined through the distance sample information of the ultrasonic radar, and the distance sample trip point can describe the starting position and the ending position of the obstacle located in the current environment, and can be matched with the type of the parking space according to the distance sample trip point and the automobile model sample, so that the parking space is identified, the parking space identification cost is reduced, and the accuracy of parking space identification is improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic view of a parking space identification system according to an embodiment of the present disclosure;
fig. 2 is a flowchart of a parking space identification method provided in the embodiment of the present application;
fig. 3 is a flowchart of another parking space identification method provided in the embodiment of the present application;
FIG. 4 is a schematic diagram of distance sample information provided by an embodiment of the present application in a two-dimensional space coordinate system;
fig. 5 is a schematic structural diagram of a parking space recognition device according to an embodiment of the present application;
fig. 6 is a schematic structural diagram of a determination module provided in an embodiment of the present application;
fig. 7 is a schematic structural diagram of an identification module according to an embodiment of the present application.
Detailed Description
To make the objects, technical solutions and advantages of the embodiments of the present application more clear, the embodiments of the present application will be further described in detail with reference to the accompanying drawings.
Before explaining the parking space identification method provided by the embodiment of the present application in detail, an application scenario and a system architecture provided by the embodiment of the present application are explained first.
First, an application scenario provided in the embodiment of the present application is explained.
With the development of automobile intellectualization, the parking space is exactly one of basic performances of automobile intellectualization. When the automobile is used for identifying the parking space, if the image vision sensor is used for identifying the parking space, the image algorithm is required to be used and is relatively complex, so that the parking space identification process is complex, and in rainy and snowy weather, the collected image is not clear enough, so that the parking space identification is not accurate enough. If the parking space is identified by the combination of the image vision sensor and the ultrasonic radar sensor, the data fusion algorithm is involved, the fusion algorithm is also complex, and the parking space identification cost is high due to the combination of the two sensors.
Based on the application scene, the embodiment of the application provides the parking space identification method which is high in reliability and concise in identification process.
A system architecture provided by the present application is explained next.
Fig. 1 is a schematic diagram of a parking space identification system architecture provided in an embodiment of the present application, and referring to fig. 1, the system architecture includes an ultrasonic radar 1 (or referred to as an ultrasonic radar sensor), an MCU controller 2, and a vehicle body controller 3. The ultrasonic radar 1 is in communication connection with pins of the MCU controller 2, and the MCU controller 2 is connected with the automobile body controller 3.
The ultrasonic radar 1 is used for obtaining distance sample information between the automobile and the obstacle and sending the obtained distance sample information to the MCU controller 2, and the ultrasonic radar can obtain the distance sample information between the automobile and the obstacle according to the time length of an ECHO high level of a timer peripheral sampling ultrasonic sensor pin inside the MCU controller 2. The body controller 3 is used for sending the body state information of the automobile to the MCU controller 2. The MCU controller 2 is used for receiving the distance sample information sent by the ultrasonic radar 1 and the car sound state information sent by the car body controller 3, establishing a two-dimensional space coordinate system according to the car body state information, determining a distance sample jumping point in the two-dimensional space coordinate system according to the distance sample information, and then identifying the parking space in the current environment of the car according to the distance sample jumping point.
As an example, the MCU controller 2 can periodically (e.g., 30 ms) trigger a control command to the ultrasonic radar 1 to make the ultrasonic radar perform obstacle distance measurement. The MCU controller 2 CAN acquire the vehicle body state information of the vehicle body controller 3 through the CAN communication, for example, acquire the current vehicle speed, steering angle, and the like.
As an example, the ultrasonic radar 1 can be of the HCSR04 type, and the ultrasonic radar 1 is installed at a side position of a front bumper of an automobile to measure an obstacle distance on both sides of the automobile body.
It should be understood by those skilled in the art that the foregoing system architecture is merely exemplary, and other modules, components, etc. that exist or may come into existence in the future, as applicable to the present application, are intended to be included within the scope of the present application and are incorporated herein by reference.
Fig. 2 is a flowchart of a parking space identification method provided in an embodiment of the present application, where the parking space identification method may include the following steps:
step 201: distance sample information is acquired by an ultrasonic radar installed in an automobile, and the distance sample information is used for describing the distance between an obstacle detected by the ultrasonic radar and the automobile.
Step 202: from the distance sample information, a distance sample trip point is determined, which describes the starting position and the ending position of an obstacle located in the current environment.
Step 203: and matching the parking space types according to the distance sample trip points and the stored automobile model samples so as to identify the parking spaces in the current environment of the automobile.
In the embodiment of the application, the distance sample trip point can be determined through the distance sample information of the ultrasonic radar, and the distance sample trip point can describe the starting position and the ending position of the obstacle located in the current environment, and can be matched with the type of the parking space according to the distance sample trip point and the automobile model sample, so that the parking space is identified, the parking space identification cost is reduced, and the accuracy of parking space identification is improved.
In some embodiments, determining a range sample trip point from the range sample information comprises:
acquiring the body state information of the automobile;
according to the vehicle body state information, taking any point in the space where the vehicle is located as an origin, taking the detection direction of the ultrasonic radar as a longitudinal axis, and taking the driving direction of the vehicle as a transverse axis to construct a two-dimensional space coordinate system;
filtering the distance sample information to filter out sample information which does not meet the distance requirement in the distance sample information;
constructing a distance curve in the two-dimensional space coordinate system through the filtered distance sample information;
the distance sample trip point is determined from the distance curve.
In some embodiments, determining the distance sample trip point from the distance curve comprises:
dividing the distance curve into two sub-sample curves by taking a reference division point in the distance curve as a division basis, wherein the reference division point is any reference point which is not selected as the division basis, and the any reference point is a point corresponding to any distance sample information;
for each reference point in each sub-sample curve, determining a mean square error for the each reference point;
adding the mean square error of each reference point in each sub-sample curve to obtain a residual value, and dividing the distance curve into two sub-sample curves by taking a reference dividing point in the distance curve as a dividing basis until a minimum residual value is obtained, or until N residual values which are more than or equal to a residual threshold value are obtained, wherein N is a positive integer which is more than or equal to 2;
when the minimum residual value is obtained, determining a reference point corresponding to the minimum residual value as the distance sample trip point; or when acquiring N residual values greater than or equal to the residual threshold, determining the reference points corresponding to the N residual values as the distance sample trip points.
In some embodiments, performing parking space type matching according to the distance sample trip point and the stored car model sample to identify the parking space in the current environment of the car includes:
determining an obstacle profile corresponding to the distance sample jumping point according to the distance sample jumping point;
determining a correlation between the obstacle profile and a stored car model sample;
when the correlation between the obstacle outline and the automobile model sample is smaller than or equal to a correlation threshold value, determining that the obstacle outline and the automobile model sample are successfully matched;
determining the parking space type corresponding to the automobile model sample as the parking space type of the parking space in the current environment of the automobile;
and identifying the parking space in the current environment of the automobile according to the parking space type and the distance sample trip point.
In some embodiments, identifying the parking space in the current environment of the automobile according to the space type and the distance sample trip point includes:
determining a space to be identified according to the distance sample jumping point, wherein the space to be identified is a space without obstacles;
and when the space distance of the space to be identified is greater than or equal to the parking distance corresponding to the parking space type, determining that the space to be identified is the parking space in the current environment of the automobile.
All the above optional technical solutions can be combined arbitrarily to form an optional embodiment of the present application, and the present application embodiment is not described in detail again.
Fig. 3 is a flowchart of a parking space identification method provided in an embodiment of the present application, which is exemplified by applying the parking space identification method to an automobile, and the parking space identification method may include the following steps:
step 301: the automobile acquires distance sample information through the installed ultrasonic radar.
It should be noted that the distance sample information is used to describe the distance between the obstacle detected by the ultrasonic radar and the vehicle.
As an example, an automobile can acquire distance sample information through an installed ultrasonic radar when receiving a search instruction.
The search command is triggered when the driver acts on the vehicle through a specified operation when the driver needs to park the vehicle. The specified operation can be a click operation, a slide operation, a voice operation, a toggle operation, and the like.
As an example, the car can also acquire distance sample information through an installed ultrasonic radar after detecting that the car enters a parking lot.
It should be noted that, when the vehicle acquires the distance sample information by the ultrasonic radar, the ultrasonic radar can acquire the distance sample information once every specified time interval, and the specified time interval can be set in advance, for example, the specified time interval can be 30 milliseconds or the like.
In some embodiments, the vehicle can locate its own position by the locating device to obtain the current position, and determine whether to enter the parking lot according to the current position.
Step 302: the automobile determines the distance sample trip point from the distance sample information.
It should be noted that the distance sample trip point is used to describe the starting position and the ending position of the obstacle located in the current environment.
As an example, the operation of the automobile to determine the trip point of the distance sample from the distance sample information includes: acquiring body state information of an automobile; according to the state information of the automobile body, taking any point in the space where the automobile is located as an origin, taking the detection direction of the ultrasonic radar as a longitudinal axis, and taking the driving direction of the automobile as a transverse axis to construct a two-dimensional space coordinate system; filtering the distance sample information to filter out sample information which does not meet the distance requirement in the distance sample information; constructing a distance curve in a two-dimensional space coordinate system through the filtered distance sample information; the distance sample trip point is determined from the distance curve.
In order to facilitate the determination of the trip point of the distance sample, the automobile can construct a two-dimensional space coordinate system, and because the ultrasonic radar is usually installed at the side position of the front bumper of the automobile, the automobile can obtain any point in the space where the automobile is located as an origin, and construct the two-dimensional space coordinate system by taking the detection direction of the ultrasonic radar as a longitudinal axis and the driving direction of the automobile as a transverse axis. For example, the automobile can establish a two-dimensional space coordinate system with the center of the automobile sound as an origin.
Because objects such as a bush may exist in a parking lot, a large gap exists between the objects, when the ultrasonic radar of the automobile transmits radar waves to perform distance detection, the reflected waves may not be received after the radar waves are transmitted, so that abnormal data exists in distance sample information, or some uneven objects may exist in the current environment of the automobile, the uneven objects may cause some clutter information acquired by the ultrasonic radar, and the clutter information may influence the identification of the automobile on a parking space, so that the automobile can perform filtering processing on the distance sample information to filter the sample information which does not meet the distance requirement in the distance sample information.
It should be noted that the distance requirement can be set in advance according to requirements, for example, the distance sample information can be sample information capable of receiving the reflected wave, and/or the distance sample information can be sample information larger than a first distance threshold and smaller than a second distance threshold, and the first distance threshold and the second distance threshold can be set in advance.
In some embodiments, the automobile can also construct a two-dimensional space coordinate system by taking any point in the space where the automobile is located as an origin, taking the detection direction of the ultrasonic radar as a longitudinal axis and taking the driving direction of the automobile as a transverse axis according to the automobile body state information; and then constructing a sample curve in a two-dimensional space coordinate system according to the collected distance sample information, and then filtering the sample curve to obtain the distance curve.
In some embodiments, the operation of the vehicle to determine the trip point of the distance sample from the distance curve comprises at least: and carrying out global search on the distance curve to obtain a distance sample trip point.
As an example, the operation of the vehicle to determine the trip point of the distance sample from the distance curve can further comprise: dividing the distance curve into two sub-sample curves by taking a reference division point in the distance curve as a division basis, wherein the reference division point is any one reference point which is not selected as the division basis, and any one reference point is a point corresponding to any distance sample information; determining, for each reference point in each sub-sample curve, a mean square error for each reference point; adding the mean square error of each reference point in each sub-sample curve to obtain a residual value, and returning to divide the distance curve into two sub-sample curves by taking the reference dividing point in the distance curve as a dividing basis until a minimum residual value is obtained, or until N residual values which are greater than or equal to a residual threshold value are obtained, wherein N is a positive integer greater than or equal to 2; when the minimum residual value is obtained, determining a reference point corresponding to the minimum residual value as a distance sample trip point; or when N residual values which are larger than or equal to the residual threshold value are acquired, determining the reference points corresponding to the N residual values as distance sample jumping points.
Because the distance sample information acquired by the automobile comprises a large amount of data, in order to improve the efficiency of determining the trip point of the distance sample, the automobile can divide the distance curve into two sub-sample curves by taking the reference dividing point in the distance curve as a dividing basis.
After passing through the distance sample trip point, the statistical characteristics of the distance curve, such as the average value, will suddenly change, and a maximum trip of the statistical root mean square error will occur near the distance sample trip point. Therefore, to determine the range sample trip point, the vehicle can determine the mean square error of each reference point for each reference point in each sub-sample curve and add the mean square errors of each reference point in each sub-sample curve to obtain a residual value.
As an example, when the distance curve is divided into two sub-sample curves, and the mth point in the distance curve is the reference division point, the curve between the 1 st to mth reference points (excluding the mth reference point) is referred to as a first sub-sample curve, and the curve between the mth to nth reference points (including the nth reference point) is referred to as a second sub-sample curve in the reference point acquisition order. The car can determine the residual value of the second sub-sample curve by the following first formula.
In the first formula (1), n is the number of reference points in the distance curve, m is the mth reference point in the n reference points, and xrDistance information of the r-th reference point.
In one implementation environment, when there are n pieces of distance sample information, that is, when there are n reference points, the distance information of the n reference points is x respectively1、x2…xnReference point xmIs selected as a reference segmentation point, and m<n, the residual value of the second sub-sample curve is the result calculated by the first formula.
When an obstacle exists in the current environment, the obstacle exists at the starting position and the ending position, and more than one obstacle exists, so that in order to determine all distance sample trip points, the automobile needs to change the position of the reference segmentation point, and repeatedly determine the residual value of each sub-sample curve to determine the minimum residual value, or in order to obtain a plurality of distance sample trip points, a residual threshold value can be set, so that N residual values larger than or equal to the residual threshold value are obtained, and then N distance sample trip points are obtained.
It should be noted that the residual threshold can be set in advance according to requirements, for example, the residual threshold can be 15m, 20m, and so on.
In one implementation, referring to fig. 4(a), the vehicle can construct a sample curve in a two-dimensional space coordinate system according to the collected distance sample information, and then the vehicle performs a filtering process on the sample curve to obtain a distance curve as shown in fig. 4(b), and the vehicle determines 5 distance sample transition points from the distance curve, referring to fig. 4(c), where the 5 distance sample transition points are the starting position and the ending position of the obstacle scanned by the ultrasonic radar.
The system is worthy of being multiple in people, and the statistical characteristic information of the distance sample information is extracted, so that the initial position of the barrier can be identified more accurately, and the accuracy of the parking space position information is improved.
Step 303: and identifying the parking space in the current environment of the automobile according to the distance sample trip points.
Although some environments have vacant lands, the vacant lands may be spaces such as pedestrian paths and the like which cannot be used for parking, at this time, even if the automobile recognizes that spaces capable of parking exist in the current environment, the spaces are not parking spaces, and traffic violation may be caused by random parking. Therefore, the automobile needs to determine the effectiveness of parking spaces in the environment, that is, the automobile needs to determine that the space in the environment where parking is not allowed is the parking space instead of a sidewalk and the like. In general, when other cars parked in the parking space exist in the current environment, the empty space in the current environment can be determined to be the effective parking space with high probability, and the distance change of the other cars parked in the parking space has a certain rule. Therefore, in order to determine that the effective parking space exists in the current environment of the automobile, the automobile can identify the parking space in the current environment of the automobile according to the distance sample trip point.
As an example, the car can directly identify the parking space in the current environment of the car according to the distance sample trip point, and can also perform space type matching according to the distance sample trip point and the stored car model sample to identify the parking space in the current environment of the car.
As an example, the operation of the automobile performing parking space type matching according to the distance sample trip point and the stored automobile model sample to identify the parking space in the environment where the automobile is currently located at least includes: determining an obstacle outline corresponding to the distance sample jumping point according to the distance sample jumping point; determining a correlation between the obstacle profile and a stored car model sample; when the correlation between the obstacle outline and the automobile model sample is smaller than or equal to a correlation threshold value, determining that the obstacle outline and the automobile model sample are successfully matched; determining the parking space type corresponding to the automobile model sample as the parking space type of the parking space in the current environment of the automobile; and identifying the parking space in the current environment of the automobile according to the parking space type and the distance sample trip point.
Because the obstacle in the current environment may be other automobiles or may not be other automobiles, when the obstacle in the current environment is other automobiles, it can be stated that the vacant space in the current environment is a parking space instead of a space such as a sidewalk and the like which is not allowed to park. Therefore, the automobile can determine that the obstacle outline is successfully matched with the automobile model sample according to the obstacle outline corresponding to the distance sample jump point and when the correlation between the obstacle outline and the automobile model sample is greater than or equal to the correlation threshold value.
It should be noted that the correlation threshold can be set in advance according to requirements, for example, the correlation threshold can be 90%, 95%, 99%, and so on.
When the correlation between the obstacle outline and the automobile model sample is larger than or equal to the correlation threshold value, the obstacle outline is the automobile outline, and the obstacle is other automobiles, so that the automobile can determine the parking space type corresponding to the automobile model sample as the parking space type of the parking space in the current environment of the automobile.
It should be noted that the car model sample and the parking space type corresponding to the car model sample can be set in advance and stored. The parking space types include vertical parking spaces, horizontal parking spaces, and the like.
In one implementation environment, referring to fig. 4(d), after the automobile performs correlation calculation between the obstacle outline and the automobile model sample, a correlation diagram as shown in fig. 4(d) can be obtained, and it can be determined through fig. 4(d) that there are 3 other automobiles parked in the parking space in the environment currently in use.
As an example, the operation of the automobile for identifying the parking space in the current environment of the automobile according to the space type and the distance sample trip point at least comprises the following steps: determining a space to be identified according to the distance sample jumping points, wherein the space to be identified is a space without obstacles; and when the space distance of the space to be identified is greater than or equal to the parking distance corresponding to the parking space type, determining that the space to be identified is the parking space in the current environment of the automobile.
Because the distance sample trip point is used for describing the starting position and the ending position of the obstacle in the current environment, the automobile can determine whether a space which can allow parking exists between any two adjacent obstacles according to the distance sample trip point, that is, the automobile can determine the space to be identified according to the distance sample trip point.
In some embodiments, the vehicle can determine whether any distance sample trip point is the starting position or the ending position of the obstacle, for example, when the distance sample trip point is detected to be a trip point with a distance from small to large, the distance sample trip point is the starting position of the obstacle, and when the distance sample trip point is detected to be a trip point with a distance from large to small, the distance sample trip point is determined to be the ending position of the obstacle; according to the distance sample jumping point, the automobile can detect the space distance between two adjacent obstacles; when the distance between two adjacent obstacles (namely the space distance of the space to be identified) is greater than or equal to the parking distance corresponding to the parking space type, determining that the space to be identified is the parking space in the current environment of the automobile.
It should be noted that, according to the different parking spaces, for example, the parking distances are different, for example, when the parking space is a horizontal parking space, the corresponding parking distances are 6 meters, 6.5 meters, and the like, and when the parking space is a vertical parking space, the corresponding parking distances are 2 meters, 2.1 meters, and the like.
It is worth explaining that correlation calculation can be performed on the obstacle outline and the automobile model sample, so that rapid matching of a large number of automobile model samples is achieved, different parking space search scenes can be adapted, feature extraction of the obstacle outline is simplified, and calculation amount is reduced.
Step 304: after the parking space is identified, the vehicle is parked in the identified parking space.
As an example, after the car identifies the parking space, the car can plan a parking path according to the location of the parking space and the current location of the car, and control the car to automatically park according to the parking path.
As an example, after the parking space is identified, the automobile can indicate the location of the parking space through the prompt message, so that the driver can drive the automobile to park in the parking space according to the prompt message.
The prompt message can be a combination of voice, text, and image.
In the embodiment of the application, the automobile can perform statistical feature extraction on distance sample information of the ultrasonic radar, so that the distance sample trip point is determined, and the starting position and the ending position of the obstacle located in the current environment can be described by the distance sample trip point, so that the parking space can be effectively identified by performing correlation calculation on the obstacle outline and the automobile model sample according to the distance sample trip point, the parking space identification cost is reduced, and the parking space identification accuracy is improved.
Fig. 5 is a schematic structural diagram of a parking space identification device provided in an embodiment of the present application, where the parking space identification device may be implemented by software, hardware, or a combination of the software and the hardware. The recognition device of this parking stall can include: an acquisition module 501, a determination module 502 and an identification module 503.
An obtaining module 501, configured to obtain distance sample information through an ultrasonic radar installed in an automobile, where the distance sample information is used to describe a distance between an obstacle detected by the ultrasonic radar and the automobile;
a determining module 502, configured to determine a distance sample trip point from the distance sample information, where the distance sample trip point is used to describe a starting position and an ending position of an obstacle located in a current environment;
and the identifying module 503 is configured to perform parking space type matching according to the distance sample trip point and the stored automobile model sample, so as to identify a parking space in the current environment of the automobile.
In some embodiments, referring to fig. 6, the determining module 502 comprises:
the obtaining submodule 5021 is used for obtaining body state information of the automobile;
the first construction submodule 5022 is used for constructing a two-dimensional space coordinate system by taking any point in the space where the automobile is located as an origin, the detection direction of the ultrasonic radar as a longitudinal axis and the driving direction of the automobile as a transverse axis according to the automobile body state information;
the filtering submodule 5023 is used for filtering the distance sample information to filter out sample information which does not meet the distance requirement in the distance sample information;
a second constructing submodule 5024, configured to construct a distance curve in the two-dimensional space coordinate system according to the filtered distance sample information;
a first determining submodule 5025 is used for determining the distance sample trip point from the distance curve.
In some embodiments, the first determination submodule 5025 is configured to:
dividing the distance curve into two sub-sample curves by taking a reference division point in the distance curve as a division basis, wherein the reference division point is any reference point which is not selected as the division basis, and the any reference point is a point corresponding to any distance sample information;
for each reference point in each sub-sample curve, determining a mean square error for the each reference point;
adding the mean square error of each reference point in each sub-sample curve to obtain a residual value, and dividing the distance curve into two sub-sample curves by taking a reference dividing point in the distance curve as a dividing basis until a minimum residual value is obtained, or until N residual values larger than or equal to a residual threshold value are obtained, wherein N is a positive integer larger than or equal to 2;
when the minimum residual value is obtained, determining a reference point corresponding to the minimum residual value as the distance sample trip point; or when N residual values which are larger than or equal to the residual threshold value are acquired, determining the reference points corresponding to the N residual values as the distance sample jumping points.
In some embodiments, referring to fig. 7, the identification module 503 comprises:
a second determining submodule 5031, configured to determine, according to the distance sample trip point, an obstacle contour corresponding to the distance sample trip point;
a third determining submodule 5032 for determining a correlation between the obstacle contour and a stored car model sample;
a fourth determining sub-module 5033, configured to determine that the obstacle contour matches the automobile model sample successfully when the correlation between the obstacle contour and the automobile model sample is less than or equal to a correlation threshold;
a fifth determining submodule 5034, configured to determine the parking space type corresponding to the automobile model sample as the parking space type of the parking space in the current environment where the automobile is located;
the identifier module 5035 is configured to identify a parking space in the current environment of the automobile according to the parking space type and the distance sample trip point.
In some embodiments, the identifier module 5035 is configured to:
determining a space to be identified according to the distance sample jumping points, wherein the space to be identified is a space without obstacles;
and when the space distance of the space to be identified is greater than or equal to the parking distance corresponding to the parking space type, determining that the space to be identified is the parking space in the current environment of the automobile.
In the embodiment of the application, the automobile can perform statistical feature extraction on distance sample information of the ultrasonic radar, so that the distance sample trip point is determined, and the starting position and the ending position of the obstacle located in the current environment can be described by the distance sample trip point, so that the parking space can be effectively identified by performing correlation calculation on the obstacle outline and the automobile model sample according to the distance sample trip point, the parking space identification cost is reduced, and the parking space identification accuracy is improved.
It should be noted that: the parking space recognition device provided by the above embodiment is exemplified only by the division of the above functional modules when recognizing a parking space, and in practical application, the above function allocation can be completed by different functional modules as required, that is, the internal structure of the device is divided into different functional modules, so as to complete all or part of the above described functions. In addition, the parking space identification device provided by the embodiment and the parking space identification method embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment and is not repeated here.
The embodiment of the application further provides a non-transitory computer-readable storage medium, and when the instruction in the storage medium is executed by the processor of the server, the server can execute the parking space identification method provided by the embodiment.
The embodiment of the application further provides a computer program product containing instructions, and when the computer program product runs on the server, the server is enabled to execute the parking space identification method provided by the embodiment.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, where the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
The above description is only a preferred embodiment of the present application and should not be taken as limiting the present application, and any modifications, equivalents, improvements, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.
Claims (10)
1. A parking space identification method is characterized by comprising the following steps:
obtaining distance sample information through an ultrasonic radar installed on an automobile, wherein the distance sample information is used for describing the distance between an obstacle detected by the ultrasonic radar and the automobile;
determining a distance sample jumping point from the distance sample information, wherein the distance sample jumping point is used for describing the starting position and the ending position of an obstacle located in the current environment;
and matching the parking space types according to the distance sample trip points and the stored automobile model samples so as to identify the parking spaces in the current environment of the automobile.
2. The method of claim 1, wherein said determining distance sample trip points from said distance sample information comprises:
acquiring body state information of the automobile;
according to the automobile body state information, taking any point in the space where the automobile is located as an origin, taking the detection direction of the ultrasonic radar as a longitudinal axis, and taking the driving direction of the automobile as a transverse axis to construct a two-dimensional space coordinate system;
filtering the distance sample information to filter out sample information which does not meet the distance requirement in the distance sample information;
constructing a distance curve in the two-dimensional space coordinate system through the filtered distance sample information;
determining the distance sample trip point from the distance curve.
3. The method of claim 2, wherein said determining said distance sample trip point from said distance curve comprises:
dividing the distance curve into two sub-sample curves by taking a reference division point in the distance curve as a division basis, wherein the reference division point is any reference point which is not selected as the division basis, and the any reference point is a point corresponding to any distance sample information;
for each reference point in each sub-sample curve, determining a mean square error for the each reference point;
adding the mean square error of each reference point in each sub-sample curve to obtain a residual value, and dividing the distance curve into two sub-sample curves by taking a reference dividing point in the distance curve as a dividing basis until a minimum residual value is obtained, or until N residual values larger than or equal to a residual threshold value are obtained, wherein N is a positive integer larger than or equal to 2;
when the minimum residual value is obtained, determining a reference point corresponding to the minimum residual value as the distance sample trip point; or when N residual values which are larger than or equal to the residual threshold value are acquired, determining the reference points corresponding to the N residual values as the distance sample jumping points.
4. The method of claim 1, wherein said performing a parking space type match based on said distance sample trip points and stored car model samples to identify parking spaces in an environment in which said car is currently located comprises:
determining an obstacle profile corresponding to the distance sample jumping point according to the distance sample jumping point;
determining a correlation between the obstacle profile and a stored car model sample;
when the correlation between the obstacle contour and the automobile model sample is smaller than or equal to a correlation threshold value, determining that the obstacle contour and the automobile model sample are successfully matched;
determining the parking space type corresponding to the automobile model sample as the parking space type of the parking space in the current environment of the automobile;
and identifying the parking space in the current environment of the automobile according to the parking space type and the distance sample trip point.
5. The method of claim 4, wherein said identifying parking spaces in the environment in which the vehicle is currently located based on the space types and the distance sample trip points comprises:
determining a space to be identified according to the distance sample jumping points, wherein the space to be identified is a space without obstacles;
and when the space distance of the space to be identified is greater than or equal to the parking distance corresponding to the parking space type, determining that the space to be identified is the parking space in the current environment of the automobile.
6. An identification device of a parking space, characterized in that the device comprises:
the system comprises an acquisition module, a detection module and a display module, wherein the acquisition module is used for acquiring distance sample information through an ultrasonic radar installed on an automobile, and the distance sample information is used for describing the distance between an obstacle detected by the ultrasonic radar and the automobile;
the determining module is used for determining a distance sample jumping point from the distance sample information, and the distance sample jumping point is used for describing the starting position and the ending position of an obstacle located in the current environment;
and the identification module is used for carrying out parking space type matching according to the distance sample trip point and the stored automobile model sample so as to identify the parking space in the current environment of the automobile.
7. The apparatus of claim 6, wherein the determining module comprises:
the acquisition submodule is used for acquiring the body state information of the automobile;
the first construction submodule is used for constructing a two-dimensional space coordinate system by taking any point in the space where the automobile is located as an origin, the detection direction of the ultrasonic radar as a longitudinal axis and the driving direction of the automobile as a transverse axis according to the automobile body state information;
the filtering submodule is used for filtering the distance sample information to filter out sample information which does not meet the distance requirement in the distance sample information;
the second construction submodule is used for constructing a distance curve in the two-dimensional space coordinate system through the filtered distance sample information;
a first determining submodule for determining the distance sample trip point from the distance curve.
8. The apparatus of claim 7, wherein the first determination submodule is to:
dividing the distance curve into two sub-sample curves by taking a reference division point in the distance curve as a division basis, wherein the reference division point is any reference point which is not selected as the division basis, and the any reference point is a point corresponding to any distance sample information;
for each reference point in each sub-sample curve, determining a mean square error for the each reference point;
adding the mean square error of each reference point in each sub-sample curve to obtain a residual value, and dividing the distance curve into two sub-sample curves by taking a reference dividing point in the distance curve as a dividing basis until a minimum residual value is obtained, or until N residual values larger than or equal to a residual threshold value are obtained, wherein N is a positive integer larger than or equal to 2;
when the minimum residual value is obtained, determining a reference point corresponding to the minimum residual value as the distance sample trip point; or when N residual values which are larger than or equal to the residual threshold value are acquired, determining the reference points corresponding to the N residual values as the distance sample jumping points.
9. The apparatus of claim 6, wherein the identification module comprises:
the second determining submodule is used for determining an obstacle outline corresponding to the distance sample jumping point according to the distance sample jumping point;
a third determining submodule for determining a correlation between the obstacle profile and a stored car model sample;
a fourth determining submodule, configured to determine that the obstacle contour and the automobile model sample are successfully matched when a correlation between the obstacle contour and the automobile model sample is smaller than or equal to a correlation threshold;
a fifth determining submodule, configured to determine a parking space type corresponding to the automobile model sample as a parking space type of a parking space in an environment where the automobile is currently located;
and the identification submodule is used for identifying the parking stall in the current environment of the automobile according to the stall type and the distance sample trip point.
10. A computer storage medium having stored thereon instructions that, when executed by a processor, perform the steps of the method of any of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110470409.XA CN113253278B (en) | 2021-04-28 | 2021-04-28 | Parking space identification method and device and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110470409.XA CN113253278B (en) | 2021-04-28 | 2021-04-28 | Parking space identification method and device and computer storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113253278A true CN113253278A (en) | 2021-08-13 |
| CN113253278B CN113253278B (en) | 2024-07-05 |
Family
ID=77222487
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110470409.XA Active CN113253278B (en) | 2021-04-28 | 2021-04-28 | Parking space identification method and device and computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113253278B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114419922A (en) * | 2022-01-17 | 2022-04-29 | 北京经纬恒润科技股份有限公司 | Parking space identification method and device |
| CN115376358A (en) * | 2022-07-18 | 2022-11-22 | 英博超算(南京)科技有限公司 | Ultrasonic parking space detection based on finite state machine |
Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101605678A (en) * | 2007-02-15 | 2009-12-16 | 丰田自动车株式会社 | Parking aid and parking assistance method |
| WO2011000483A1 (en) * | 2009-07-02 | 2011-01-06 | Valeo Schalter Und Sensoren Gmbh | Method for detecting and correcting an incorrect position of a distance sensor of a driver assistance system for vehicles |
| CN103241239A (en) * | 2013-04-27 | 2013-08-14 | 重庆邮电大学 | Parking space identifying method for automatic parking system |
| JP2014159182A (en) * | 2013-02-19 | 2014-09-04 | Nippon Soken Inc | Parking space sensing device |
| KR101559248B1 (en) * | 2014-05-12 | 2015-10-13 | 현대오트론 주식회사 | Method and apparatus for recognizing parking area |
| CN108569279A (en) * | 2017-12-15 | 2018-09-25 | 蔚来汽车有限公司 | The method and apparatus of parking stall for identification |
| CN109239360A (en) * | 2018-09-14 | 2019-01-18 | 深圳开立生物医疗科技股份有限公司 | A kind of response curve method for detecting abnormality and device |
| CN109484303A (en) * | 2018-11-27 | 2019-03-19 | 山东省科学院自动化研究所 | A kind of auxiliary parking apparatus, system and auxiliary are parked method |
| CN109738900A (en) * | 2019-01-02 | 2019-05-10 | 广州小鹏汽车科技有限公司 | It is a kind of can parking stall detection method and device |
| CN110203195A (en) * | 2019-04-29 | 2019-09-06 | 惠州市德赛西威汽车电子股份有限公司 | A kind of active predicting is parked the method for intention |
| CN110618420A (en) * | 2019-10-15 | 2019-12-27 | 广州小鹏汽车科技有限公司 | Ultrasonic data processing method and system, vehicle and storage medium |
| JP2020004368A (en) * | 2018-06-25 | 2020-01-09 | 株式会社デンソーテン | Parking section recognition device |
| CN110667570A (en) * | 2019-09-29 | 2020-01-10 | 奇瑞汽车股份有限公司 | Automatic parking space searching system and parking space searching method thereof |
| CN110687539A (en) * | 2018-07-06 | 2020-01-14 | 广州小鹏汽车科技有限公司 | Parking space detection method, device, medium and equipment |
| CN110803157A (en) * | 2019-11-26 | 2020-02-18 | 奇瑞汽车股份有限公司 | Parking space identification method and system based on automatic parking |
| CN110956847A (en) * | 2019-12-20 | 2020-04-03 | 奇瑞汽车股份有限公司 | Parking space identification method and device and storage medium |
| DE102018219227A1 (en) * | 2018-11-12 | 2020-05-14 | Robert Bosch Gmbh | Method and device for generating a representation of obstacles in the vicinity of a vehicle |
| CN111257893A (en) * | 2020-01-20 | 2020-06-09 | 珠海上富电技股份有限公司 | Parking space detection method and automatic parking method |
| CN112034466A (en) * | 2019-05-14 | 2020-12-04 | 广州汽车集团股份有限公司 | Parking space identification method and device |
-
2021
- 2021-04-28 CN CN202110470409.XA patent/CN113253278B/en active Active
Patent Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101605678A (en) * | 2007-02-15 | 2009-12-16 | 丰田自动车株式会社 | Parking aid and parking assistance method |
| WO2011000483A1 (en) * | 2009-07-02 | 2011-01-06 | Valeo Schalter Und Sensoren Gmbh | Method for detecting and correcting an incorrect position of a distance sensor of a driver assistance system for vehicles |
| JP2014159182A (en) * | 2013-02-19 | 2014-09-04 | Nippon Soken Inc | Parking space sensing device |
| CN103241239A (en) * | 2013-04-27 | 2013-08-14 | 重庆邮电大学 | Parking space identifying method for automatic parking system |
| KR101559248B1 (en) * | 2014-05-12 | 2015-10-13 | 현대오트론 주식회사 | Method and apparatus for recognizing parking area |
| CN108569279A (en) * | 2017-12-15 | 2018-09-25 | 蔚来汽车有限公司 | The method and apparatus of parking stall for identification |
| JP2020004368A (en) * | 2018-06-25 | 2020-01-09 | 株式会社デンソーテン | Parking section recognition device |
| CN110687539A (en) * | 2018-07-06 | 2020-01-14 | 广州小鹏汽车科技有限公司 | Parking space detection method, device, medium and equipment |
| CN109239360A (en) * | 2018-09-14 | 2019-01-18 | 深圳开立生物医疗科技股份有限公司 | A kind of response curve method for detecting abnormality and device |
| DE102018219227A1 (en) * | 2018-11-12 | 2020-05-14 | Robert Bosch Gmbh | Method and device for generating a representation of obstacles in the vicinity of a vehicle |
| CN109484303A (en) * | 2018-11-27 | 2019-03-19 | 山东省科学院自动化研究所 | A kind of auxiliary parking apparatus, system and auxiliary are parked method |
| CN109738900A (en) * | 2019-01-02 | 2019-05-10 | 广州小鹏汽车科技有限公司 | It is a kind of can parking stall detection method and device |
| CN110203195A (en) * | 2019-04-29 | 2019-09-06 | 惠州市德赛西威汽车电子股份有限公司 | A kind of active predicting is parked the method for intention |
| CN112034466A (en) * | 2019-05-14 | 2020-12-04 | 广州汽车集团股份有限公司 | Parking space identification method and device |
| CN110667570A (en) * | 2019-09-29 | 2020-01-10 | 奇瑞汽车股份有限公司 | Automatic parking space searching system and parking space searching method thereof |
| CN110618420A (en) * | 2019-10-15 | 2019-12-27 | 广州小鹏汽车科技有限公司 | Ultrasonic data processing method and system, vehicle and storage medium |
| CN110803157A (en) * | 2019-11-26 | 2020-02-18 | 奇瑞汽车股份有限公司 | Parking space identification method and system based on automatic parking |
| CN110956847A (en) * | 2019-12-20 | 2020-04-03 | 奇瑞汽车股份有限公司 | Parking space identification method and device and storage medium |
| CN111257893A (en) * | 2020-01-20 | 2020-06-09 | 珠海上富电技股份有限公司 | Parking space detection method and automatic parking method |
Non-Patent Citations (2)
| Title |
|---|
| 王晓彤: "自动泊车***关键技术研究", 《中国优秀硕士学位论文全文数据库工程科技II辑》, 15 November 2020 (2020-11-15), pages 035 - 22 * |
| 陈无畏;方玉杰;魏振亚;: "基于遗传算法优化的双向垂直泊车路径规划", 汽车工程, no. 11, 25 November 2017 (2017-11-25), pages 106 - 113 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114419922A (en) * | 2022-01-17 | 2022-04-29 | 北京经纬恒润科技股份有限公司 | Parking space identification method and device |
| CN115376358A (en) * | 2022-07-18 | 2022-11-22 | 英博超算(南京)科技有限公司 | Ultrasonic parking space detection based on finite state machine |
| CN115376358B (en) * | 2022-07-18 | 2023-12-05 | 英博超算(南京)科技有限公司 | Ultrasonic parking space detection based on finite state machine |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113253278B (en) | 2024-07-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111798698B (en) | Method and device for determining front target vehicle and vehicle | |
| CN109583416B (en) | Pseudo lane line identification method and system | |
| CN113253278B (en) | Parking space identification method and device and computer storage medium | |
| KR102569900B1 (en) | Apparatus and method for performing omnidirectional sensor-fusion and vehicle including the same | |
| CN114056324B (en) | Parking space recognition method and system based on data fusion | |
| CN111796286B (en) | Brake grade evaluation method and device, vehicle and storage medium | |
| JP2016148547A (en) | Detection device | |
| CN110333725B (en) | Method, system, equipment and storage medium for automatically driving to avoid pedestrians | |
| US11487293B2 (en) | Map-information obstacle-tracking system and method | |
| CN111754798A (en) | Method for realizing detection of vehicle and surrounding obstacles by fusing roadside laser radar and video | |
| CN111123262A (en) | Automatic driving 3D modeling method, device and system | |
| CN115273512A (en) | Anti-collision auxiliary method, device, equipment and medium for automatically driving vehicle | |
| CN110533921B (en) | Triggering snapshot method and system for vehicle | |
| CN115729245A (en) | Obstacle fusion detection method, chip and terminal for mine ramp | |
| CN109887321B (en) | Unmanned vehicle lane change safety judgment method and device and storage medium | |
| CN113650607B (en) | Low-speed scene automatic driving method, system and automobile | |
| CN109637148B (en) | Vehicle-mounted whistling monitoring system, method, storage medium and equipment | |
| CN111539305B (en) | Map construction method and system, vehicle and storage medium | |
| CN112863242A (en) | Parking space detection method and device | |
| CN114779257A (en) | Parking space detection method and device, storage medium and vehicle | |
| US11643093B2 (en) | Method for predicting traffic light information by using lidar and server using the same | |
| CN110309741B (en) | Obstacle detection method and device | |
| CN112419717B (en) | Object management method, device, vehicle and storage medium | |
| US20240240963A1 (en) | Parking assistance device and parking assistance method | |
| KR20240020541A (en) | Device of vehicle for preventing misrecognition of object and method therefor |
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 |