CN112985404A - Method, device, equipment and medium for generating crowdsourcing map of parking lot - Google Patents
Method, device, equipment and medium for generating crowdsourcing map of parking lot Download PDFInfo
- Publication number
- CN112985404A CN112985404A CN202110178689.7A CN202110178689A CN112985404A CN 112985404 A CN112985404 A CN 112985404A CN 202110178689 A CN202110178689 A CN 202110178689A CN 112985404 A CN112985404 A CN 112985404A
- Authority
- CN
- China
- Prior art keywords
- parking lot
- crowdsourcing
- track
- data
- vehicle
- 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 60
- 230000009466 transformation Effects 0.000 claims description 34
- 230000004927 fusion Effects 0.000 claims description 27
- 238000005457 optimization Methods 0.000 claims description 25
- 238000006243 chemical reaction Methods 0.000 claims description 14
- 230000008859 change Effects 0.000 claims description 9
- 230000001131 transforming effect Effects 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 3
- 230000006872 improvement Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 229910052704 radon Inorganic materials 0.000 description 2
- SYUHGPGVQRZVTB-UHFFFAOYSA-N radon atom Chemical compound [Rn] SYUHGPGVQRZVTB-UHFFFAOYSA-N 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007499 fusion processing Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/20—Instruments for performing navigational calculations
- G01C21/206—Instruments for performing navigational calculations specially adapted for indoor navigation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/10—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration
- G01C21/12—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning
- G01C21/16—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation
- G01C21/165—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation combined with non-inertial navigation instruments
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/86—Combinations of radar systems with non-radar systems, e.g. sonar, direction finder
- G01S13/862—Combination of radar systems with sonar systems
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/86—Combinations of radar systems with non-radar systems, e.g. sonar, direction finder
- G01S13/865—Combination of radar systems with lidar systems
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/86—Combinations of radar systems with non-radar systems, e.g. sonar, direction finder
- G01S13/867—Combination of radar systems with cameras
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S15/00—Systems using the reflection or reradiation of acoustic waves, e.g. sonar systems
- G01S15/86—Combinations of sonar systems with lidar systems; Combinations of sonar systems with systems not using wave reflection
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S15/00—Systems using the reflection or reradiation of acoustic waves, e.g. sonar systems
- G01S15/88—Sonar systems specially adapted for specific applications
- G01S15/93—Sonar systems specially adapted for specific applications for anti-collision purposes
- G01S15/931—Sonar systems specially adapted for specific applications for anti-collision purposes of land vehicles
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/86—Combinations of lidar systems with systems other than lidar, radar or sonar, e.g. with direction finders
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/88—Lidar systems specially adapted for specific applications
- G01S17/93—Lidar systems specially adapted for specific applications for anti-collision purposes
- G01S17/931—Lidar systems specially adapted for specific applications for anti-collision purposes of land vehicles
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
- G01S19/38—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system
- G01S19/39—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system the satellite radio beacon positioning system transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
- G01S19/42—Determining position
- G01S19/45—Determining position by combining measurements of signals from the satellite radio beacon positioning system with a supplementary measurement
- G01S19/47—Determining position by combining measurements of signals from the satellite radio beacon positioning system with a supplementary measurement the supplementary measurement being an inertial measurement, e.g. tightly coupled inertial
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/14—Traffic control systems for road vehicles indicating individual free spaces in parking areas
- G08G1/145—Traffic control systems for road vehicles indicating individual free spaces in parking areas where the indication depends on the parking areas
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Electromagnetism (AREA)
- Automation & Control Theory (AREA)
- Acoustics & Sound (AREA)
- Navigation (AREA)
Abstract
The application discloses a method, a device, equipment and a medium for generating a parking lot crowdsourcing map, wherein the method comprises the following steps: acquiring crowdsourcing parking lot data acquired by each vehicle end sensor; carrying out track matching on vehicle tracks in the crowdsourcing parking lot data, and grouping the crowdsourcing parking lot data according to the obtained track matching degree; carrying out parking lot feature alignment on crowdsourcing parking lot data in each group, and fusing the aligned crowdsourcing parking lot data among the groups; and generating a parking lot crowdsourcing map based on the fused crowdsourcing parking lot data. The technical problem that in an area with weak GPS signals, especially an indoor parking lot, the generated crowdsourcing map is incomplete and accurate due to incomplete and accurate collected map data in the existing crowdsourcing map generation method is solved.
Description
Technical Field
The present application relates to the field of map generation technologies, and in particular, to a method, an apparatus, a device, and a medium for generating a parking lot crowdsourcing map.
Background
The crowdsourcing map is a map constructed by map data acquired in a crowdsourcing mode, and the map data is acquired by each common vehicle by distributing data acquisition work to each common vehicle, so that the process of on-site acquisition and survey of a specially-assigned person is avoided. However, most of the existing crowdsourcing map generation methods acquire track data through a Global Positioning System (GPS), and in areas with weak GPS signals, especially in indoor parking lots, there are situations where the acquired map data is not complete and accurate enough, resulting in incomplete and accurate crowdsourcing maps.
Disclosure of Invention
The application provides a method, a device, equipment and a medium for generating a crowdsourcing map of a parking lot, which are used for improving the technical problem that in an area with weak GPS signals, especially an indoor parking lot, the generated crowdsourcing map is incomplete and accurate due to incomplete and accurate collected map data in the existing crowdsourcing map generation method.
In view of this, a first aspect of the present application provides a method for generating a parking lot crowdsourcing map, including:
acquiring crowdsourcing parking lot data acquired by each vehicle end sensor;
carrying out track matching on vehicle tracks in the crowdsourced parking lot data, and grouping the crowdsourced parking lot data according to the obtained track matching degree;
carrying out parking lot feature alignment on the crowdsourcing parking lot data in each group, and fusing the crowdsourcing parking lot data aligned among the groups;
and generating a parking lot crowdsourcing map based on the fused crowdsourcing parking lot data.
Optionally, the performing parking lot feature alignment on the crowd-sourced parking lot data in each group includes:
carrying out track matching on vehicle tracks in the crowdsourced parking lot data in each group to obtain a plurality of track point pairs;
constructing a pose graph based on the track point pairs;
optimizing the pose graph, and aligning the parking lot features of the crowdsourced parking lot data in each group according to the obtained optimization result.
Optionally, constructing a pose graph based on the pairs of trajectory points includes:
matching the parking lot characteristics around each track point pair to obtain a plurality of characteristic point pairs, wherein the parking lot characteristics comprise lane lines, parking places, arrows or speed bumps;
calculating a first position and posture conversion parameter of the corresponding track point pair according to the relative position relation of each characteristic point pair, and calculating a second position and posture conversion parameter according to the relative position relation between adjacent track points in each vehicle track;
and constructing a pose graph by taking track points in each vehicle track as vertexes and taking the first pose transformation parameter and the second pose transformation parameter as sides.
Optionally, constructing a pose graph based on the pairs of trajectory points includes:
obtaining a third posture transformation parameter between the vehicle tracks according to the relative position relation of each track point pair;
and constructing a pose graph by taking each vehicle track as a vertex and the third transformation parameters as edges.
Optionally, the optimizing the pose graph, and performing parking lot feature alignment on the crowd-sourced parking lot data in each group according to an obtained optimization result includes:
optimizing the pose graph by a graph optimization method to obtain the optimized position of each vertex;
and transforming the vertexes according to the optimized positions of the vertexes so as to realize the parking lot feature alignment.
Optionally, the crowd-sourced parking lot data in each group is aligned with the parking lot features, and the crowd-sourced parking lot data aligned between each group is fused, and then the method further includes:
acquiring alignment quality according to a distance error between the aligned parking lot features, and acquiring fusion gain according to a change condition of the parking lot features of the fused crowd-sourced parking lot data;
and determining whether to manually check the crowdsourcing parking lot data according to the alignment quality and the fusion gain.
Optionally, the obtaining crowd-sourced parking lot data collected by the vehicle end further includes:
and eliminating the crowdsourcing parking lot data with the vehicle track length being lower than the preset length or the parking lot feature quantity being less than the preset quantity.
The second aspect of the present application provides a parking lot crowdsourcing map generating device, including:
the acquisition unit is used for acquiring crowdsourcing parking lot data acquired by each vehicle-end sensor;
the matching and grouping unit is used for carrying out track matching on vehicle tracks in the crowdsourced parking lot data and grouping the crowdsourced parking lot data according to the obtained track matching degree;
the alignment and fusion unit is used for performing parking lot feature alignment on the crowdsourced parking lot data in each group and fusing the crowdsourced parking lot data aligned among the groups;
and the generation unit is used for generating the parking lot crowdsourcing map based on the fused crowdsourcing parking lot data.
Optionally, the alignment and fusion unit specifically includes:
the matching subunit is used for carrying out track matching on vehicle tracks in the crowdsourced parking lot data in each group to obtain a plurality of track point pairs;
the construction subunit is used for constructing a pose graph based on the track point pairs;
the optimization subunit is used for optimizing the pose graph and performing parking lot feature alignment on the crowdsourced parking lot data in each group according to the obtained optimization result;
and the fusion subunit is used for fusing the crowdsourced parking lot data after alignment among the groups.
Optionally, the building subunit is specifically configured to:
matching the parking lot characteristics around each track point pair to obtain a plurality of characteristic point pairs, wherein the parking lot characteristics comprise lane lines or parking spaces;
calculating a first position and posture conversion parameter of the track point pair corresponding to the characteristic point pair according to the relative position relation of each characteristic point pair, and calculating a second position and posture conversion parameter according to the relative position relation between adjacent track points in each vehicle track;
and constructing a pose graph by taking track points in each vehicle track as vertexes and taking the first pose transformation parameter and the second pose transformation parameter as edges.
Optionally, the building subunit is further specifically configured to:
obtaining a third posture transformation parameter between the vehicle tracks according to the relative position relation of each track point pair;
and constructing a pose graph by taking each vehicle track as a vertex and the third transformation parameter as an edge.
A third aspect of the present application provides a parking lot crowdsourcing map generating device, the device comprising a processor and a memory;
the memory is used for storing program codes and transmitting the program codes to the processor;
the processor is configured to execute the parking lot crowdsourcing map generating method according to any one of the first aspect according to instructions in the program code.
A fourth aspect of the present application provides a computer-readable storage medium for storing program code for executing the method for generating a crowd-sourced parking lot map according to any one of the first aspects.
According to the technical scheme, the method has the following advantages:
the application provides a parking lot crowdsourcing map generation method, which comprises the following steps: acquiring crowdsourcing parking lot data acquired by each vehicle end sensor; carrying out track matching on vehicle tracks in the crowdsourcing parking lot data, and grouping the crowdsourcing parking lot data according to the obtained track matching degree; carrying out parking lot feature alignment on crowdsourcing parking lot data in each group, and fusing the aligned crowdsourcing parking lot data among the groups; and generating a parking lot crowdsourcing map based on the fused crowdsourcing parking lot data.
In the application, vehicle track and other crowdsourcing parking lot data are collected through the vehicle end sensor, so that the influence on the integrity and accuracy of the collected crowdsourcing parking lot data when a GPS signal is weak is avoided; in addition, the crowdsourcing parking lot data are grouped according to the track matching degree among the crowdsourcing parking lot data, so that the crowdsourcing parking lot data with high track matching degree are grouped into one group, the parking lot feature alignment is preferentially carried out on the crowdsourcing parking lot data with high track matching degree, and the accuracy of the crowdsourcing map of the parking lot is improved; and finally, fusing the crowd-sourced parking lot data after the group alignment to obtain a final parking lot crowd-sourced map, thereby improving the technical problem that the generated crowd-sourced map is incomplete and accurate due to incomplete and accurate acquired map data in an area with weak GPS signals, particularly an indoor parking lot, in the conventional crowd-sourced map generation method.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without inventive exercise.
Fig. 1 is a schematic flowchart of a method for generating a parking lot crowdsourcing map according to an embodiment of the present application;
fig. 2 is a pose diagram provided in the embodiment of the present application;
fig. 3 is another schematic flow chart of a parking lot crowdsourcing map generating method according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of a parking lot crowdsourcing map generating device according to an embodiment of the present application.
Detailed Description
The application provides a method, a device, equipment and a medium for generating a crowdsourcing map of a parking lot, which are used for improving the technical problem that in an area with weak GPS signals, especially an indoor parking lot, the generated crowdsourcing map is incomplete and accurate due to incomplete and accurate collected map data in the existing crowdsourcing map generation method.
In order to make the technical solutions of the present application better understood, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
For easy understanding, please refer to fig. 1, an embodiment of a parking lot crowdsourcing map generating method provided by the present application includes:
The cloud end can follow the car end and acquire crowdsourcing parking area data, and the car end passes through car end sensor collection crowdsourcing parking area data when the parking area is gone, and wherein, crowdsourcing parking area data are through crowdsourcing mode acquisition. The vehicle-end sensor may include an IMU (Inertial Measurement Unit), a wheel speed meter, a camera, an ultrasonic radar, a laser radar, or a millimeter wave radar, etc., and the corresponding crowd-sourced parking lot data may include a odometer, a parking lot image, point cloud data, etc. The embodiment of the application considers that the GPS signal of the indoor parking lot is weak, and accurate vehicle track data are difficult to acquire through the GPS. To ameliorate this problem, odometers can be generated by the IMU and wheel speed meter at the vehicle end to derive a vehicle trajectory that includes discrete trajectory point coordinates and pose.
Further, the cloud end can initialize the crowdsourcing parking lot data acquired by the vehicle end sensor to acquire some reference information, such as the entrance position of the parking lot, and can issue the reference information to other vehicles to guide the other vehicles to acquire more accurate crowdsourcing parking lot data, and more sufficient parking lot data acquisition can be performed on the parking lot area with more information loss through each vehicle.
Further, the high in the clouds can carry out data screening to the crowdsourcing parking area who obtains, is less than the crowdsourcing parking area data that preset length or parking area characteristic quantity are less than the preset quantity with vehicle orbit length and rejects to select higher quality crowdsourcing parking area data, improve the accuracy of parking area crowdsourcing map.
And 102, carrying out track matching on vehicle tracks in the crowdsourced parking lot data, and grouping the crowdsourced parking lot data according to the obtained track matching degree.
The cloud can carry out track matching to the vehicle track in each crowdsourcing parking lot data through an ICP (Iterative Closest Point) matching algorithm, and then can calculate the track matching degree of each crowdsourcing parking lot data according to the vehicle track of the matching part, and then group the crowdsourcing parking lot data according to the track matching degree, and can divide two or more groups of crowdsourcing parking lot data with the highest track matching degree into one group to obtain a plurality of groups of crowdsourcing parking lot data. Crowd-sourced parking lot data are grouped through the track matching degree, the crowd-sourced parking lot data with the high track matching degree are divided into a group, and therefore parking lot feature alignment is preferentially carried out on the crowd-sourced parking lot data with the high track matching degree.
And 103, carrying out parking lot feature alignment on the crowdsourcing parking lot data in each group, and fusing the aligned crowdsourcing parking lot data among the groups.
The cloud carries out parking lot feature alignment on crowdsourcing parking lot data in each group after grouping the crowdsourcing parking lot data, and fuses the crowdsourcing parking lot data after aligning among the groups. Specifically, track matching is carried out on vehicle tracks in crowdsourced parking lot data in each group to obtain a plurality of track point pairs; constructing a pose graph based on the track point pairs; optimizing the pose graph, and aligning the parking lot features of the crowdsourced parking lot data in each group according to the obtained optimization result. Only one vehicle track is arranged in each group of crowd-sourced parking lot data after alignment; and then fusing the crowdsourcing parking lot data aligned among the groups, wherein only one vehicle track is in the crowdsourcing parking lot data finally fused. The inter-group fusion process is similar to the intra-group alignment process, and is not described herein again.
The crowd-sourced parking lot data are grouped through the track matching degree in the embodiment of the application, the crowd-sourced parking lot data with the high track matching degree are divided into a group, the parking lot feature alignment is preferentially carried out on the crowd-sourced parking lot data with the high track matching degree, namely, the parking lot feature alignment is preferentially carried out on the crowd-sourced parking lot data with the high similarity, the parking lot feature alignment effect is favorably ensured, the parking lot feature alignment is directly carried out on all the crowd-sourced parking lot data, the alignment error is higher, and the accuracy of a follow-up crowd-sourced parking lot map is influenced.
In one embodiment, the pose graph can be constructed as follows:
and A1, matching the parking lot characteristics around each track point pair to obtain a plurality of characteristic point pairs, wherein the parking lot characteristics comprise lane lines, parking spaces, arrows or speed bumps.
The vehicle tracks obtained when the vehicle runs on the same road of the parking lot have deviation, and if the vehicle tracks are directly aligned, the error is large. Regardless of how the vehicle travels on the same road in the parking lot, the parking lot features (lane lines, parking spaces, arrows, or speed bumps) around the road are fixed, and therefore, the accuracy of the parking lot crowdsourcing map can be ensured even more by aligning the parking lot features in the crowdsourcing parking lot data. Referring to fig. 2, the track point a in the vehicle track 1 and the track point a 'in the vehicle track 2 are obtained through track matching as a pair of track point pairs, and the parking lot features around the track point a and the track point a' are selected to be matched, such as parking spaces and lane lines, so that parking space point pairs and lane line point pairs can be obtained.
And A2, calculating the first position and posture conversion parameter of the corresponding track point pair according to the relative position relation of each characteristic point pair, and calculating the second position and posture conversion parameter according to the relative position relation between the adjacent track points in each vehicle track.
Calculating pose transformation parameters, namely rotation and translation parameters, according to the relative position relation of each characteristic point pair; and then, the pose transformation parameters of the characteristic point pairs are used as first pose transformation parameters between the track point pairs corresponding to the characteristic point pairs to obtain the relative pose constraint between the two track points. When a plurality of vehicle tracks exist in each group, first position transformation parameter calculation is carried out between every two vehicle tracks.
And calculating pose transformation parameters in each vehicle track, and calculating a second position transformation parameter according to the relative position relation between two adjacent track points in each vehicle track, wherein the second position transformation parameter is used as a fixed constraint between the adjacent track points in each vehicle track and is used for keeping the shape of the vehicle track so as to ensure that the shape of each vehicle track is not changed when the features of the parking lot are aligned.
And A3, constructing a pose graph by taking track points in each vehicle track as vertexes and taking the first pose transformation parameter and the second pose transformation parameter as sides.
The vehicle track is composed of a plurality of track points, a pose graph is constructed by taking the track points in each vehicle track as vertexes and taking the first pose transformation parameter and the second pose transformation parameter as sides, the obtained pose graph can refer to fig. 2, 4 vehicle tracks are shown in fig. 2, a connecting line (namely a transverse connecting line) between the interiors of each vehicle track is fixed constraint between two adjacent track points of the connecting line, and a connecting line (namely a longitudinal connecting line) of a track point pair between each vehicle track is relative pose constraint between the track point pairs.
Further, the pose graph can be optimized through a graph optimization method to obtain the optimized position of each vertex; and transforming each vertex according to the optimized position of each vertex so as to realize the alignment of the features of the parking lot.
Specifically, the optimization of the pose graph can be realized by using a nonlinear optimization toolkit, edges in the pose graph are constraint items, vertexes are items to be optimized, track points are optimized through optimizing the pose graph, the optimized positions of the vertexes are obtained, when the track points (vertexes) in the vehicle tracks are moved to the corresponding optimized positions, parking lot features can keep relative relation with the track points and move together, and therefore the alignment of the parking lot features of different vehicle tracks is realized.
In the embodiment of the application, in the parking lot feature alignment process, nonlinear optimization rather than rigid body change is adopted, so that the problem that vehicle track data cannot be completely aligned due to accumulated errors of the odometer can be solved.
In another embodiment, the pose graph can be constructed in the following way:
and B1, acquiring a third posture conversion parameter between the vehicle tracks according to the relative position relation of each track point pair.
Although the vehicle trajectories obtained when the vehicle travels on the same road in the parking lot are all deviated, the absolute deviation between the two vehicle trajectories may be calculated. And after a plurality of track point pairs are obtained by carrying out track matching on the vehicle tracks in the crowdsourced parking lot data in each group, calculating a pose transformation parameter according to the relative position relation between each track point pair to obtain a third pose transformation parameter between each vehicle track to be used as the relative pose constraint between each vehicle track. And when a plurality of vehicle tracks exist, calculating a third posture change parameter between every two vehicle tracks.
And B2, constructing a pose graph by taking each vehicle track as a vertex and the third transformation parameter as an edge.
According to the method and the device, each vehicle track is used as a vertex, and the third transformation parameters among the vehicle tracks are used as edges to construct the pose graph.
Further, optimizing the pose graph by a graph optimization method to obtain the optimized position of each vertex; and transforming each vertex according to the optimized position of each vertex so as to realize the alignment of the features of the parking lot.
Specifically, the optimization of the position and pose graph can be realized by using a nonlinear optimization toolkit, edges in the position and pose graph are constraint items, vertexes are items to be optimized, the vertexes are optimized through optimizing the position and optimization positions of the vertexes, when a vehicle track (vertex) is moved to the corresponding optimization position, the whole vehicle track is transformed, track points in the vehicle track naturally also can be transformed correspondingly, and therefore the shape of each vehicle track is kept, the relative position relation between parking lot features around the track points and the track points is fixed, and the parking lot features can naturally move along with the movement, so that the alignment of the parking lot features is realized.
Of course, besides the above method, other methods, such as Radon transform (Radon transform), exhaustion method, etc., may be adopted to perform coarse alignment first, and then the alignment effect is improved by the above nonlinear optimization.
And step 104, generating a parking lot crowdsourcing map based on the fused crowdsourcing parking lot data.
The integrated crowd-sourced parking lot map can be generated through the fused crowd-sourced parking lot data, and the generated crowd-sourced parking lot map takes the position of the parking lot entrance as the origin. After the cloud generates the crowd-sourced map of the parking lot, the crowd-sourced map can be issued to each vehicle end, and logic information such as intersections is included besides static parking lot features, so that a path to be matched can be found quickly when the vehicle end is positioned.
In the embodiment of the application, vehicle track and other crowdsourcing parking lot data are collected through the vehicle end sensor, so that the influence on the integrity and accuracy of the collected crowdsourcing parking lot data when a GPS signal is weak is avoided; in addition, the crowdsourcing parking lot data are grouped according to the track matching degree among the crowdsourcing parking lot data, so that the crowdsourcing parking lot data with high track matching degree are grouped into one group, the parking lot feature alignment is preferentially carried out on the crowdsourcing parking lot data with high track matching degree, and the accuracy of the crowdsourcing map of the parking lot is improved; and finally, fusing the crowd-sourced parking lot data after the group alignment to obtain a final parking lot crowd-sourced map, thereby improving the technical problem that the generated crowd-sourced map is incomplete and accurate due to incomplete and accurate acquired map data in an area with weak GPS signals, particularly an indoor parking lot, in the conventional crowd-sourced map generation method.
The above is an embodiment of the parking lot crowdsourcing map generation method provided by the present application, and the following is another embodiment of the parking lot crowdsourcing map generation method provided by the present application.
Referring to fig. 3, a method for generating a parking lot crowdsourcing map provided in an embodiment of the present application includes:
And step 202, carrying out track matching on vehicle tracks in the crowdsourced parking lot data, and grouping the crowdsourced parking lot data according to the obtained track matching degree.
And step 203, carrying out parking lot feature alignment on the crowdsourced parking lot data in each group, and fusing the crowdsourced parking lot data aligned among the groups.
The specific contents of step 201 to step 203 are the same as the specific contents of step 101 to step 103, and are not described herein again.
And 204, acquiring alignment quality according to the distance error between the aligned parking lot features, and acquiring fusion gain according to the change condition of the parking lot features of the fused crowd-sourced parking lot data.
When the crowd-sourced parking lot data is aligned in the parking lot, for example, when two parking spaces are aligned, the two parking spaces should be completely overlapped in an ideal state, that is, the distance error between the two parking spaces is 0, when the two parking spaces are not completely overlapped after being aligned, the distance error exists, the distance error can be calculated through the distance deviation between the two parking spaces, and when the distance error exceeds an error threshold value, the alignment quality is judged to be poor. It will be appreciated that statistical global or local distance errors may be used to determine alignment quality.
The fusion gain is obtained according to the change condition of the parking lot features of the fused parking lot crowdsourcing map, and the fusion gain condition can be judged by comparing the increase condition of the parking lot feature quantity in the crowdsourcing parking lot data before fusion according to the parking lot feature quantity in the fused crowdsourcing parking lot data. Specifically, the fusion gain condition can be judged by calculating the feature quantity for discrete features such as parking spaces and the like, the fusion gain condition can be judged by calculating the feature coverage rate for continuous features such as lane lines and the like, and when the increase quantity of the discrete features such as parking spaces and the like in the fused data is less than the preset increase quantity threshold value, or the increase coverage rate of the continuous features such as lane lines and the like is less than the preset increase coverage rate threshold value, the fusion gain is judged to be smaller.
And step 205, determining whether to manually check the crowdsourced parking lot data according to the alignment quality and the fusion gain.
And manually checking crowdsourcing parking lot data with poor alignment quality and low fusion gain to ensure the accuracy of the generated crowdsourcing parking lot map.
And step 206, generating a parking lot crowdsourcing map based on the fused crowdsourcing parking lot data.
And a complete parking lot crowdsourcing map can be obtained through the fused crowdsourcing parking lot data. Further, parking lot features such as parking spaces and lane lines can be refined based on priori knowledge, for example, the lane lines are refined according to the priori knowledge that the lane lines are parallel to each other and one lane line is collinear, then a high-precision parking lot crowdsourcing map is generated, and the generated parking lot crowdsourcing map takes the parking lot entrance position as an origin. After the cloud generates the crowd-sourced map of the parking lot, the crowd-sourced map can be issued to each vehicle end, and logic information such as intersections is included besides static parking lot features, so that a path to be matched can be found quickly when the vehicle end is positioned.
In the embodiment of the application, vehicle track and other crowdsourcing parking lot data are collected through the vehicle end sensor, so that the influence on the integrity and accuracy of the collected crowdsourcing parking lot data when a GPS signal is weak is avoided; in addition, the crowdsourcing parking lot data are grouped according to the track matching degree among the crowdsourcing parking lot data, so that the crowdsourcing parking lot data with high track matching degree are grouped into one group, the parking lot feature alignment is preferentially carried out on the crowdsourcing parking lot data with high track matching degree, and the accuracy of the crowdsourcing map of the parking lot is improved; and finally, fusing the crowd-sourced parking lot data after the group alignment to obtain a final parking lot crowd-sourced map, thereby improving the technical problem that the generated crowd-sourced map is incomplete and accurate due to incomplete and accurate acquired map data in an area with weak GPS signals, particularly an indoor parking lot, in the conventional crowd-sourced map generation method.
Further, according to the embodiment of the application, the alignment quality is obtained according to the distance error between the aligned parking lot features, the fusion gain is obtained according to the change situation of the parking lot features of the fused parking lot crowdsourcing map, and the crowdsourcing parking lot data with poor alignment quality and low fusion gain is manually checked to ensure the accuracy of the generated parking lot crowdsourcing map.
The foregoing is another embodiment of the parking lot crowdsourcing map generating method provided by the embodiment of the present application, and the following is an embodiment of the parking lot crowdsourcing map generating device provided by the present application.
Referring to fig. 4, an embodiment of the present application provides a parking lot crowdsourcing map generating device, including:
the acquisition unit is used for acquiring crowdsourcing parking lot data acquired by each vehicle-end sensor;
the matching and grouping unit is used for carrying out track matching on vehicle tracks in the crowdsourced parking lot data and grouping the crowdsourced parking lot data according to the obtained track matching degree;
the alignment and fusion unit is used for performing parking lot feature alignment on the crowdsourcing parking lot data in each group and fusing the aligned crowdsourcing parking lot data among the groups;
and the generation unit is used for generating the parking lot crowdsourcing map based on the fused crowdsourcing parking lot data.
As a further improvement, the alignment and fusion unit specifically comprises:
the matching subunit is used for carrying out track matching on vehicle tracks in the crowdsourced parking lot data in each group to obtain a plurality of track point pairs;
the construction subunit is used for constructing a pose graph based on the track point pairs;
the optimization subunit is used for optimizing the pose graph and aligning the parking lot features of the crowdsourced parking lot data in each group according to the obtained optimization result;
and the fusion subunit is used for fusing the crowdsourced parking lot data aligned among the groups.
As a further improvement, the building subunit is specifically for:
matching the parking lot characteristics around each track point pair to obtain a plurality of characteristic point pairs, wherein the parking lot characteristics comprise lane lines or parking spaces;
calculating a first position and posture conversion parameter of a track point pair corresponding to the characteristic point pair according to the relative position relation of the characteristic point pair, and calculating a second position and posture conversion parameter according to the relative position relation between adjacent track points in each vehicle track;
and constructing a pose graph by taking track points in each vehicle track as vertexes and taking the first pose transformation parameter and the second pose transformation parameter as sides.
As a further improvement, the building subunit is further specifically configured to:
acquiring a third posture conversion parameter between the vehicle tracks according to the relative position relation of each track point pair;
and constructing a pose graph by taking each vehicle track as a vertex and the third transformation parameter as an edge.
As a further improvement, the optimization subunit is specifically configured to:
optimizing the pose graph by a graph optimization method to obtain the optimized position of each vertex;
and transforming each vertex according to the optimized position of each vertex so as to realize the alignment of the features of the parking lot.
As a further improvement, the method further comprises the following steps: a verification unit for
Acquiring alignment quality according to distance errors among the aligned parking lot features, and acquiring fusion gain according to the change condition of the parking lot features of the fused crowd-sourced parking lot data;
and determining whether to manually check the crowdsourced parking lot data according to the alignment quality and the fusion gain.
As a further improvement, the method further comprises the following steps: a rejection unit for:
and eliminating crowd-sourced parking lot data with the vehicle track length being lower than the preset length or the parking lot feature quantity being less than the preset quantity.
In the embodiment of the application, vehicle track and other crowdsourcing parking lot data are collected through the vehicle end sensor, so that the influence on the integrity and accuracy of the collected crowdsourcing parking lot data when a GPS signal is weak is avoided; in addition, the crowdsourcing parking lot data are grouped according to the track matching degree among the crowdsourcing parking lot data, so that the crowdsourcing parking lot data with high track matching degree are grouped into one group, the parking lot feature alignment is preferentially carried out on the crowdsourcing parking lot data with high track matching degree, and the accuracy of the crowdsourcing map of the parking lot is improved; and finally, fusing the crowd-sourced parking lot data after the group alignment to obtain a final parking lot crowd-sourced map, thereby improving the technical problem that the generated crowd-sourced map is incomplete and accurate due to incomplete and accurate acquired map data in an area with weak GPS signals, particularly an indoor parking lot, in the conventional crowd-sourced map generation method.
Further, according to the embodiment of the application, the alignment quality is obtained according to the distance error between the aligned parking lot features, the fusion gain is obtained according to the change situation of the parking lot features of the fused parking lot crowdsourcing map, and the crowdsourcing parking lot data with poor alignment quality and low fusion gain is manually checked to ensure the accuracy of the generated parking lot crowdsourcing map.
The embodiment of the application also provides a parking lot crowdsourcing map generating device, which comprises a processor and a memory;
the memory is used for storing the program codes and transmitting the program codes to the processor;
the processor is configured to execute the parking lot crowdsourcing map generating method in the foregoing method embodiment according to instructions in the program code.
The embodiment of the application also provides a computer-readable storage medium, which is used for storing program codes, and the program codes are used for executing the parking lot crowdsourcing map generating method in the foregoing method embodiment.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for executing all or part of the steps of the method described in the embodiments of the present application through a computer device (which may be a personal computer, a server, or a network device). And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions in the embodiments of the present application.
Claims (13)
1. A parking lot crowdsourcing map generation method is characterized by comprising the following steps:
acquiring crowdsourcing parking lot data acquired by each vehicle end sensor;
carrying out track matching on vehicle tracks in the crowdsourced parking lot data, and grouping the crowdsourced parking lot data according to the obtained track matching degree;
carrying out parking lot feature alignment on the crowdsourcing parking lot data in each group, and fusing the crowdsourcing parking lot data aligned among the groups;
and generating a parking lot crowdsourcing map based on the fused crowdsourcing parking lot data.
2. The method of generating a parking lot crowdsourcing map according to claim 1, wherein said performing parking lot feature alignment on the crowdsourced parking lot data within each group comprises:
carrying out track matching on vehicle tracks in the crowdsourced parking lot data in each group to obtain a plurality of track point pairs;
constructing a pose graph based on the track point pairs;
optimizing the pose graph, and aligning the parking lot features of the crowdsourced parking lot data in each group according to the obtained optimization result.
3. The parking lot crowdsourcing map generating method of claim 2, wherein the constructing a pose graph based on the pairs of trajectory points comprises:
matching the parking lot characteristics around each track point pair to obtain a plurality of characteristic point pairs, wherein the parking lot characteristics comprise lane lines, parking places, arrows or speed bumps;
calculating a first position and posture conversion parameter of the corresponding track point pair according to the relative position relation of each characteristic point pair, and calculating a second position and posture conversion parameter according to the relative position relation between adjacent track points in each vehicle track;
and constructing a pose graph by taking track points in each vehicle track as vertexes and taking the first pose transformation parameter and the second pose transformation parameter as sides.
4. The parking lot crowdsourcing map generating method of claim 2, wherein the constructing a pose graph based on the pairs of trajectory points comprises:
obtaining a third posture transformation parameter between the vehicle tracks according to the relative position relation of each track point pair;
and constructing a pose graph by taking each vehicle track as a vertex and the third transformation parameters as edges.
5. The parking lot crowdsourcing map generation method according to claim 3 or 4, wherein optimizing the pose graph and performing parking lot feature alignment on the crowdsourcing parking lot data in each group according to the obtained optimization result comprises:
optimizing the pose graph by a graph optimization method to obtain the optimized position of each vertex;
and transforming the vertexes according to the optimized positions of the vertexes so as to realize the parking lot feature alignment.
6. The method for generating the crowd-sourced parking lot map according to claim 1, wherein the performing parking lot feature alignment on the crowd-sourced parking lot data in each group and fusing the crowd-sourced parking lot data aligned between each group further comprises:
acquiring alignment quality according to a distance error between the aligned parking lot features, and acquiring fusion gain according to a change condition of the parking lot features of the fused crowd-sourced parking lot data;
and determining whether to manually check the crowdsourcing parking lot data according to the alignment quality and the fusion gain.
7. The method for generating the crowdsourcing map for the parking lot according to claim 1, wherein the obtaining of the crowdsourcing parking lot data collected by the vehicle end further comprises:
and eliminating the crowdsourcing parking lot data with the vehicle track length being lower than the preset length or the parking lot feature quantity being less than the preset quantity.
8. A parking lot crowdsourcing map generation apparatus, comprising:
the acquisition unit is used for acquiring crowdsourcing parking lot data acquired by each vehicle-end sensor;
the matching and grouping unit is used for carrying out track matching on vehicle tracks in the crowdsourced parking lot data and grouping the crowdsourced parking lot data according to the obtained track matching degree;
the alignment and fusion unit is used for performing parking lot feature alignment on the crowdsourced parking lot data in each group and fusing the crowdsourced parking lot data aligned among the groups;
and the generation unit is used for generating the parking lot crowdsourcing map based on the fused crowdsourcing parking lot data.
9. The parking lot crowdsourcing map generating device according to claim 8, wherein the aligning and fusing unit specifically comprises:
the matching subunit is used for carrying out track matching on vehicle tracks in the crowdsourced parking lot data in each group to obtain a plurality of track point pairs;
the construction subunit is used for constructing a pose graph based on the track point pairs;
the optimization subunit is used for optimizing the pose graph and performing parking lot feature alignment on the crowdsourced parking lot data in each group according to the obtained optimization result;
and the fusion subunit is used for fusing the crowdsourced parking lot data after alignment among the groups.
10. The parking lot crowdsourcing map generating device of claim 9, wherein the building subunit is specifically configured to:
matching the parking lot characteristics around each track point pair to obtain a plurality of characteristic point pairs, wherein the parking lot characteristics comprise lane lines or parking spaces;
calculating a first position and posture conversion parameter of the track point pair corresponding to the characteristic point pair according to the relative position relation of each characteristic point pair, and calculating a second position and posture conversion parameter according to the relative position relation between adjacent track points in each vehicle track;
and constructing a pose graph by taking track points in each vehicle track as vertexes and taking the first pose transformation parameter and the second pose transformation parameter as edges.
11. The parking lot crowdsourcing map generating device of claim 9, wherein the building subunit is further configured to:
obtaining a third posture transformation parameter between the vehicle tracks according to the relative position relation of each track point pair;
and constructing a pose graph by taking each vehicle track as a vertex and the third transformation parameter as an edge.
12. A parking lot crowdsourcing map generation device, the device comprising a processor and a memory;
the memory is used for storing program codes and transmitting the program codes to the processor;
the processor is configured to execute the parking lot crowdsourcing map generating method of any one of claims 1-7 according to instructions in the program code.
13. A computer-readable storage medium storing program code for executing the parking lot crowdsourcing map generating method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110178689.7A CN112985404A (en) | 2021-02-09 | 2021-02-09 | Method, device, equipment and medium for generating crowdsourcing map of parking lot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110178689.7A CN112985404A (en) | 2021-02-09 | 2021-02-09 | Method, device, equipment and medium for generating crowdsourcing map of parking lot |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112985404A true CN112985404A (en) | 2021-06-18 |
Family
ID=76392682
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110178689.7A Pending CN112985404A (en) | 2021-02-09 | 2021-02-09 | Method, device, equipment and medium for generating crowdsourcing map of parking lot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112985404A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113407559A (en) * | 2021-07-15 | 2021-09-17 | 广州小鹏自动驾驶科技有限公司 | Updating method, device and computer storage medium |
| CN114034295A (en) * | 2021-11-05 | 2022-02-11 | 阿波罗智能技术(北京)有限公司 | High-precision map generation method, device, electronic device, medium, and program product |
| CN114111815A (en) * | 2021-11-01 | 2022-03-01 | 广州小鹏自动驾驶科技有限公司 | Map data processing method and device |
| CN114359870A (en) * | 2021-12-27 | 2022-04-15 | 广州小鹏自动驾驶科技有限公司 | Data processing method and device |
| CN115752501A (en) * | 2022-12-01 | 2023-03-07 | 广州小鹏自动驾驶科技有限公司 | Navigation path recommendation method, device, equipment and storage medium |
| WO2024139507A1 (en) * | 2022-12-30 | 2024-07-04 | 广州小鹏自动驾驶科技有限公司 | Parking lot map generation method, apparatus and device, and storage medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107688665A (en) * | 2017-09-27 | 2018-02-13 | 深圳大学 | A kind of indoor map method for auto constructing, device and storage medium |
| CN108847121A (en) * | 2018-07-04 | 2018-11-20 | 深圳地平线机器人科技有限公司 | The method and apparatus for constructing high-precision map |
| CN110146097A (en) * | 2018-08-28 | 2019-08-20 | 北京初速度科技有限公司 | Method and system for generating automatic driving navigation map, vehicle-mounted terminal and server |
| CN110543473A (en) * | 2019-08-20 | 2019-12-06 | 武汉中海庭数据技术有限公司 | Crowdsourcing data fusion optimization method and device and storage medium |
| CN110849380A (en) * | 2019-10-28 | 2020-02-28 | 北京影谱科技股份有限公司 | Map alignment method and system based on collaborative VSLAM |
| US20200334841A1 (en) * | 2018-09-07 | 2020-10-22 | Huawei Technologies Co., Ltd. | Device and method for performing simultaneous localization and mapping |
| CN111885138A (en) * | 2020-07-16 | 2020-11-03 | 广州小鹏车联网科技有限公司 | Control method, vehicle and server |
| CN112084289A (en) * | 2020-09-18 | 2020-12-15 | 湖北亿咖通科技有限公司 | Track fusion method and device |
| CN112328730A (en) * | 2021-01-04 | 2021-02-05 | 腾讯科技（深圳）有限公司 | Map data updating method, related device, equipment and storage medium |
-
2021
- 2021-02-09 CN CN202110178689.7A patent/CN112985404A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107688665A (en) * | 2017-09-27 | 2018-02-13 | 深圳大学 | A kind of indoor map method for auto constructing, device and storage medium |
| CN108847121A (en) * | 2018-07-04 | 2018-11-20 | 深圳地平线机器人科技有限公司 | The method and apparatus for constructing high-precision map |
| CN110146097A (en) * | 2018-08-28 | 2019-08-20 | 北京初速度科技有限公司 | Method and system for generating automatic driving navigation map, vehicle-mounted terminal and server |
| WO2020042348A1 (en) * | 2018-08-28 | 2020-03-05 | 初速度（苏州）科技有限公司 | Method for generating autonomous driving navigation map, system, vehicle-mounted terminal, and server |
| US20200334841A1 (en) * | 2018-09-07 | 2020-10-22 | Huawei Technologies Co., Ltd. | Device and method for performing simultaneous localization and mapping |
| CN110543473A (en) * | 2019-08-20 | 2019-12-06 | 武汉中海庭数据技术有限公司 | Crowdsourcing data fusion optimization method and device and storage medium |
| CN110849380A (en) * | 2019-10-28 | 2020-02-28 | 北京影谱科技股份有限公司 | Map alignment method and system based on collaborative VSLAM |
| CN111885138A (en) * | 2020-07-16 | 2020-11-03 | 广州小鹏车联网科技有限公司 | Control method, vehicle and server |
| CN112084289A (en) * | 2020-09-18 | 2020-12-15 | 湖北亿咖通科技有限公司 | Track fusion method and device |
| CN112328730A (en) * | 2021-01-04 | 2021-02-05 | 腾讯科技（深圳）有限公司 | Map data updating method, related device, equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 蒋民锋;: "地下停车场出入口众包构建方法及应用探析", 现代信息科技, no. 04 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113407559A (en) * | 2021-07-15 | 2021-09-17 | 广州小鹏自动驾驶科技有限公司 | Updating method, device and computer storage medium |
| CN114111815A (en) * | 2021-11-01 | 2022-03-01 | 广州小鹏自动驾驶科技有限公司 | Map data processing method and device |
| CN114111815B (en) * | 2021-11-01 | 2023-02-03 | 广州小鹏自动驾驶科技有限公司 | Map data processing method and device |
| CN114034295A (en) * | 2021-11-05 | 2022-02-11 | 阿波罗智能技术(北京)有限公司 | High-precision map generation method, device, electronic device, medium, and program product |
| CN114034295B (en) * | 2021-11-05 | 2024-06-25 | 阿波罗智能技术(北京)有限公司 | High-precision map generation method, device, electronic equipment, medium and program product |
| CN114359870A (en) * | 2021-12-27 | 2022-04-15 | 广州小鹏自动驾驶科技有限公司 | Data processing method and device |
| CN115752501A (en) * | 2022-12-01 | 2023-03-07 | 广州小鹏自动驾驶科技有限公司 | Navigation path recommendation method, device, equipment and storage medium |
| CN115752501B (en) * | 2022-12-01 | 2024-03-26 | 广州小鹏汽车科技有限公司 | Navigation path recommending method, device, equipment and storage medium |
| WO2024139507A1 (en) * | 2022-12-30 | 2024-07-04 | 广州小鹏自动驾驶科技有限公司 | Parking lot map generation method, apparatus and device, and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112985404A (en) | Method, device, equipment and medium for generating crowdsourcing map of parking lot | |
| US10838426B2 (en) | Distributing a crowdsourced sparse map for autonomous vehicle navigation | |
| US10248124B2 (en) | Localizing vehicle navigation using lane measurements | |
| CN108303103B (en) | Method and device for determining target lane | |
| CN109410735B (en) | Reflection value map construction method and device | |
| Alonso et al. | Accurate global localization using visual odometry and digital maps on urban environments | |
| US9978161B2 (en) | Supporting a creation of a representation of road geometry | |
| US20190072392A1 (en) | System and method for self-geoposition unmanned aerial vehicle | |
| CN108732603A (en) | Method and apparatus for positioning vehicle | |
| CN104677361B (en) | A kind of method of comprehensive location | |
| CN110160542A (en) | The localization method and device of lane line, storage medium, electronic device | |
| Gikas et al. | A novel geodetic engineering method for accurate and automated road/railway centerline geometry extraction based on the bearing diagram and fractal behavior | |
| CN111552757B (en) | Method, device and equipment for generating electronic map and storage medium | |
| CN114323050B (en) | Vehicle positioning method and device and electronic equipment | |
| CN113450455B (en) | Method, apparatus and computer program product for generating a map of a road link of a parking lot | |
| Marinelli et al. | Mobile mapping systems and spatial data collection strategies assessment in the identification of horizontal alignment of highways | |
| CN113177974B (en) | Point cloud registration method and device, electronic equipment and storage medium | |
| KR102291805B1 (en) | GPS error correction method by comparing 3D precision map in overlapping area | |
| CN115493601A (en) | Road network matching-based vehicle autonomous positioning method and device and storage medium | |
| CN115564865A (en) | Construction method and system of crowdsourcing high-precision map, electronic equipment and vehicle | |
| Meis et al. | A new method for robust far-distance road course estimation in advanced driver assistance systems | |
| CN116958316B (en) | Topology map generation method, device, computer equipment and storage medium | |
| CN112154355B (en) | High-precision map positioning method, system, platform and computer readable storage medium | |
| CN113227713A (en) | Method and system for generating environment model for positioning | |
| Tummala et al. | SmartDashCam: automatic live calibration for DashCams |
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 |