CN110057373A - For generating the method, apparatus and computer storage medium of fine semanteme map - Google Patents
For generating the method, apparatus and computer storage medium of fine semanteme map Download PDFInfo
- Publication number
- CN110057373A CN110057373A CN201910323449.4A CN201910323449A CN110057373A CN 110057373 A CN110057373 A CN 110057373A CN 201910323449 A CN201910323449 A CN 201910323449A CN 110057373 A CN110057373 A CN 110057373A
- Authority
- CN
- China
- Prior art keywords
- map
- fine
- point cloud
- image
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 41
- 230000003068 static effect Effects 0.000 claims abstract description 19
- 238000012545 processing Methods 0.000 claims description 55
- 238000012937 correction Methods 0.000 claims description 25
- 238000002310 reflectometry Methods 0.000 claims description 13
- 238000010586 diagram Methods 0.000 claims description 12
- 230000004927 fusion Effects 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 6
- 230000009466 transformation Effects 0.000 claims description 6
- 238000009933 burial Methods 0.000 claims description 3
- 230000001360 synchronised effect Effects 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 5
- 238000013507 mapping Methods 0.000 abstract description 3
- 241001269238 Data Species 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000004387 environmental modeling Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
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
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/28—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network with correlation of data from several navigational instruments
- G01C21/30—Map- or contour-matching
- G01C21/32—Structuring or formatting of map data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
Landscapes
- Engineering & Computer Science (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Automation & Control Theory (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Navigation (AREA)
- Traffic Control Systems (AREA)
Abstract
The present invention relates to automobile navigation technologies and automatic Pilot technology, in particular to are used to generate the method, apparatus, computer storage medium and the navigation map mapping vehicle comprising the device of fine semanteme map.Acquisition cloud map and multiple images are comprised the steps of at relevant to ambient enviroment according to the method for generating fine semanteme map of one aspect of the invention;Semantics recognition object is determined by the target and corresponding target in point cloud map that identify in image, the object is associated with the object being located in the plane intersected with ground;Static environment semantic feature is extracted from cloud map;Semantics recognition object and the descriptor about static environment semantic feature are stored in semantic Orientation on map figure layer;Fine geographical class probability map for extracting floor line is generated by image and point cloud map;And fine semanteme map planning chart layer is generated using semantics recognition object and the fine geographical class probability map, which includes that road topology relationship, lane topological relation and elementary path indicate information.
Description
Technical field
The present invention relates to automobile navigation technologies and automatic Pilot technology, in particular to for generating fine semanteme map
Method, apparatus, computer storage medium and the navigation map comprising described device survey and draw vehicle.
Background technique
Conventional navigation map is unable to satisfy the needs of automatic Pilot due to precision deficiency.Fine map is driven as nobody
Sail a necessary ring becomes common recognition in industry gradually, has many advantages, such as that precision height and dimension are more.Fine map can
The information instruction more looked forward to the prospect and information redundancy are provided for control loop, realizes the matching positioning of automobile, enables control loop
Larger range of traffic situation is perceived, guarantees the safety of automatic Pilot.
In fine map, point cloud map due to its not by ambient lighting influenced the advantages that accurate with environmental modeling and again
By the favor of automatic Pilot industrial circle.But the data volume for putting cloud map is huge, this is stored to map and On-line matching positions all
Bring great obstruction.In recent years, although industrial circle merges and put semantic structure etc. inside cloud map to sensor
It studies, but drawing generating method in high-precision that is high-precision while effectively reducing data volume can kept by not yet providing
And device.
Summary of the invention
The method, apparatus and computer that it is an object of the present invention to provide a kind of for generating fine semanteme map are deposited
Storage media can reduce the data volume of map in the case where ensuring map fine grade.
It is comprised the steps of according to the method for generating fine semanteme map of one aspect of the invention
Obtain cloud map and multiple images at relevant to ambient enviroment;
Semantics recognition object is determined by corresponding target in the target identified in described image and described cloud map, it is described
Semantics recognition object is associated with the object being located in the plane intersected with ground;
Static environment semantic feature is extracted from described cloud map;
The semantics recognition object and the descriptor about static environment semantic feature are stored in semantic Orientation on map figure
In layer;
Fine geographical class probability map for extracting floor line is generated by described image and point cloud map;And
Fine semanteme map planning chart layer is generated using semantics recognition object and fine geographical class probability map, it is described
Fine semanteme map planning chart layer includes that road topology relationship, lane topological relation and elementary path indicate information.
Optionally, in the above-mentioned methods, each described image obtains as follows:
Distortion correction processing is carried out to the monocular image that multiple monocular cameras absorb using internal calibrating parameters;And
Using extrinsic calibration parameter, multiple monocular images handled by distortion correction are spliced into an image.
Optionally, in the above-mentioned methods, described cloud map obtains as follows:
Reflectivity correction processing and kinematic error compensation processing are carried out to point cloud data frame;And
According to location information, will exist by the point cloud data frame splicing of reflectivity correction processing and kinematic error compensation processing
Together to obtain described cloud map.
Optionally, in the above-mentioned methods, make fused filtering resolving processing by two or more data in will be following
Obtain the location information: GNSS/INS integrated navigation data, wheel speed data, based on laser radar point cloud data while position
It positions with while building figure location data and polyphaser and builds figure location data.
Optionally, in the above-mentioned methods, the target be traffic sign, traffic lights and static-obstacle thing at least
It is a kind of.
Optionally, in the above-mentioned methods, the step of determining semantics recognition object include:
The target is identified in described image;
Corresponding target is identified in described cloud map;And
By described image and point cloud map between combined calibrating transformation relation by the target identified in described image with
Corresponding target carries out fusion matching treatment with the determination semantics recognition object in described cloud map.
Optionally, in the above-mentioned methods, the static environment semantic feature include edge feature in point cloud data frame and
Plane characteristic.
Optionally, in the above-mentioned methods, the semantics recognition object is stored in the semantic map with vectorized form and determines
In bitmap layer.
Optionally, in the above-mentioned methods, the fine geographical classification generated as follows for extracting floor line is general
Rate map:
The first geographical classification probability map for extracting floor line is generated by described image;
The second geographical classification probability map for extracting floor line is generated by the point cloud data frame;And
It is described subtly by merging the described first geographical classification probability map and the second geographical classification probability map generation
Manage class probability map.
Optionally, in the above-mentioned methods, the fine geographical class probability map is stored in institute's predicate with vectorized form
Free burial ground for the destitute figure is planned in figure layer.
Optionally, in the above-mentioned methods, the step of generation fine semanteme map planning chart layer includes:
According to the semantics recognition object, by divisional line, the road extracted in the fine geographical class probability map
Roadside edge and stop line generate lane topological diagram and road topology group picture.
Include according to the onboard system for generating fine semanteme map of another aspect of the invention:
Image acquisition units are configured to obtain multiple images relevant to ambient enviroment;
Point cloud data acquisition unit is configured to obtain relevant to ambient enviroment cloud map;
Processing unit is configured to execute the following steps:
Semantics recognition object is determined by corresponding target in the target identified in described image and described cloud map, it is described
Semantics recognition object is associated with the object being located in the plane intersected with ground;
Static environment semantic feature is extracted from described cloud map;
The semantics recognition object and the descriptor about static environment semantic feature are stored in semantic Orientation on map figure
In layer;
Fine geographical class probability map for extracting floor line is generated by described image and point cloud map;And
Fine semanteme map planning chart layer is generated using semantics recognition object and fine geographical class probability map, it is described
Fine semanteme map planning chart layer includes that lane topological diagram, road topology figure and elementary path indicate information.
Optionally, in above-mentioned onboard system, described image acquisition unit includes:
Multiple monocular cameras;
Image processor is configured to execute the following steps:
Distortion correction processing, the internal calibration are carried out to the monocular image that monocular camera is shot using internal calibrating parameters
The image data for the same calibration object that parameter is shot according to a monocular camera with different angle and different distance determines;
Multiple monocular images handled by distortion correction are spliced into an image using extrinsic calibration parameter, it is described outer
The image for the same calibration object that portion's calibrating parameters are shot according to multiple monocular cameras determines.
Optionally, in above-mentioned onboard system, the point cloud data acquisition unit includes:
Laser radar is configured to transmitting first laser beam and receives the second laser beam of reflection;
Processor is configured to execute the following steps:
Reflectivity correction processing and kinematic error compensation processing are carried out to point cloud data frame;And
According to location information, will exist by the point cloud data frame splicing of reflectivity correction processing and kinematic error compensation processing
Together to obtain described cloud map.
Optionally, in above-mentioned onboard system, further comprise:
GNSS/INS unit is configured to provide for GNSS/INS integrated navigation data;
Vehicle wheel speed meter unit, is configured to provide for wheel speed data;
Multi-sensor data time synchronization unit, be configured to make described image acquisition unit, point cloud data acquisition unit,
GNSS/INS unit is synchronous with the data of vehicle wheel speed meter unit,
The processing unit is configured to make fused filtering resolving by two or more data in will be following to handle
To the location information: GNSS/INS integrated navigation data, wheel speed data, be based on while laser radar point cloud data positioning with
It is positioned while building figure location data and polyphaser and builds figure location data.
Device according to another aspect of the invention for generating fine semanteme map include memory, processor with
And it is stored in the computer program that can be run on the memory and on the processor, described program is executed to realize such as
The upper method.
According to the computer readable storage medium of a further aspect of the invention, computer program is stored thereon, wherein should
Method as described above is realized when program is executed by processor.
Vehicle is surveyed and drawn according to the navigation map of a further aspect of the invention, it is one or more as described above it includes having
The device for being used to generate fine semanteme map of feature.
In one or more embodiments according to the invention, semantics recognition object and about static environment semantic feature
Descriptor is saved in semantic Orientation on map figure layer, and is based on semantics recognition object, is generated by semantic map planning chart layer
Fine semanteme map planning chart layer, this makes fine semanteme map generated have flexible, expansible graphic layer structure,
It not only facilitates and is docked with matching positioning function needed for automatic Pilot and path planning function, and convenient for safeguarding and update.
In addition, data can be effectively reduced by saving semantics recognition object, descriptor and fine geographical class probability map with approach vector
Amount.
Detailed description of the invention
Above-mentioned and/or other aspects and advantage of the invention will be become by the description of the various aspects below in conjunction with attached drawing
It is more clear and is easier to understand, the same or similar unit, which is adopted, in attached drawing is indicated by the same numeral.Attached drawing includes:
Fig. 1 is the block diagram according to the onboard system for generating fine semanteme map of one embodiment of the invention.
Fig. 2A and 2B is top view and the side of the navigation map mapping vehicle according to another embodiment of the present invention
View.
Fig. 3 is the flow chart according to the method for generating fine semanteme map of a further embodiment of the present invention.
Fig. 4 is the block diagram according to the device for generating fine semanteme map of a further embodiment of the present invention.
Specific embodiment
Referring to which illustrates the attached drawings of illustrative examples of the present invention to more fully illustrate the present invention.But this hair
It is bright to be realized by different form, and be not construed as being only limitted to each embodiment given herein.The above-mentioned each implementation provided
Example is intended to make the disclosure of this paper comprehensively complete, and protection scope of the present invention is more fully communicated to those skilled in the art
Member.
In the present specification, the term of such as "comprising" and " comprising " etc indicates to want in addition to having in specification and right
Asking has in book directly and other than the unit clearly stated and step, technical solution of the present invention be also not excluded for having not by directly or
The situation of the other units clearly stated and step.
The term of such as " first " and " second " etc be not offered as unit the time, space, in terms of sequence
It and is only to make differentiation each unit to be used.
Fig. 1 is the block diagram according to the onboard system for generating fine semanteme map of one embodiment of the invention.
Onboard system 10 shown in FIG. 1 for generating fine semanteme map includes image acquisition units 110, point cloud number
According to acquisition unit 120, processing unit 130, global navigation satellite-inertial navigation combination (GNSS/INS) unit 140, vehicle wheel speed
Count unit 150 and multi-sensor data time synchronization unit 160.It should be pointed out that optionally, GNSS/INS unit 140, vehicle
Wheel speed meter unit 150 and multi-sensor data time synchronization unit 160 can be considered as the external unit of onboard system 10.
In 10 in onboard system shown in Fig. 1, image acquisition units 110 are configured to obtain relevant to ambient enviroment more
A image, point cloud data acquisition unit 120 are configured to obtain relevant to ambient enviroment cloud map.GNSS/INS unit 140
GNSS/INS integrated navigation data are configured to provide for, vehicle wheel speed meter unit 150 is configured to provide for wheel speed data.
Optionally, image acquisition units 110 include multiple monocular cameras 111 and the image processor coupled with monocular camera
112.Image procossing 112 is configured to generate piece image as follows: receiving synchronization and is clapped by multiple monocular cameras 111
The multiple monocular images taken the photograph then carry out the image that the monocular camera is shot according to the inside calibrating parameters of each monocular camera
Multiple monocular images handled by distortion correction are stitched together by distortion correction processing followed by extrinsic calibration parameter,
Thus generate piece image.In the present embodiment, optionally, it can be clapped according to a monocular camera with different angle and different distance
The image data for the same calibration object taken the photograph is come the same calibration that determines internal calibrating parameters, and shot according to multiple monocular cameras
The image of object determines extrinsic calibration parameter.
Optionally, point cloud data acquisition unit 120 includes laser radar 121 (such as inclination multi-line laser radar) and processing
Device 122.Laser radar 121 be configured to ambient enviroment emit first laser beam and receive object in environment (such as building, hand over
Ventilating signal lamp, traffic mark, vehicle, pedestrian, road separator, road etc.) reflection second laser beam.Processor 122 configures
To generate a cloud map as follows: being carried out at reflectivity correction processing and kinematic error compensation to each point cloud data frame
Reason will exist then according to location information by the point cloud data frame splicing of reflectivity correction processing and kinematic error compensation processing
Together to obtain a cloud map.
Location information can come from and one of the following or a variety of location datas: GNSS/INS integrated navigation data, wheel
Fast data, based on laser radar point cloud data while positioning and positioning while building figure location data and polyphaser with to build figure fixed
Position data.When using a variety of location datas, processing unit 130 is configured to by the way that two or more data are made fused filtering
Resolving is handled to obtain location information.
Optionally, school is carried out to point cloud data frame using based on the reflectivity correction table obtained based on reflectivity correction algorithm
Positive processing, and based on integrated navigation data (such as being provided by GNSS/INS unit 140) and wheel speed data (such as by vehicle wheel
Speed meter unit 150) to point cloud data frame carry out kinematic error compensation.
As shown in Figure 1, multi-sensor data time synchronization unit 160 and image acquisition units 110, point cloud data acquisition list
Member 120, processing unit 130, GNSS/INS unit 140, vehicle wheel speed meter unit 150 couple, and are configured to make Image Acquisition list
The data that member, point cloud data acquisition unit, GNSS/INS unit, vehicle wheel speed meter unit obtain are synchronous.
Processing unit 130 and image acquisition units 110, point cloud data acquisition unit 120, GNSS/INS unit 140, vehicle
Wheel speed meter unit 150 couples.
In the present embodiment, processing unit 130 is configured to execute the proving operation of sensing data, including but not limited to swashs
The calibration of calibrating parameters, polyphaser extrinsic calibration ginseng inside optical radar and the combined calibrating of the data of integrated navigation, monocular camera
The combined calibrating of the data of several calibration and image acquisition units and laser radar.For example, processing unit 130 can be to laser
Point cloud data, GNSS/INS integrated navigation data and the wheel speed data of vehicle wheel speed meter acquisition of radar acquisition carry out joint mark
It is fixed, to obtain the transformation relation of laser radar sensor coordinate system and integrated navigation sensor coordinate system.For another example, processing unit
The image datas of the 130 same calibration objects that can be shot according to a monocular camera with different angle and different distance determines the list
The inside calibrating parameters of mesh camera, and determine that extrinsic calibration is joined according to the image of the same calibration object of multiple monocular cameras shooting
Number.Also such as, processing unit 130 (such as can be spelled in the way of inside and outside calibrating parameters according to uncalibrated image according to aforementioned
The image connect) and calibration laser radar point cloud data (such as based on point cloud data, GNSS/INS integrated navigation data and wheel
The combined calibrating mode of fast data) it determines image and puts the combined calibrating transformation relation between cloud map.
In the present embodiment, processing unit 130 is additionally configured to generate comprising semantic Orientation on map figure layer and semantic map rule
Draw the fine semanteme map of figure layer.
Optionally, semantic Orientation on map figure layer includes semantics recognition object and the description as described in static environment semantic feature
Symbol.Semantics recognition object described here can be associated with the object being located in the plane that intersects with ground, for example including but not
It is limited to traffic sign, traffic lights and static-obstacle thing.In the present embodiment, semantics recognition pair can be determined in the following manner
As: identify in the picture target (such as traffic sign, traffic lights and such as traffic isolation railing (pier), street lamp etc it is quiet
State barrier etc.) and corresponding target is identified in cloud map, then combine mark by between image and point cloud map
Determine transformation relation and the target identified in image is subjected to fusion matching treatment with corresponding target in described cloud map with determination
Semantics recognition object.
In the present embodiment, static environment semantic feature extraction puts cloud map and certainly about static environment semantic feature
Descriptor is saved in semantic Orientation on map figure layer.Optionally, static environment semantic feature includes the side in point cloud data frame
Edge feature and plane characteristic.
In the present embodiment, fine semanteme map planning chart layer includes lane topological diagram, road topology figure and basic road
Road indicates information.For example, the fine geographical class probability for extracting floor line can be generated by image and point cloud map
Scheme and save it in semantic map planning chart layer, then according to semantics recognition object, by fine geographical class probability map
Divisional line, road edge and the stop line of middle extraction generate lane topological diagram and road topology group picture.
It is alternatively possible to which following manner generates fine geographical class probability map: being generated by image for extracting ground mark
Then the geographical classification probability map of the first of line is generated the second geographical class probability for extracting floor line by cloud map
It is general then to generate fine geographical classification by the geographical classification probability map of fusion first and the second geographical classification probability map for map
Rate map.Typically, the fine degree of the first geographical classification probability map is better than the second geographical classification probability map.
Fig. 2A and 2B is top view and the side of the navigation map mapping vehicle according to another embodiment of the present invention
View.
As shown in Figure 2 A and 2B, multiple monocular cameras 210 are arranged on the outside of vehicle 20 (such as before vehicle upper surface
Portion).As shown, the mounting height of monocular camera 210 is for example set to ensure the combination of their provided monocular images
At least three lanes can be covered and at the same time guaranteeing there are enough visual fields to be overlapped between two monocular cameras;GNSS module 220
(such as double antenna GNSS signal receiving module) is for example mounted on the middle part of the upper surface of vehicle 20, and mutual spacing is not less than
1m is optionally 1.2~1.5 meters;Laser radar 230 (such as inclination multi-line laser radar module) is installed in the upper of vehicle 20
The rear portion on surface, mounting height, which is for example chosen to be, ensures that it is not blocked by the tailstock, and the tilt angle of installation is at 30 degree~60 degree
In the range of, to guarantee that its visual field is not blocked and as far as possible in tailstock safe distance between vehicles;Vehicle wheel speed meter unit 240 is mounted
Near wheel (such as near rear wheels);Integrated navigation and location unit 250 is installed on vehicle central axes close to vehicle rear axle
Center and setting angle be for example set as far as possible be aligned vehicle central axes direction, it includes accelerometer, gyroscope and
Processing unit, the processor be configured to by the received satellite positioning signal of GNSS module 220 with based on accelerometer, gyroscope it is used
Property navigation signal fusion to generate GNSS/INS integrated navigation data.As shown, vehicle 20 further includes being set to vehicular sideview
Multi-sensor data time synchronization module 260.
Fig. 3 is the flow chart according to the method for generating fine semanteme map of a further embodiment of the present invention.
Illustratively, here using device shown in FIG. 1 as the entity for implementing the present embodiment method, it should be noted however that this reality
It applies example and the improvement to it, change or change and is not only suitable for device shown in FIG. 1, apply also for that there are other knots
The device of structure.
As shown in figure 3, in step 310, processing unit 130 is from image acquisition units 110 and point cloud data acquisition unit 120
Multiple images relevant to ambient enviroment and point cloud map are received respectively.Illustratively, can use by multiple monocular cameras Lai
Obtain each image.Such as set forth above, it is possible to the monocular image that multiple monocular cameras are absorbed using internal calibrating parameters into
Line distortion correction process and using extrinsic calibration parameter by it is multiple by distortion correction handle monocular images be spliced into one
The point cloud map of image, laser radar can will pass through at reflectivity correction processing and kinematic error compensation according to location information
The point cloud data frame of reason is stitched together to obtain.
Similarly, location information can be a kind of location data, can also be obtained by merging a variety of location datas.Example
Such as can by GNSS/INS navigation positioning data, wheel speed data, based on laser radar point cloud data while positioning with build figure positioning
Two or more data for positioning and building in figure location data while data and polyphaser are made fused filtering resolving processing and are come
Obtain location information.
Step 320 is subsequently entered, target of the processing unit 130 by identifying in image and corresponding target in point cloud map are true
Determine semantics recognition object.In step 320, processing unit 130 can become by the combined calibrating between image and point cloud map
It changes relationship and the target identified in image is subjected to fusion matching treatment with corresponding target in described cloud map, so that it is determined that language
Justice identification object.
Step 330 is subsequently entered, processing unit 130 extracts static environment semantic feature from cloud map.It may be noted that
, step 320 can be interchanged with 330 sequence.
Then in step 340, processing unit 130 is by semantics recognition object and the description as described in static environment semantic feature
Symbol is stored in semantic Orientation on map figure layer.Optionally, semantics recognition object is stored in semantic Orientation on map with vectorized form
In figure layer.
After step 340, method flow shown in Fig. 3 enters step 350.In this step, processing unit 130 is by scheming
Picture and point cloud map generate the fine geographical class probability map for extracting floor line and are stored in semantic map planning chart
In layer.Optionally, in step 350, with generating the fine geographical class probability for extracting floor line as follows
Figure: the first geographical classification probability map for extracting floor line is generated by image and is generated by point cloud data frame for mentioning
The the second geographical classification probability map for taking floor line, then passes through the geographical classification probability map of fusion first and the second GEOGRAPHIC ATTRIBUTES
Other probability map generates fine geographical class probability map.Optionally, fine geographical class probability map is protected with vectorized form
There are in semantic map planning chart layer.
Step 360 is subsequently entered, processing unit 130 is based on semantics recognition object, is generated by semantic map planning chart layer high
Fine semanteme map planning chart layer.Illustratively, processing unit 130 is according to semantics recognition object, by fine geographical class probability
Divisional line, road edge and the stop line extracted in map generates lane topological diagram and road topology group picture.
Fig. 4 is the block diagram according to the device for generating fine semanteme map of a further embodiment of the present invention.
Device 40 shown in Fig. 4 includes memory 410, processor 420 and is stored on memory 410 and can handle
The computer program 430 run on device 420, wherein executing computer program 430 may be implemented above by side described in Fig. 3
Method.
It is another aspect of this invention to provide that additionally providing a kind of computer readable storage medium, computer journey is stored thereon
Sequence can be realized above when the program is executed by processor by method described in Fig. 3.
Embodiments and examples set forth herein is provided, to be best described by the reality according to this technology and its specific application
Example is applied, and thus enables those skilled in the art to implement and using the present invention.But those skilled in the art will
Know, provides above description and example only for the purposes of illustrating and illustrating.The description proposed is not intended to cover the present invention
Various aspects or limit the invention to disclosed precise forms.
In view of the above, the scope of the present disclosure is determined by following claims.
Claims (21)
1. a kind of method for generating fine semanteme map, which is characterized in that comprise the steps of
Obtain cloud map and multiple images at relevant to ambient enviroment;
Semantics recognition object, the semanteme are determined by corresponding target in the target identified in described image and described cloud map
Identification object is associated with the object being located in the plane intersected with ground;
Static environment semantic feature is extracted from described cloud map;
The semantics recognition object and the descriptor about static environment semantic feature are stored in semantic Orientation on map figure layer;
Fine geographical class probability map for extracting floor line is generated by described image and point cloud map;And
Fine semanteme map planning chart layer is generated using semantics recognition object and fine geographical class probability map, it is described high-precision
Whisper free burial ground for the destitute figure plans that figure layer includes that road topology relationship, lane topological relation and elementary path indicate information.
2. the method for claim 1, wherein each described image obtains as follows:
Distortion correction processing is carried out to the monocular image that multiple monocular cameras absorb using internal calibrating parameters;And
Using extrinsic calibration parameter, multiple monocular images handled by distortion correction are spliced into an image.
3. the method for claim 1, wherein described cloud map obtains as follows:
Reflectivity correction processing and kinematic error compensation processing are carried out to point cloud data frame;And
According to location information, will be stitched together by the point cloud data frame of reflectivity correction processing and kinematic error compensation processing
To obtain described cloud map.
4. method as claimed in claim 3, wherein make fused filtering resolving by two or more data in will be following
Processing obtains the location information: integrated navigation and location data, wheel speed data, based on laser radar point cloud data while position
It positions with while building figure location data and polyphaser and builds figure location data.
5. the method for claim 1, wherein the target is in traffic sign, traffic lights and static-obstacle thing
At least one.
6. the method for claim 1, wherein determining and including: the step of semantics recognition object
The target is identified in described image;
Corresponding target is identified in described cloud map;And
By described image and point cloud map between combined calibrating transformation relation by the target identified in described image with it is described
Corresponding target carries out fusion matching treatment with the determination semantics recognition object in point cloud map.
7. the method for claim 1, wherein the static environment semantic feature includes that the edge in point cloud data frame is special
It seeks peace plane characteristic.
8. the method for claim 1, wherein the semantics recognition object with vectorized form be stored in it is described semantically
In figure positioning figure layer.
9. the method for claim 1, wherein generating the fine GEOGRAPHIC ATTRIBUTES for extracting floor line as follows
Other probability map:
The first geographical classification probability map for extracting floor line is generated by described image;
The second geographical classification probability map for extracting floor line is generated by the point cloud data frame;And
The fine GEOGRAPHIC ATTRIBUTES is generated by merging the described first geographical classification probability map and the second geographical classification probability map
Other probability map.
10. method as claimed in claim 9, wherein the fine geographical class probability map is stored in vectorized form
In the semanteme map planning chart layer.
11. the step of the method for claim 1, wherein generating fine semanteme map planning chart layer includes:
According to the semantics recognition object, by extracted in the fine geographical class probability map divisional line, road roadside
Edge and stop line generate lane topological diagram and road topology group picture.
12. it is a kind of for generating the onboard system of fine semanteme map, characterized by comprising:
Image acquisition units are configured to obtain multiple images relevant to ambient enviroment;
Point cloud data acquisition unit is configured to obtain relevant to ambient enviroment cloud map;
Processing unit is configured to execute the following steps:
Semantics recognition object, the semanteme are determined by corresponding target in the target identified in described image and described cloud map
Identification object is associated with the object being located in the plane intersected with ground;
Static environment semantic feature is extracted from described cloud map;
The semantics recognition object and the descriptor about static environment semantic feature are stored in semantic Orientation on map figure layer;
Fine geographical class probability map for extracting floor line is generated by described image and point cloud map;And
Fine semanteme map planning chart layer is generated using semantics recognition object and fine geographical class probability map, it is described high-precision
Whisper free burial ground for the destitute figure plans that figure layer includes that lane topological diagram, road topology figure and elementary path indicate information.
13. onboard system as claimed in claim 12, wherein described image acquisition unit includes:
Multiple monocular cameras;
Image processor is configured to execute the following steps:
Distortion correction processing, the internal calibrating parameters are carried out to the monocular image that monocular camera is shot using internal calibrating parameters
The image data of the same calibration object shot according to a monocular camera with different angle and different distance determines;
Multiple monocular images handled by distortion correction are spliced into an image, the external mark using extrinsic calibration parameter
The image for determining the same calibration object that parameter is shot according to multiple monocular cameras determines.
14. onboard system as claimed in claim 12, wherein the point cloud data acquisition unit includes:
Laser radar is configured to transmitting first laser beam and receives the second laser beam of reflection;
Processor is configured to execute the following steps:
Reflectivity correction processing and kinematic error compensation processing are carried out to point cloud data frame;And
According to location information, will be stitched together by the point cloud data frame of reflectivity correction processing and kinematic error compensation processing
To obtain described cloud map.
15. onboard system as claimed in claim 14, wherein further comprise:
GNSS/INS unit is configured to provide for GNSS/INS integrated navigation data;
Vehicle wheel speed meter unit, is configured to provide for wheel speed data;
Multi-sensor data time synchronization unit is configured to make described image acquisition unit, point cloud data acquisition unit, GNSS/
INS unit is synchronous with the data of vehicle wheel speed meter unit,
The processing unit is configured to make fused filtering resolving by two or more data in will be following to handle to obtain institute
State location information: GNSS/INS integrated navigation data, wheel speed data, based on laser radar point cloud data while positioning with build figure
It is positioned while location data and polyphaser and builds figure location data.
16. onboard system as claimed in claim 12, wherein the processing unit determines semantics recognition pair as follows
As:
The target is identified in described image;
Corresponding target is identified in described cloud map;And
By described image and point cloud map between combined calibrating transformation relation by the target identified in described image with it is described
Corresponding target carries out fusion matching treatment with the determination semantics recognition object in point cloud map.
17. onboard system as claimed in claim 12, wherein the processing unit is generated as follows for extracting ground
The fine geographical class probability map of face graticule:
The first geographical classification probability map for extracting floor line is generated by described image;
The second geographical classification probability map for extracting floor line is generated by described cloud map;And
The fine GEOGRAPHIC ATTRIBUTES is generated by merging the described first geographical classification probability map and the second geographical classification probability map
Other probability map.
18. onboard system as claimed in claim 12, wherein the processing unit generates fine semanteme as follows
Map plans figure layer:
According to the semantics recognition object, by extracted in the fine geographical class probability map divisional line, road roadside
Edge and stop line generate lane topological diagram and road topology group picture.
19. it is a kind of for generating the device of fine semanteme map, it includes memory, processor and it is stored in the storage
On device and the computer program that can run on the processor, which is characterized in that execute described program to realize that right such as is wanted
Seek method described in any one of 1-11.
20. a kind of computer readable storage medium, stores computer program thereon, which is characterized in that the program is held by processor
Such as method of any of claims 1-11 is realized when row.
21. a kind of navigation map surveys and draws vehicle, which is characterized in that include the use as described in any one of claim 12-19
In the device for generating fine semanteme map.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910323449.4A CN110057373B (en) | 2019-04-22 | 2019-04-22 | Method, apparatus and computer storage medium for generating high-definition semantic map |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910323449.4A CN110057373B (en) | 2019-04-22 | 2019-04-22 | Method, apparatus and computer storage medium for generating high-definition semantic map |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110057373A true CN110057373A (en) | 2019-07-26 |
CN110057373B CN110057373B (en) | 2023-11-03 |
Family
ID=67320043
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910323449.4A Active CN110057373B (en) | 2019-04-22 | 2019-04-22 | Method, apparatus and computer storage medium for generating high-definition semantic map |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110057373B (en) |
Cited By (31)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110825093A (en) * | 2019-11-28 | 2020-02-21 | 安徽江淮汽车集团股份有限公司 | Automatic driving strategy generation method, device, equipment and storage medium |
CN110986945A (en) * | 2019-11-14 | 2020-04-10 | 上海交通大学 | Local navigation method and system based on semantic height map |
CN111008660A (en) * | 2019-12-03 | 2020-04-14 | 北京京东乾石科技有限公司 | Semantic map generation method, device and system, storage medium and electronic equipment |
CN111025331A (en) * | 2019-12-25 | 2020-04-17 | 湖北省国土资源研究院(湖北省国土资源厅不动产登记中心) | Laser radar mapping method based on rotating structure and scanning system thereof |
CN111176279A (en) * | 2019-12-31 | 2020-05-19 | 北京四维图新科技股份有限公司 | Method, device, equipment and storage medium for determining vulnerable crowd area |
CN111192341A (en) * | 2019-12-31 | 2020-05-22 | 北京三快在线科技有限公司 | Method and device for generating high-precision map, automatic driving equipment and storage medium |
CN111207762A (en) * | 2019-12-31 | 2020-05-29 | 深圳一清创新科技有限公司 | Map generation method and device, computer equipment and storage medium |
CN111311709A (en) * | 2020-02-05 | 2020-06-19 | 北京三快在线科技有限公司 | Method and device for generating high-precision map |
CN111710040A (en) * | 2020-06-03 | 2020-09-25 | 纵目科技(上海)股份有限公司 | Method, system, terminal and storage medium for constructing high-precision map |
CN111912419A (en) * | 2020-08-28 | 2020-11-10 | 清华大学苏州汽车研究院(吴江) | High-precision semantic navigation map construction method and device based on laser radar |
CN111958592A (en) * | 2020-07-30 | 2020-11-20 | 国网智能科技股份有限公司 | Image semantic analysis system and method for transformer substation inspection robot |
CN112254737A (en) * | 2020-10-27 | 2021-01-22 | 北京晶众智慧交通科技股份有限公司 | Map data conversion method |
CN112419404A (en) * | 2019-08-21 | 2021-02-26 | 北京初速度科技有限公司 | Map data acquisition method and device |
CN112556654A (en) * | 2020-12-17 | 2021-03-26 | 武汉中海庭数据技术有限公司 | High-precision map data acquisition device and method |
CN112802095A (en) * | 2019-11-14 | 2021-05-14 | 北京四维图新科技股份有限公司 | Positioning method, device and equipment and automatic driving positioning system |
CN112986979A (en) * | 2019-12-17 | 2021-06-18 | 动态Ad有限责任公司 | Automatic object labeling using fused camera/LiDAR data points |
WO2021135371A1 (en) * | 2019-12-31 | 2021-07-08 | 华为技术有限公司 | Automatic driving method, related device and computer-readable storage medium |
CN113269977A (en) * | 2020-01-29 | 2021-08-17 | 丰田自动车株式会社 | Map generation data collection device and map generation data collection method |
CN113419245A (en) * | 2021-06-23 | 2021-09-21 | 北京易航远智科技有限公司 | Real-time mapping system and mapping method based on V2X |
CN113418528A (en) * | 2021-05-31 | 2021-09-21 | 江苏大学 | Intelligent automobile-oriented traffic scene semantic modeling device, modeling method and positioning method |
WO2021223116A1 (en) * | 2020-05-06 | 2021-11-11 | 上海欧菲智能车联科技有限公司 | Perceptual map generation method and apparatus, computer device and storage medium |
CN113656525A (en) * | 2021-08-19 | 2021-11-16 | 广州小鹏自动驾驶科技有限公司 | Map processing method and device |
WO2021227520A1 (en) * | 2020-05-14 | 2021-11-18 | 广州文远知行科技有限公司 | Visual interface display method and apparatus, electronic device, and storage medium |
WO2021232470A1 (en) * | 2020-05-19 | 2021-11-25 | 北京数字绿土科技有限公司 | Multi-sensor fusion-based slam method and system |
CN113721599A (en) * | 2020-05-25 | 2021-11-30 | 华为技术有限公司 | Positioning method and positioning device |
CN113945222A (en) * | 2021-10-14 | 2022-01-18 | 华为技术有限公司 | Method and device for identifying road information, electronic equipment, vehicle and medium |
CN113978484A (en) * | 2021-09-30 | 2022-01-28 | 东风汽车集团股份有限公司 | Vehicle control method, device, electronic device and storage medium |
CN114842211A (en) * | 2022-03-28 | 2022-08-02 | 高德软件有限公司 | Angular point extraction, precision evaluation and carrier positioning method, equipment, medium and product |
CN114973910A (en) * | 2022-07-27 | 2022-08-30 | 禾多科技(北京)有限公司 | Map generation method and device, electronic equipment and computer readable medium |
CN115100631A (en) * | 2022-07-18 | 2022-09-23 | 浙江省交通运输科学研究院 | Road map acquisition system and method for multi-source information composite feature extraction |
CN115164918A (en) * | 2022-09-06 | 2022-10-11 | 联友智连科技有限公司 | Semantic point cloud map construction method and device and electronic equipment |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107063258A (en) * | 2017-03-07 | 2017-08-18 | 重庆邮电大学 | A kind of mobile robot indoor navigation method based on semantic information |
CN107451526A (en) * | 2017-06-09 | 2017-12-08 | 蔚来汽车有限公司 | The structure of map and its application |
US20180232583A1 (en) * | 2017-02-16 | 2018-08-16 | Honda Motor Co., Ltd. | Systems for generating parking maps and methods thereof |
CN109117718A (en) * | 2018-07-02 | 2019-01-01 | 东南大学 | A kind of semantic map structuring of three-dimensional towards road scene and storage method |
CN109410301A (en) * | 2018-10-16 | 2019-03-01 | 张亮 | High-precision semanteme map production method towards pilotless automobile |
CN109461211A (en) * | 2018-11-12 | 2019-03-12 | 南京人工智能高等研究院有限公司 | Semantic vector map constructing method, device and the electronic equipment of view-based access control model point cloud |
CN109556617A (en) * | 2018-11-09 | 2019-04-02 | 同济大学 | A kind of map elements extracting method of automatic Jian Tu robot |
CN109556615A (en) * | 2018-10-10 | 2019-04-02 | 吉林大学 | The driving map generation method of Multi-sensor Fusion cognition based on automatic Pilot |
-
2019
- 2019-04-22 CN CN201910323449.4A patent/CN110057373B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20180232583A1 (en) * | 2017-02-16 | 2018-08-16 | Honda Motor Co., Ltd. | Systems for generating parking maps and methods thereof |
CN107063258A (en) * | 2017-03-07 | 2017-08-18 | 重庆邮电大学 | A kind of mobile robot indoor navigation method based on semantic information |
CN107451526A (en) * | 2017-06-09 | 2017-12-08 | 蔚来汽车有限公司 | The structure of map and its application |
CN109117718A (en) * | 2018-07-02 | 2019-01-01 | 东南大学 | A kind of semantic map structuring of three-dimensional towards road scene and storage method |
CN109556615A (en) * | 2018-10-10 | 2019-04-02 | 吉林大学 | The driving map generation method of Multi-sensor Fusion cognition based on automatic Pilot |
CN109410301A (en) * | 2018-10-16 | 2019-03-01 | 张亮 | High-precision semanteme map production method towards pilotless automobile |
CN109556617A (en) * | 2018-11-09 | 2019-04-02 | 同济大学 | A kind of map elements extracting method of automatic Jian Tu robot |
CN109461211A (en) * | 2018-11-12 | 2019-03-12 | 南京人工智能高等研究院有限公司 | Semantic vector map constructing method, device and the electronic equipment of view-based access control model point cloud |
Non-Patent Citations (1)
Title |
---|
杨玉荣;李峰;: "基于激光点云扫描的高精导航地图关键技术研究", no. 09 * |
Cited By (46)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112419404A (en) * | 2019-08-21 | 2021-02-26 | 北京初速度科技有限公司 | Map data acquisition method and device |
CN112419404B (en) * | 2019-08-21 | 2024-07-02 | 北京初速度科技有限公司 | Map data acquisition method and device |
CN112802095B (en) * | 2019-11-14 | 2024-04-16 | 北京四维图新科技股份有限公司 | Positioning method, device and equipment, and automatic driving positioning system |
CN110986945A (en) * | 2019-11-14 | 2020-04-10 | 上海交通大学 | Local navigation method and system based on semantic height map |
CN110986945B (en) * | 2019-11-14 | 2023-06-27 | 上海交通大学 | Local navigation method and system based on semantic altitude map |
CN112802095A (en) * | 2019-11-14 | 2021-05-14 | 北京四维图新科技股份有限公司 | Positioning method, device and equipment and automatic driving positioning system |
CN110825093A (en) * | 2019-11-28 | 2020-02-21 | 安徽江淮汽车集团股份有限公司 | Automatic driving strategy generation method, device, equipment and storage medium |
CN111008660A (en) * | 2019-12-03 | 2020-04-14 | 北京京东乾石科技有限公司 | Semantic map generation method, device and system, storage medium and electronic equipment |
CN112986979A (en) * | 2019-12-17 | 2021-06-18 | 动态Ad有限责任公司 | Automatic object labeling using fused camera/LiDAR data points |
CN111025331A (en) * | 2019-12-25 | 2020-04-17 | 湖北省国土资源研究院(湖北省国土资源厅不动产登记中心) | Laser radar mapping method based on rotating structure and scanning system thereof |
CN111176279B (en) * | 2019-12-31 | 2023-09-26 | 北京四维图新科技股份有限公司 | Determination method, device, equipment and storage medium for vulnerable crowd area |
CN111207762A (en) * | 2019-12-31 | 2020-05-29 | 深圳一清创新科技有限公司 | Map generation method and device, computer equipment and storage medium |
CN111207762B (en) * | 2019-12-31 | 2021-12-07 | 深圳一清创新科技有限公司 | Map generation method and device, computer equipment and storage medium |
CN111192341A (en) * | 2019-12-31 | 2020-05-22 | 北京三快在线科技有限公司 | Method and device for generating high-precision map, automatic driving equipment and storage medium |
WO2021135371A1 (en) * | 2019-12-31 | 2021-07-08 | 华为技术有限公司 | Automatic driving method, related device and computer-readable storage medium |
CN111176279A (en) * | 2019-12-31 | 2020-05-19 | 北京四维图新科技股份有限公司 | Method, device, equipment and storage medium for determining vulnerable crowd area |
CN113269977A (en) * | 2020-01-29 | 2021-08-17 | 丰田自动车株式会社 | Map generation data collection device and map generation data collection method |
CN111311709B (en) * | 2020-02-05 | 2023-06-20 | 北京三快在线科技有限公司 | Method and device for generating high-precision map |
CN111311709A (en) * | 2020-02-05 | 2020-06-19 | 北京三快在线科技有限公司 | Method and device for generating high-precision map |
WO2021223116A1 (en) * | 2020-05-06 | 2021-11-11 | 上海欧菲智能车联科技有限公司 | Perceptual map generation method and apparatus, computer device and storage medium |
WO2021227520A1 (en) * | 2020-05-14 | 2021-11-18 | 广州文远知行科技有限公司 | Visual interface display method and apparatus, electronic device, and storage medium |
WO2021232470A1 (en) * | 2020-05-19 | 2021-11-25 | 北京数字绿土科技有限公司 | Multi-sensor fusion-based slam method and system |
EP4141600A4 (en) * | 2020-05-25 | 2023-11-01 | Huawei Technologies Co., Ltd. | Positioning method and positioning apparatus |
CN113721599A (en) * | 2020-05-25 | 2021-11-30 | 华为技术有限公司 | Positioning method and positioning device |
CN113721599B (en) * | 2020-05-25 | 2023-10-20 | 华为技术有限公司 | Positioning method and positioning device |
CN111710040B (en) * | 2020-06-03 | 2024-04-09 | 纵目科技(上海)股份有限公司 | High-precision map construction method, system, terminal and storage medium |
CN111710040A (en) * | 2020-06-03 | 2020-09-25 | 纵目科技(上海)股份有限公司 | Method, system, terminal and storage medium for constructing high-precision map |
CN111958592B (en) * | 2020-07-30 | 2021-08-20 | 国网智能科技股份有限公司 | Image semantic analysis system and method for transformer substation inspection robot |
CN111958592A (en) * | 2020-07-30 | 2020-11-20 | 国网智能科技股份有限公司 | Image semantic analysis system and method for transformer substation inspection robot |
CN111912419A (en) * | 2020-08-28 | 2020-11-10 | 清华大学苏州汽车研究院(吴江) | High-precision semantic navigation map construction method and device based on laser radar |
CN112254737A (en) * | 2020-10-27 | 2021-01-22 | 北京晶众智慧交通科技股份有限公司 | Map data conversion method |
CN112556654A (en) * | 2020-12-17 | 2021-03-26 | 武汉中海庭数据技术有限公司 | High-precision map data acquisition device and method |
CN113418528B (en) * | 2021-05-31 | 2024-07-12 | 江苏大学 | Traffic scene semantic modeling device, modeling method and positioning method for intelligent automobile |
CN113418528A (en) * | 2021-05-31 | 2021-09-21 | 江苏大学 | Intelligent automobile-oriented traffic scene semantic modeling device, modeling method and positioning method |
CN113419245A (en) * | 2021-06-23 | 2021-09-21 | 北京易航远智科技有限公司 | Real-time mapping system and mapping method based on V2X |
CN113656525A (en) * | 2021-08-19 | 2021-11-16 | 广州小鹏自动驾驶科技有限公司 | Map processing method and device |
CN113656525B (en) * | 2021-08-19 | 2024-04-16 | 广州小鹏自动驾驶科技有限公司 | Map processing method and device |
CN113978484A (en) * | 2021-09-30 | 2022-01-28 | 东风汽车集团股份有限公司 | Vehicle control method, device, electronic device and storage medium |
CN113945222B (en) * | 2021-10-14 | 2024-04-12 | 华为技术有限公司 | Road information identification method and device, electronic equipment, vehicle and medium |
CN113945222A (en) * | 2021-10-14 | 2022-01-18 | 华为技术有限公司 | Method and device for identifying road information, electronic equipment, vehicle and medium |
CN114842211A (en) * | 2022-03-28 | 2022-08-02 | 高德软件有限公司 | Angular point extraction, precision evaluation and carrier positioning method, equipment, medium and product |
CN114842211B (en) * | 2022-03-28 | 2024-07-23 | 高德软件有限公司 | Angular point extraction, precision evaluation and carrier positioning method, equipment, medium and product |
CN115100631A (en) * | 2022-07-18 | 2022-09-23 | 浙江省交通运输科学研究院 | Road map acquisition system and method for multi-source information composite feature extraction |
CN114973910B (en) * | 2022-07-27 | 2022-11-11 | 禾多科技(北京)有限公司 | Map generation method and device, electronic equipment and computer readable medium |
CN114973910A (en) * | 2022-07-27 | 2022-08-30 | 禾多科技(北京)有限公司 | Map generation method and device, electronic equipment and computer readable medium |
CN115164918A (en) * | 2022-09-06 | 2022-10-11 | 联友智连科技有限公司 | Semantic point cloud map construction method and device and electronic equipment |
Also Published As
Publication number | Publication date |
---|---|
CN110057373B (en) | 2023-11-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110057373A (en) | For generating the method, apparatus and computer storage medium of fine semanteme map | |
CN109991984A (en) | For generating the method, apparatus and computer storage medium of fine map | |
CN108801276B (en) | High-precision map generation method and device | |
CN109029422B (en) | Method and device for building three-dimensional survey map through cooperation of multiple unmanned aerial vehicles | |
JP7127941B2 (en) | Method, system and program | |
CN106441319B (en) | A kind of generation system and method for automatic driving vehicle lane grade navigation map | |
JP5227065B2 (en) | 3D machine map, 3D machine map generation device, navigation device and automatic driving device | |
CN106461402B (en) | For determining the method and system of the position relative to numerical map | |
CN108885106A (en) | It is controlled using the vehicle part of map | |
EP3650814B1 (en) | Vision augmented navigation | |
US20190101649A1 (en) | Systems, devices, and methods for autonomous vehicle localization | |
Brenner | Extraction of features from mobile laser scanning data for future driver assistance systems | |
CN106980657A (en) | A kind of track level electronic map construction method based on information fusion | |
CN110906954A (en) | High-precision map test evaluation method and device based on automatic driving platform | |
CN110211228A (en) | For building the data processing method and device of figure | |
CN111426320B (en) | Vehicle autonomous navigation method based on image matching/inertial navigation/milemeter | |
CN106501829A (en) | A kind of Navigation of Pilotless Aircraft method and apparatus | |
CN109753084A (en) | A kind of unmanned device and method | |
US11866167B2 (en) | Method and algorithm for flight, movement, autonomy, in GPS, communication, degraded, denied, obstructed non optimal environment | |
Shunsuke et al. | GNSS/INS/on-board camera integration for vehicle self-localization in urban canyon | |
CN109446973A (en) | A kind of vehicle positioning method based on deep neural network image recognition | |
CA2682530C (en) | Self-orienting reticle | |
CN115027482B (en) | Fusion positioning method in intelligent driving | |
CN109490931A (en) | Flight localization method, device and unmanned plane | |
CN110388939A (en) | One kind being based on the matched vehicle-mounted inertial navigation position error modification method of Aerial Images |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |