CN116546424A - Laser mapping method and device, laser positioning method and device - Google Patents
Laser mapping method and device, laser positioning method and device Download PDFInfo
- Publication number
- CN116546424A CN116546424A CN202310124937.9A CN202310124937A CN116546424A CN 116546424 A CN116546424 A CN 116546424A CN 202310124937 A CN202310124937 A CN 202310124937A CN 116546424 A CN116546424 A CN 116546424A
- Authority
- CN
- China
- Prior art keywords
- point cloud
- laser
- cloud data
- operation area
- preset operation
- 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 77
- 238000013507 mapping Methods 0.000 title claims description 54
- 230000004927 fusion Effects 0.000 claims abstract description 59
- 238000007781 pre-processing Methods 0.000 claims abstract description 45
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 34
- 238000010276 construction Methods 0.000 claims abstract description 16
- 238000012805 post-processing Methods 0.000 claims abstract description 16
- 238000003860 storage Methods 0.000 claims description 16
- 238000010586 diagram Methods 0.000 description 14
- 230000008859 change Effects 0.000 description 11
- 238000004590 computer program Methods 0.000 description 10
- 238000005516 engineering process Methods 0.000 description 10
- 238000012545 processing Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000011022 operating instruction Methods 0.000 description 1
- 238000000059 patterning Methods 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000001932 seasonal effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 230000001502 supplementing effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/021—Services related to particular areas, e.g. point of interest [POI] services, venue services or geofences
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
- G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/042—Detecting movement of traffic to be counted or controlled using inductive or magnetic detectors
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Navigation (AREA)
Abstract
The application discloses a laser image construction method and a device thereof, a laser positioning method and a device thereof, wherein the laser image construction method comprises the following steps: acquiring first image data and first laser point cloud data acquired by a first vehicle in a preset operation area, and fusing the first image data and the first laser point cloud data by using a preset fusion algorithm to obtain a first fusion result; determining a target and a corresponding target type in the first laser point cloud data according to the first fusion result; preprocessing targets in the first laser point cloud data by utilizing a preset preprocessing strategy according to target types corresponding to the targets to obtain preprocessed first laser point cloud data; and constructing a point cloud map of a preset operation area according to the preprocessed first laser point cloud data and the corresponding post-processing positioning data. According to the method and the device, the image data and the laser point cloud data are fused to perform target identification, so that the target identification precision is improved, different preprocessing operations are adopted for the laser point cloud data aiming at different target types, and the laser map building and positioning precision is improved.
Description
Technical Field
The application relates to the technical field of automatic driving, in particular to a laser mapping method and device, a laser positioning method and device.
Background
As the maturity of the autopilot technology is higher, the operation areas of Robotaxi (automatic taxi) and Robobus (automatic bus) are also diversified, and as there are various scenes in cities that affect the conventional combined navigation positioning effect, such as urban canyons, disc bridges, etc., the Multi-sensor Fusion (MSF) technology is also more applied to the positioning scheme of the autopilot vehicle.
The multi-sensor fusion positioning technology mainly comprises a visual map construction and positioning technology and a laser map construction and positioning technology. Compared with a monocular or binocular vision positioning technology, the laser mapping and positioning technology has better engineering framework and higher precision and stability, so the laser mapping and positioning technology is used as a preferred scheme in practical application, and is used as an auxiliary observation when GNSS (Global Navigation Satellite System )/RTK (Real-time kinematic) fails, so that the centimeter-level positioning precision of the whole time and the whole climate of an operation area is ensured.
Ideally, the accuracy of point cloud matching positioning can reach centimeter level (within 10 cm), but if the scene in the map building and the scene in the positioning change greatly, for example, more vehicles near a parking lot in the map building and fewer vehicles in the positioning, the effective transformation cannot be calculated through an ICP (Iterative Closest Point) or NDT (Normal Distribution Transform) matching algorithm, the positioning accuracy can be affected, the error can be expanded to decimeter level, even the accurate positioning result with high confidence can not be output, and the normal running of the automatic driving vehicle can be affected.
Disclosure of Invention
The embodiment of the application provides a laser image construction method and device, a laser positioning method and device, so as to improve the laser image construction precision and positioning precision.
The embodiment of the application adopts the following technical scheme:
in a first aspect, an embodiment of the present application provides a laser mapping method, where the laser mapping method includes:
acquiring first image data and first laser point cloud data acquired by a first vehicle in a preset operation area, and fusing the first image data and the first laser point cloud data by using a preset fusion algorithm to obtain a first fusion result;
Determining a target and a corresponding target type in the first laser point cloud data according to the first fusion result;
preprocessing the target in the first laser point cloud data by utilizing a preset preprocessing strategy according to the target type corresponding to the target in the first laser point cloud data to obtain preprocessed first laser point cloud data;
and constructing a point cloud map of the preset operation area according to the preprocessed first laser point cloud data and post-processing positioning data corresponding to the first laser point cloud data.
Optionally, the targets include a foreground target and a background target, the background target includes a changeable background target and an unchangeable background target, and preprocessing the targets in the first laser point cloud data by using a preset preprocessing strategy according to a target type corresponding to the targets in the first laser point cloud data, so as to obtain preprocessed first laser point cloud data includes:
and eliminating the foreground target from the first laser point cloud data, and respectively setting the point cloud weights of a changeable background target and an unchangeable background target in the first laser point cloud data, wherein the point cloud weight of the set changeable background target is smaller than that of the set unchangeable background target, so as to obtain the preprocessed first laser point cloud data.
Optionally, after constructing the point cloud map of the preset operation area according to the preprocessed first laser point cloud data and the post-processing positioning data corresponding to the first laser point cloud data, the method further includes:
acquiring a laser positioning result of a second vehicle in the preset operation area and acquiring a point cloud missing position set of the preset operation area;
and determining whether to update a point cloud map of the preset operation area according to a laser positioning result of the second vehicle in the preset operation area and a point cloud missing position set of the preset operation area.
Optionally, the acquiring the point cloud missing location set of the preset operation area includes:
determining a scene area where the first vehicle is currently located, wherein the scene area is located in the preset operation area;
determining the relative quantity of foreground targets in the first laser point cloud data according to the targets in the first laser point cloud data and the corresponding target types;
and constructing a point cloud missing position set of the preset operation area according to the relative quantity of the scene area where the first vehicle is currently located and the foreground target.
Optionally, the constructing the point cloud missing location set of the preset operation area according to the relative number of the scene area where the first vehicle is currently located and the foreground object includes:
acquiring data of a scene area where the first vehicle is currently located based on high-precision map data, wherein the data of the scene area comprises a scene area type and a scene area position;
determining a point cloud map update identifier according to the relative quantity of the foreground targets, wherein the point cloud map update identifier comprises an updatable identifier and a non-updatable identifier;
and constructing a point cloud missing position set of the preset operation area according to the data of the scene area where the first vehicle is currently located and the point cloud map updating mark.
Optionally, the determining the point cloud map update identifier according to the relative number of the foreground objects includes:
if the relative number of the foreground targets is larger than a preset relative number threshold, determining that the point cloud map updating mark is the non-updatable mark;
and if the relative number of the foreground targets is not greater than a preset relative number threshold, determining the point cloud map updating identifier as the updatable identifier.
Optionally, the laser positioning result of the second vehicle in the preset operation area includes a laser positioning position and a laser positioning confidence, the point cloud missing position set includes a point cloud map update identifier, and determining whether to update the point cloud map of the preset operation area according to the laser positioning result of the second vehicle in the preset operation area and the point cloud missing position set of the preset operation area includes:
If the laser positioning confidence is greater than a preset map updating threshold, the laser positioning position is located in the point cloud missing position set, and the corresponding point cloud map updating mark is an updatable mark, determining to update the point cloud map of the preset operation area, and updating the point cloud map of the preset operation area according to the laser positioning result of the second vehicle in the preset operation area;
otherwise, determining not to update the point cloud map of the preset operation area.
In a second aspect, embodiments of the present application further provide a laser positioning method, where the laser positioning method includes:
acquiring third image data and third laser point cloud data acquired by a third vehicle in a preset operation area, and fusing the third image data and the third laser point cloud data by using a preset fusion algorithm to obtain a third fusion result;
determining a target and a corresponding target type in the third laser point cloud data according to the third fusion result;
preprocessing the target in the third laser point cloud data by utilizing a preset preprocessing strategy according to the target type corresponding to the target in the third laser point cloud data to obtain preprocessed second laser point cloud data;
Determining a laser positioning result of the third vehicle in the preset operation area according to the preprocessed second laser point cloud data and the point cloud map of the preset operation area;
the point cloud map of the preset operation area is obtained based on any one of the laser mapping methods.
Optionally, after acquiring the third image data and the third laser point cloud data acquired by the third vehicle in the preset operation area, the method further includes:
acquiring a point cloud missing position set of the preset operation area, wherein the point cloud missing position set comprises a point cloud map updating identifier, and the point cloud map updating identifier comprises an non-updatable identifier;
determining whether the third vehicle enters a scene area corresponding to an updatable identifier according to the point cloud missing position set of the preset operation area and post-processing positioning data corresponding to the third laser point cloud data;
if yes, determining a laser positioning result of the third vehicle in the preset operation area by utilizing a laser SLAM algorithm according to the third laser point cloud data.
In a third aspect, an embodiment of the present application further provides a laser mapping apparatus, where the laser mapping apparatus includes:
The first fusion unit is used for acquiring first image data and first laser point cloud data acquired by a first vehicle in a preset operation area, and fusing the first image data and the first laser point cloud data by utilizing a preset fusion algorithm to obtain a first fusion result;
the first determining unit is used for determining a target and a corresponding target type in the first laser point cloud data according to the first fusion result;
the first preprocessing unit is used for preprocessing the targets in the first laser point cloud data by utilizing a preset preprocessing strategy according to the target types corresponding to the targets in the first laser point cloud data to obtain preprocessed first laser point cloud data;
the construction unit is used for constructing the point cloud map of the preset operation area according to the preprocessed first laser point cloud data and the post-processing positioning data corresponding to the first laser point cloud data.
In a fourth aspect, embodiments of the present application further provide a laser positioning device, where the laser positioning device includes:
the second fusion unit is used for acquiring third image data and third laser point cloud data acquired by a third vehicle in a preset operation area, and fusing the third image data and the third laser point cloud data by utilizing a preset fusion algorithm to acquire a third fusion result;
The second determining unit is used for determining a target and a corresponding target type in the third laser point cloud data according to the third fusion result;
the second preprocessing unit is used for preprocessing the targets in the third laser point cloud data by utilizing a preset preprocessing strategy according to the target types corresponding to the targets in the third laser point cloud data to obtain preprocessed second laser point cloud data;
the first positioning unit is used for determining a laser positioning result of the third vehicle in the preset operation area according to the preprocessed second laser point cloud data and the point cloud map of the preset operation area;
the point cloud map of the preset operation area is obtained based on the laser mapping device.
In a fifth aspect, embodiments of the present application further provide an electronic device, including:
a processor; and
a memory arranged to store computer executable instructions which, when executed, cause the processor to perform any of the methods described hereinbefore.
In a sixth aspect, embodiments of the present application also provide a computer-readable storage medium storing one or more programs that, when executed by an electronic device comprising a plurality of application programs, cause the electronic device to perform any of the methods described above.
The above-mentioned at least one technical scheme that this application embodiment adopted can reach following beneficial effect: the laser mapping method comprises the steps of firstly obtaining first image data and first laser point cloud data acquired by a first vehicle in a preset operation area, and fusing the first image data and the first laser point cloud data by using a preset fusion algorithm to obtain a first fusion result; then determining a target and a corresponding target type in the first laser point cloud data according to the first fusion result; preprocessing the target in the first laser point cloud data by utilizing a preset preprocessing strategy according to the target type corresponding to the target in the first laser point cloud data to obtain preprocessed first laser point cloud data; and finally, constructing a point cloud map of a preset operation area according to the preprocessed first laser point cloud data and post-processing positioning data corresponding to the first laser point cloud data. According to the laser mapping method, the image data and the laser point cloud data are fused for target identification, the target identification accuracy of the laser point cloud data is improved, the target type is further determined according to the fusion result, different preprocessing operations are adopted for the laser point cloud data according to different target types, and the accuracy of the point cloud map is improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute an undue limitation to the application. In the drawings:
FIG. 1 is a schematic flow chart of a laser mapping method according to an embodiment of the present application;
FIG. 2 is a schematic structural diagram of a laser patterning device according to an embodiment of the present disclosure;
FIG. 3 is a schematic flow chart of a laser positioning method according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of a laser positioning device according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of an electronic device in an embodiment of the present application.
Detailed Description
For the purposes, technical solutions and advantages of the present application, the technical solutions of the present application will be clearly and completely described below with reference to specific embodiments of the present application and corresponding drawings. It will be apparent that the described embodiments are only some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.
The following describes in detail the technical solutions provided by the embodiments of the present application with reference to the accompanying drawings.
The embodiment of the application provides a laser mapping method, as shown in fig. 1, and provides a flow schematic diagram of the laser mapping method in the embodiment of the application, where the laser mapping method at least includes the following steps S110 to S140:
step S110, first image data and first laser point cloud data acquired by a first vehicle in a preset operation area are acquired, and fusion is carried out on the first image data and the first laser point cloud data by using a preset fusion algorithm, so that a first fusion result is obtained.
When the point cloud map is constructed, first image data and first laser point cloud data acquired by a first vehicle in a preset operation area are required to be acquired, the first vehicle can be a data acquisition vehicle provided with sensors such as truth equipment, cameras and laser radars, and all the sensors are calibrated in advance. The preset operation area can be flexibly determined according to an actual application scene, for example, can be determined according to the operation service range of Robotaxi or Robotbus.
The first image data are acquired by a camera on the data acquisition vehicle, the first laser point cloud data are acquired by a laser radar on the data acquisition vehicle, and because the data output frequencies of the camera and the laser radar are different, time synchronization processing can be carried out on the image data acquired by the camera and the laser point cloud data acquired by the laser radar so as to ensure the accuracy of subsequent data processing, namely the first image data and the first laser point cloud data can be regarded as data after the time synchronization processing.
And then fusing the first image data and the first laser point cloud data by using a preset fusion algorithm to obtain a first fusion result, wherein the preset fusion algorithm can be flexibly selected according to the existing image-laser point cloud fusion algorithm, such as target detection and recognition realized on the basis of a deep learning algorithm. Because the target recognition algorithm realized based on the laser point cloud data is not high in recognition accuracy particularly for small targets such as pedestrians, bicycles and the like, the target detection and recognition are performed through the fusion result of the image data and the laser point cloud data, the recognition accuracy of only using the laser point cloud data can be improved, and the accuracy of drawing and positioning is further improved.
Step S120, determining a target and a corresponding target type in the first laser point cloud data according to the first fusion result.
The target in the first laser point cloud data and the corresponding target type can be identified based on the fusion result of the image data and the corresponding laser point cloud data, wherein the target type can comprise a foreground target and a background target.
Step S130, preprocessing the target in the first laser point cloud data by using a preset preprocessing strategy according to the target type corresponding to the target in the first laser point cloud data, so as to obtain preprocessed first laser point cloud data.
Ideally, the positioning accuracy achieved based on the point cloud map can reach the centimeter level, but if the scene difference between the map construction and the positioning is large, the positioning result and the positioning accuracy are affected, and the magnitude of the scene change difference is related to the targets existing in the scene and the target types, for example, if the background targets are more, the dynamic foreground targets are less, the scene change is relatively small, otherwise, if the background targets are less, the dynamic foreground targets are more, and the scene change is relatively large.
Based on this, according to the embodiment of the present application, a certain preprocessing policy may be adopted to preprocess the targets in the first laser point cloud data according to different target types included in the first laser point cloud data, so as to obtain preprocessed first laser point cloud data, where the preprocessing principle is to reduce the influence of scene differences on the laser point cloud mapping and positioning accuracy as much as possible.
Step S140, constructing a point cloud map of the preset operation area according to the preprocessed first laser point cloud data and the post-processing positioning data corresponding to the first laser point cloud data.
After the preprocessed first laser point cloud data is obtained, a corresponding positioning truth value is also needed to be obtained through a post-processing algorithm, mapping is carried out on the preprocessed first laser point cloud data based on the positioning truth value, and because the positioning accuracy of the post-processing positioning truth value is generally within 1cm, the positioning truth value can be directly used for carrying out operations such as point cloud projection, matching and the like, so that a point cloud map of a preset operation area is generated.
In some embodiments of the present application, the targets include a foreground target and a background target, the background target includes a changeable background target and an unchangeable background target, and preprocessing the targets in the first laser point cloud data by using a preset preprocessing strategy according to a target type corresponding to the targets in the first laser point cloud data, where obtaining preprocessed first laser point cloud data includes: and eliminating the foreground target from the first laser point cloud data, and respectively setting the point cloud weights of a changeable background target and an unchangeable background target in the first laser point cloud data, wherein the point cloud weight of the set changeable background target is smaller than that of the set unchangeable background target, so as to obtain the preprocessed first laser point cloud data.
The objects in the embodiments of the present application are mainly classified into a foreground object and a background object, where the foreground object is a dynamic object such as a vehicle or a pedestrian, and the background object is a sign board, a tree, a building, or the like on two sides of a road, so that the background object may be further classified into a changeable background object and an unchangeable background object, where the changeable background object may be a tree on two sides of a road, which generally changes with a seasonal change, but has a lower change frequency compared with the foreground object, and the unchangeable background object may be a building or the like on two sides of a road, which generally does not change with time, or may be regarded as an object with a relatively lowest change frequency, so that the change frequencies of different objects in corresponding scenes are different.
Based on the method, in order to reduce the influence of scene change difference on laser mapping and positioning precision as much as possible, when a point cloud map is constructed, laser point cloud data of an unchangeable background target can be more relied, and the dependence on a foreground target and the changeable background target is reduced. For example, the foreground target in the first laser point cloud data can be directly removed, and the point cloud map is constructed by only relying on the laser point cloud data of the background target, so that the influence of the dynamic foreground target on the map construction and positioning accuracy is avoided. In addition, the point cloud weight of the changeable background object in the first laser point cloud data can be reduced, for example, the point cloud weight of the unchangeable background object is set to be 0.5, and the point cloud weight of the unchangeable background object is increased, for example, the point cloud weight of the unchangeable background object is set to be 1, so that the influence of the laser point cloud data of the changeable background object is properly reduced, and the laser point cloud data of the unchangeable background object is fully utilized, so that the laser mapping and positioning accuracy is improved.
In some embodiments of the present application, after constructing the point cloud map of the preset operation area according to the preprocessed first laser point cloud data and the post-processed positioning data corresponding to the first laser point cloud data, the method further includes: acquiring a laser positioning result of a second vehicle in the preset operation area and acquiring a point cloud missing position set of the preset operation area; and determining whether to update a point cloud map of the preset operation area according to a laser positioning result of the second vehicle in the preset operation area and a point cloud missing position set of the preset operation area.
Because the number of foreground objects in the actual scene is more or less, for example, the foreground objects near a parking lot, near a subway entrance and the like are relatively more, and the foreground objects in a driving road section area are relatively less, the foreground objects in different scene areas can cause different degrees of shielding on the background, and after the laser point cloud data of the foreground objects are removed, the loss of the background point cloud of different degrees can occur, so that a point cloud loss position set of a preset operation area can be established according to different object identification results, and a point cloud map can be updated according to the point cloud loss position set and the actual laser positioning result of a subsequent second vehicle in the preset operation area. The second vehicle may be a vehicle actually operated in the operation area, and since there are more operation vehicles, the background point cloud data may be continuously compensated and perfected by the actual positioning result of the operation vehicles, so as to improve the integrity and positioning accuracy of the point cloud map.
In some embodiments of the present application, the acquiring the set of point cloud missing positions of the preset operation area includes: determining a scene area where the first vehicle is currently located, wherein the scene area is located in the preset operation area; determining the relative quantity of foreground targets in the first laser point cloud data according to the targets in the first laser point cloud data and the corresponding target types; and constructing a point cloud missing position set of the preset operation area according to the relative quantity of the scene area where the first vehicle is currently located and the foreground target.
As described above, the relative number of foreground objects in different scene areas is different, for example, the foreground objects near a parking lot, near a subway entrance and exit are relatively more, but the foreground objects in a driving road section area are relatively less, so that the foreground objects in different scene areas can cause different degrees of shielding to the background.
Based on the targets in the first laser point cloud data and the corresponding target types, the relative quantity of the foreground targets in the first laser point cloud data can be determined, for example, the percentage of the laser point cloud data of the foreground targets to the whole laser point cloud data can be counted, if the ratio of the foreground targets is higher, the relative quantity of the foreground targets is larger, the relative quantity of the background targets is smaller, otherwise, the relative quantity of the foreground targets is smaller, the relative quantity of the background targets is larger, and further a point cloud missing position set of a preset operation area can be constructed according to the relative quantity of the foreground targets, for example, the information such as the type of a scene area, the absolute position of missing and the like can be included.
In some embodiments of the present application, the constructing the point cloud missing location set of the preset operation area according to the relative number of the scene area where the first vehicle is currently located and the foreground object includes: acquiring data of a scene area where the first vehicle is currently located based on high-precision map data, wherein the data of the scene area comprises a scene area type and a scene area position; determining a point cloud map update identifier according to the relative quantity of the foreground targets, wherein the point cloud map update identifier comprises an updatable identifier and a non-updatable identifier; and constructing a point cloud missing position set of the preset operation area according to the data of the scene area where the first vehicle is currently located and the point cloud map updating mark.
The high-precision map data can provide absolute position information of different road sections and different scene areas, so that the data of the scene area where the first vehicle is currently located can be obtained from the high-precision map data, wherein the data comprise scene area types and scene area positions, the scene area types can be characterized and distinguished by scene area identifiers, and the scene area positions refer to an absolute position set corresponding to the scene areas.
In addition, the relative quantity of the foreground targets reflects the shielding degree of the foreground targets on a background region in a scene, the relative quantity of the foreground targets of the whole scene region can be comprehensively considered, whether the point cloud map of the scene region can be updated or not is determined according to the relative quantity of the foreground targets of the whole scene region, and finally, a point cloud missing position set of a preset operation region is generated by combining the scene region type and the scene region position.
In some embodiments of the present application, the determining the point cloud map update identification according to the relative number of foreground objects includes: if the relative number of the foreground targets is larger than a preset relative number threshold, determining that the point cloud map updating mark is the non-updatable mark; and if the relative number of the foreground targets is not greater than a preset relative number threshold, determining the point cloud map updating identifier as the updatable identifier.
The more the relative number of foreground objects is, the fewer the relative number of background objects is, for example, the vicinity of a parking area, the vicinity of a subway entrance and the like are all scene areas with more foreground objects, and for such areas, the meaning of positioning by adopting a point cloud map constructed in advance is not great, because the area is difficult to ensure the accuracy of matching positioning through continuous supplement and perfection of the background point cloud, the point cloud map updating marks of the areas can be defined as non-updatable marks. When the vehicle is traveling to the area, the point cloud map may not be updated and may be switched to other positioning strategies, such as a strategy of laser SLAM (Simultaneous Localization And Mapping, synchronous positioning and mapping).
Conversely, if the relative number of foreground objects is smaller, the relative number of background objects is larger, such as a normal driving road section, and the laser mapping and positioning of the areas are affected by the foreground objects, the point cloud map can be continuously updated by continuously supplementing and perfecting the background point cloud data, so that the accuracy of matching positioning is ensured, and therefore, the point cloud map updating identifications of the areas can be defined as updatable identifications. When the vehicle travels to the area, the point cloud map may be updated in combination with the positioning result.
In some embodiments of the present application, the laser positioning result of the second vehicle in the preset operation area includes a laser positioning position and a laser positioning confidence, the set of point cloud missing positions includes a point cloud map update identifier, and determining, according to the laser positioning result of the second vehicle in the preset operation area and the set of point cloud missing positions in the preset operation area, whether to update the point cloud map in the preset operation area includes: if the laser positioning confidence is greater than a preset map updating threshold, the laser positioning position is located in the point cloud missing position set, and the corresponding point cloud map updating mark is an updatable mark, determining to update the point cloud map of the preset operation area, and updating the point cloud map of the preset operation area according to the laser positioning result of the second vehicle in the preset operation area; otherwise, determining not to update the point cloud map of the preset operation area.
For updating the point cloud map, besides the point cloud missing position set of the preset operation area constructed by the embodiment, the current actual laser positioning result of the vehicle can be considered. Because the foreground targets detected by different vehicles when running to the same position are not completely consistent, the point cloud map can be updated in real time according to the laser positioning result, for example, the foreground targets shield a certain background area in the construction stage, but the background area is not shielded in the positioning stage, and at the moment, the point cloud map can be updated according to the point cloud data of the position, for example, the missing background point cloud data is compensated.
The laser positioning result mainly comprises a laser positioning position and a laser positioning confidence coefficient, the laser positioning position can be obtained by matching current laser point cloud data with a point cloud map based on the existing point cloud matching algorithm such as ICP or NDT algorithm, the laser positioning confidence coefficient can be used for evaluating the reliability of the laser positioning position based on the existing confidence coefficient evaluating algorithm such as the NDT matching probability score of Autoware, the laser positioning confidence coefficient is larger than a preset positioning effective threshold value, and the fact that the current positioning result meets positioning precision requirements is an effective positioning result is indicated.
If the laser positioning confidence is greater than the preset positioning effective threshold, whether the laser positioning confidence reaches the preset map updating threshold can be further judged, the preset positioning effective threshold and the preset map updating threshold can be set to different values, the preset map updating threshold can be obtained through offline statistical calculation, and the preset map updating threshold can be higher than the preset positioning effective threshold.
If the laser positioning confidence is greater than the preset map updating threshold, and the laser positioning position is located in the point cloud missing position set, the corresponding point cloud map updating mark is an updatable mark, and the point cloud map of the preset operation area can be updated by using the current laser positioning result. If the laser positioning confidence is not greater than the preset map updating threshold, or the laser positioning position is not located in the point cloud missing position set, or the corresponding point cloud map updating mark is an non-updatable mark, the point cloud map is not updated.
According to the embodiment of the application, the point cloud map can be updated in real time by operating the vehicle based on the data returned after the point cloud map is successfully positioned, so that the instantaneity of the point cloud map is ensured, periodic collection of the collected vehicle and establishment of the point cloud map are not needed, the map construction efficiency is improved, and the map construction cost is reduced.
The embodiment of the application further provides a laser mapping device 200, as shown in fig. 2, and a schematic structural diagram of the laser mapping device in the embodiment of the application is provided, where the laser mapping device 200 includes: a first fusion unit 210, a first determination unit 220, a first preprocessing unit 230, and a construction unit 240, wherein:
the first fusion unit 210 is configured to obtain first image data and first laser point cloud data acquired by a first vehicle in a preset operation area, and fuse the first image data and the first laser point cloud data by using a preset fusion algorithm to obtain a first fusion result;
a first determining unit 220, configured to determine a target and a corresponding target type in the first laser point cloud data according to the first fusion result;
a first preprocessing unit 230, configured to preprocess the target in the first laser point cloud data by using a preset preprocessing policy according to a target type corresponding to the target in the first laser point cloud data, so as to obtain preprocessed first laser point cloud data;
the construction unit 240 is configured to construct a point cloud map of the preset operation area according to the preprocessed first laser point cloud data and post-processing positioning data corresponding to the first laser point cloud data.
In some embodiments of the present application, the targets include foreground targets and background targets, the background targets including changeable background targets and non-changeable background targets, and the first preprocessing unit 230 is specifically configured to: and eliminating the foreground target from the first laser point cloud data, and respectively setting the point cloud weights of a changeable background target and an unchangeable background target in the first laser point cloud data, wherein the point cloud weight of the set changeable background target is smaller than that of the set unchangeable background target, so as to obtain the preprocessed first laser point cloud data.
In some embodiments of the present application, the laser positioning device further comprises: the first acquisition unit is used for acquiring a laser positioning result of the second vehicle in the preset operation area and acquiring a point cloud missing position set of the preset operation area; and the third determining unit is used for determining whether to update the point cloud map of the preset operation area according to the laser positioning result of the second vehicle in the preset operation area and the point cloud missing position set of the preset operation area.
In some embodiments of the present application, the first obtaining unit is specifically configured to: determining a scene area where the first vehicle is currently located, wherein the scene area is located in the preset operation area; determining the relative quantity of foreground targets in the first laser point cloud data according to the targets in the first laser point cloud data and the corresponding target types; and constructing a point cloud missing position set of the preset operation area according to the relative quantity of the scene area where the first vehicle is currently located and the foreground target.
In some embodiments of the present application, the first obtaining unit is specifically configured to: acquiring data of a scene area where the first vehicle is currently located based on high-precision map data, wherein the data of the scene area comprises a scene area type and a scene area position; determining a point cloud map update identifier according to the relative quantity of the foreground targets, wherein the point cloud map update identifier comprises an updatable identifier and a non-updatable identifier; and constructing a point cloud missing position set of the preset operation area according to the data of the scene area where the first vehicle is currently located and the point cloud map updating mark.
In some embodiments of the present application, the first obtaining unit is specifically configured to: if the relative number of the foreground targets is larger than a preset relative number threshold, determining that the point cloud map updating mark is the non-updatable mark; and if the relative number of the foreground targets is not greater than a preset relative number threshold, determining the point cloud map updating identifier as the updatable identifier.
In some embodiments of the present application, the laser positioning result of the second vehicle in the preset operation area includes a laser positioning position and a laser positioning confidence, the point cloud missing position set includes a point cloud map update identifier, and the third determining unit is specifically configured to: if the laser positioning confidence is greater than a preset map updating threshold, the laser positioning position is located in the point cloud missing position set, and the corresponding point cloud map updating mark is an updatable mark, determining to update the point cloud map of the preset operation area, and updating the point cloud map of the preset operation area according to the laser positioning result of the second vehicle in the preset operation area; otherwise, determining not to update the point cloud map of the preset operation area.
It can be understood that the laser mapping device can implement each step of the laser mapping method provided in the foregoing embodiment, and the relevant explanation about the laser mapping method is applicable to the laser mapping device, which is not repeated herein.
The embodiment of the application also provides a laser positioning method, as shown in fig. 3, and provides a flow schematic diagram of the laser positioning method in the embodiment of the application, where the laser positioning method at least includes the following steps S310 to S340:
s310, acquiring third image data and third laser point cloud data acquired by a third vehicle in a preset operation area, and fusing the third image data and the third laser point cloud data by using a preset fusion algorithm to obtain a third fusion result.
S320, determining a target and a corresponding target type in the third laser point cloud data according to the third fusion result.
S330, preprocessing the target in the third laser point cloud data by utilizing a preset preprocessing strategy according to the target type corresponding to the target in the third laser point cloud data, and obtaining preprocessed second laser point cloud data.
S340, determining a laser positioning result of the third vehicle in the preset operation area according to the preprocessed second laser point cloud data and the point cloud map of the preset operation area; the point cloud map of the preset operation area is obtained based on the laser mapping method.
Steps S310-S330 are substantially identical to steps S110-S130 of the previous embodiments, except that the raw data during the positioning phase originates from the third vehicle that is actually operating. In the laser positioning stage, after the preprocessed second laser point cloud data is obtained, a certain point cloud matching algorithm is needed to match the preprocessed second laser point cloud data with a point cloud map of a preset operation area established in advance, so that a laser positioning result of a third vehicle in the preset operation area is obtained, and the point cloud map is constructed based on the laser mapping method of the previous embodiment.
Similarly, the obtained laser positioning result of the third vehicle in the preset operation area can also be used for updating the point cloud map under the condition that the preset map updating threshold is met, specifically, third laser point cloud data generated by the third vehicle in real time can be further screened, only background point cloud data which remain after being matched with the point cloud map in the third laser point cloud data, namely, background point cloud data which are missing during the previous map building process are reserved, the background point cloud data are returned to the cloud after being processed to a certain degree, for example, the cloud weight is set, the coordinates are converted and the like, and the cloud can update the point cloud map according to the data in the operation ending period and deploy a new point cloud map when the next operation starts.
In some embodiments of the present application, after acquiring the third image data and the third laser point cloud data acquired by the third vehicle in the preset operation area, the method further includes: acquiring a point cloud missing position set of the preset operation area, wherein the point cloud missing position set comprises a point cloud map updating identifier, and the point cloud map updating identifier comprises an non-updatable identifier; determining whether the third vehicle enters a scene area corresponding to an updatable identifier according to the point cloud missing position set of the preset operation area and post-processing positioning data corresponding to the third laser point cloud data; if yes, determining a laser positioning result of the third vehicle in the preset operation area by utilizing a laser SLAM algorithm according to the third laser point cloud data.
The laser SLAM algorithm is a scheme for synchronous positioning and mapping, and different from the laser SLAM algorithm, the laser positioning scheme and the laser mapping scheme in the embodiment of the application can be regarded as two independent stages, namely, a point cloud map of the whole preset operation area is built, then the built point cloud map of the preset operation area is utilized for real-time positioning, and a positioning result can be used for updating the point cloud map under the condition that the condition is met.
In some special scene areas, such as areas near a parking lot, subway entrances and exits, and the like, most of the areas are the conditions of more foreground targets and more open background, and the position areas are more suitable for positioning by adopting a laser SLAM algorithm, so that the embodiment of the application can firstly position based on the strategy of positioning based on the prior point cloud map in the embodiment of the application when in actual positioning, and simultaneously can combine the positioning true value calculated through post-processing and the point cloud missing position set of the preset operation area constructed in the map construction stage to determine whether the positioning strategy needs to be switched at present, for example, the positioning strategy is switched to the positioning strategy based on the laser SLAM algorithm, thereby ensuring the integral positioning precision.
Because the point cloud missing position set contains the point cloud missing position and the corresponding point cloud map updating identification, whether the position corresponding to the current positioning true value is a position which can be updated or needs to be updated or not can be determined, if the point cloud map updating identification corresponding to the position is an non-updatable identification, the point cloud map does not need to be updated, and at the moment, the positioning strategy of the vehicle can be switched into a laser SLAM algorithm.
The embodiment of the application further provides a laser positioning device 400, as shown in fig. 4, and a schematic structural diagram of the laser positioning device in the embodiment of the application is provided, where the laser positioning device 400 includes: a second fusing unit 410, a second determining unit 420, a second preprocessing unit 430, and a first positioning unit 440, wherein:
The second fusion unit 410 is configured to obtain third image data and third laser point cloud data acquired by a third vehicle in a preset operation area, and fuse the third image data and the third laser point cloud data by using a preset fusion algorithm to obtain a third fusion result;
a second determining unit 420, configured to determine a target and a corresponding target type in the third laser point cloud data according to the third fusion result;
a second preprocessing unit 430, configured to preprocess the target in the third laser point cloud data by using a preset preprocessing policy according to a target type corresponding to the target in the third laser point cloud data, so as to obtain preprocessed second laser point cloud data;
a first positioning unit 440, configured to determine a laser positioning result of the third vehicle in the preset operation area according to the preprocessed second laser point cloud data and the point cloud map of the preset operation area;
the point cloud map of the preset operation area is obtained based on the laser mapping device.
In some embodiments of the present application, the apparatus further comprises: the second acquisition unit is used for acquiring a point cloud missing position set of the preset operation area, wherein the point cloud missing position set comprises a point cloud map update identifier, and the point cloud map update identifier comprises a non-updatable identifier; a fourth determining unit, configured to determine, according to the point cloud missing position set of the preset operation area and post-processing positioning data corresponding to the third laser point cloud data, whether the third vehicle enters a scene area corresponding to an updatable identifier; and the second positioning unit is used for determining a laser positioning result of the third vehicle in the preset operation area by utilizing a laser SLAM algorithm according to the third laser point cloud data if the third vehicle is in the preset operation area.
It can be understood that the above-mentioned laser positioning device can implement each step of the laser positioning method provided in the foregoing embodiment, and the relevant explanation about the laser positioning method is applicable to the laser positioning device, which is not repeated herein.
Fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application. Referring to fig. 5, at the hardware level, the electronic device includes a processor, and optionally an internal bus, a network interface, and a memory. The Memory may include a Memory, such as a Random-Access Memory (RAM), and may further include a non-volatile Memory (non-volatile Memory), such as at least 1 disk Memory. Of course, the electronic device may also include hardware required for other services.
The processor, network interface, and memory may be interconnected by an internal bus, which may be an ISA (Industry Standard Architecture ) bus, a PCI (Peripheral Component Interconnect, peripheral component interconnect standard) bus, or EISA (Extended Industry Standard Architecture ) bus, among others. The buses may be classified as address buses, data buses, control buses, etc. For ease of illustration, only one bi-directional arrow is shown in FIG. 5, but not only one bus or type of bus.
And the memory is used for storing programs. In particular, the program may include program code including computer-operating instructions. The memory may include memory and non-volatile storage and provide instructions and data to the processor.
The processor reads the corresponding computer program from the nonvolatile memory to the memory and then runs, and the laser mapping device and the laser positioning device are formed on the logic level. The processor executes the program stored in the memory, and is specifically configured to execute the method executed by the laser mapping apparatus disclosed in the embodiment shown in fig. 1 and the method executed by the laser positioning apparatus disclosed in the embodiment shown in fig. 3.
The method performed by the laser mapping apparatus disclosed in the embodiment shown in fig. 1 and the method performed by the laser positioning apparatus disclosed in the embodiment shown in fig. 3 may be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in a processor or by instructions in the form of software. The processor may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc.; but also digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The disclosed methods, steps, and logic blocks in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the embodiments of the present application may be embodied directly in hardware, in a decoded processor, or in a combination of hardware and software modules in a decoded processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in a memory, and the processor reads the information in the memory and, in combination with its hardware, performs the steps of the above method.
The embodiments of the present application also provide a computer readable storage medium storing one or more programs, where the one or more programs include instructions, which when executed by an electronic device including a plurality of application programs, enable the electronic device to perform a method performed by the laser mapping apparatus in the embodiment shown in fig. 1 and a method performed by the laser positioning apparatus disclosed in the embodiment shown in fig. 3.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.
Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and changes may be made to the present application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. which are within the spirit and principles of the present application are intended to be included within the scope of the claims of the present application.
Claims (13)
1. A laser mapping method, wherein the laser mapping method comprises:
acquiring first image data and first laser point cloud data acquired by a first vehicle in a preset operation area, and fusing the first image data and the first laser point cloud data by using a preset fusion algorithm to obtain a first fusion result;
Determining a target and a corresponding target type in the first laser point cloud data according to the first fusion result;
preprocessing the target in the first laser point cloud data by utilizing a preset preprocessing strategy according to the target type corresponding to the target in the first laser point cloud data to obtain preprocessed first laser point cloud data;
and constructing a point cloud map of the preset operation area according to the preprocessed first laser point cloud data and post-processing positioning data corresponding to the first laser point cloud data.
2. The laser mapping method of claim 1, wherein the targets include foreground targets and background targets, the background targets include changeable background targets and unchangeable background targets, the preprocessing the targets in the first laser point cloud data by using a preset preprocessing strategy according to target types corresponding to the targets in the first laser point cloud data, and obtaining preprocessed first laser point cloud data includes:
and eliminating the foreground target from the first laser point cloud data, and respectively setting the point cloud weights of a changeable background target and an unchangeable background target in the first laser point cloud data, wherein the point cloud weight of the set changeable background target is smaller than that of the set unchangeable background target, so as to obtain the preprocessed first laser point cloud data.
3. The laser mapping method of claim 1, wherein after constructing the point cloud map of the preset operation area according to the preprocessed first laser point cloud data and the post-processed positioning data corresponding to the first laser point cloud data, the method further comprises:
acquiring a laser positioning result of a second vehicle in the preset operation area and acquiring a point cloud missing position set of the preset operation area;
and determining whether to update a point cloud map of the preset operation area according to a laser positioning result of the second vehicle in the preset operation area and a point cloud missing position set of the preset operation area.
4. The laser mapping method of claim 3, wherein the obtaining the set of point cloud missing positions of the preset operation area comprises:
determining a scene area where the first vehicle is currently located, wherein the scene area is located in the preset operation area;
determining the relative quantity of foreground targets in the first laser point cloud data according to the targets in the first laser point cloud data and the corresponding target types;
and constructing a point cloud missing position set of the preset operation area according to the relative quantity of the scene area where the first vehicle is currently located and the foreground target.
5. The laser mapping method of claim 4, wherein the constructing the set of point cloud missing locations of the preset operation region according to the relative number of the scene region where the first vehicle is currently located and the foreground object comprises:
acquiring data of a scene area where the first vehicle is currently located based on high-precision map data, wherein the data of the scene area comprises a scene area type and a scene area position;
determining a point cloud map update identifier according to the relative quantity of the foreground targets, wherein the point cloud map update identifier comprises an updatable identifier and a non-updatable identifier;
and constructing a point cloud missing position set of the preset operation area according to the data of the scene area where the first vehicle is currently located and the point cloud map updating mark.
6. The laser mapping method of claim 5, wherein the determining a point cloud map update identification from the relative number of foreground objects comprises:
if the relative number of the foreground targets is larger than a preset relative number threshold, determining that the point cloud map updating mark is the non-updatable mark;
and if the relative number of the foreground targets is not greater than a preset relative number threshold, determining the point cloud map updating identifier as the updatable identifier.
7. The laser mapping method of claim 3, wherein the laser positioning result of the second vehicle in the preset operation area includes a laser positioning position and a laser positioning confidence, the set of point cloud missing positions includes a point cloud map update identifier, and determining whether to update a point cloud map of the preset operation area according to the laser positioning result of the second vehicle in the preset operation area and the set of point cloud missing positions of the preset operation area includes:
if the laser positioning confidence is greater than a preset map updating threshold, the laser positioning position is located in the point cloud missing position set, and the corresponding point cloud map updating mark is an updatable mark, determining to update the point cloud map of the preset operation area, and updating the point cloud map of the preset operation area according to the laser positioning result of the second vehicle in the preset operation area;
otherwise, determining not to update the point cloud map of the preset operation area.
8. A laser positioning method, wherein the laser positioning method comprises:
acquiring third image data and third laser point cloud data acquired by a third vehicle in a preset operation area, and fusing the third image data and the third laser point cloud data by using a preset fusion algorithm to obtain a third fusion result;
Determining a target and a corresponding target type in the third laser point cloud data according to the third fusion result;
preprocessing the target in the third laser point cloud data by utilizing a preset preprocessing strategy according to the target type corresponding to the target in the third laser point cloud data to obtain preprocessed second laser point cloud data;
determining a laser positioning result of the third vehicle in the preset operation area according to the preprocessed second laser point cloud data and the point cloud map of the preset operation area;
the point cloud map of the preset operation area is obtained based on the laser mapping method of any one of claims 1-7.
9. The laser positioning method of claim 8, wherein after acquiring the third image data and the third laser point cloud data acquired by the third vehicle in the preset operation region, the method further comprises:
acquiring a point cloud missing position set of the preset operation area, wherein the point cloud missing position set comprises a point cloud map updating identifier, and the point cloud map updating identifier comprises an non-updatable identifier;
determining whether the third vehicle enters a scene area corresponding to an updatable identifier according to the point cloud missing position set of the preset operation area and post-processing positioning data corresponding to the third laser point cloud data;
If yes, determining a laser positioning result of the third vehicle in the preset operation area by utilizing a laser SLAM algorithm according to the third laser point cloud data.
10. A laser mapping apparatus, wherein the laser mapping apparatus comprises:
the first fusion unit is used for acquiring first image data and first laser point cloud data acquired by a first vehicle in a preset operation area, and fusing the first image data and the first laser point cloud data by utilizing a preset fusion algorithm to obtain a first fusion result;
the first determining unit is used for determining a target and a corresponding target type in the first laser point cloud data according to the first fusion result;
the first preprocessing unit is used for preprocessing the targets in the first laser point cloud data by utilizing a preset preprocessing strategy according to the target types corresponding to the targets in the first laser point cloud data to obtain preprocessed first laser point cloud data;
the construction unit is used for constructing the point cloud map of the preset operation area according to the preprocessed first laser point cloud data and the post-processing positioning data corresponding to the first laser point cloud data.
11. A laser positioning device, wherein the laser positioning device comprises:
the second fusion unit is used for acquiring third image data and third laser point cloud data acquired by a third vehicle in a preset operation area, and fusing the third image data and the third laser point cloud data by utilizing a preset fusion algorithm to acquire a third fusion result;
the second determining unit is used for determining a target and a corresponding target type in the third laser point cloud data according to the third fusion result;
the second preprocessing unit is used for preprocessing the targets in the third laser point cloud data by utilizing a preset preprocessing strategy according to the target types corresponding to the targets in the third laser point cloud data to obtain preprocessed second laser point cloud data;
the first positioning unit is used for determining a laser positioning result of the third vehicle in the preset operation area according to the preprocessed second laser point cloud data and the point cloud map of the preset operation area;
the point cloud map of the preset operation area is obtained based on the laser mapping device of claim 10.
12. An electronic device, comprising:
A processor; and
a memory arranged to store computer executable instructions which, when executed, cause the processor to perform the laser mapping method of any of claims 1 to 7 or to perform the laser positioning method of any of claims 8 to 9.
13. A computer readable storage medium storing one or more programs, which when executed by an electronic device comprising a plurality of application programs, cause the electronic device to perform the laser mapping method of any of claims 1-7, or to perform the laser positioning method of any of claims 8-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310124937.9A CN116546424A (en) | 2023-02-07 | 2023-02-07 | Laser mapping method and device, laser positioning method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310124937.9A CN116546424A (en) | 2023-02-07 | 2023-02-07 | Laser mapping method and device, laser positioning method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116546424A true CN116546424A (en) | 2023-08-04 |
Family
ID=87453093
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310124937.9A Pending CN116546424A (en) | 2023-02-07 | 2023-02-07 | Laser mapping method and device, laser positioning method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116546424A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117056749A (en) * | 2023-10-12 | 2023-11-14 | 深圳市信润富联数字科技有限公司 | Point cloud data processing method and device, electronic equipment and readable storage medium |
-
2023
- 2023-02-07 CN CN202310124937.9A patent/CN116546424A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117056749A (en) * | 2023-10-12 | 2023-11-14 | 深圳市信润富联数字科技有限公司 | Point cloud data processing method and device, electronic equipment and readable storage medium |
| CN117056749B (en) * | 2023-10-12 | 2024-02-06 | 深圳市信润富联数字科技有限公司 | Point cloud data processing method and device, electronic equipment and readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111742326A (en) | Lane line detection method, electronic device, and storage medium | |
| CN114279453B (en) | Automatic driving vehicle positioning method and device based on vehicle-road cooperation and electronic equipment | |
| CN113405555B (en) | Automatic driving positioning sensing method, system and device | |
| CN114088114B (en) | Vehicle pose calibration method and device and electronic equipment | |
| CN115390086B (en) | Fusion positioning method and device for automatic driving, electronic equipment and storage medium | |
| CN115493602A (en) | Semantic map construction method and device, electronic equipment and storage medium | |
| CN113009539A (en) | Automatic lane changing processing method for vehicle, vehicle and equipment | |
| CN111323038B (en) | Method and system for positioning unmanned vehicle in tunnel and electronic equipment | |
| CN116546424A (en) | Laser mapping method and device, laser positioning method and device | |
| CN115143952A (en) | Automatic driving vehicle positioning method and device based on visual assistance | |
| CN114754778B (en) | Vehicle positioning method and device, electronic equipment and storage medium | |
| CN115962774A (en) | Point cloud map updating method and device, electronic equipment and storage medium | |
| CN114547222A (en) | Semantic map construction method and device and electronic equipment | |
| CN114966632A (en) | Laser radar calibration method and device, electronic equipment and storage medium | |
| CN116027375B (en) | Positioning method and device for automatic driving vehicle, electronic equipment and storage medium | |
| CN115950441B (en) | Fusion positioning method and device for automatic driving vehicle and electronic equipment | |
| CN115856979B (en) | Positioning method and device for automatic driving vehicle, electronic equipment and storage medium | |
| CN114910083A (en) | Positioning method, positioning device, electronic apparatus, and storage medium | |
| CN115112125A (en) | Positioning method and device for automatic driving vehicle, electronic equipment and storage medium | |
| CN114754782A (en) | Map construction method and device, electronic equipment and computer readable storage medium | |
| CN114964293A (en) | Vehicle path planning method and device, electronic equipment and storage medium | |
| CN115031755A (en) | Automatic driving vehicle positioning method and device, electronic equipment and storage medium | |
| CN116625384B (en) | Data association method and device and electronic equipment | |
| CN116559899B (en) | Fusion positioning method and device for automatic driving vehicle and electronic equipment | |
| CN116543360A (en) | Road side map construction method and device and electronic equipment |
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 |