CN116394924A - Automatic parking planning method and device, electronic equipment and storage medium - Google Patents
Automatic parking planning method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN116394924A CN116394924A CN202310420827.7A CN202310420827A CN116394924A CN 116394924 A CN116394924 A CN 116394924A CN 202310420827 A CN202310420827 A CN 202310420827A CN 116394924 A CN116394924 A CN 116394924A
- Authority
- CN
- China
- Prior art keywords
- height
- target
- vehicle
- determining
- groups
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000003860 storage Methods 0.000 title claims abstract description 13
- 239000011159 matrix material Substances 0.000 claims abstract description 51
- 238000004364 calculation method Methods 0.000 claims abstract description 20
- 239000013598 vector Substances 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 7
- 238000013519 translation Methods 0.000 claims description 7
- 238000011161 development Methods 0.000 claims description 3
- 230000007613 environmental effect Effects 0.000 abstract description 6
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000005516 engineering process Methods 0.000 description 7
- 230000008859 change Effects 0.000 description 6
- 238000004891 communication Methods 0.000 description 6
- 238000001514 detection method Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000001133 acceleration Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000000284 resting effect Effects 0.000 description 3
- 230000009466 transformation Effects 0.000 description 3
- 238000012937 correction Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 241000251468 Actinopterygii Species 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000000725 suspension Substances 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units, or advanced driver assistance systems for ensuring comfort, stability and safety or drive control systems for propelling or retarding the vehicle
- B60W30/06—Automatic manoeuvring for parking
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W2050/0001—Details of the control system
- B60W2050/0002—Automatic control, details of type of controller or control system architecture
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Abstract
The invention discloses an automatic parking planning method, an automatic parking planning device, electronic equipment and a storage medium, wherein the automatic parking planning method comprises the following steps: when the identified parking space angular point coordinates are identified, determining the current posture information of the vehicle body, wherein the posture information comprises the height H of a rear center shaft r The method comprises the steps of carrying out a first treatment on the surface of the At the height H of the rear center shaft r Performing similarity calculation of the current gesture information in the corresponding gesture information model, and determining N groups of target gesture information, wherein N is more than or equal to 2; calculating a target external parameter matrix according to N groups of external parameter matrices corresponding to the N groups of target attitude information; and updating the parking space angular point coordinates according to the target external parameter matrix. The beneficial effects are that: overcomes the problem that when a single tire of a vehicle is under-pressure and the load of the vehicle is uneven, the height of the looking-around fish-eye camera relative to the ground is greatly changed, and the vehicle is identifiedThe parking space deviation and the skew improve the recognition precision, avoid the track deviation caused by the continuous insufficient tire pressure, and improve the automatic parking accuracy and the environmental adaptability.
Description
Technical Field
The present invention relates to the field of vehicle control technologies, and in particular, to an automatic parking planning method, an automatic parking planning device, an electronic device, and a storage medium.
Background
And according to the checkerboard calibration result, the controller in charge of image processing stores parameters, and when the looking-around image is activated subsequently, image stretching and splicing are carried out according to fixed parameters. If the vehicle is askew (the tire pressure of a single tire is insufficient, the vehicle is on a slope, the weight distribution in the cabin is uneven, etc.), the original parameters cannot continuously correspond to the real world, the identified corner points are askew, and the parking space is askew and the parking position is deviated.
In the prior art, for example, chinese patent CN107424116 a-a parking space detection method based on a side looking-around camera, the actual size of the planar area is calculated by performing inverse perspective transformation through segmentation of the passable area in the scene of the looking-around camera, and the area is repeatedly confirmed by combining multi-frame time-sequence image data with the motion state of the vehicle, so as to finally realize parking space detection. However, this corresponds to the first identification of the effective area and the conversion of the internal and external parameters based on the calibration. There is no way to avoid the skew caused by the inverse parametric transformation used when the recognized area passes through the original horizontal position when the posture of the vehicle body is not correct.
In another example, chinese patent CN111873986 a-parking space recognition and correction system and method, the vehicle height detection module is used to detect the real-time vehicle body height of the vehicle, and the corrected actual distance is obtained by combining the detection result with the coordinates of four corner points of the parking space and performing triangle geometric calculation. However, the distortion correction principle of the fisheye camera and the external parameter change caused by the elevation angle change of the camera are not considered and described, the new distances of four corner points are determined according to the plane triangle geometric calculation simply through the vehicle height change, the fit reality is not realized, and the skew of a parking space caused by the distortion of the camera due to the angle change cannot be avoided.
Therefore, the conventional automatic parking ring-view image calibration is carried out on a standard field with a fixed horizontal ground body posture, when a single tire of a vehicle is under-voltage and the vehicle load is uneven, the ring-view fisheye camera is greatly changed relative to the ground, and due to radial distortion and camera pose change, the original conversion matrix can not restore the real image proportional relationship any more, so that the parking space deviation and skew recognized by the vehicle are caused.
Disclosure of Invention
In view of the above-mentioned drawbacks or improvements of the prior art, an object of the present invention is to provide an automatic parking planning method, apparatus, electronic device and storage medium.
To achieve the purpose, the invention adopts the following technical scheme:
in a first aspect, a method of automated parking planning,
in one embodiment, the method comprises the steps of:
when a parking space is searched, determining the current attitude information of the vehicle body, wherein the attitude information comprises the height H of a rear center shaft r ；
At the height H of the rear center shaft r Performing similarity calculation of the current gesture information in a gesture information model, and determining N groups of target gesture information, wherein N is more than or equal to 2;
calculating a target external parameter matrix according to N groups of external parameter matrices corresponding to the N groups of target attitude information;
and updating the parking space angular point coordinates according to the target external parameter matrix.
In a preferred embodiment of the above automatic parking planning method, the vehicle body posture information further includes a front height difference Δh f Rear height difference Δh r And a pitch height difference Δh.
In the preferred embodiment of the automatic parking planning method, four corner points of the vehicle body are all provided with height sensors, the four corner points include a left front corner point, a right front corner point, a left rear corner point and a right rear corner point, and the step of determining the current posture information of the vehicle body includes:
acquiring the height H of the left front corner point f1 Height of right front corner H f2 Left rear corner height H r1 And right rear corner height H r2 ；
According to the height H of the left front corner point f1 And the right front corner height H f2 Determining the front height difference ΔH f ；
According toThe height H of the left rear corner point r1 And the right rear corner point height H r2 Determining a rear height difference delta H r ；
According to the front height difference delta H f And the rear height difference DeltaH r The pitch height difference Δh is determined.
In a preferred embodiment of the above automatic parking planning method, when the identified parking space angular point coordinates are, before determining the current pose information of the vehicle body, the method further includes the following steps:
and determining the inclination of the vehicle body and running at a constant speed below a preset speed.
In a preferred embodiment of the above automatic parking planning method, the step of performing similarity calculation of the current pose information in the pose information model corresponding to the rear center axis height Hr, and determining N sets of target pose information includes:
in the vehicle development stage, respectively placing each tire of the vehicle on a corresponding lifting table, wherein the vehicle is positioned in a checkerboard enclosure, and each checkerboard corner has a three-dimensional coordinate (x, y, z) relative to the calibration center of the vehicle;
the corresponding external parameter matrix is calibrated through the following relation real vehicle:
wherein λ represents a scale factor, u represents a display pixel lateral position, v represents a display pixel longitudinal position, f represents a focal length, s represents a shape characteristic of a pixel unit, dx represents a lateral dimension of a single pixel, dy represents a display pixel longitudinal dimension, R represents a rotation matrix, T represents a translation matrix,
representing the extrinsic matrix.
In a preferred embodiment of the above automatic parking planning method, the step of calculating the similarity of the current pose information in the pose information model corresponding to the rear center axis height Hr, and determining N sets of target pose information further includes:
constructing vectors for attitude information at the same rear center axis height H r The distance between each calibration vector in the gesture information model and the corresponding vector of the current gesture information;
and arranging the distances from large to small, and determining the gesture information corresponding to the N groups of target vectors before arrangement as target gesture information.
In a preferred embodiment of the above automatic parking planning method, the step of calculating the target appearance matrix according to N sets of appearance matrices corresponding to the N sets of target posture information includes:
and carrying out average value calculation on each item in the N groups of external parameter matrixes, and forming the average value of each item into a target external parameter matrix.
In a second aspect, an automatic parking planning apparatus includes:
the first module determines the current attitude information of the vehicle body when the identified parking space angular point coordinates are obtained, wherein the attitude information comprises the height H of a rear center shaft r ；
A second module for at the same rear center shaft height H r Performing similarity calculation of the current gesture information in a gesture information model, and determining N groups of target gesture information, wherein N is more than or equal to 2;
the third module is used for calculating a target external parameter matrix according to N groups of external parameter matrices corresponding to the N groups of target attitude information;
and the fourth module is used for updating the parking space angular point coordinates according to the target external parameter matrix.
In a third aspect, an electronic device comprises a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the auto park planning method as described above when executing the computer program.
In a fourth aspect, a computer-readable storage medium stores computer instructions that cause the computer to perform the steps of the automated parking planning method as described above.
The invention has the beneficial effects that:
for an automatic parking planning method, an automatic parking planning device, electronic equipment and a storage medium, determining current posture information of a vehicle body when the recognized parking space angular point coordinates are adopted, wherein the posture information comprises a rear center shaft height H r The method comprises the steps of carrying out a first treatment on the surface of the At the height H of the rear center shaft r Performing similarity calculation of the current gesture information in the corresponding gesture information model, and determining N groups of target gesture information, wherein N is more than or equal to 2; calculating a target external parameter matrix according to N groups of external parameter matrices corresponding to the N groups of target attitude information; according to the target external parameter matrix, the parking space angular point coordinates are updated, the problem that when a vehicle tire is under-pressure and the vehicle load is uneven, the camera is greatly changed relative to the ground, and the caused vehicle is used for recognizing parking space deviation and skew is solved, the vehicle control precision is improved, the track deviation caused by continuous tire pressure insufficiency is avoided, and the automatic parking accuracy and the environmental adaptability are improved.
Additional aspects and advantages of the application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the application.
Drawings
The foregoing and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings, in which:
fig. 1 is a flow chart of an automatic parking planning method provided in the present embodiment;
fig. 2 is a schematic view of a scene provided in the present embodiment;
FIG. 3 is a side view of a vehicle resting on a lift table;
FIG. 4 is a front view of a vehicle resting on a lift table;
FIG. 5 is a top view of a vehicle resting on a lift table;
FIG. 6 is the same rear center axis height H r Under the condition of delta H f ，ΔH r Schematic diagram of a spatial coordinate system formed by delta H;
fig. 7 is a schematic structural view of an automatic parking planning apparatus provided in the present embodiment;
fig. 8 is a schematic structural diagram of an electronic device provided in the present embodiment.
Detailed Description
The invention is described in further detail below with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting thereof. It should be further noted that, for convenience of description, only some, but not all of the structures related to the present invention are shown in the drawings.
In the description of the present invention, unless explicitly stated and limited otherwise, the terms "connected," "connected," and "fixed" are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally formed; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communicated with the inside of two elements or the interaction relationship of the two elements. The specific meaning of the above terms in the present invention will be understood in specific cases by those of ordinary skill in the art.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless expressly stated otherwise, as understood by those skilled in the art. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It will be understood by those skilled in the art that all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs unless defined otherwise. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
Several terms which are referred to in this application are first introduced and explained:
automatic parking: after the vehicle finds the parking space, the steering and braking are automatically controlled, and the vehicle is parked into the parking space. The vision mode is used for searching the parking space, the four surrounding cameras arranged around the vehicle can be used for receiving image signals, carrying out picture orthodontics and splicing, identifying the corner points of the parking space frame in a machine learning mode based on the processed panoramic picture, and constructing the parking space. The parking space can be obtained by scanning the ultrasonic radar along with the running process of the vehicle.
Looking around and calibrating: because the original picture input of the circular splicing comes from the fisheye camera, the image distortion is larger, and the distance between each point in the video is not completely corresponding to the real world, the planar image is restored by stretching the image on a standard checkerboard. In the calibration, the checkerboard image is adjusted by obtaining the external parameters of the fish-eye camera, and the relative positions of the checkerboard image and the real plane top view correspond to each other.
External parameters: is a transformation rotation, translation parameter in world coordinates, related to the position of the object from world coordinates to camera coordinates and the direction of rotation.
Internal parameters: the relationship from camera coordinates to pixel coordinates is reflected in relation to the self characteristics of the fish eye camera, such as the focal length of the camera, the pixel size, and the distortion coefficient.
IMU: an inertial measurement unit (Inertial measurement unit, abbreviated as IMU) is a device for measuring three-axis attitude angles and accelerations of an object. A typical IMU includes a tri-axis gyroscope and tri-axis accelerometer, and an IMU equipped on a vehicle can provide vehicle horizontal lateral, horizontal longitudinal and vertical acceleration and rotational angular velocity about these three directions.
The embodiment provides an automatic parking planning method, which is applicable to the fields of map, navigation, automatic driving, intelligent vehicle control, internet of vehicles, intelligent traffic, cloud computing and the like, such as an intelligent traffic system (Intelligent Traffic System, ITS) in the traffic field.
The intelligent transportation system is also called an intelligent transportation system (Intelligent Transportation System), and is an integrated transportation system which effectively and comprehensively applies advanced scientific technologies (information technology, computer technology, data communication technology, sensor technology, electronic control technology, automatic control theory, operation research, artificial intelligence and the like) to transportation, service control and vehicle manufacturing, and enhances the connection among vehicles, roads and users, thereby forming the integrated transportation system for guaranteeing safety, improving efficiency, improving environment and saving energy. Based on the automatic parking planning method provided by the embodiment of the application, the parking route of the vehicle can be accurately determined, so that powerful guarantee is provided for aspects such as transportation, service control and the like.
The automatic parking planning method provided by the embodiment of the application can be executed by a server or a terminal. The server may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing cloud computing service. The terminal may be a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart speaker, a smart watch, a vehicle-mounted terminal, a smart television, etc., and may specifically be determined based on actual application scene requirements, which is not limited herein.
Fig. 1 is a flow chart of an automatic parking planning method provided in the present embodiment. Referring to fig. 1, the automatic parking planning method provided in the present embodiment includes steps S10 to S40.
The automatic parking planning method provided by the embodiment of the application can be suitable for a parking scene with a gradient, such as a vehicle running in an underground parking lot with a downhill. Or the automatic parking planning method provided by the embodiment of the application can be also suitable for driving scenes with complex road conditions, such as ground parking lots or business areas with poor road conditions and more fluctuation. As shown in fig. 2, fig. 2 is a schematic view of a scene provided in the present embodiment, a vehicle A1 travels in a garage B1, the garage B1 has a parking space C1, the parking space C1 is a rectangular line drawn on the ground, specifically, the rectangular line has a front side, a rear side, a left side and a right side, and the parking space C1 is on the horizontal ground. When the vehicle A1 parks in the parking space C1, the vehicle body of the vehicle A1 will be in a stationary state if the vehicle is not loaded unevenly or the tires leak or the heights of the four corners are consistent with respect to the ground, otherwise, the vehicle body will be in an inclined state.
Further, the vehicle A1 of the present embodiment has at least the following devices:
and the wheel speed pulse counter is used for calculating the rolling distance of the wheels.
The height sensor is used for determining the height of four corners of the vehicle relative to the ground by using schemes such as infrared ranging, suspension position detection and the like.
And the IMU is used for measuring the acceleration and the rotation angular velocity of the vehicle in all directions.
And the chassis control unit is used for calculating the vehicle posture and controlling chassis braking and steering by combining the information such as the height sensor, the wheel speed pulse and the like.
The looking-around camera is arranged on the front, back, left and right cameras/fish-eye cameras of the vehicle.
And step S10, determining the current posture information of the vehicle body when the identified parking space angular point coordinates are identified.
Specifically, the identified parking space angular point coordinates indicate that a parking space is searched, in other words, the parking space is identified through the looking-around camera. It should be noted that the recognition of the parking space is not limited to recognition of two, three or four right-angle sides. For example, front side C11 and left side C13 are identified, or front side C11, left side C13, and right side C14 are identified.
Further, the current posture information of the vehicle body comprises a rear center shaft height H r Front height difference Δh f Rear height difference Δh r And a pitch height difference Δh. Left front corner height H f1 Height of right front corner H f2 Left rear corner height H r1 And right rear corner height H r2 。
The step S10 includes:
acquiring the height H of the left front corner point f1 Height of right front corner H f2 Left rear corner height H r1 And right rear corner height H r2 . According to the height H of the left front corner point f1 And right front corner height H f2 Determining the front height difference ΔH f . According to the height H of the left rear corner point r1 And right rear corner height H r2 Determining the height H of the rear center shaft r And a rear height difference DeltaH r . According to the front height difference delta H f And a rear height difference DeltaH r The pitch height difference Δh is determined.
Specifically:
rear center shaft height H r ＝(H r1 +H r2 )/2；
Front height difference Δh f ＝H f1 -H f2 ；
Rear height difference Δh r ＝H r1 -H r2 ；
Pitch height difference Δh=Δh f -ΔH r 。
In other words, (H) r ，ΔH f ，ΔH r Δh) constitutes a set of body posture information reflecting height information of four corners and a plurality of portions of the vehicle.
It should be noted that, in step S10, a precondition is that: and determining the inclination of the vehicle body and running at a constant speed below a preset speed. Further, the present embodiment sets the front height difference Δh f Rear height difference Δh r And when the pitch height difference delta H is 0, the vehicle body is in a stable state. When any of the above parameters is not 0, it indicates that the vehicle body is inclined.
When the vehicle body is not inclined, the radial distortion is smaller, the camera pose change is smaller, and the original conversion matrix can restore the real image proportional relation. And, the vehicle body should be in a uniform traveling state below a preset speed, at which time the vehicle is in a balanced stable state, and if the vehicle body is traveling at a relatively high speed or is accelerating or decelerating, the vehicle is in an unbalanced unstable state, and the determined vehicle body posture information (H r ，ΔH f ，ΔH r ，ΔH)。
In the present embodiment, the preset speed is set to 15km/H, that is, when the vehicle is inclined and traveling at a constant speed of 15km/H or less, a set of body posture information (H r ，ΔH f ，ΔH r ，ΔH)。
Step S20, at the same rear center axis height H r And carrying out similarity calculation on the current gesture information in the corresponding gesture information model, and determining N groups of target gesture information.
Step S20 includes step S201, during a vehicle development stage, placing each tire of the vehicle on a corresponding lifting platform, while the vehicle is located in a checkerboard enclosure, and each corner of the checkerboard has a three-dimensional coordinate (x, y, z) with respect to a calibration center of the vehicle.
Fig. 3 is a side view of a vehicle placed on a lifting platform, fig. 4 is a front view of the vehicle placed on the lifting platform, fig. 5 is a top view of the vehicle placed on the lifting platform, as shown in fig. 3-5, four wheels of the vehicle are respectively placed on one lifting platform, the lifting platform can lift corresponding wheel parts to ascend and descend, and checkerboards are respectively arranged right in front of, right behind, left side, right side, left front side, right front side, left rear side and right rear side of the vehicle, each checkerboard consists of black and white checks, the black checks and the white checks are adjacently arranged, diagonal lines between the black checks and the black checks are arranged, and diagonal lines between the white checks and the white checks are arranged. The center of each of the black and white cells has one coordinate. The coordinates include coordinates in spatial position relative to the vehicle calibration center: horizontal position coordinates (x, y) and height coordinates (z).
It should be noted that the size and number of the lattices may be determined according to the actual accuracy requirement, and the embodiment is not limited.
Step S201 further comprises real vehicle calibration of corresponding external parameter matrix through the following relation:
wherein λ represents a scale factor, u represents a display pixel lateral position, v represents a display pixel longitudinal position, f represents a focal length, s represents a shape characteristic of a pixel unit, dx represents a lateral dimension of a single pixel, dy represents a display pixel longitudinal dimension, R represents a rotation matrix, T represents a translation matrix,
representing the extrinsic matrix.
The height H of the middle shaft after n groups can be obtained by adjusting the height of the lifting platform r Lower, the left and right front wheels are respectively lifted and lowered to cause m delta H with different values f The corresponding left and right rear wheels are not lifted and lowered respectivelyK delta H of the same value r Z Δh corresponding to different pitch height differences, n groups of z×m×k (H r ，ΔH f ，ΔH r Δh) and four looking-around cameras in one-to-one correspondence with the vehicle body posture at that time
The vehicle parking control unit is stored in the cloud, but the embodiment is not limited thereto.
by analogy, a rotation matrix Rx of β is rotated around the X-axis, and a rotation matrix Ry of γ is rotated around the Y-axis, so that the overall rotation matrix R can be obtained as a 3*3 matrix from r=rzrxry
The translation only needs to be added with the translation amount on the corresponding x, y and z axes, so +.>
T is->
and a, b and c correspond to the coordinate translation amount between the coordinate center of the camera and the target.
FIG. 6 is the same rear center axis height H r Under the condition of delta H f ，ΔH r Schematic diagram of the spatial coordinate system constituted by Δh. As shown in FIG. 6, the same rear center axis height H r Conditions (conditions)Down, deltaH f ，ΔH r Δh is the three axes of the spatial coordinate system, respectively, and each group (Δh is identified in this case f ，ΔH r Δh) constitute points of the spatial coordinate system. I.e. different rear centre shaft heights H r Under the condition, different space coordinate systems are provided.
In the actual calibration process, H is selected according to the preset precision r 、ΔH f 、ΔH r And the delta H is taken, so that the total calibration work amount is controlled.
For example, with 2mm as a preset accuracy, different sets of body posture information (H r ，ΔH f ，ΔH r ，ΔH)。
Step S20 further includes: steps S202 to S203.
Step S202, constructing vectors related to attitude information, and determining the height H of the middle axis at the same rear r The distance between each calibration vector in the gesture information model and the corresponding vector of the current gesture information.
Same rear center shaft height H r The posture information is (delta H) f ` ，ΔH r ` ，ΔH ` ) The pose information model is calibrated as (delta H) f1 ，ΔH r1 ，ΔH 1 )、(ΔH f2 ，ΔH r2 ，ΔH 2 )……(ΔH fm ，ΔH rm ，ΔH m ) Each calibration sum (ΔH) is calculated according to a vector distance calculation formula f ` ，ΔH r ` ，ΔH ` ) Distance of (1) to obtain l 1 、l 2 ……l m 。
Step S203, distance l 1 、l 2 ……l m And determining the gesture information corresponding to the N groups of target vectors before arrangement as target gesture information from large to small. It is understood that N is less than m and N is not less than 2.
In this embodiment, N is set to 3, that is, posture information corresponding to three groups of target vectors closest to each other is taken as target posture information. It should be noted that
And step S30, calculating a target external parameter matrix according to N groups of external parameter matrices corresponding to the N groups of target attitude information.
In this embodiment, the object extrinsic matrices are calculated according to three sets of extrinsic matrices corresponding to three sets of object pose information.
Specifically, the mean value of each item in the three sets of external reference matrices is calculated, and the mean value of each item (R, T) is formed into a target external reference matrix.
And S40, updating the parking space corner coordinates according to the target external parameter matrix.
Step S40 is that in the prior art, the target external parameter matrix is used for carrying out looking-around image orthodontics and projection, new parking space angular point coordinates are identified on the corrected image, and then parking track planning is carried out based on the parking space angular point coordinates.
According to the automatic parking planning method provided by the embodiment, when the coordinates of the corner points of the parking space are identified, the current posture information of the vehicle body is determined, wherein the posture information comprises the height Hr of the rear center shaft; performing similarity calculation of the current attitude information in an attitude information model corresponding to the rear center axis height Hr, and determining N groups of target attitude information, wherein N is more than or equal to 2; calculating a target external parameter matrix according to N groups of external parameter matrices corresponding to the N groups of target attitude information; according to the target external parameter matrix, the parking space angular point coordinates are updated, the problem that when a vehicle tire is under-pressure and the vehicle load is uneven, the camera is greatly changed relative to the ground, and the caused vehicle is used for recognizing parking space deviation and skew is solved, the vehicle control precision is improved, the track deviation caused by continuous tire pressure insufficiency is avoided, and the automatic parking accuracy and the environmental adaptability are improved.
The present embodiment also provides an automatic parking planning apparatus, as shown in fig. 7, which includes a first module 71, a second module 72, a third module 73, and a fourth module 74.
The first module 71 is configured to determine current attitude information of the vehicle body when the vehicle is searched, where the attitude information includes a rear center shaft height H r 。
The second module 72 is for the same rear center axis height H r And (3) carrying out similarity calculation on the current gesture information in the gesture information model, and determining N groups of target gesture information, wherein N is more than or equal to 2.
The third module 73 is configured to calculate a target outlier matrix according to the N sets of outlier matrices corresponding to the N sets of target pose information.
The fourth module 74 is configured to identify the parking space corner coordinates according to the target extrinsic matrix.
It should be noted that the automatic parking planning apparatus provided in this embodiment may also be a computer program (including program code) running in a computer device, for example, the automatic parking planning apparatus is an application program, and may be used to perform the corresponding steps in the method provided in the embodiment of the present application.
In some possible implementations, the automatic parking planning apparatus provided in this embodiment may be implemented in a combination of software and hardware, and by way of example, the automatic parking planning apparatus in this embodiment may be a processor in the form of a hardware decoding processor that is programmed to perform the automatic parking planning method provided in this embodiment, for example, the processor in the form of a hardware decoding processor may use one or more application specific integrated circuits (ASIC, application Specific Integrated Circuit), digital signal processors (digital signal processor, DSP), programmable logic devices (PLD, programmable Logic Device), complex programmable logic devices (CPLD, complex Programmable Logic Device), field programmable gate arrays (FPGA, field-Programmable Gate Array), or other electronic components.
In some possible implementations, the automatic parking planning device provided in this embodiment may be implemented in software, which may be software in the form of a program, a plug-in, or the like, and includes a series of modules to implement the automatic parking planning method provided in this embodiment of the present invention.
According to the automatic parking planning device provided by the embodiment, when the coordinates of the corner points of the parking space are identified, the current posture information of the vehicle body is determined, wherein the posture information comprises the height Hr of the rear center shaft; performing similarity calculation of the current attitude information in an attitude information model corresponding to the rear center axis height Hr, and determining N groups of target attitude information, wherein N is more than or equal to 2; calculating a target external parameter matrix according to N groups of external parameter matrices corresponding to the N groups of target attitude information; according to the target external parameter matrix, the parking space angular point coordinates are updated, the problem that when a vehicle tire is under-pressure and the vehicle load is uneven, the camera is greatly changed relative to the ground, and the caused vehicle is used for recognizing parking space deviation and skew is solved, the vehicle control precision is improved, the track deviation caused by continuous tire pressure insufficiency is avoided, and the automatic parking accuracy and the environmental adaptability are improved.
An electronic device is further provided in this embodiment, and fig. 8 is a schematic structural diagram of the electronic device in this embodiment, as shown in fig. 8, where an electronic device 1000 in this embodiment may include: processor 1001, network interface 1004, and memory 1005, and in addition, the electronic device 1000 may further include: a user interface 1003, and at least one communication bus 1002. Wherein the communication bus 1002 is used to enable connected communication between these components. The user interface 1003 may include a Display (Display), a Keyboard (Keyboard), and the optional user interface 1003 may further include a standard wired interface, a wireless interface, among others. The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface). The memory 1004 may be a high-speed RAM memory or a non-volatile memory (non-volatile memory), such as at least one disk memory. The memory 1005 may also optionally be at least one storage device located remotely from the processor 1001. As shown in fig. 8, an operating system, a network communication module, a user interface module, and a device control application may be included in a memory 1005, which is a type of computer-readable storage medium.
In the electronic device 1000 shown in fig. 8, the network interface 1004 may provide a network communication function; while user interface 1003 is primarily used as an interface for providing input to a user; and the processor 1001 may be used to invoke a device control application stored in the memory 1005 to implement:
when a parking space is searched, determining the current attitude information of the vehicle body, wherein the attitude information comprises the height H of a rear center shaft r 。
At the same rear center axis height H r In the attitude information model of (2) to calculate the similarity of the current attitude information and determine N groups of target attitude informationAnd (3) extinguishing, wherein N is more than or equal to 2.
And calculating the target external parameter matrix according to the N groups of external parameter matrices corresponding to the N groups of target attitude information.
And identifying the angular point coordinates of the parking space according to the target external parameter matrix.
It should be appreciated that in some possible embodiments, the processor 1001 described above may be a central processing unit (central processing unit, CPU), which may also be other general purpose processors, DSP, ASIC, FPGA or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The memory may include read only memory and random access memory and provide instructions and data to the processor. A portion of the memory may also include non-volatile random access memory. For example, the memory may also store information of the device type.
In a specific implementation, the electronic device 1000 may execute, through each functional module built in the electronic device, an implementation manner provided by each step of the control method, and specifically, the implementation manner provided by each step may be referred to, which is not described herein again.
When the electronic equipment provided by the embodiment passes through the identified parking space angular point coordinates, determining the current posture information of the vehicle body, wherein the posture information comprises the rear center shaft height Hr; performing similarity calculation of the current attitude information in an attitude information model corresponding to the rear center axis height Hr, and determining N groups of target attitude information, wherein N is more than or equal to 2; calculating a target external parameter matrix according to N groups of external parameter matrices corresponding to the N groups of target attitude information; according to the target external parameter matrix, the parking space angular point coordinates are updated, the problem that when a vehicle tire is under-pressure and the vehicle load is uneven, the camera is greatly changed relative to the ground, and the caused vehicle is used for recognizing parking space deviation and skew is solved, the vehicle control precision is improved, the track deviation caused by continuous tire pressure insufficiency is avoided, and the automatic parking accuracy and the environmental adaptability are improved.
The embodiment of the present application further provides a computer readable storage medium, where the computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement each step in the automatic parking planning method in the foregoing embodiment, and specifically, the implementation manner provided by each step may be referred to, which is not described herein again.
The computer readable storage medium provided by the embodiment determines the current posture information of the vehicle body through the recognized parking space angular point coordinates, wherein the posture information comprises the rear center shaft height Hr; performing similarity calculation of the current attitude information in an attitude information model corresponding to the rear center axis height Hr, and determining N groups of target attitude information, wherein N is more than or equal to 2; calculating a target external parameter matrix according to N groups of external parameter matrices corresponding to the N groups of target attitude information; according to the target external parameter matrix, the parking space angular point coordinates are updated, the problem that when a vehicle tire is under-pressure and the vehicle load is uneven, the camera is greatly changed relative to the ground, and the caused vehicle is used for recognizing parking space deviation and skew is solved, the vehicle control precision is improved, the track deviation caused by continuous tire pressure insufficiency is avoided, and the automatic parking accuracy and the environmental adaptability are improved.
It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited in order and may be performed in other orders, unless explicitly stated herein. Moreover, at least some of the steps in the flowcharts of the figures may include a plurality of sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, the order of their execution not necessarily being sequential, but may be performed in turn or alternately with other steps or at least a portion of the other steps or stages.
The foregoing is only a partial embodiment of the present application, and it should be noted that, for a person skilled in the art, several improvements and modifications can be made without departing from the principle of the present application, and these improvements and modifications should also be considered as the protection scope of the present application.
Claims (10)
1. An automatic parking planning method is characterized by comprising the following steps:
when the identified parking space angular point coordinates are identified, determining the current posture information of the vehicle body, wherein the posture information comprises the height H of a rear center shaft r ；
At the height H of the rear center shaft r Performing similarity calculation of the current gesture information in the corresponding gesture information model, and determining N groups of target gesture information, wherein N is more than or equal to 2;
calculating a target external parameter matrix according to N groups of external parameter matrices corresponding to the N groups of target attitude information;
and updating the parking space angular point coordinates according to the target external parameter matrix.
2. The automatic parking planning method according to claim 1, wherein the vehicle body posture information further includes a front height difference Δh f Rear height difference Δh r And a pitch height difference Δh.
3. The automatic parking planning method according to claim 2, wherein four corner points of the vehicle body are each provided with a height sensor, the four corner points include a front left corner point, a front right corner point, a rear left corner point, and a rear right corner point, and the step of determining the current posture information of the vehicle body includes:
acquiring the height H of the left front corner point f1 Height of right front corner H f2 Left rear corner height H r1 And right rear corner height H r2 ；
According to the height H of the left front corner point f1 And the right front corner height H f2 Determining the front height difference ΔH f ；
According to the height H of the left rear corner point r1 And the right rear corner point height H r2 Determining a rear height difference delta H r ；
According to the front height difference delta H f And the rear height difference DeltaH r The pitch height difference Δh is determined.
4. The automatic parking planning method according to claim 1, wherein the step of determining the current posture information of the vehicle body before determining the identified parking space angular point coordinates further comprises the steps of:
and determining the inclination of the vehicle body and running at a constant speed below a preset speed.
5. The automatic parking planning method according to claim 1, wherein the rear center axis height H r The similarity calculation of the current gesture information is carried out in the corresponding gesture information model, and the step of determining N groups of target gesture information comprises the following steps:
in the vehicle development stage, respectively placing each tire of the vehicle on a corresponding lifting table, wherein the vehicle is positioned in a checkerboard enclosure, and each checkerboard corner has a three-dimensional coordinate (x, y, z) relative to the calibration center of the vehicle;
the corresponding external parameter matrix is calibrated through the following relation real vehicle:
wherein λ represents a scale factor, u represents a display pixel lateral position, v represents a display pixel longitudinal position, f represents a focal length, s represents a shape characteristic of a pixel unit, dx represents a lateral dimension of a single pixel, dy represents a display pixel longitudinal dimension, R represents a rotation matrix, T represents a translation matrix,
representing the extrinsic matrix.
6. The automatic parking planning method according to claim 5, wherein the step of performing similarity calculation of the current attitude information in the attitude information model corresponding to the rear center axis height Hr, and determining N sets of target attitude information further includes:
constructing vectors related to attitude information, and raising the central axis in the same rearDegree H r The distance between each calibration vector in the gesture information model and the corresponding vector of the current gesture information;
and arranging the distances from large to small, and determining the gesture information corresponding to the N groups of target vectors before arrangement as target gesture information.
7. The automatic parking planning method according to claim 1, wherein the step of calculating the target extrinsic matrices from the N sets of extrinsic matrices corresponding to the N sets of target attitude information includes:
and carrying out average value calculation on each item in the N groups of external parameter matrixes, and forming the average value of each item into a target external parameter matrix.
8. An automatic parking planning apparatus, comprising:
the first module determines the current attitude information of the vehicle body when the identified parking space angular point coordinates are obtained, wherein the attitude information comprises the height H of a rear center shaft r ；
A second module for at the rear center shaft height H r Performing similarity calculation of the current gesture information in a gesture information model, and determining N groups of target gesture information, wherein N is more than or equal to 2;
the third module is used for calculating a target external parameter matrix according to N groups of external parameter matrices corresponding to the N groups of target attitude information;
and the fourth module is used for updating the parking space angular point coordinates according to the target external parameter matrix.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the automated parking planning method according to any one of claims 1 to 7 when the computer program is executed by the processor.
10. A computer-readable storage medium storing computer instructions that cause the computer to perform the steps of the automatic parking planning method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310420827.7A CN116394924A (en) | 2023-04-18 | 2023-04-18 | Automatic parking planning method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310420827.7A CN116394924A (en) | 2023-04-18 | 2023-04-18 | Automatic parking planning method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116394924A true CN116394924A (en) | 2023-07-07 |
Family
ID=87015846
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310420827.7A Pending CN116394924A (en) | 2023-04-18 | 2023-04-18 | Automatic parking planning method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116394924A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116778457A (en) * | 2023-08-16 | 2023-09-19 | 钧捷科技（北京）有限公司 | Automatic parking auxiliary control system and device for vehicle |
-
2023
- 2023-04-18 CN CN202310420827.7A patent/CN116394924A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116778457A (en) * | 2023-08-16 | 2023-09-19 | 钧捷科技（北京）有限公司 | Automatic parking auxiliary control system and device for vehicle |
| CN116778457B (en) * | 2023-08-16 | 2023-11-03 | 钧捷科技（北京）有限公司 | Automatic parking auxiliary control system and device for vehicle |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10659677B2 (en) | Camera parameter set calculation apparatus, camera parameter set calculation method, and recording medium | |
| CN113554698B (en) | Vehicle pose information generation method and device, electronic equipment and storage medium | |
| CN110148185B (en) | Method and device for determining coordinate system conversion parameters of imaging equipment and electronic equipment | |
| US10434877B2 (en) | Driver-assistance method and a driver-assistance apparatus | |
| CN109360245B (en) | External parameter calibration method for multi-camera system of unmanned vehicle | |
| CN108805934B (en) | External parameter calibration method and device for vehicle-mounted camera | |
| CN110826357B (en) | Method, device, medium and equipment for three-dimensional detection and intelligent driving control of object | |
| US11036965B2 (en) | Shape estimating apparatus | |
| US11657319B2 (en) | Information processing apparatus, system, information processing method, and non-transitory computer-readable storage medium for obtaining position and/or orientation information | |
| US20190304120A1 (en) | Obstacle avoidance system based on embedded stereo vision for unmanned aerial vehicles | |
| KR102295809B1 (en) | Apparatus for acquisition distance for all directions of vehicle | |
| CN110119698B (en) | Method, apparatus, device and storage medium for determining object state | |
| CN114144809A (en) | Vehicle environment modeling by camera | |
| CN109544633B (en) | Target ranging method, device and equipment | |
| CN111127497B (en) | Robot and stair climbing control method and device thereof | |
| CN112183241A (en) | Target detection method and device based on monocular image | |
| CN116394924A (en) | Automatic parking planning method and device, electronic equipment and storage medium | |
| CN109883433B (en) | Vehicle positioning method in structured environment based on 360-degree panoramic view | |
| CN101980292B (en) | Regular octagonal template-based board camera intrinsic parameter calibration method | |
| CN116529561A (en) | System and method for monocular-based object detection | |
| CN117058209B (en) | Method for calculating depth information of visual image of aerocar based on three-dimensional map | |
| CN108376384B (en) | Method and device for correcting disparity map and storage medium | |
| CN116012805B (en) | Target perception method, device, computer equipment and storage medium | |
| CN113673288A (en) | Idle parking space detection method and device, computer equipment and storage medium | |
| CN113658262B (en) | Camera external parameter calibration method, device, system and storage medium |
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 |