CN112115741B - Parking garage position detection method and device - Google Patents
Parking garage position detection method and device Download PDFInfo
- Publication number
- CN112115741B CN112115741B CN201910537656.XA CN201910537656A CN112115741B CN 112115741 B CN112115741 B CN 112115741B CN 201910537656 A CN201910537656 A CN 201910537656A CN 112115741 B CN112115741 B CN 112115741B
- Authority
- CN
- China
- Prior art keywords
- library
- coordinate
- map
- vehicle
- under
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 20
- 238000000034 method Methods 0.000 claims abstract description 39
- 238000010276 construction Methods 0.000 claims description 19
- 230000008569 process Effects 0.000 claims description 16
- 230000000007 visual effect Effects 0.000 abstract description 4
- 238000013145 classification model Methods 0.000 description 6
- 230000009471 action Effects 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012821 model calculation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
- G06V20/586—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of parking space
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B29/00—Maps; Plans; Charts; Diagrams, e.g. route diagram
- G09B29/001—Planning boards
- G09B29/002—Planning boards using magnetic elements
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Mathematical Physics (AREA)
- Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a parking space detection method and device, wherein the method comprises the following steps: acquiring the current position coordinates of the vehicle under the ink card support coordinate system; a pre-constructed library position map is called, wherein the library position map comprises position coordinates of a plurality of library positions under an ink card bracket coordinate system; and selecting a target bin with a position coordinate matched with the current position coordinate from the plurality of bins, and feeding back the target position coordinate corresponding to the target bin. According to the invention, the library map can be constructed in advance, and after the library map is constructed, the target library with matched position coordinates can be directly selected when the vehicle is parked again, so that the accurate library position can be reliably provided, the dependence of the visual detection library on weather and surrounding environment is obviously reduced, and the robustness of library identification is greatly improved.
Description
Technical Field
The invention relates to the technical field of intelligent driving, in particular to a parking space detection method and device.
Background
With the continuous development of unmanned technology, various large companies continuously perfect automatic driving functions in different scenes, wherein automatic parking is one of the most practical functions in low-speed scenes.
The most important ring in automatic parking is to sense the exact location of the garage. In the current stage, a camera is generally adopted to realize the perception of the position of the library. However, due to the fact that the dependence degree of the camera on weather conditions is high, accurate positioning of the garage position cannot be achieved in rainy and snowy weather, evening or shielding conditions.
Disclosure of Invention
In view of the above, the present invention provides a parking space detection method and apparatus. The technical proposal is as follows:
a method of parking space detection, the method comprising:
acquiring the current position coordinates of the vehicle under the ink card support coordinate system;
a pre-constructed library position map is called, wherein the library position map comprises position coordinates of a plurality of library positions under the ink card support coordinate system;
and selecting a target bin with a position coordinate matched with the current position coordinate from the plurality of bins, and feeding back the target position coordinate corresponding to the target bin.
Preferably, the process of pre-constructing the library map includes:
acquiring a live-action image shot by a vehicle-mounted surrounding camera, and splicing the live-action image into a vehicle overhead image;
determining a first position coordinate of a library to be constructed in the vehicle overhead image under a pixel coordinate system;
determining a second position coordinate of the library to be constructed under a vehicle coordinate system based on the first position coordinate;
acquiring a third position coordinate of the vehicle under the ink card support coordinate system, and determining a fourth position coordinate of the library to be constructed under the ink card support coordinate system by utilizing the third position coordinate and the second position coordinate;
and generating a library position map containing the library positions to be constructed at least based on the fourth position coordinates.
Preferably, the determining the first position coordinate of the library to be constructed in the vehicle overhead image under the pixel coordinate system includes:
identifying a library entry corner in the vehicle overhead image;
under the condition that the corner point of the bin inlet is identified, identifying the bin type in the vehicle overhead image;
and determining a first position coordinate of the library to be constructed under a pixel coordinate system based on the library entry corner point and the library type.
Preferably, before determining the second position coordinate of the to-be-constructed library position in the vehicle coordinate system based on the first position coordinate, the method further includes:
acquiring the pose of the vehicle;
and adjusting the first position coordinate based on the pose.
Preferably, the method further comprises:
updating the library map.
A parking space detection apparatus, the apparatus comprising: the system comprises a coordinate acquisition module, a map calling module and a coordinate matching module, wherein the map calling module comprises a map construction unit;
the coordinate acquisition module is used for acquiring the current position coordinate of the vehicle under the ink card support coordinate system;
the map construction unit is used for pre-constructing a library position map, wherein the library position map comprises position coordinates of a plurality of library positions under the ink card support coordinate system;
the map retrieving module is used for retrieving the library map;
the coordinate matching module is used for selecting a target bin with a position coordinate matched with the current position coordinate from the plurality of bins and feeding back the target position coordinate corresponding to the target bin.
Preferably, the map construction unit is specifically configured to:
acquiring a live-action image shot by a vehicle-mounted surrounding camera, and splicing the live-action image into a vehicle overhead image; determining a first position coordinate of a library to be constructed in the vehicle overhead image under a pixel coordinate system; determining a second position coordinate of the library to be constructed under a vehicle coordinate system based on the first position coordinate; acquiring a third position coordinate of the vehicle under the ink card support coordinate system, and determining a fourth position coordinate of the library to be constructed under the ink card support coordinate system by utilizing the third position coordinate and the second position coordinate; and generating a library position map containing the library positions to be constructed at least based on the fourth position coordinates.
Preferably, the map construction unit for determining a first position coordinate of a library to be constructed in the vehicle overhead image in a pixel coordinate system is specifically configured to:
identifying a library entry corner in the vehicle overhead image; under the condition that the corner point of the bin inlet is identified, identifying the bin type in the vehicle overhead image; and determining a first position coordinate of the library to be constructed under a pixel coordinate system based on the library entry corner point and the library type.
Preferably, the map construction unit is further configured to:
acquiring the pose of the vehicle; and adjusting the first position coordinate based on the pose.
Preferably, the map construction unit is further configured to:
updating the library map.
According to the parking space detection method and device, the space map can be built in advance, the target space with the matched position coordinates can be directly selected when the vehicle parks again after the space map is built, accurate space positions can be reliably given, the dependence degree of the visual detection space on weather and surrounding environment is obviously reduced, and the robustness of space recognition is greatly improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present invention, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for detecting a parking space according to an embodiment of the present invention;
FIG. 2 is an example of a library map;
FIG. 3 is a partial flow chart of a parking garage position detection method according to an embodiment of the present invention;
FIG. 4 is a flowchart of another method of detecting a parking garage according to an embodiment of the present invention;
FIG. 5 is an example of a library bit;
fig. 6 is a schematic structural diagram of a parking space detection device according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The embodiment of the invention provides a parking space detection method, a method flow chart of which is shown in fig. 1, comprising the following steps:
s10, acquiring the current position coordinates of the vehicle under the ink card support coordinate system.
In this embodiment, the current longitude and latitude of the vehicle may be determined through the GPS signal of the vehicle, so as to convert the current longitude and latitude into the current position coordinate under the mercator coordinate system. The conversion relationship between the longitude and latitude and the position coordinates in the ink card support coordinate system can be calibrated in advance, which is not limited in this embodiment.
S20, a pre-built library position map is called, wherein the library position map comprises position coordinates of a plurality of library positions under an ink card support coordinate system.
Such as the library map example shown in fig. 2. The library position map at least comprises position coordinates of each library position in the plurality of library positions under the ink card support coordinate system. Of course, the library bit map may further include a library bit type, a library bit identifier, and the like of each library bit, which is not limited in this embodiment.
In a specific implementation process, the process of pre-constructing the library map in step S20 may include the following steps, where a method flowchart is shown in fig. 3:
s201, acquiring a live-action image shot by a vehicle-mounted looking-around camera, and splicing the live-action image into a vehicle overhead image.
In the process of executing step S201, multiple paths of vehicle-mounted looking-around cameras pre-installed on the vehicle may respectively capture live-action images at the same time, and then the aerial view images of the vehicle may be obtained by mapping the live-action images onto the plane where the calibrated checkerboard is located.
Of course, before the stitching process, the distortion removal process may also be performed on the live-action image, so as to improve usability of the live-action image.
S202, determining first position coordinates of a library to be constructed in a vehicle overhead image under a pixel coordinate system.
In the process of executing step S202, the pixel coordinate system may use the upper left corner of the vehicle overhead image as the origin of coordinates, with the width direction being the X axis and the height direction being the Y axis. Firstly, whether a vehicle overhead image contains a library position to be constructed or not is identified, and then under the condition that the library position to be constructed is identified, the position coordinate of the library position to be constructed under a pixel coordinate system is determined to be a first position coordinate of the library position to be constructed under the pixel coordinate system.
Specifically, step S202 "determining the first position coordinate of the library to be constructed in the vehicle overhead image under the pixel coordinate system" may include the following steps, where the method flowchart is shown in fig. 4:
s2021, identifying a bin entry corner in the vehicle overhead image.
In the process of executing step S2021, the bin entry corner points in the vehicle overhead image may be identified in a machine learning or deep learning manner. Specifically, samples of different bin entry corners can be marked on a large scale in advance, and then the samples are put into a classification model to adjust the weight of the classification model, and the classification model after the weight adjustment has the capability of identifying the bin entry corners.
S2022, in the case where the bin entry corner point is identified, identifies a bin type in the vehicle overhead image.
In the process of executing step S2022, the type of the library in the vehicle overhead image (e.g., straight library, inclined library, parallel library, etc.) may be identified by machine learning or deep learning. Specifically, samples with different bin types can be marked on a large scale in advance, and then the samples are put into a classification model to adjust the weight of the classification model, and the classification model after the weight adjustment has the capability of identifying the entry corner points of the bin.
S2023, determining a first position coordinate of the to-be-constructed library under the pixel coordinate system based on the library entry corner and the library type.
Such as the bin example shown in fig. 5. The region of the library to be constructed in the vehicle overhead image can be determined based on the library entry corner points and the library types, and further, the first position coordinates of the region corresponding to the library to be constructed are determined based on the pixel coordinate system corresponding to the vehicle overhead image, for example, the position coordinates of the central position of the library to be constructed can be used as the first position coordinates.
On this basis, in order to solve the problem that the model calculation takes a long time, resulting in the lag of identifying the library position and low update frequency, before executing step S203, the following steps may be further adopted:
acquiring the pose of a vehicle; the first position coordinates are adjusted based on the pose.
In this embodiment, information such as angular acceleration, yaw rate, azimuth angle and the like of the vehicle on X, Y and Z three axes can be obtained by combining inertial navigation (RTK) signals, and then the pose of the vehicle is estimated by a motion model, and the first position coordinate is updated and corrected by coordinate transformation, so that accurate positioning of the garage to be constructed in a pixel coordinate system is realized.
S203, determining second position coordinates of the library to be constructed under the vehicle coordinate system based on the first position coordinates.
In the process of executing step S203, a certain image area of the vehicle overhead view in the pixel coordinate system corresponds to an actual area fixed in the vehicle coordinate system. The first position coordinates in the pixel coordinate system can thus be converted into second position coordinates in the vehicle coordinate system by means of the first position coordinates and the mapping matrix between the pixel coordinate system and the vehicle coordinate system.
S204, obtaining a third position coordinate of the vehicle under the ink card support coordinate system, and determining a fourth position coordinate of the library to be constructed under the ink card support coordinate system by utilizing the third position coordinate and the second position coordinate.
In the process of executing step S204, the longitude and latitude of the vehicle may be determined by the GPS signal of the vehicle, and then the longitude and latitude are converted into the third position coordinate under the ink card holder coordinate system. And because the second position coordinate represents the relative position relation between the to-be-constructed library position and the vehicle, the fourth position coordinate of the to-be-constructed library position under the ink card support coordinate system can be determined by combining the third position coordinate.
S205, generating a library position map containing library positions to be constructed at least based on the fourth position coordinates.
In the process of performing step S205, the position of the library bit to be constructed may be drawn in the library bit map based on the fourth position coordinates. Further, if a library bit type or a library bit identification for a library bit to be constructed is obtained, and the like, it is also possible to correspondingly record and manage.
S30, selecting a target position with the position coordinate matched with the current position coordinate from the plurality of positions, and feeding back the target position coordinate corresponding to the target position.
In this embodiment, a target library position whose distance between the position coordinate and the current position coordinate is within a certain range may be selected.
In other embodiments, to adapt to environmental changes, the method for detecting the parking space shown in fig. 1 may further include the following steps:
updating the library map.
In this embodiment, the library map at least includes a position coordinate of each of the plurality of library positions under the ink card support coordinate system. Therefore, when the vehicle detects a new bank again at a similar position of a certain bank, the position coordinates of the new bank under the ink card tray coordinate system can be replaced by the position coordinates of the new bank under the ink card tray coordinate system. In addition, when the library position map also comprises information such as the library position type, the library position identification and the like of each library position, the information corresponding to the library position is reassigned to the new library position.
In addition, if the difference of the position coordinates of the new library position under the ink card support coordinate system or the library position type and the like detected at the position of the library position is large, the library position map can be reconstructed so as to solve the problems that the library position is re-divided in a parking lot or has large-scale physical change and the like.
According to the garage parking position detection method disclosed by the embodiment of the invention, the garage position map can be constructed in advance, and after the construction of the garage position map is completed, the target garage position with the matched position coordinates can be directly selected when the vehicle parks again, so that the accurate garage position can be reliably given, the dependence of the visual detection garage position on weather and surrounding environment is obviously reduced, and the robustness of garage position identification is greatly improved.
Based on the parking space detection method disclosed in the above embodiment, the embodiment of the present invention correspondingly discloses a device for executing the parking space detection method, where a schematic structural diagram of the device is shown in fig. 6, and the device includes: the system comprises a coordinate acquisition module 10, a map retrieval module 20 and a coordinate matching module 30, wherein the map retrieval module 20 comprises a map construction unit 201;
the coordinate acquisition module 10 is used for acquiring the current position coordinate of the vehicle under the ink card support coordinate system.
The map construction unit 201 is configured to construct a library map in advance, where the library map includes position coordinates of a plurality of library positions in an ink card coordinate system.
The map retrieving module 20 is configured to retrieve a map of a library.
The coordinate matching module 30 is configured to select a target bin whose position coordinate matches the current position coordinate from the plurality of bins, and feed back a target position coordinate corresponding to the target bin.
Optionally, the map construction unit 201 is specifically configured to:
acquiring a live-action image shot by a vehicle-mounted looking-around camera, and splicing the live-action image into a vehicle overhead image; determining a first position coordinate of a library to be constructed in a vehicle overhead image under a pixel coordinate system; determining a second position coordinate of the library to be constructed under the vehicle coordinate system based on the first position coordinate; acquiring a third position coordinate of the vehicle under the ink card support coordinate system, and determining a fourth position coordinate of the library to be constructed under the ink card support coordinate system by utilizing the third position coordinate and the second position coordinate; and generating a library position map containing library positions to be constructed at least based on the fourth position coordinates.
Optionally, the map construction unit 201 for determining a first position coordinate of a library to be constructed in the vehicle overhead image in a pixel coordinate system is specifically configured to:
identifying a library entry corner in the vehicle overhead image; under the condition that the corner point of the entrance of the garage is identified, the garage type in the aerial view image of the vehicle is identified; and determining a first position coordinate of the library to be constructed under the pixel coordinate system based on the library entry corner and the library type.
Optionally, the map construction unit 201 is further configured to:
acquiring the pose of a vehicle; the first position coordinates are adjusted based on the pose.
Optionally, the map construction unit 201 is further configured to:
and the map updating module is used for updating the library position map.
According to the parking space detection device disclosed by the embodiment of the invention, the space map can be constructed in advance, and after the space map is constructed, the target space with the matched position coordinates can be directly selected when the vehicle parks again, so that the accurate space position can be reliably given, the dependence of the visual detection space on weather and surrounding environment is obviously reduced, and the robustness of the space identification is greatly improved.
The above description of the method and apparatus for detecting a parking space provided by the present invention applies specific examples to illustrate the principles and embodiments of the present invention, and the above description of the examples is only used to help understand the method and core ideas of the present invention; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present invention, the present description should not be construed as limiting the present invention in view of the above.
It should be noted that, in the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described as different from other embodiments, and identical and similar parts between the embodiments are all enough to be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
It is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include, or is intended to include, elements inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (6)
1. A method for detecting a parking space, the method comprising:
acquiring the current position coordinates of the vehicle under the ink card support coordinate system;
a pre-constructed library position map is called, wherein the library position map comprises position coordinates of a plurality of library positions under the ink card support coordinate system;
selecting a target bin with a position coordinate matched with the current position coordinate from the plurality of bins, and feeding back a target position coordinate corresponding to the target bin;
the process of pre-constructing the library map comprises the following steps:
acquiring a live-action image shot by a vehicle-mounted surrounding camera, and splicing the live-action image into a vehicle overhead image;
determining a first position coordinate of a library to be constructed in the vehicle overhead image under a pixel coordinate system;
determining a second position coordinate of the library to be constructed under a vehicle coordinate system based on the first position coordinate;
acquiring a third position coordinate of the vehicle under the ink card support coordinate system, and determining a fourth position coordinate of the library to be constructed under the ink card support coordinate system by utilizing the third position coordinate and the second position coordinate;
generating a library position map containing the library position to be constructed at least based on the fourth position coordinates;
the determining a first position coordinate of a library to be constructed in the vehicle overhead image under a pixel coordinate system includes:
identifying a library entry corner in the vehicle overhead image;
under the condition that the corner point of the bin inlet is identified, identifying the bin type in the vehicle overhead image;
and determining a first position coordinate of the library to be constructed under a pixel coordinate system based on the library entry corner point and the library type.
2. The method of claim 1, wherein the determining the second location coordinates of the library to be built in the vehicle coordinate system based on the first location coordinates is preceded by:
acquiring the pose of the vehicle;
and adjusting the first position coordinate based on the pose.
3. The method according to claim 1, wherein the method further comprises:
updating the library map.
4. A parking space detection apparatus, characterized in that the apparatus comprises: the system comprises a coordinate acquisition module, a map calling module and a coordinate matching module, wherein the map calling module comprises a map construction unit;
the coordinate acquisition module is used for acquiring the current position coordinate of the vehicle under the ink card support coordinate system;
the map construction unit is used for pre-constructing a library position map, wherein the library position map comprises position coordinates of a plurality of library positions under the ink card support coordinate system;
the map retrieving module is used for retrieving the library map;
the coordinate matching module is used for selecting a target bin with a position coordinate matched with the current position coordinate from the plurality of bins and feeding back the target position coordinate corresponding to the target bin;
the map construction unit is specifically configured to:
acquiring a live-action image shot by a vehicle-mounted surrounding camera, and splicing the live-action image into a vehicle overhead image; determining a first position coordinate of a library to be constructed in the vehicle overhead image under a pixel coordinate system; determining a second position coordinate of the library to be constructed under a vehicle coordinate system based on the first position coordinate; acquiring a third position coordinate of the vehicle under the ink card support coordinate system, and determining a fourth position coordinate of the library to be constructed under the ink card support coordinate system by utilizing the third position coordinate and the second position coordinate; generating a library position map containing the library position to be constructed at least based on the fourth position coordinates;
the map construction unit is used for determining a first position coordinate of a library to be constructed in the vehicle overhead image under a pixel coordinate system, and is specifically used for:
identifying a library entry corner in the vehicle overhead image; under the condition that the corner point of the bin inlet is identified, identifying the bin type in the vehicle overhead image; and determining a first position coordinate of the library to be constructed under a pixel coordinate system based on the library entry corner point and the library type.
5. The apparatus of claim 4, wherein the map construction unit is further configured to:
acquiring the pose of the vehicle; and adjusting the first position coordinate based on the pose.
6. The apparatus of claim 4, wherein the map construction unit is further configured to:
updating the library map.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910537656.XA CN112115741B (en) | 2019-06-20 | 2019-06-20 | Parking garage position detection method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910537656.XA CN112115741B (en) | 2019-06-20 | 2019-06-20 | Parking garage position detection method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112115741A CN112115741A (en) | 2020-12-22 |
CN112115741B true CN112115741B (en) | 2024-02-20 |
Family
ID=73796138
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910537656.XA Active CN112115741B (en) | 2019-06-20 | 2019-06-20 | Parking garage position detection method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112115741B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114030463B (en) * | 2021-11-23 | 2024-05-14 | 上海汽车集团股份有限公司 | Path planning method and device for automatic parking system |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE102015008422B3 (en) * | 2015-06-30 | 2016-10-13 | Audi Ag | Method and system for detecting vehicles parked incorrectly in a parking lot |
CN108154472A (en) * | 2017-11-30 | 2018-06-12 | 惠州市德赛西威汽车电子股份有限公司 | Merge the parking position visible detection method and system of navigation information |
CN108564814A (en) * | 2018-06-06 | 2018-09-21 | 清华大学苏州汽车研究院(吴江) | A kind of parking position detection method and device based on image |
CN109131318A (en) * | 2018-10-19 | 2019-01-04 | 清华大学 | A kind of autonomous parking path coordination approach based on topological map |
CN109817018A (en) * | 2019-02-20 | 2019-05-28 | 东软睿驰汽车技术(沈阳)有限公司 | A kind of automatic parking method and relevant apparatus |
-
2019
- 2019-06-20 CN CN201910537656.XA patent/CN112115741B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE102015008422B3 (en) * | 2015-06-30 | 2016-10-13 | Audi Ag | Method and system for detecting vehicles parked incorrectly in a parking lot |
CN108154472A (en) * | 2017-11-30 | 2018-06-12 | 惠州市德赛西威汽车电子股份有限公司 | Merge the parking position visible detection method and system of navigation information |
CN108564814A (en) * | 2018-06-06 | 2018-09-21 | 清华大学苏州汽车研究院(吴江) | A kind of parking position detection method and device based on image |
CN109131318A (en) * | 2018-10-19 | 2019-01-04 | 清华大学 | A kind of autonomous parking path coordination approach based on topological map |
CN109817018A (en) * | 2019-02-20 | 2019-05-28 | 东软睿驰汽车技术(沈阳)有限公司 | A kind of automatic parking method and relevant apparatus |
Also Published As
Publication number | Publication date |
---|---|
CN112115741A (en) | 2020-12-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20200173803A1 (en) | Vision augmented navigation | |
CN111830953B (en) | Vehicle self-positioning method, device and system | |
EP3644013B1 (en) | Method, apparatus, and system for location correction based on feature point correspondence | |
CN106056958A (en) | Auxiliary vehicle search system and realization method thereof | |
CN112862881B (en) | Road map construction and fusion method based on crowd-sourced multi-vehicle camera data | |
CN114067564B (en) | Traffic condition comprehensive monitoring method based on YOLO | |
CN115164918B (en) | Semantic point cloud map construction method and device and electronic equipment | |
CN111340877A (en) | Vehicle positioning method and device | |
JP6278790B2 (en) | Vehicle position detection device, vehicle position detection method, vehicle position detection computer program, and vehicle position detection system | |
JP2017181476A (en) | Vehicle location detection device, vehicle location detection method and vehicle location detection-purpose computer program | |
CN108694381A (en) | Object positioning method and object trajectory method for tracing | |
CN112883058A (en) | Calibration method, device, equipment, vehicle and medium for vehicle positioning | |
CN114639085A (en) | Traffic signal lamp identification method and device, computer equipment and storage medium | |
US20220250627A1 (en) | Information processing system, program, and information processing method | |
CN112115741B (en) | Parking garage position detection method and device | |
CN114419922A (en) | Parking space identification method and device | |
CN111238490A (en) | Visual positioning method and device and electronic equipment | |
CN110135387B (en) | Image rapid identification method based on sensor fusion | |
CN115235493B (en) | Method and device for automatic driving positioning based on vector map | |
CN115790568A (en) | Map generation method based on semantic information and related equipment | |
CN108242163A (en) | The driver assistance system of motor vehicle | |
CN112880692B (en) | Map data labeling method and device and storage medium | |
CN109655073B (en) | Map drawing method and device in no-signal or weak-signal area and vehicle | |
JP2012203722A (en) | Feature selection system, feature selection program, and feature selection method | |
CN113205144B (en) | Model training method and device |
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 | ||
TA01 | Transfer of patent application right | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20220119 Address after: No. 203, Shanghai Songjiang Road, No. 201563, Pudong New Area Applicant after: SAIC Motor Corp.,Ltd. Applicant after: Shanghai Automotive Industry Corporation (Group) Address before: 201203 Room 509, Building No. 1, 563 Songtao Road, Zhangjiang High-tech Park, Pudong New Area, Shanghai Applicant before: SAIC Motor Corp.,Ltd. |
|
GR01 | Patent grant | ||
GR01 | Patent grant |